Search

As remote sensing technology has advanced, the use of satellites and similar technologies has become increasingly prevalent in daily life. Now, it plays a crucial role in hydrology, agriculture, and geography. Nevertheless, because of the distinct qualities of remote sensing, including expansive scenes and small, densely packed targets, there are many challenges in detecting remote sensing objects. Those challenges lead to insufficient accuracy in remote sensing object detection. Consequently, developing a new model is essential to enhance the identification capabilities for objects in remote sensing imagery. To solve these constraints, we have designed the OD-YOLO approach that uses multi-scale feature fusion to improve the performance of the YOLOv8n model in small target detection. Firstly, traditional convolutions have poor recognition capabilities for certain geometric shapes. Therefore, in this paper, we introduce the Detection Refinement Module (DRmodule) into the backbone architecture. This module utilizes Deformable Convolutional Networks and the Hybrid Attention Transformer to strengthen the model's capability for feature extraction from geometric shapes and blurred objects effectively. Meanwhile, based on the Feature Pyramid Network of YOLO, at the head of the model framework, this paper enhances the detection capability by introducing a Dynamic Head to strengthen the fusion of different scales features in the feature pyramid. Additionally, to address the issue of detecting small objects in remote sensing images, this paper specifically designs the OIoU loss function to finely describe the difference between the detection box and the true box, further enhancing model performance. Experiments on the VisDrone dataset show that OD-YOLO surpasses the compared models by at least 5.2% in mAP50 and 4.4% in mAP75, and experiments on the Foggy Cityscapes dataset demonstrated that OD-YOLO improved mAP by 6.5%, demonstrating outstanding results in tasks related to remote sensing images and adverse weather object detection. This work not only advances the research in remote sensing image analysis, but also provides effective technical support for the practical deployment of future remote sensing applications. [ABSTRACT FROM AUTHOR]

The process of image fusion is the process of enriching an image and improving the image's quality, so as to facilitate the subsequent image processing and analysis. With the increasing importance of image fusion technology, the fusion of infrared and visible images has received extensive attention. In today's deep learning environment, deep learning is widely used in the field of image fusion. However, in some applications, it is not possible to obtain a large amount of training data. Because some special organs of snakes can receive and process infrared information and visible information, the fusion method of infrared and visible light to simulate the visual mechanism of snakes came into being. Therefore, this paper takes into account the perspective of visual bionics to achieve image fusion; such methods do not need to obtain a significant amount of training data. However, most of the fusion methods for simulating snakes face the problem of unclear details, so this paper combines this method with a pulse coupled neural network (PCNN). By studying two receptive field models of retinal nerve cells, six dual-mode cell imaging mechanisms of rattlesnakes and their mathematical models and the PCNN model, an improved fusion method of infrared and visible images was proposed. For the proposed fusion method, eleven groups of source images were used, and three non-reference image quality evaluation indexes were compared with seven other fusion methods. The experimental results show that the improved algorithm proposed in this paper is better overall than the comparison method for the three evaluation indexes. [ABSTRACT FROM AUTHOR]

In this study, we are reporting the fabrication of a nanocellulose (NFC) paper-based food indicator for chicken breast spoilage detection by both visual color change observation and smartphone image analysis. The indicator consists of a nanocellulose paper (nanopaper) substrate and a pH-responsive dye, bromocresol green (BCG), that adsorbs on the nanopaper. The nanopaper is prepared through vacuum filtration and high-pressure compression. The nanopaper exhibits good optical transparency and strong mechanical strength. The color change from yellow to blue in the nanopaper indicator corresponding to an increase in the solution pH and chicken breast meat storage data were observed and analyzed, respectively. Further, we were able to use color differences determined by the RGB values from smartphone images to analyze the results, which indicates a simple, sensitive, and readily deployable approach toward the development of future smartphone-based food spoilage tests. [ABSTRACT FROM AUTHOR]

This paper mainly updates the image segmentation and multi-target recognition algorithm through the support vector machine algorithm in ML, and verifies the reliability of the new proposed algorithm through simulation experiments, and determines that the ML-based image segmentation and multi-target recognition algorithm can have stronger processing capability in image recognition and processing. Finally, the performance of traditional image segmentation and multi class object recognition algorithms and the image segmentation and multi class object recognition algorithms proposed in this paper were compared through experiments. The results showed that the performance of the ML based image segmentation and multi class object recognition algorithms proposed in this paper has increased by 29.1% on average in all aspects. Article Highlight: This paper studies the different modes of machine learning algorithm models, and combines machine learning algorithm models with image segmentation and multi-target recognition modes, so that image segmentation and multi-target recognition algorithms can be used in image data analysis, data processing, and intelligent processing. Three aspects have better performance. In image data analysis and data processing, the advantages of machine learning models for data processing are mainly used. Through training on large amounts of data, a dedicated machine learning model for image data analysis and processing is established. The intelligent processing is reflected in the continuous improvement of this model and the further improvement of the degree of automation. [ABSTRACT FROM AUTHOR]

