Search

Fractional-order derivative is attracting more and more attention of researchers in image processing because of its better property in restoring more texture than the total variation. To improve the performance of fractional-order variation model in image restoration, a truncated fractional-order variation model was proposed in Chan and Liang [Truncated fractional-order variation model for image restoration, J. Oper. Res. Soc. China]. In this paper, we propose a dual approach to solve this truncated fractional-order variation model on noise removal. The proposed algorithm is based on the dual approach proposed by Chambolle [An algorithm for total variation minimisation and applications, J. Math Imaging Vis. 20 (2004), pp. 89–97]. Conversely, the Chambolle's dual approach can be treated as a special case of the proposed algorithm with fractional order α = 1. The work of this paper modifies the result in Zhang et al. [Adaptive fractional-order multi-scale method for image denoising, J. Math. Imaging Vis. 43(1) (2012), pp. 39–49. Springer Netherlands 0924–9907, Computer Science, pp. 1–11, 2011], where the convergence is not analysed. Based on the truncation, the convergence of the proposed dual method can be analysed and the convergence criteria can be provided. In addition, the accuracy of the reconstruction is improved after the truncation is taken. [ABSTRACT FROM AUTHOR]

Simple Summary: In the sorting process of Chinese softshell turtles, it is necessary to classify them based on their weight and accurately identify their plastron and carapace. This process requires heavy manual labor and complex mechanical processing methods. To improve processing efficiency and reduce costs, this article introduces machine vision technology, and a new image processing method is proposed. This method can estimate the weight of Chinese softshell turtles and accurately locate the positions of their plastron and carapace. The automation level of aquaculture can be greatly enhanced, and hardware costs can be reduced through software optimization through this approach. With the rapid development of the turtle breeding industry in China, the demand for automated turtle sorting is increasing. The automatic sorting of Chinese softshell turtles mainly consists of three parts: visual recognition, weight prediction, and individual sorting. This paper focuses on two aspects, i.e., visual recognition and weight prediction, and a novel method for the object detection and weight prediction of Chinese softshell turtles is proposed. In the individual sorting process, computer vision technology is used to estimate the weight of Chinese softshell turtles and classify them by weight. For the visual recognition of the body parts of Chinese softshell turtles, a color space model is proposed in this paper to separate the turtles from the background effectively. By applying multiple linear regression analysis for modeling, the relationship between the weight and morphological parameters of Chinese softshell turtles is obtained, which can be used to estimate the weight of turtles well. An improved deep learning object detection network is used to extract the features of the plastron and carapace of the Chinese softshell turtles, achieving excellent detection results. The mAP of the improved network reached 96.23%, which can meet the requirements for the accurate identification of the body parts of Chinese softshell turtles. [ABSTRACT FROM AUTHOR]

Using deep learning in remote sensing interpretation could reduce a lot of human and material costs. Semantic segmentation is the main method for this task. It can automatically outline the objects and it has recently achieved great success in remote sensing images. However, in the appliance of remote sensing interpretation, the accuracy of contour largely determines the evaluation of remote sensing interpretation. Though the current loss functions reflect the segmentation performance, they could not guide the model to optimize itself toward a more precise contour. This paper proposed an exactly defined contour loss (CL) for remote sensing interpretation with Residual Attention U-Net (RA U-Net) as the main framework. The RA U-Net uses the residual attention module as the skip connection layer. It enhances the judgment of U-Net. In CL, image processing methods are used to extract the contours of the foreground. And elements-sum and elements-subtract operations are used to transfer the contour information to a matrix of the same size as label images. Then, these matrices would be the weights for CE. By assigning different weights for different elements in different regions, this function will guide the model to reach a balance between accurate segmentation results and precise contours. The experiment on open datasets shows a good performance. The proposed model was also trained on the Construction Disturbance Dataset collected from Jiang Xi Province, China. The dataset was labeled manually. The evaluation enhanced a lot on the Construction Disturbance Dataset and the IoU on two datasets increased 1 % to 2 % when using CL as the loss function. This paper also compared the proposed method with other state-of-the-art methods and the results showed extensive effectiveness. [ABSTRACT FROM AUTHOR]

The number of excavated tunnels is increasing day by day, and the corresponding engineering scale is also getting increasing. Safe, efficient, and economically beneficial tunnel construction methods are indispensable in the process of crossing mountains and steep ridges in the southwest region. However, behind the improvement of transportation infrastructure in Southwest China is the support provided by the rapid development of blasting industry engineering technology in China. In the process of tunnel construction using the drilling and blasting method, in addition to blasting vibration disasters the phenomenon of overbreak and underbreak caused by blasting construction is a prominent problem. This phenomenon not only affects the safety and stability of the tunnel excavation but also seriously increases the construction cost. Based on a short mountain hard rock tunnel project in southwest China, this paper studies the effect of blasting construction on the blasting vibration of adjacent structures and the influence of tunnel contour forming quality. Through the monitoring and analysis of in situ blasting vibration, the Sadowski formula is used to study the attenuation law of blasting vibration velocity in different tunnel sites, which provides a theoretical basis for tunnel blasting vibration control. This article compares the use of overbreak and underbreak value with the traditional method to determine the degree of overbreak and underbreak. It introduces the analysis of contour section fractal dimension value and uses fractal theory in the Python image processing module to accurately and quantitatively describe the problems of tunnel overbreak and underbreak. The feasibility and accuracy of this method have been verified, by combining the total station and 3D laser scanner results of overbreak and underbreak measurements of the Brenner Base Tunnel and a short hard rock tunnel in a mountainous area of southwestern China. The blasting scheme was optimized from the aspects of cut hole form, detonator interval time, and peripheral hole charge structure, and the rationality of the optimized scheme was verified according to the on-site blasting experiments. It has a profound influence on strengthening the protection of adjacent tunnel structures and improving the economic benefit of mountain highway projects. [ABSTRACT FROM AUTHOR]

The product design major was formally established in 2011 and has been an important part of Chinese art education since then. At the same time, it has laid a solid foundation for the development of China's higher education. Therefore, the product design major occupies an important position in China's higher education and plays an irreplaceable role in cultivating industrial design talents for the country. With the continuous development and progress of national education, the teaching of product design is also constantly innovating, in order to better improve the teaching effect of product design and cultivate more product design professionals for the country. The purpose of this paper is to study the teaching of product design major based on intelligent network teaching, establish an intelligent network teaching system, and carry out intelligent network teaching experiment of product design major based on this system. The experiment concluded that the overall satisfaction of the students majoring in product design on the intelligent network teaching reached 82%, and the intelligent network teaching mode also increased the outstanding performance rate of the students majoring in product design by 30%. [ABSTRACT FROM AUTHOR]