An edge-cloud computing collaborative dust concentration detection architecture is proposed for real-time operation of intelligent algorithms to reduce the warning delay. And, an end-to-end three-channel convolutional neural network (E2E-SCNN) method is proposed in the paper to facilitate intelligent monitoring and management of dust concentration in tobacco production workshops. This model, which includes three sub-networks-a local feature branch, a global feature branch, and a spatial feature branch, learns the detail texture, overall layout, and spatial distribution information of the input image respectively. A fusion of the three complementary features is performed at the end of the network for the final dust concentration regression prediction. The design, when compared with the single network structure that directly regresses the entire image, is shown to more fully represent the overall information of the image and enhance monitoring performance. A richly annotated image dataset of tobacco production workshops is constructed to verify the effectiveness of the proposed method. The prediction error of E2E-SCNN is compared with existing image estimation algorithms, dual-channel networks, and other methods on this dataset using indicators such as Mean Absolute Error (MAE) and R 2 . It is shown by the results that excellent performance is achieved by the E2E-SCNN algorithm, significantly surpassing other comparison methods. The paper demonstrates that the accuracy and robustness of dust concentration prediction can be greatly improved by using a three-channel convolutional neural network spatial information monitoring framework. This achievement provides an effective means for dust supervision and governance during the tobacco production process and offers a technical route that can be referred to for image analysis tasks in other similar fields. [ABSTRACT FROM AUTHOR]

The 2019 International Symposium on Remote Sensing (ISRS-2019) took place in Taipei, Taiwan from 17 to 19 April 2019. ISRS is one of the distinguished conferences on the photogrammetry, remote sensing and spatial information sciences, especially in East Asia. More than 220 papers were presented in 37 technical sessions organized at the conference. This Special Issue publishes a limited number of featured peer-reviewed papers extended from their original contributions at ISRS-2019. The selected papers highlight a variety of topics pertaining to innovative concepts, algorithms and applications with geospatial sensors, systems, and data, in conjunction with emerging technologies such as artificial intelligence, machine leaning and advanced spatial analysis algorithms. The topics of the selected papers include the following: the on-orbit radiometric calibration of satellite optical sensors, environmental characteristics assessment with remote sensing, machine learning-based photogrammetry and image analysis, and the integration of remote sensing and spatial analysis. The selected contributions also demonstrate and discuss various sophisticated applications in utilizing remote sensing, geospatial data, and technologies to address different environmental and societal issues. Readers should find the Special Issue enlightening and insightful for understanding state-of-the-art remote sensing and spatial information science research, development and applications. [ABSTRACT FROM AUTHOR]

A great deal of the images found in scientific publications are retouched, reused, or composed to enhance the quality of the presentation. In most instances, these edits are benign and help the reader better understand the material in a paper. However, some edits are instances of scientific misconduct and undermine the integrity of the presented research. Determining the legitimacy of edits made to scientific images is an open problem that no current technology can perform satisfactorily in a fully automated fashion. It thus remains up to human experts to inspect images as part of the peer-review process. Nonetheless, image analysis technologies promise to become helpful to experts to perform such an essential yet arduous task. Therefore, we introduce SILA, a system that makes image analysis tools available to reviewers and editors in a principled way. Further, SILA is the first human-in-the-loop end-to-end system that starts by processing article PDF files, performs image manipulation detection on the automatically extracted figures, and ends with image provenance graphs expressing the relationships between the images in question, to explain potential problems. To assess its efficacy, we introduce a dataset of scientific papers from around the globe containing annotated image manipulations and inadvertent reuse, which can serve as a benchmark for the problem at hand. Qualitative and quantitative results of the system are described using this dataset. [ABSTRACT FROM AUTHOR]

A method for semi-automatic landslide detection, with the ability to separate source and run-out areas, is presented in this paper. It combines object-based image analysis and a Support Vector Machine classifier on a GeoEye-1 multispectral image, sensed 3 days after the major damaging landslide event that occurred in Madeira island (20 February 2010), with a pre-event LIDAR Digital Elevation Model. The testing is developed in a 15 km²-wide study area, where 95% of the landslides scars are detected by this supervised approach. The classifier presents a good performance in the delineation of the overall landslide area. In addition, fair results are achieved in the separation of the source from the run-out landslide areas, although in less illuminated slopes this discrimination is less effective than in sunnier east facing-slopes. [ABSTRACT FROM AUTHOR]

Describes the above-named upcoming special issue or section. May include topics to be covered or calls for papers. [ABSTRACT FROM AUTHOR]

Background: The increasing number of physicians that are trained in point-of-care ultrasound (POCUS) warrants critical evaluation and improvement of current training methods. Performing POCUS is a complex task and it is unknown which (neuro)cognitive mechanisms are most important in competence development of this skill. This systematic review was conducted to identify determinants of POCUS competence development that can be used to optimize POCUS training. Methods: PubMed, Web of Science, Cochrane Library, Emcare, PsycINFO and ERIC databases were searched for studies measuring ultrasound (US) skills and aptitude. The papers were divided into three categories: "Relevant knowledge", "Psychomotor ability" and 'Visuospatial ability'. The 'Relevant knowledge' category was further subdivided in 'image interpretation', 'technical aspects' and 'general cognitive abilities'. Visuospatial ability was subdivided in visuospatial subcategories based on the Cattell-Horn-Carroll (CHC) Model of Intelligence v2.2, which includes visuospatial manipulation and visuospatial perception. Post-hoc, a meta-analysis was performed to calculate pooled correlations. Results: 26 papers were selected for inclusion in the review. 15 reported on relevant knowledge with a pooled coefficient of determination of 0.26. Four papers reported on psychomotor abilities, one reported a significant relationship with POCUS competence. 13 papers reported on visuospatial abilities, the pooled coefficient of determination was 0.16. Conclusion: There was a lot of heterogeneity in methods to assess possible determinants of POCUS competence and POCUS competence acquisition. This makes it difficult to draw strong conclusions on which determinants should be part of a framework to improve POCUS education. However, we identified two determinants of POCUS competence development: relevant knowledge and visuospatial ability. The content of relevant knowledge could not be retrieved in more depth. For visuospatial ability we used the CHC model as theoretical framework to analyze this skill. We could not point out psychomotor ability as a determinant of POCUS competence. [ABSTRACT FROM AUTHOR]

This paper accounts for the diagnostic campaign aimed at understanding the phenomenon of black stains appeared on the passepartout close to the margins of Folio 843 of Leonardo da Vinci's Codex Atlanticus. Previous studies excluded microbiological deterioration processes. The study is based on a multi-analytical approach, including non-invasive imaging measurements of the folio, micro-imaging and synchrotron spectroscopy investigations of passepartout fragments at different magnifications and spectral ranges. Photoluminescence hyperspectral and lifetime imaging highlighted that black stains are not composed of fluorescent materials. μATR-FTIR imaging of fragments from the passepartout revealed the presence of a mixture of starch and PVAc glues localized only in the stained areas close to the margin of the folio. FE-SEM observations showed that the dark stains are localized inside cavities formed among cellulose fibers, where an accumulation of inorganic roundish particles (∅100–200 nm in diameter size), composed of Hg and S, was detected. Finally, by employing synchrotron μXRF, μXANES and HR-XRD analyses it was possible to identify these particles as metacinnabar (β-HgS). Further research is needed to assess the chemical process leading to the metacinnabar formation in the controlled conservation condition of Leonardo's Codex. [ABSTRACT FROM AUTHOR]

Episcopic imaging using techniques such as High Resolution Episcopic Microscopy (HREM) and its variants, allows biological samples to be visualized in three dimensions over a large field of view. Quantitative analysis of episcopic image data is undertaken using a range of methods. In this systematic review, we look at trends in quantitative analysis of episcopic images and discuss avenues for further research. Papers published between 2011 and 2022 were analyzed for details about quantitative analysis approaches, methods of image annotation and choice of image processing software. It is shown that quantitative processing is becoming more common in episcopic microscopy and that manual annotation is the predominant method of image analysis. Our meta-analysis highlights where tools and methods require further development in this field, and we discuss what this means for the future of quantitative episcopic imaging, as well as how annotation and quantification may be automated and standardized across the field. [ABSTRACT FROM AUTHOR]

The article offers information on the winners of the ESRI Award for Best Scientific Paper in GIS awards. It states that the American Society for Photogrammetry and Remote Sensing (ASPRS) ESRI Award Selection Committee made the announcement concerning the winners of this award. Winners include Rongxing Li, Jue Wang, and Sanchit Agarwal for their paper "A WebGIS for Spatial Data Processing, Analysis, and Distribution for the MER 2003 Mission," Qiuming Cheng and C. Vincent Tao for their paper "A Network-centric Modeling Approach for Infrastructure Interdependency," and Pravara Thanapura and Dennis L. Helder for their work "Mapping Urban Land Cover Using Quickbird NDVI and GIS Spatial Modeling for Runoff Coefficient Determination."

This paper evaluates the efficiency of thermochromic offset prints recycling using deinking flotation method. Since offset thermochromic inks differ in their composition from conventional offset inks, the aim of this research was to determine how effectively they can be recycled. In the experimental part of the work, the laboratory printing of two thermochromic inks was conducted. For both types of inks, white uncoated paper was used as a substrate. After accelerated aging, the prints were mixed in equal proportions and then recycled in laboratory conditions, by means of deinking flotation. During the recycling process, handsheets and filter pads were prepared from the pulp obtained before and after deinking flotation. Handsheets and filter pads were also prepared from unprinted paper that was used as printing substrate, in order to obtain reference samples. The deinking flotation efficiency was evaluated by calculating the flotation loss, ash elimination, pulp's brightness and whiteness increase and determination of residual ink area. The obtained results indicate that thermochromic prints are poorly deinkable. A small increase in deinked pulp's brightness and whiteness (approx. 7% and 11%) is noticed. The image analysis shows that flotation deinking managed to eliminate around 40% of the total dirt area of thermochromic ink. [ABSTRACT FROM AUTHOR]

Most multiple object tracking algorithms depend on the output of the detector. Aiming at the problem that the higher detection quality model is restricted by the computing power, and the robustness of the lightweight detection model is easily affected by motion blur, this paper proposes a lightweight moving object detector based on improved YOLOv8 combined with dynamic confidence compensation algorithm. The algorithm combines various technical means such as network structure optimization, lightweight design, self‐knowledge distillation, loss function improvement and dynamic confidence compensation. ByteTrack is used as a tracker to conduct experiments on PASCAL VOC07+12 data set and UA‐DETRAC test sequence. Compared with the baseline YOLOv8n+ByteTrack, the proposed algorithm improves the HOTA by 1.3% when the single frame tracking delay is reduced by 1.1%. Mostly tracked target is improved by 79.7%, mostly lost target is reduced by 10.9%, and the detection effect is better than the original detector and other popular object detectors. The YOLODCC model achieves a balance between lightweight and multi‐object motion blur. [ABSTRACT FROM AUTHOR]