Crab aquaculture is an important component of the freshwater aquaculture industry in China, encompassing an expansive farming area of over 6000 km2 nationwide. Currently, crab farmers rely on manually monitored feeding platforms to count the number and assess the distribution of crabs in the pond. However, this method is inefficient and lacks automation. To address the problem of efficient and rapid detection of crabs via automated systems based on machine vision in low-brightness underwater environments, a two-step color correction and improved dark channel prior underwater image processing approach for crab detection is proposed in this paper. Firstly, the parameters of the dark channel prior are optimized with guided filtering and quadtrees to solve the problems of blurred underwater images and artificial lighting. Then, the gray world assumption, the perfect reflection assumption, and a strong channel to compensate for the weak channel are applied to improve the pixels of red and blue channels, correct the color of the defogged image, optimize the visual effect of the image, and enrich the image information. Finally, ShuffleNetV2 is applied to optimize the target detection model to improve the model detection speed and real-time performance. The experimental results show that the proposed method has a detection rate of 90.78% and an average confidence level of 0.75. Compared with the improved YOLOv5s detection results of the original image, the detection rate of the proposed method is increased by 21.41%, and the average confidence level is increased by 47.06%, which meets a good standard. This approach could effectively build an underwater crab distribution map and provide scientific guidance for crab farming. [ABSTRACT FROM AUTHOR]

Copyright of Forensic Science & Technology is the property of Institute of Forensic Science, Ministry of Public Security and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Currently, the frequency of landslides is increasing. Scientific monitoring methods are playing an essential role in effectively reducing landslide disasters. This paper proposes a method for identifying the cracks at the trailing edge of a landslide (TEL) based on image processing technology and adopts the custom interval median comparison algorithm (IMCA) to calculate the crack motion parameters. First, we perform a series of processes on the TEL images, including image preprocessing, Otsu's algorithm processing, and Canny edge detection processing, to identify the outline of the TEL. Then, we propose using the azimuth and displacement to characterize the motion of the cracks and using the IMCA to calculate the changes before and after motion of any two groups of cracks. Finally, we design a computer program using a free and open-source widget toolkit (named QT platform) based on the calculation model that corresponds to the proposed method, and we apply the crack monitoring test to a 3D simulation model, a gravel model, a soil model, and a collapsed body of the Panzhihua Airport landslide in southwestern China. From the results, it can be assessed that the method can identify the outline of the TEL and calculate the azimuth and displacement of two crack curves before and after motion. These two parameters can describe the movement of the trailing edge cracks of the monitored landslide. Thus, this method can be used in early warning system for landslide hazards. [ABSTRACT FROM AUTHOR]

BACKGROUND: Cardiovascular diseases are the top cause of death in China. Manual segmentation of cardiovascular images, prone to errors, demands an automated, rapid, and precise solution for clinical diagnosis. OBJECTIVE: The paper highlights deep learning in automatic cardiovascular image segmentation, efficiently identifying pixel regions of interest for auxiliary diagnosis and research in cardiovascular diseases. METHODS: In our study, we introduce innovative Region Weighted Fusion (RWF) and Shape Feature Refinement (SFR) modules, utilizing polarized self-attention for significant performance improvement in multiscale feature integration and shape fine-tuning. The RWF module includes reshaping, weight computation, and feature fusion, enhancing high-resolution attention computation and reducing information loss. Model optimization through loss functions offers a more reliable solution for cardiovascular medical image processing. RESULTS: Our method excels in segmentation accuracy, emphasizing the vital role of the RWF module. It demonstrates outstanding performance in cardiovascular image segmentation, potentially raising clinical practice standards. CONCLUSIONS: Our method ensures reliable medical image processing, guiding cardiovascular segmentation for future advancements in practical healthcare and contributing scientifically to enhanced disease diagnosis and treatment. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate the capabilities of the inexpensive theodolite created by the authors, compared with modern commercial instruments, equipped with a Leica TPS1203 robotic total station with built-in GoPro Hero6 camera image sensors. This theodolite was tested in the laboratory where simulated dynamic displacements were determined. The results of the experimental tests showed that the displacement errors and differences between the simulated displacements of the test machine and those detected by the theodolite were in the range of Δ = − 0. 1 5 mm to +0.13 mm depending on the simulated amplitude. The theodolite was further used in the field for static and dynamic tests of the Wanzhou Railway Bridge, China. Determination of the dynamic motions of the bridge and the results of calculating the natural frequencies from the measurement data are presented. During loading tests of the bridge, the frequencies were also determined by accelerometers and these data were used as a reference to assess the accuracy of the theodolite and its suitability for dynamic tests. An original algorithm was developed in the MATLAB software environment to process the recorded videos, i.e. image processing to determine displacements and natural frequencies. It is demonstrated that the position of the theodolite at a distance of 28.5 m from the bridge provides the correspondence of one pixel of 0.333 mm, which provides a high level of accuracy when determining the dynamic vertical displacements of a moving target. It is established that the proposed theodolite will cost less than 5 000 euros. The results obtained are relevant for use in civil engineering for monitoring the amplitude vibrations of structures. [ABSTRACT FROM AUTHOR]

Automatic weed identification and detection are crucial for precision weeding operations. In recent years, deep learning (DL) has gained widespread attention for its potential in crop weed identification. This paper provides a review of the current research status and development trends of weed identification in crop fields based on DL. Through an analysis of relevant literature from both within and outside of China, the author summarizes the development history, research progress, and identification and detection methods of DL-based weed identification technology. Emphasis is placed on data sources and DL models applied to different technical tasks. Additionally, the paper discusses the challenges of time-consuming and laborious dataset preparation, poor generality, unbalanced data categories, and low accuracy of field identification in DL for weed identification. Corresponding solutions are proposed to provide a reference for future research directions in weed identification. [ABSTRACT FROM AUTHOR]

With the rapid development of society, the improvement of material level and the current situation of the large-scale population flow in China, the awareness of security is becoming more and more important in people's life. With the rapid development of image processing and computer vision technology, people try to analyze, process and understand the collected video image automatically without human intervention. The intelligent video monitoring system collects video signals of interested objects in a dynamic scene through a camera, and processes and analyzes image information by a computer. Only by establishing a reasonable and effective urban video monitoring management system can government departments find out problems in the first time. The traditional highway monitoring and commanding traffic scheduling system based on GIS, which can obtain road traffic information and conduct traffic scheduling by remote sensing, has the disadvantage of poor effect on traffic scheduling. In this paper, real-time communication technology and computer vision acquisition technology are used to build a city monitoring system. The experimental results show that this method has strong timeliness and good monitoring effect. Compared with the state-of-the-art methodologies, the proposed framework is efficient and accurate. [ABSTRACT FROM AUTHOR]