The combination of medical imaging and deep learning has significantly improved diagnostic and prognostic capabilities in the healthcare domain. Nevertheless, the inherent complexity of deep learning models poses challenges in understanding their decision-making processes. Interpretability and visualization techniques have emerged as crucial tools to unravel the black-box nature of these models, providing insights into their inner workings and enhancing trust in their predictions. This survey paper comprehensively examines various interpretation and visualization techniques applied to deep learning models in medical imaging. The paper reviews methodologies, discusses their applications, and evaluates their effectiveness in enhancing the interpretability, reliability, and clinical relevance of deep learning models in medical image analysis. [ABSTRACT FROM AUTHOR]

Remote sensing images often need to be merged into a larger mosaic image to support analysis on large areas in many applications. However, the performance of the mosaic imagery may be severely restricted if there are many areas with cloud coverage or if these images used for merging have a long-time span. Therefore, this paper proposes a method of image selection for full coverage image (i.e. a mosaic image with no cloud-contaminated pixels) generation. Specifically, a novel High-Frequency-Aware (HFA)-Net based on Swin-Transformer for region quality grading is presented to provide a data basis for image selection. Spatiotemporal constraints are presented to optimize the image selection. In the temporal dimension, the shortest-time-span constraint shortens the time span of the selected images, obviously improving the timeliness of the image selection results (i.e. with a shorter time span). In the spatial dimension, a spatial continuity constraint is proposed to select data with better quality and larger area, thus improving the radiometric continuity of the results. Experiments on the GF-1 images indicate that the proposed method reduces the averages by 76.1% and 38.7% in terms of the shortest time span compared to the Improved Coverage-oriented Retrieval algorithm (MICR) and Retrieval Method based on Grid Compensation (RMGC) methods, respectively. Moreover, the proposed method also reduces the residual cloud amount by an average of 91.2%, 89.8%, and 83.4% when compared to the MICR, RMGC, and Pixel-based Time-series Synthesis Method (PTSM) methods, respectively. [ABSTRACT FROM AUTHOR]

Counting high‐density objects quickly and accurately is a popular area of research. Crowd counting has significant social and economic value and is a major focus in artificial intelligence. Despite many advancements in this field, many of them are not widely known, especially in terms of research data. The authors proposed a three‐tier standardised dataset taxonomy (TSDT). The Taxonomy divides datasets into small‐scale, large‐scale and hyper‐scale, according to different application scenarios. This theory can help researchers make more efficient use of datasets and improve the performance of AI algorithms in specific fields. Additionally, the authors proposed a new evaluation index for the clarity of the dataset: average pixel occupied by each object (APO). This new evaluation index is more suitable for evaluating the clarity of the dataset in the object counting task than the image resolution. Moreover, the authors classified the crowd counting methods from a data‐driven perspective: multi‐scale networks, single‐column networks, multi‐column networks, multi‐task networks, attention networks and weak‐supervised networks and introduced the classic crowd counting methods of each class. The authors classified the existing 36 datasets according to the theory of three‐tier standardised dataset taxonomy and discussed and evaluated these datasets. The authors evaluated the performance of more than 100 methods in the past five years on different levels of popular datasets. Recently, progress in research on small‐scale datasets has slowed down. There are few new datasets and algorithms on small‐scale datasets. The studies focused on large or hyper‐scale datasets appear to be reaching a saturation point. The combined use of multiple approaches began to be a major research direction. The authors discussed the theoretical and practical challenges of crowd counting from the perspective of data, algorithms and computing resources. The field of crowd counting is moving towards combining multiple methods and requires fresh, targeted datasets. Despite advancements, the field still faces challenges such as handling real‐world scenarios and processing large crowds in real‐time. Researchers are exploring transfer learning to overcome the limitations of small datasets. The development of effective algorithms for crowd counting remains a challenging and important task in computer vision and AI, with many opportunities for future research. [ABSTRACT FROM AUTHOR]

Conditional image retrieval (CIR), which involves retrieving images by a query image along with user-specified conditions, is essential in computer vision research for efficient image search and automated image analysis. The existing approaches, such as composed image retrieval (CoIR) methods, have been actively studied. However, these methods face challenges as they require either a triplet dataset or richly annotated image-text pairs, which are expensive to obtain. In this work, we demonstrate that CIR at the image-level concept can be achieved using an inverse mapping approach that explores the model's inductive knowledge. Our proposed CIR method, called Backward Search, updates the query embedding to conform to the condition. Specifically, the embedding of the query image is updated by predicting the probability of the label and minimizing the difference from the condition label. This enables CIR with image-level concepts while preserving the context of the query. In this paper, we introduce the Backward Search method that enables single and multi-conditional image retrieval. Moreover, we efficiently reduce the computation time by distilling the knowledge. We conduct experiments using the WikiArt, aPY, and CUB benchmark datasets. The proposed method achieves an average mAP@10 of 0.541 on the datasets, demonstrating a marked improvement compared to the CoIR methods in our comparative experiments. Furthermore, by employing knowledge distillation with the Backward Search model as the teacher, the student model achieves a significant reduction in computation time, up to 160 times faster with only a slight decrease in performance. The implementation of our method is available at the following URL: https://github.com/dhlee-work/BackwardSearch. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach to enhance the performance of the stochastic gradient descent (SGD) algorithm by incorporating a modified decay step size based on .... The proposed step size integrates a logarithmic term, leading to the selection of smaller values in the final iterations. Our analysis establishes a convergence rate of O ... for smooth non-convex functions without the Polyak-Łojasiewicz condition. To evaluate the effectiveness of our approach, we conducted numerical experiments on image classification tasks using the Fashion-MNIST and CIFAR10 datasets, and the results demonstrate significant improvements in accuracy, with enhancements of 0:5% and 1:4% observed, respectively, compared to the traditional p1 t step size. [ABSTRACT FROM AUTHOR]