In the operation of railway vehicles, the quality of bogies directly affects the operation quality and driving safety. Wheel set is one of the most important components in bogie, so the maintenance of wheel set is very important. For a long time, the detection of train wheel sets in China is still in the stage of manual measurement with backward technology and low efficiency. A new automatic detection method of wheel flange tread based on fuzzy neural network image processing technology is proposed in this paper. This method can accurately detect the defects of wheel flange tread. It collects the original image of the tested wheel set through the digital camera, inputs it into the computer, through certain calculation and processing, and compares it with the model established based on fuzzy neural network, so as to detect the defects of wheel flange and tread. First, the research status of wheel tread defect detection is summarized. Second, the basic principles of digital image technology are studied, the image processing models are confirmed, and the image processing method based on fuzzy neural network is established. Finally, eight wheel set treads are selected to carry out defect detection, and the analysis results show that the proposed method can obtain the better inspection precision. [ABSTRACT FROM AUTHOR]

GF-3 is the first C-band multipolarization synthetic aperture radar (SAR) satellite in China. The SAR system is equipped with an active phased array antenna to electronically generate various antenna beams. The accuracy of SAR antenna patterns is of main importance for precise SAR image processing. The traditional method for antenna pattern measurement is the near-field method but it is unable to satisfy the demand for fast measuring in-orbit. In order to measure the SAR antenna pattern quickly with high accuracy, we propose the internal calibration method. The internal calibration uses calibration signals which are routed along the nominal signal path in SAR systems, thus monitoring the gain and phase variations for each T/R channel is possible. This paper will focus on this method, including its principle, operation steps, and results, compared to the near-field method. The internal calibration method provides a valuable solution for SAR antenna pattern measurement. [ABSTRACT FROM AUTHOR]

In the cold season, wine aids in maintaining body temperature and is advised for military officers. This paper proposes a study on the multimotor drive control method of the upper-retort-robot based on machine vision for wine brewing automation to meet the demand of military areas located in cold regions, as wine is recommended to keep soldiers' body temperatures normal in China's extremely cold regions. Based on machine vision, the target is converted into an image signal by an image pickup device and is sent to the image processing system. Pixel distribution, brightness, color, and other data are transformed to digital signals, and target attributes are retrieved to control the field equipment's operations. The Monte-Carlo approach is used to generate joint variables at random within each joint's fluctuation range. The positive aspects of kinematics model are utilized and the working space of the upper-retort-robot is calculated using multimotor drive control method. The multimotor drive compensates the harmonic ripple torque and establishes the fault-tolerant automatic control of the system to maintain quality of the liquor. The results of the experiments reveal that the robot arm can reach any place within the barrel's set range. To control the quality of the liquor, the robot will function in an automatic manner. The robot's transmission performance is capable of meeting the requirements for automated liquor quality control during the production of wine from grapes. The results show that the suggested multimotor drive control (MMDCM) approach is robust and viable in terms of robot transmission performance and dexterity. [ABSTRACT FROM AUTHOR]

The research results of this paper provide new ideas and perspectives for the construction of trading market of China's carbon emission rights, so as to better alleviate the difficulties in China's energy conservation and emission reduction. Data evaluation and image analysis based on wavelet transform image processing technology and deep learning were used in the study. Moreover, wavelet transform was used to extract the edge, and compared with the results of several other methods for extracting edges, so as to further study and analyze the trend of carbon emissions trading. The fluctuations in the price of carbon emissions trading, the shift of state, and the period of ups and downs are affected by many random factors. Through research algorithms, we can estimate the situation, seize opportunities, and forecast the prospects. In addition, based on the research, this paper obtains the relevant strategies for carbon emissions trading and value assessment in China. [ABSTRACT FROM AUTHOR]

The purpose is to use medical image processing technology to avoid the influence of subjective factors through the mutual penetration and development of clinical medicine and computer science. Can diagnose the degree of malignancy of ischemic optic neuropathy as quickly as possible, and can take an effective treatment plan for the patient early.Therefore, image segmentation of ischemic optic neuropathy based on fuzzy clustering theory is particularly important for the diagnosis of disease in patients. This paper analyzes the research status of medical image segmentation at home and abroad and the development trend in this aspect in China. Discussed the fuzzy C-means clustering (FCM) image segmentation algorithm in depth, studied the effects of iterative cutoff error, initial clustering center, number of clustering categories and fuzzy weighted index on the practical application of the algorithm. At the same time, the traditional algorithm is not sensitive to the spatial information of the image, making the algorithm sensitive to noise. Firstly, introduced the spatial information of the image, and introduced the algorithm based on spatial information constraint, Based on the above description and based on the neighborhood properties described by the two-dimensional histogram, studied and proposed a relatively easy to understand multidimensional distance measurement method. That is, the two-dimensional pixel value and the neighborhood pixel value viewpoint that can be updated in the two-dimensional direction, by setting a clustering objective function, a clustering measurement method includes neighborhood information. Through the above two-dimensional image segmentation algorithm based on neighborhood spatial information, proposed an image segmentation algorithm for ischemic optic neuropathy of fuzzy kernel clustering theory combined with spatial information. The experimental results show that the proposed algorithm can show excellent results in ischemic neuropathy image segmentation, and the algorithm has faster convergence speed and higher classification accuracy. Experimental results of artificial images and actual images show that the algorithm has strong noise immunity and practicability. [ABSTRACT FROM AUTHOR]

GaoFen1 is the first high-resolution earth observation satellite built in China, and carries four wide field-of-view (WFV) cameras to achieve large-scale monitoring and mapping. However, the unstable attitude measurement accuracy of the satellite generally imparts low geopositioning accuracy and inconsistent geometric error in overlapping areas of WFV images. A feasible and effective large-scale planar block adjustment (PBA) method is presented that corrects the geometric errors of the vast WFV images integrally, further improving the geometric accuracy of these images. In addition, whether ground control points (GCPs) are needed, and the effect of different numbers of GCPs on PBA accuracy is also investigated. Two key technologies are used in this paper. First, a universal PBA error equation based on the virtual control points is presented to allow PBA with or without GCPs. Second, an adjustment method aided by a digital elevation model is adopted to overcome the weak convergence geometry among WFV images, further ensuring stable estimation of PBA. The effectiveness of the proposed method was verified by 664 WFV images covering most of mainland China. The satisfactory experimental results indicate that the method presented herein is reasonable and effective, but that a certain number of GCPs is needed to ensure the accuracy of large-scale PBA results for WFV images. [ABSTRACT FROM AUTHOR]

The new coronavirus infection (COVID-19) has spread to numerous countries around the world since several cases of the disease were first reported in late December 2019 in China. Currently, the WHO strongly recommends infection prevention measures such as wearing masks, hand washing, and frequent disinfection of high-touch surfaces, but there were many arguments against infection prevention policy in March 2020. For example, the WHO did not recommend the use of masks for the healthy general public. In Japan, wearing a mask was required before the habit of wearing a mask was established, which gave additional works of checking whether customer was wearing a mask to the employees. To reduce the workloads of employee and ensure mask-wearing, we started providing the mask-wearing system free of charge on March 5, 2020. We also developed hand washing time estimation and disinfection support system. It is useful to accumulate data on the status of implementation of countermeasures by our application, which leads to gain useful knowledge regarding countermeasures against COVID-19 as well as other infectious diseases. In this paper, we describe the development and introduction impacts of these systems in a pandemic emergencies. In addition, because of the security and privacy issues in running these image analysis applications, we discuss the delivery methods suitable for each service. [ABSTRACT FROM AUTHOR]