Underwater image enhancement technology is crucial for the human exploration and exploitation of marine resources. The visibility of underwater images is affected by visible light attenuation. This paper proposes an image reconstruction method based on the decomposition–fusion of multi-channel luminance data to enhance the visibility of underwater images. The proposed method is a single-image approach to cope with the condition that underwater paired images are difficult to obtain. The original image is first divided into its three RGB channels. To reduce artifacts and inconsistencies in the fused images, a multi-resolution fusion process based on the Laplace–Gaussian pyramid guided by a weight map is employed. Image saliency analysis and mask sharpening methods are also introduced to color-correct the fused images. The results indicate that the method presented in this paper effectively enhances the visibility of dark regions in the original image and globally improves its color, contrast, and sharpness compared to current state-of-the-art methods. Our method can enhance underwater images in engineering practice, laying the foundation for in-depth research on underwater images. [ABSTRACT FROM AUTHOR]

Diagnosing a disease requires observing the affected tissues and drawing conclusions based on specific known features. Conventionally, a pathologist would diagnose the sample manually by placing it on a glass slide and viewing it under the microscope. These microscopes existed 400 years ago, but over the years, there have been modifications aimed at digitizing every possible diagnostic test. One of the major advantages of digitizing the process is the reduced time consumption for acquiring, processing, and analyzing the slides. Another positive aspect is the reduction in subjectivity achieved by utilizing artificial intelligence (AI) algorithms to classify and diagnose specific diseases. This is achieved by attaching a digital camera to the microscope, which captures images of the glass slides for subsequent processing and diagnosis. There has been a lot of research in this field, but its implementation has been hindered by challenges such as interoperability and high-resolution data, resulting in large file sizes. Various applications for whole slide imaging, such as disease diagnosis techniques, whole slide imaging (WSI) scanners, digital slide scanners, the Internet of Things (IoT), and AI, have been explored in this study. This paper reviews the trends and evolution of microscopes leading to present-day digital pathology scanners, with a major focus on one of the digital techniques, which is whole slide imaging. It also explores various areas where AI has been integrated into whole-slide imaging. [ABSTRACT FROM AUTHOR]

Metallographic image analysis is vital in the field of metal science due to its potential to automate the sensing process for grain and particle size estimation. To ensure the good quality and reliability of metal products, analysis of the integrity of metallic components is required. In contemporary manufacturing processes, microscopic analysis is a crucial step, mainly when complex systems like gearboxes, turbines, or engines are assembled using various components from multiple suppliers. A final product's quality, durability, and lifespan are determined via the quality analysis of properties of a material with proper tolerances. A flaw in a single component can cause the breakdown of the entire finished product. To ensure the good quality of a material, micro-structural analysis is necessary, which includes the routine measurement of inclusions. The particle and grain sizes of particulate samples are the most crucial physical characteristics of metals. Their measurement is routinely conducted across various industries, and they are frequently considered essential parameters in the creation of many products. This paper discusses the role of sensors in enhancing the accuracy and efficiency of metallographic image analysis, as well as the challenges and limitations associated with this technology. The paper also highlights the potential applications of sensor-assisted metallographic image analysis in various industries, such as aerospace, automotive, and construction. The paper concludes by identifying future research directions for this emerging field, including the development of more sophisticated algorithms for grain and particle size estimation, the integration of multiple sensors for more accurate measurements, and the exploration of new sensing modalities for metallographic image analysis. [ABSTRACT FROM AUTHOR]

Topological data analysis (TDA) is a method of feature extraction based on data topological structure. Image feature extraction using TDA has been shown to be superior to other feature extraction techniques in some problems, so it has recently received the attention of researchers. In this paper, clothing image retrieval based on topology features and color texture features is studied. The main work is as follows: (1) Based on the analysis of image data by persistent homology, the feature construction method of a topology feature histogram is proposed, which can represent the ruler of image local topological data, and make up for the shortcomings of traditional feature extraction methods. (2) The improvement of Wasserstein distance is presented, while the similarity measure method named topology feature histogram distance is proposed. (3) Because the single feature has some problems such as the incomplete description of image information and poor robustness, the clothing image retrieval is realized by combining the topology feature with the color texture feature. The experimental results show that the proposed algorithm, namely topology feature histogram + corresponding distance, can effectively reduce the computation time while ensuring the accuracy. Compared with the method using only color texture, the retrieval rate of top5 is improved by 14.9%. Compared with the method using cubic complex + Wasserstein distance, the retrieval rate of top5 is improved by 3.8%, while saving 3.93 s computation time. [ABSTRACT FROM AUTHOR]

Cables are vital load-bearing components of cable-stayed bridges. Surface defects can lead to internal corrosion and fracturing, significantly impacting the stability of the bridge structure. The detection of surface defects from bridge cable images faces numerous challenges, including shadow disturbances due to uneven lighting and difficulties in addressing multiscale defect features. To address these challenges, this paper proposes a novel and cost-effective deep learning segmentation network, named Trans-DCN, to detect defects in the surface of the bridge cable. The network leverages an efficient Transformer-based encoder and integrates multiscale features to overcome the limitations associated with local feature inadequacy. The decoder implements an atrous Deformable Convolution (DCN) pyramid and dynamically fuses low-level feature information to perceive the complex distribution of defects. The effectiveness of Trans-DCN is evaluated by comparing it with state-of-the-art segmentation baseline models using a dataset comprising cable bridge defect images. Experimental results demonstrate that our network outperforms the state-of-the-art network SegFormer, achieving a 27.1% reduction in GFLOPs, a 1.2% increase in mean Intersection over Union, and a 1.5% increase in the F1 score. Ablation experiments confirmed the effectiveness of each module within our network, further substantiating the significant validity and advantages of Trans-DCN in the task of bridge cable defect segmentation. The network proposed in this paper provides an effective solution for downstream cable bridge image analysis. [ABSTRACT FROM AUTHOR]

Supervised learning has been the cornerstone of many successful medical imaging applications. However, its reliance on large labeled datasets poses significant challenges, especially in the medical domain, where data annotation is time-consuming and expensive. In response, self-supervised learning (SSL) has emerged as a promising alternative, leveraging unlabeled data to learn meaningful representations without explicit supervision. This paper provides a detailed overview of supervised learning and its limitations in medical imaging, underscoring the need for more efficient and scalable approaches. The study emphasizes the importance of the area under the curve (AUC) as a key evaluation metric in assessing SSL performance. The AUC offers a comprehensive measure of model performance across different operating points, which is crucial in medical applications, where false positives and negatives have significant consequences. Evaluating SSL methods based on the AUC allows for robust comparisons and ensures that models generalize well to real-world scenarios. This paper reviews recent advances in SSL for medical imaging, demonstrating their potential to revolutionize the field by mitigating challenges associated with supervised learning. Key results show that SSL techniques, by leveraging unlabeled data and optimizing performance metrics like the AUC, can significantly improve the diagnostic accuracy, scalability, and efficiency in medical image analysis. The findings highlight SSL's capability to reduce the dependency on labeled datasets and present a path forward for more scalable and effective medical imaging solutions. [ABSTRACT FROM AUTHOR]

The accurate distribution of joints on the tunnel face is crucial for assessing the stability and safety of surrounding rock during tunnel construction. This paper introduces the Mask R-CNN image segmentation algorithm, a state-of-the-art deep learning model, to achieve efficient and accurate identification and extraction of joints on tunnel face images. First, digital images of tunnel faces were captured and stitched, resulting in 286 complete images suitable for analysis. Then, the joints on the tunnel face were extracted using traditional image processing algorithms, the commonly used U-net image segmentation model, and the Mask R-CNN image segmentation model introduced in this paper to address the lack of recognition accuracy. Finally, the extraction results obtained by the three methods were compared. The comparison results show that the joint extraction method based on the Mask R-CNN image segmentation deep learning model introduced in this paper achieved the best joint extraction effect with a Dice similarity coefficient of 87.48%, outperforming traditional methods and the U-net model, which scored 60.59% and 75.36%, respectively, realizing accurate and efficient acquisition of tunnel face rock joints. These findings suggest that the Mask R-CNN model can be effectively implemented in real-time monitoring systems for tunnel construction projects. [ABSTRACT FROM AUTHOR]

Image classification is a critical task in the field of computer vision, and its importance has significantly increased over the past few years. Machine learning and deep learning techniques have demonstrated immense potential in this field. However, traditional image classification models require a vast amount of training data, which can be challenging and expensive to obtain. To overcome this limitation, researchers are turning to few-shot learning, which aims to classify images with limited training samples. This paper presents a detailed analysis of the field of image classification using few-shot learning. First, it investigates the use of data augmentation, transfer learning, and meta-learning methods in this field. Then, it introduces several commonly used datasets and evaluation metrics in few-shot classification, compares several classical few-shot classification methods, and summarizes the experimental results obtained from public datasets. Finally, this paper analyzes the current challenges in few-shot image classification and suggests potential future directions. [ABSTRACT FROM AUTHOR]

Computer visualization can intuitively reflect the process and results of crustal deformation. In this paper, taking into account the intraplate deformation, combined with computer visualization technology, using robust estimation method that can identify data with high collapse pollution rate, combined with the overall rotation and linear strain model (RELSM) that describes block movement, the GPS observation velocity field data of the Chinese Mainland tectonic environment monitoring network located in Ordos and its adjacent areas are screened, and the strain data are calculated to generate visual images for analysis. The results show that the method proposed in this paper can effectively consider the smoothness of internal plate deformation and the differences in local structures, suppress gross errors, and obtain good velocity field fitting results. [ABSTRACT FROM AUTHOR]