With the deepening internationalization of China's economy and society, English has gradually become a common language for Chinese people to connect with the world, and plays an increasingly important role in daily life. At the same time, Chinese people's mastery of English is gradually improving. Grasping the foundation of this period can effectively improve students' English level, and it will play a very important role in further learning English or job hunting in the future. Therefore, how to improve the interest of college school students in English learning and improve their ability and level of English learning is particularly important. Virtual community refers to a group of people who communicate and discuss through the Internet and are willing to share some knowledge and information in the exchange, and gradually develop into a social network aggregation. This paper designs an English learning platform for college school students based on virtual community and image processing technology. The platform is developed with SSM framework. After the development, the platform is tested for college school students in several schools in Xi'an. The experimental results show that the system can effectively stimulate students' interest in learning English, and then improve students' vocabulary and academic performance, which provides an effective reference for the study of students' learning methods. [ABSTRACT FROM AUTHOR]

Blue calico is a highly valued folk handicraft that forms part of China's national intangible cultural heritage. Thus, blue calico is a worthy target for reconstruction using modern image processing technology. Extracting the visual components or elements of a blue calico pattern is one way to capture the underlying design and enable innovation in traditional patterns using modern techniques. This paper presents a method of element extraction and classification based on a smart convolutional neural network (CNN), with an improved CifarNet structure, which we call CalicoNet. Initially, the algorithm for element extraction is implemented to generate element samples of blue calico. This process includes gray scaling, binarization, and contour extraction. We construct a data set of elements with 12 types. Then, four critical hyper-parameters, the batch-size, dropout ratio, learning rate, and pooling strategy, are optimized by a comparative analysis. A combination classifier strategy is subsequently added to the fully connected layers to strengthen the feature expression in the corresponding classes. Finally, the superiority of the proposed CalicoNet is verified through a comparison with other sophisticated CNNs. Experimental results demonstrate that CalicoNet achieves a validation accuracy of 99.2% for the training set, a total time of 1.13 hours for the whole data set, and a test mean accuracy precision of 98.66%. The robust performance of the proposed method across the element data set indicates that CalicoNet is a promising approach for element extraction and classification. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Potholes are the most common form of distress on cement concrete pavements, which can compromise pavement safety and ridability. Thus, timely and accurate pothole detection is an important task in developing proper maintenance strategies and ensuring driving safety. This paper proposes a method of integrating the processing of grayscale and texture features. This method mainly combines industrial camera to realize rapid and accurate detection of pothole. Image processing techniques including texture filters, image grayscale, morphology, and extraction of the maximum connected domain are used synergistically to extract useful features from digital images. A machine learning model based on the library for support vector machine (LIBSVM) is constructed to distinguish potholes from longitudinal cracks, transverse cracks, and complex cracks. The method is validated using data collected from agricultural and pastoral areas of Inner Mongolia, China. The comprehensive experiments for recognition of potholes show that the recall, precision, and F1-Score achieved are 100%, 97.4%, and 98.7%, respectively. In addition, the overlap rate between the extracted pothole region and the original image is estimated. Images with an overlap rate greater than 90% accounted for 76.8% of the total image, and images with an overlap rate greater than 80% accounted for 94% of the total image. A comparison discloses that the proposed approach is superior to the existing method not only from the perspective of the accuracy of pothole detection but also from the perspective of the segmentation effect and processing efficiency. [ABSTRACT FROM AUTHOR]

In China, traditional techniques for measuring structural subsidence cannot keep pace with the rapid development of critical national infrastructure such as the growing network of highspeed railways. Traditional monitoring methods using leveling instruments are inefficient and time consuming when monitoring structures like bridges and tunnels. Thus, a fast, economical, and more accurate and precise way to survey building subsidence is urgently needed to address this problem. This paper introduces a new close-range photogrammetry technique that deploys a fixed camera with tilt compensator to measure changes in height over small areas. A barcode subsidence mark that can be identified automatically during digital image processing replaces the leveling points used in traditional methods. Four experiments at different locations verified that results from the new method were stable and consistent with total station measurements. This approach is simple, inexpensive, and produces accurate and precise results as our evaluation results show. [ABSTRACT FROM AUTHOR]

Global warming has caused severe regional water security risks, and from the theory of the hydrological cycle, the daily extreme temperature could also bring an impact on the streamflow volume, which could be even more important than the average temperature. Therefore, based on the level of the maximum or minimum temperature warming scenarios, a variety of meteorological datasets were selected to assess the asymmetric effect of increased daily extreme temperature on the streamflow from a multi-scale perspective by using the Variable Infiltration Capacity (VIC) model. Model simulations indicate that the streamflow experiences more significant changes in response to the maximum temperature than in response to the minimum temperature, and the relationships of streamflow with both the maximum and minimum temperatures show an upwards parabolic response function, but the response function varies with the type of warming. Additionally, the seasonal and monthly duration curves results show that the increases in both the maximum and minimum temperatures demonstrate a similar response that leads the proportion of the flood period streamflow to be increased (Tmin : 0.16–0.53%/°C; Tmax : 0.11–0.51%/°C). When the minimum temperature increases, the higher the original temperature in the region, the greater the proportion of the flood period streamflow increases. However, when the maximum temperature increases, the opposite effect occurs. • This paper included a numerical analysis of the sensitivity of streamflow to daily extreme temperature increases. • This paper discusses in detail the regional asymmetric effect of daily extreme temperature increase to streamflow. • A relatively complete picture of the hydrological processes caused by daily extreme temperature rise is presented. [ABSTRACT FROM AUTHOR]

Purpose This study aims to find a feasible precise navigation model for the planed Lunar rover. Autonomous navigation is one of the most important missions in the Chinese Lunar exploration project. Machine vision is expected to be a promising option for this mission because of the dramatic development of an image processing technique. However, existing attempts are often subject to low accuracy and errors accumulation.Design/methodology/approach In this paper, a novel autonomous navigation model was developed, based on the rigid geometric and photogrammetric theory, including stereo perception, relative positioning and absolute adjustment. The first step was planned to detect accurate three-dimensional (3D) surroundings around the rover by matching stereo-paired images; the second was used to decide the local location and orientation changes of the rover by matching adjacent images; and the third was adopted to find the rover’s location in the whole scene by matching ground image with satellite image. Among them, the SURF algorithm that had been commonly believed as the best algorithm for matching images was adopted to find matched images.Findings Experiments indicated that the accurate 3D scene, relative positioning and absolute adjustment were easily generated and illustrated with the matching results. More importantly, the proposed algorithm is able to match images with great differences in illumination, scale and observation angle. All experiments and findings in this study proved that the proposed method could be an alternative navigation model for the planed Lunar rover.Originality/value With the matching results, an accurate 3D scene, relative positioning and absolute adjustment of rover can be easily generated. The whole test proves that the proposed method could be a feasible navigation model for the planed Lunar rover. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract With the development of the game industry, and the new electronic consumption chain to promote the development of the game industry model continues to strengthen. Therefore, it is more necessary to make good use of good technology to do a good job of games. From the momentum of the development of mobile terminal games in recent years, the game industry has become a new economic growth point in China's economic transformation. With the development of computer and Internet, graphics and image processing technology has entered another unprecedented stage. In recent years, different image processing techniques have been used to process and analyze the game interface. Appropriate image processing methods include image enhancement, image binarization, image edge detection and image feature extraction. In this paper, by changing the mapping function from priority to probability and comparing the single mapping function of the previous algorithm, the mapping function of playback learning with higher probability of the important priority playback unit is found. In the experiment, the intuitive model strategy analysis of the improved algorithm is carried out firstly. Then the choice of CNN network layer structure, cost function analysis, efficiency analysis and game score comparison of each algorithm are carried out. Finally, the test results show that the new algorithm in this paper can make more effective decisions in video games and achieve the goal of winning higher scores and spending less time. [ABSTRACT FROM AUTHOR]

Different satellite images have different positioning accuracy. For example, stereo satellite images have higher positioning accuracy than resource survey satellite images. In addition, for a large number of non stereo satellite images, due to the inability to build a strong triangulation model, it is impossible to carry out block adjustment alone to improve the image positioning accuracy. High precision and high resolution Orthophoto Images are the basis of resource investigation and monitoring and basic geographic information updating. For example, China's third national land survey, national geographic situation monitoring and other national projects require that the survey base map must reach the accuracy of 1:10000 scale, that is, the mean square plane error of points is less than 5m. For most satellite images, a certain number of ground control points need to be deployed to achieve this accuracy. Due to the difficulty of obtaining high-precision ground control points and DEM data in difficult areas, high-precision mapping has always been an unsolved problem, such as Western China. In addition, due to the limited coverage of a single satellite image, to realize the complete coverage of an image in a large area requires the joint application of multiple satellite images. In this paper, the high-precision collaborative geometric processing model and technical method of high-resolution multi-source remote sensing satellite images are proposed. The high-precision collaborative geometric processing of more than ten kinds of high-resolution domestic satellite images is completed by integrating multi-source observation data. An automatic construction method of large-scale block adjustment model of remote sensing images from domestic satellites based on multivariate generalized control network is proposed, including key technologies such as automatic optimization of optimal tie points under different modes, automatic matching of multi-node parallelization tie points, multi-level gross error elimination and so on, which realizes the automatic and stable construction of aerial triangulation model. The test shows that the positioning accuracy of satellite images is better than the accuracy requirements of 1:10000 scale without ground control points, which solves the problem of geometric positioning of 1:10000 scale accuracy in areas where it is difficult to obtain ground control points in the field of Western China. [ABSTRACT FROM AUTHOR]

Crop yield predictions are important for crop monitoring and agronomic management. The traditional methods for yield predictions are complicated and resource consuming. With the availability of affordable handheld imaging and computing devices, the image processing-based yield prediction methods are gaining popularity. In this work, RGB images of rice panicles are captured using DSLR camera with simple background and processed to determine the panicle area in terms of number of pixels. A machine learning-based model is developed to make predictions for rice yield. The model is trained to make predictions on unseen data. Various machine learning-based regression algorithms including decision tree, random forest, support vector machine, and convolution neural network are tested. The experiments are performed on a publically available dataset from China as well as on a self-acquired dataset in India. The results have shown that image processing and machine learning-based methods can make yield predictions satisfactorily as evident from the coefficient of determination ( R 2 ) that ranges 0.80–0.97 for different cultivars. The prediction error is determined in terms of root mean square error (RMSE) and mean absolute error (MAE). RMSE for different methods lies between 0.14 and 0.40, whereas MAE varies from 0.11 to 0.30. Among the tested algorithms, linear regression achieved the best precision with R 2 = 0.97, RMSE = 0.14, and MAE = 0.11. [ABSTRACT FROM AUTHOR]

Few-shot segmentation (FSS) is a cutting-edge technology that can meet requirements using a small workload. With the development of China Aerospace Engineering, FSS plays a fundamental role in astronaut working scene (AWS) intelligent parsing. Although mainstream FSS methods have made considerable breakthroughs in natural data, they are not suitable for AWSs. AWSs are characterized by a similar foreground (FG) and background (BG), indistinguishable categories, and the strong influence of light, all of which place higher demands on FSS methods. We design a pixel-wise and class-wise network (PCNet) to match support and query features using pixel-wise and class-wise semantic cues. Specifically, PCNet extracts pixel-wise semantic information at each layer of the backbone using novel cross-attention. Dense prototypes are further utilized to extract class-wise semantic cues as a supplement. In addition, the deep prototype is distilled in reverse to the shallow layer to improve its quality. Furthermore, we customize a dataset for AWSs and conduct abundant experiments. The results indicate that PCNet outperforms the published best method by 4.34% and 5.15% in accuracy under one-shot and five-shot settings, respectively. Moreover, PCNet compares favorably with the traditional semantic segmentation model under the 13-shot setting. [ABSTRACT FROM AUTHOR]

Turfy soil is a kind of special soil accumulated by undecomposed plants which is detrimental to the engineering. In this paper, particular identified patterns for the turfy soil in the northeast of China was raised including the method of extracting threshold value, block analysis and fuzzy evaluation. And field investigations were undertaken to verify the accuracy of identification by remote sensing, and the correlation of field result and remote sensing result was summarized so as to analyze the regularities of distribution and evolutionary mechanism of turfy soil. The result shows that the combination of extracting threshold value, block analysis and fuzzy evaluation are effective methods to predict the distribution of the turfy soil; with the correlation of membership degree and field result, we can analyze the evolutionary mechanism of turfy soil affected by both nature factors and human activities, which is beneficial for the preservation of the turfy soil and also shows significant environmental ecological benefit. [ABSTRACT FROM AUTHOR]