Structural planes decrease the strength and stability of rock masses, severely affecting their mechanical properties and deformation and failure characteristics. Therefore, investigation and analysis of structural planes are crucial tasks in mining rock mechanics. The drilling camera obtains image information of deep structural planes of rock masses through high-definition camera methods, providing important data sources for the analysis of deep structural planes of rock masses. This paper addresses the problems of high workload, low efficiency, high subjectivity, and poor accuracy brought about by manual processing based on current borehole image analysis and conducts an intelligent segmentation study of borehole image structural planes based on the U2-Net network. By collecting data from 20 different borehole images in different lithological regions, a dataset consisting of 1,013 borehole images with structural plane type, lithology, and color was established. Data augmentation methods such as image flipping, color jittering, blurring, and mixup were applied to expand the dataset to 12,421 images, meeting the requirements for deep network training data. Based on the PyTorch deep learning framework, the initial U2-Net network weights were set, the learning rate was set to 0.001, the training batch was 4, and the Adam optimizer adaptively adjusted the learning rate during the training process. A dedicated network model for segmenting structural planes was obtained, and the model achieved a maximum F-measure value of 0.749 when the confidence threshold was set to 0.7, with an accuracy rate of up to 0.85 within the range of recall rate greater than 0.5. Overall, the model has high accuracy for segmenting structural planes and very low mean absolute error, indicating good segmentation accuracy and certain generalization of the network. The research method in this paper can serve as a reference for the study of intelligent identification of structural planes in borehole images. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods. [ABSTRACT FROM AUTHOR]

With the rapid development of sports, the number of sports images has increased dramatically. Intelligent and automatic processing and analysis of moving images are significant, which can not only facilitate users to quickly search and access moving images but also facilitate staff to store and manage moving image data and contribute to the intellectual development of the sports industry. In this paper, a method of table tennis identification and positioning based on a convolutional neural network is proposed, which solves the problem that the identification and positioning method based on color features and contour features is not adaptable in various environments. At the same time, the learning methods and techniques of table tennis detection, positioning, and trajectory prediction are studied. A deep learning framework for recognition learning of rotating flying table tennis is put forward. The mechanism and methods of positioning, trajectory prediction, and intelligent automatic processing of moving images are studied, and the self-built data sets are trained and verified. [ABSTRACT FROM AUTHOR]

The article announces the 2009 Boeing Award for Best Paper in Image Analysis and Interpretation given to Robert A. Chastain Jr., Matthew A. Struckhoff, and David R. Larsen from the American Society for Photogrammetry and Remote Sensing (ASPRS).

The article provides information on the Boeing Award for Best Paper in Image Analysis and Interpretation.

The article offers information on the winners of the Boeing Award for Best Paper in Image Analysis and Interpretation. The American Society for Photogrammetry and Remote Sensing (ASPRS) Boeing Award Selection Committee has announced that Xiaoliang Lu, Ronggao Liu, Jiyuan Liu, and Shunling Liang have received this award. Relative to this, it is posed that presentation of this award will take place in May 2008 during the ASPRS Annual Conference to be conducted in Portland, Oregon. The award aims to induce development and recognize achievement in image interpretation and analysis through acknowledgement of efficient publication in this field.

Cancer is a serious disease that causes death by genomic disorder combination and diversity of unreasoning changes. This paper study the major deep learning techniques that are addressing medical image analysis and summarizes over 200 contributed articles to the subject, in particular those studies that are published in the last 6 years (since 2016). The main purpose of this paper study is to survey the deep learning algorithms for cancer detection and diagnosis. the results show that the convolutional neural network (CNN) is the most broadly used when it comes to deep learning and medical image analysis. [ABSTRACT FROM AUTHOR]

This paper describes a novel feature-based stereovision matching process based on a pair of omnidirectional images in forest stands acquired with a stereovision sensor equipped with fish-eye lenses. The stereo analysis problem consists of the following steps: image acquisition, camera modelling, feature extraction, image matching and depth determination. Once the depths of significant points on the trees are obtained, the growing stock volume can be estimated by considering the geometrical camera modelling, which is the final goal. The key steps are feature extraction and image matching. This paper is devoted solely to these two steps. At a first stage a segmentation process extracts the trunks, which are the regions used as features, where each feature is identified through a set of attributes of properties useful for matching. In the second step the features are matched based on the application of the following four well known matching constraints, epipolar, similarity, ordering and uniqueness. The combination of the segmentation and matching processes for this specific kind of sensors make the main contribution of the paper. The method is tested with satisfactory results and compared against the human expert criterion. [ABSTRACT FROM AUTHOR]

Technological advances in unmanned aerial vehicles (UAVs) pursued by artificial intelligence (AI) are improving remote sensing applications in smart agriculture. These are valuable tools for monitoring and disease identification of plants as they can collect data with no damage and effects on plants. However, their limited carrying and battery capacities restrict their performance in larger areas. Therefore, using multiple UAVs, especially in the form of a swarm is more significant for monitoring larger areas such as crop fields and forests. The diversity of research studies necessitates a literature review for more progress and contribution in the agricultural field. In this review, the comparative analysis of existing literature surveys is explored. This paper aims to provide an overview of AIbased UAV swarms, different cameras and sensors, image processing, and machine learning (ML) algorithms for image analysis having the purpose of monitoring and disease identification. Brassica plants are focused as they are grown on wider scales globally. Brassica species, the commonly infected diseases, and different types of disease detectionmethods are discussed. Investigations show the significance of using UAV swarms for growthmonitoring growth for yield estimation, health monitoring, water status monitoring and irrigation management, nutrition disorders monitoring, pest and disease detection, and pesticide and fertilizer spraying in Brassica plants. Finally, some challenges of swarm-based applications are also addressed that require future consideration. The significance of this paper is that it suggests its readers embrace swarm-based technologies in the pursuit of more efficient production with relevant economic benefits. [ABSTRACT FROM AUTHOR]