Soil water content (SWC) plays a vital role in agricultural management, geotechnical engineering, hydrological modeling, and climate research. Image-based SWC recognition methods show great potential compared to traditional methods. However, their accuracy and efficiency limitations hinder wide application due to their status as a nascent approach. To address this, we design the LG-SWC-R3 model based on an attention mechanism to leverage its powerful learning capabilities. To enhance efficiency, we propose a simple yet effective encoder–decoder architecture (PVP-Transformer-ED) designed on the principle of eliminating redundant spatial information from images. This architecture involves masking a high proportion of soil images and predicting the original image from the unmasked area to aid the PVP-Transformer-ED in understanding the spatial information correlation of the soil image. Subsequently, we fine-tune the SWC recognition model on the pre-trained encoder of the PVP-Transformer-ED. Extensive experimental results demonstrate the excellent performance of our designed model (R2 = 0.950, RMSE = 1.351%, MAPE = 0.081, MAE = 1.369%), surpassing traditional models. Although this method involves processing only a small fraction of original image pixels (approximately 25%), which may impact model performance, it significantly reduces training time while maintaining model error within an acceptable range. Our study provides valuable references and insights for the popularization and application of image-based SWC recognition methods. [ABSTRACT FROM AUTHOR]

The creation of lightscapes in colleges and universities are of great significance in enhancing the perception of the campus environment, improving physical and mental health, and shaping humanistic connotations. This research aims to examine lightscape perceptions and impacts of different campuses. At Chongqing University A and B Campuses, lightscape walking experiments, subjective questionnaires, objective luminance measurements, and HDR picture processing were used to examine lightscape perception and factors. The relevance and differences in the perception of circadian lightscapes in the two campuses were analyzed using SPSS software. The study found: (1) natural lightscapes such as sky light, cloud shadow, and lake water reflection were the most popular during the daytime, while artificial lightscapes, such as decorative lighting of buildings, were positively evaluated at night; (2) the frequency of visits by a crowd directly impacts the ambiance of the environmental area; (3) males showed strong emotional awareness and social interaction skills in daytime, leading to increased social activity and stronger emotional responses, but no differences in nighttime; (4) optimal nighttime luminance enhances the overall perception satisfaction of the illumination; (5) the amount and arrangement of outdoor space, vegetation, minor landscape design, and service facilities all affect the perception of circadian lightscapes. In conclusion, design concepts and proposals of landscapes were suggested to optimize college and university lightscapes. [ABSTRACT FROM AUTHOR]

The accurate extraction of burned area is important for biomass burning monitoring and loss evaluation. Environment and Disasters Monitoring Microsatellite Constellation put forward by China has two satellites of HJ-1A and HJ-1B in orbit. Each satellite has two CCD cameras with four bands to meet the need of mapping burned area. In order to evaluate the capability for mapping the burned area using HJ satellite's CCD data, a forest fire occurring in Yuxi, Yunnan Province of Southwest China, was selected to analyze the spectral characteristic in the range of visible and near infrared in this paper. The research of mapping burned area was carried out based on the HJ satellites using three spectral indices (NDVI, GEMI and BAI). The color composite images including NIR band could reflect the spectral change in post-fire vegetation with a higher repetition cycle (2 days, or 1 day in some region) and higher spatial resolution (30 m). Through the comparison with the discrimination index M and extraction accuracy, the BAI has higher discrimination capability than NDVI and GEMI, and the highest M value is 2.1943. The extraction of burned area based on BAI showed higher accuracy, and the highest kappa value is 0.8957. Using HJ satellites, the map of burned area with higher temporal-spatial resolution and higher accuracy could provide the potential for dynamic monitoring and analyzing fire behavior. [ABSTRACT FROM AUTHOR]

The quick and precise location of the burning zones of coal fires, which are continuously burning in abandoned coal mines worldwide, has long been a technical problem. The unmanned aerial vehicle (UAV) can reduce field work intensity, improve data collection efficiency, and ensure high accuracy at low cost. In order to visualize the distribution of burning points of coal fires, the UAV-based thermal infrared oblique photography is adopted. A 4-step 3D thermal imaging method is proposed in which the processing of thermal images is the most crucial. Furthermore, a software program is developed to improve the contrast and quality of batches of thermal images in one-click as well as to unify the temperature level and scale in each thermal image. This methodology is implemented in the Maoergou coal fires in China to reconstruct the surface thermal field in genuine 3D. The high-temperature zones are illustrated clearly in the 3D thermal model. The results indicate that this methodology can be used as a tool for the delineation of coal fires and other types of thermal anomaly scenario. [ABSTRACT FROM AUTHOR]

In recent years, with the growth of China's economy and the development of the automobile manufacturing industry, the number of various vehicles has continuously increased, and the incidence of traffic accidents has also increased. Especially in traffic blind areas, right-turning areas of vehicles, etc., traffic accidents such as vehicle collisions are extremely easy to occur, which poses a serious threat to people's lives and property, and is extremely harmful. Therefore, related research on collision detection of people and vehicles has been traffic-safe and has received extensive attention from field researchers. At present, the research on human-vehicle collision detection is to detect human-vehicle collision accidents by tracking the track of vehicles and pedestrians, but there are problems such as poor tracking effect, low accuracy of collision discrimination and complex algorithms. Aiming at these problems, this paper studies the human-vehicle collision detection algorithm based on image processing. Through the image processing of traffic monitoring video, the vehicle and pedestrian contour information is extracted. Based on this, a mathematical model for collision detection is constructed to realize human-vehicle collision detection. The results show that the proposed method can effectively distinguish the collision between pedestrians and vehicles, and the algorithm for image processing is simpler than the traditional tracking algorithm, and the time is shorter. The results show that the image-based collision detection algorithm based on image processing can effectively and quickly identify the traffic accidents in which people and vehicles collide, and then can issue alarm signals in time, shortening the accident processing time and reducing the accident time. The possibility of a secondary accident has a high practicability in the detection of traffic accidents in which people and vehicles collide. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: Breast fibroadenoma poses a significant health concern, particularly for young women. Computer-aided diagnosis has emerged as an effective and efficient method for the early and accurate detection of various solid tumors. Automatic segmentation of the breast fibroadenoma is important and potentially reduces unnecessary biopsies, but challenging due to the low image quality and presence of various artifacts in sonography. Methods: Human learning involves modularizing complete information and then integrating it through dense contextual connections in an intuitive and efficient way. Here, a human learning paradigm was introduced to guide the neural network by using two consecutive phases: the feature fragmentation stage and the information aggregation stage. To optimize this paradigm, three fragmentation attention mechanisms and information aggregation mechanisms were adapted according to the characteristics of sonography. The evaluation was conducted using a local dataset comprising 600 breast ultrasound images from 30 patients at Suining Central Hospital in China. Additionally, a public dataset consisting of 246 breast ultrasound images from Dataset_BUSI and DatasetB was used to further validate the robustness of the proposed network. Segmentation performance and inference speed were assessed by Dice similarity coefficient (DSC), Hausdorff distance (HD), and training time and then compared with those of the baseline model (TransUNet) and other state-of-the-art methods. Results: Most models guided by the human learning paradigm demonstrated improved segmentation on the local dataset with the best one (incorporating C3ECA and LogSparse Attention modules) outperforming the baseline model by 0.76% in DSC and 3.14 mm in HD and reducing the training time by 31.25%. Its robustness and efficiency on the public dataset are also confirmed, surpassing TransUNet by 0.42% in DSC and 5.13 mm in HD. Conclusions: Our proposed human learning paradigm has demonstrated the superiority and efficiency of ultrasound breast fibroadenoma segmentation across both public and local datasets. This intuitive and efficient learning paradigm as the core of neural networks holds immense potential in medical image processing. [ABSTRACT FROM AUTHOR]

Heat flow is a geothermal parameter for indicating the heat source distribution and evaluating geothermal reservoirs. Only 1,230 heat flow points are distributed unevenly in China, mainly concentrated in high‐temperature geothermal and southeast regions. The Songliao Basin is a potential geothermal field in China. Still, only 20 measurement points are known, making evaluating the geothermal genetic mechanism difficult. Sparse data interpolation using deep learning methods is highly accurate and widely used in fields such as image processing. In this work, we propose a deep neural network for predicting heat flow in the Songliao Basin. More than 4,000 global heat flows and 23 geological and geophysical parameters are used as reference constraints for training. The uncertainty error of the prediction is estimated based on the correlation and distance‐based generalized sensitivity analysis. The results show that the maximum heat flow is 85 mW/m2, the average is 67.1 mW/m2, and the error with the measured data is 10.64%. The previous geophysical and geological interpretation results indicate that the heat flow is higher in the west and lower in the east, with high anomalies in the central region, which may be related to the uplift of the deep mantle and the depression of the shallow low‐velocity sedimentary layer. Some high‐temperature melt bodies are in the deep layers, forming the current potential geothermal field. The measured data validates that the DNN is an effective method for predicting regional‐scale heat flow, providing reliable heat source information for evaluating geothermal resources. Plain Language Summary: Geothermal has received extensive global attention as a new renewable energy resource. Geothermal heat flow (GHF) is crucial among various indicators for assessing potential geothermal fields, with over 20,000 measurement points worldwide. However, due to the expensive cost of drilling measurements, the spatial distribution of heat flow points could be more balanced, posing challenges to geothermal exploration and investigation. Traditional heat flow prediction methods rely on interpolation based on sparse measurement points to estimate the regional heat flow distribution. However, spatial variations in the measurement points often affect the prediction results, leading to lower accuracy. Therefore, this study proposes a deep learning approach to establish the complex relationship between heat flow and geological/geophysical features, aiming to estimate the heat flow distribution in the target area. The proposed method has been successfully applied to heat flow prediction in the Songliao Basin, accompanied by an uncertainty analysis technique that provides confidence intervals for the prediction results. These findings offer direct evidence for the geothermal formation mechanisms and thermal evolution laws in the Songliao Basin. Key Points: We propose a deep neural network (DNN) method for predicting terrestrial heat flowCorrelation and Distance‐based Generalized Sensitivity Analysis (DGSA) methods are used to evaluate the uncertainty of DNN predicted heat flow resultsThe prediction of terrestrial heat flow in the Songliao Basin provides direct evidence for deep heat source channels and geothermal genesis mechanisms [ABSTRACT FROM AUTHOR]

Pedestrian dynamics in emergent situations such as stampedes and fire hazards have been widely studied, while few studies are focusing on human behavior in terrorist attack events. The research is vitally important for guiding efficient evacuation of the attacked crowd and reducing casualties. However, the research is insufficient due to the lack of researching materials. Besides, it is unconvincing for researchers to carry out these types of experiments. In this paper, the recorded video of the 3 ⋅ 1 Kunming terrorist attack event in China is analyzed. The instantaneous velocity field of the attacked crowd in the ticket hall is extracted from the video material, which is based on an image processing method. By analyzing the statistical characteristics of crowd velocity, crowd movement frequency and crowd entropy, several phenomena are found including crowd oscillating phenomenon, self-organizing grouping phenomenon. These discoveries will benefit the understanding of crowd dynamic in close-range attacks which is essential for the evacuation guidance efficiency, better design of architecture layout, and better defending strategies against the terrorists. • Crowd velocity peak is oscillating back and forth within the attacked crowd. • The velocity entropy of crowd is shown oscillating around the mean value 6.7. • The characteristic frequency of crowd movement is about 0.4 Hz. • Crowd in different area who have different movement behavior patterns show grouping phenomenon. [ABSTRACT FROM AUTHOR]

Accurate near-surface velocity models are necessary for land seismic imaging. First-arrival traveltime tomography (FTT) routinely used for estimating near-surface velocity models may fail in geological complex areas. Supervised deep learning (SDL) is capable of building accurate velocity models, based on tens of thousands of velocity model-shot gathers training pairs. It takes lots of time and memory space, which may be unaffordable for practical applications. We propose integrating the FTT and SDL to build near-surface velocity models. During the neural network training, the FTT-inverted models rather than the original seismic data are used as the network inputs and corresponding true models are the outputs. The FTT-inverted and true models are the same physical quantities and with the same dimensions. Their relationship is less non-linear than that between shot gathers and true models. Thus, the neural network of the proposed method can be trained well using only a small number of training samples, dramatically reducing the time and memory costs. Numerical tests demonstrate the feasibility and effectiveness of the proposed method. We applied the proposed method to a land data set obtained in mountainous areas in the west of China and obtained satisfactory near-surface velocity models and stacking images. [ABSTRACT FROM AUTHOR]

To address the phenomenon of color shift and low contrast in underwater images caused by wavelength- and distance-related attenuation and scattering when light propagates in water, we propose a method based on an attention mechanism and adversarial autoencoder for enhancing underwater images. Firstly, the pixel and channel attention mechanisms are utilized to extract rich discriminative image information from multiple color spaces. Secondly, the above image information and the original image reverse medium transmittance map are feature-fused by a feature fusion module to enhance the network response to the image quality degradation region. Finally, the encoder learning is guided by the adversarial mechanism of the adversarial autoencoder, and the hidden space of the autoencoder is continuously approached to the hidden space of the pre-trained model. The results of the experimental images acquired from the Beihai Bay area of China on the HYSY-163 platform show that the average value of the Natural Image Quality Evaluator is reduced by 27.8%, the average value of the Underwater Color Image Quality Evaluation is improved by 28.8%, and the average values of the Structural Similarity and Peak Signal-to-Noise Ratio are improved by 35.7% and 42.8%, respectively, compared with the unprocessed real underwater images, and the enhanced underwater images have improved clarity and more realistic colors. In summary, our network can effectively improve the visibility of underwater target objects, especially the quality of images of submarine pipelines and marine organisms, and is expected to be applied in the future with underwater robots for pile legs of offshore wellhead platforms and large ship bottom sea life cleaning. [ABSTRACT FROM AUTHOR]

In recent decades, various kinds of remote sensing-based drought indexes have been proposed and widely used in the field of drought monitoring. However, the drought-related software and platform development lag behind the theoretical research. The current drought monitoring systems focus mainly on information management and publishing, and cannot implement professional drought monitoring or parameter inversion modelling, especially the models based on multi-dimensional feature space. In view of the above problems, this paper aims at fixing this gap with a component-based system named RSDMS to facilitate the application of drought monitoring by remote sensing. The system is designed and developed based on Component Object Model (COM) to ensure the flexibility and extendibility of modules. RSDMS realizes general image-related functions such as data management, image display, spatial reference management, image processing and analysis, and further provides drought monitoring and evaluation functions based on internal and external models. Finally, China’s Ningxia region is selected as the study area to validate the performance of RSDMS. The experimental results show that RSDMS provide an efficient and scalable support to agricultural drought monitoring. [ABSTRACT FROM AUTHOR]

As one of the most consumed stable foods around the world, wheat plays a crucial role in ensuring global food security. The ability to quantify key yield components under complex field conditions can help breeders and researchers assess wheat's yield performance effectively. Nevertheless, it is still challenging to conduct large-scale phenotyping to analyse canopy-level wheat spikes and relevant performance traits, in the field and in an automated manner. Here, we present CropQuant-Air, an AI-powered software system that combines state-of-the-art deep learning (DL) models and image processing algorithms to enable the detection of wheat spikes and phenotypic analysis using wheat canopy images acquired by low-cost drones. The system includes the YOLACT-Plot model for plot segmentation, an optimised YOLOv7 model for quantifying the spike number per m² (SNpM²) trait, and performance-related trait analysis using spectral and texture features at the canopy level. Besides using our labelled dataset for model training, we also employed the Global Wheat Head Detection dataset to incorporate varietal features into the DL models, facilitating us to perform reliable yield-based analysis from hundreds of varieties selected from main wheat production regions in China. Finally, we employed the SNpM² and performance traits to develop a yield classification model using the Extreme Gradient Boosting (XGBoost) ensemble and obtained significant positive correlations between the computational analysis results and manual scoring, indicating the reliability of CropQuant-Air. To ensure that our work could reach wider researchers, we created a graphical user interface for CropQuant-Air, so that non-expert users could readily use our work. We believe that our work represents valuable advances in yield-based field phenotyping and phenotypic analysis, providing useful and reliable toolkits to enable breeders, researchers, growers, and farmers to assess crop-yield performance in a costeffective approach. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The ecological environment in the karst region of southwest China is fragile, and vegetation degradation is considered the main cause of this phenomenon. Vegetation growth is affected by preferential flow due to a large number of fissures and macropores in the soil. Therefore, the preferential flow and preferential paths in local typical vegetation need to be studied. The distribution and developmental characteristics of preferential flow and preferential paths in three typical local stands were obtained by conducting field staining tracer experiments and using image processing techniques. The results showed that there was preferential flow movement in the soil moisture of the local understorey and that there was a high degree of preferential flow development and high variability. The degree of preferential flow in several typical forests can be expressed, from highest to lowest, in the following order: secondary forests, Cupressus duclouxiana Hickel (Hickel., 1814) forest, and Pinus massoniana (Lamb., 1803) forest. The preferential paths in the soil were mainly distributed above 15 cm, and the number of preferential paths with a small influence radius was much greater than that with a large influence radius. The preferential paths with an influence radius of 2.5~5 mm accounted for the largest proportion. The total number of preferential paths in the P. massoniana forest was small. The preferential paths in the secondary and C. duclouxiana Hickel forests were similar in number, but the secondary forests had more preferential paths with a large influence radius. This study investigated the characteristics of preferential flow and preferential paths in the typical forests of the karst region in southwest China, and it can provide data and research directions for the study of hydrological processes in local forest vegetation. [ABSTRACT FROM AUTHOR]

Bridge deck pavement damage has a significant effect on the driving safety and long-term durability of bridges. To achieve the damage detection and localization of bridge deck pavement, a three-stage detection method based on the you-only-look-once version 7 (YOLOv7) network and the revised LaneNet was proposed in this study. In stage 1, the Road Damage Dataset 202 (RDD2022) is preprocessed and adopted to train the YOLOv7 model, and five classes of damage were obtained. In stage 2, the LaneNet network was pruned to retain the semantic segmentation part, with the VGG16 network as an encoder to generate lane line binary images. In stage 3, the lane line binary images were post-processed by a proposed image processing algorithm to obtain the lane area. Based on the damage coordinates from stage 1, the final pavement damage classes and lane localization were obtained. The proposed method was compared and analyzed in the RDD2022 dataset, and was applied on the Fourth Nanjing Yangtze River Bridge in China. The results shows that the mean average precision (mAP) of YOLOv7 on the preprocessed RDD2022 dataset reaches 0.663, higher than that of other models in the YOLO series. The accuracy of the lane localization of the revised LaneNet is 0.933, higher than that of instance segmentation, 0.856. Meanwhile, the inference speed of the revised LaneNet is 12.3 frames per second (FPS) on NVIDIA GeForce RTX 3090, higher than that of instance segmentation 6.53 FPS. The proposed method can provide a reference for the maintenance of bridge deck pavement. [ABSTRACT FROM AUTHOR]

The Earth observation system heavily relies on sophisticated remotely sensed satellites, an important means to obtain global high-precision geospatial products and an important strategic area for the world's major scientific and technological powers to develop. Although China's satellites currently have real-time or quasi-real-time observations with a high temporal resolution, there are still a lot of gaps between their positioning accuracy and the world's advanced level. This essay aims to study an efficient ground image processing technology and apply it to high-resolution satellite remote sensing images. The convolutional neural network is an efficient deep learning method for image recognition and feature extraction. In this essay, people use a convolutional neural network (CNN) to identify ground images, use a support vector machine (SVM) to classify and summarize images, and then use a Kalman filter for noise reduction, so as to obtain sophisticated remotely sensed images. In the experiment, 100 satellite remote sensing images in the GeoImageDB database were selected for the simulation test, the images were divided into 5 types, and their recognition accuracy, classification accuracy, image signal-to-noise ratio, and resolution were analyzed. The results show that the accuracy of CNN's recognition of different types of images is up to about 94%, and the lowest is about 85%. The accuracy of the SVM for image classification is above 80%, and the highest is about 95%. The SNR of the image after noise reduction is basically above 6.5, and some even reach above 8.0. The resolution of the image is basically above 800ppi, and the highest even reaches an ultra-high resolution of 1400ppi. Overall, the processed images are of high quality. This shows that this essay uses CNN for image recognition and then uses an SVM for classification, and finally, the method of denoising the image has certain feasibility and has achieved good results through experiments. [ABSTRACT FROM AUTHOR]