With the increase in the amount of images online, the whole Internet is becoming an image database. Since there are so many available images, it is difficult for users to find the desired images. Unlike text search engines, image search engines cannot fully recognize the visual meaning of an image. In addition, it is difficult to obtain the desired images from the keywords provided by the user, since a keyword may contain multiple meanings. To solve these problems, this paper proposes a psychological intention diagram of past users, if inquiring using a keyword, to predict the images that these users want. Based upon the novel psychological diagram, this paper proposes a search engine that analyzes images in the sequential probing of the current user if he/she inquires after the same keywords as previous users. Moreover, this paper also constructs a psychological intention diagram of the designers of the web pages containing the keyword. This type of psychological intention diagram is used when a query is not issued by past users. To the best of our knowledge, this paper is the first one considering the psychological viewpoint of users and web designers in guiding the retrieval of the search engine. The experimental results show that the proposed image search engine has high precision; therefore, the method of providing images can help users to find their desired image more easily. [ABSTRACT FROM AUTHOR]

This study characterizes and compares the parameters of the quality reproduction of fine elements in flexography on coated and uncoated paper as well as on OPP film (oriented polypropylene). A monochrome test form was created and printed using cyan UV ink. The analysis of results confirms the importance of interaction between the printing substrate and ink; it also indicates identical line and text deformations on the print. Quality reproduction on coated paper is higher in relation to OPP film for all the research parameters. The ink penetrates significantly more and with more irregularity into the pores and throats of the uncoated paper, which results in less homogeneous elements, and in such way that it loses its original shape. In coated paper and OPP film, the ink spreads more on the substrate area which gives it a significantly more homogeneous shape. However, due to the surface spread of the ink, the biggest changes in the size of fine elements are noticeable in the OPP film. The scientific contribution of this paper is based on the comparison of print quality parameters of fine elements, which can contribute to the optimization of the production process and quality of the final graphical product. [ABSTRACT FROM AUTHOR]

Object detection remains a pivotal aspect of remote sensing image analysis, and recent strides in Earth observation technology coupled with convolutional neural networks (CNNs) have propelled the field forward. Despite advancements, challenges persist, especially in detecting objects across diverse scales and pinpointing small-sized targets. This paper introduces YOLO-SE, a novel YOLOv8-based network that innovatively addresses these challenges. First, the introduction of a lightweight convolution SEConv in lieu of standard convolutions reduces the network's parameter count, thereby expediting the detection process. To tackle multi-scale object detection, the paper proposes the SEF module, an enhancement based on SEConv. Second, an ingenious Efficient Multi-Scale Attention (EMA) mechanism is integrated into the network, forming the SPPFE module. This addition augments the network's feature extraction capabilities, adeptly handling challenges in multi-scale object detection. Furthermore, a dedicated prediction head for tiny object detection is incorporated, and the original detection head is replaced by a transformer prediction head. To address adverse gradients stemming from low-quality instances in the target detection training dataset, the paper introduces the Wise-IoU bounding box loss function. YOLO-SE showcases remarkable performance, achieving an average precision at IoU threshold 0.5 (AP50) of 86.5% on the optical remote sensing dataset SIMD. This represents a noteworthy 2.1% improvement over YOLOv8 and YOLO-SE outperforms the state-of-the-art model by 0.91%. In further validation, experiments on the NWPU VHR-10 dataset demonstrated YOLO-SE's superiority with an accuracy of 94.9%, surpassing that of YOLOv8 by 2.6%. The proposed advancements position YOLO-SE as a compelling solution in the realm of deep learning-based remote sensing image object detection. [ABSTRACT FROM AUTHOR]

This smartphone colorimetry investigated RGB (red, green and blue), HSV (hue, saturation and value of brightness) and CMYK (cyan, magenta, yellow and key) color parameters for characterizing bloodstains. Blood samples, separately deposited on cotton cloths and tissue papers, were analyzed by the 'Colorimeter X' application on an iPhone XR after 1, 5, 7, 9 and 11 days. The reductions in RGB and V values recorded by the smartphone application are consistent with darker bloodstain over time. Bloodstain colors are sensitive to the substrate and person-to-person variation, but a similar correlation with time could be established by a linear least squares fitting. With the highest coefficient of determination averaged from four samples, the V value is the most effective parameter for describing bloodstain ageing. For other color spaces, the R and K almost match the V value in measuring the bloodstains. Because these three values may be susceptible to the deviation in the measurement, the B value is suggested as an additional parameter in the bloodstain characterization. This small-scale study demonstrates the potential of colorimetric parameters in an on-site analysis by a cost-effective smartphone. [ABSTRACT FROM AUTHOR]

Intelligent wheelchair blind spot obstacle detection is an important issue for semi-enclosed special environments in elderly communities. However, the LiDAR- and 3D-point-cloud-based solutions are expensive, complex to deploy, and require significant computing resources and time. This paper proposed an improved YOLOV5 lightweight obstacle detection model, named GC-YOLO, and built an obstacle dataset that consists of incomplete target images captured in the blind spot view of the smart wheelchair. The feature extraction operations are simplified in the backbone and neck sections of GC-YOLO. The backbone network uses GhostConv in the GhostNet network to replace the ordinary convolution in the original feature extraction network, reducing the model size. Meanwhile, the CoordAttention is applied, aiming to reduce the loss of location information caused by GhostConv. Further, the neck stem section uses a combination module of the lighter SE Attention module and the GhostConv module to enhance the feature extraction capability. The experimental results show that the proposed GC-YOLO outperforms the YOLO5 in terms of model parameters, GFLOPS and F1. Compared with the YOLO5, the number of model parameters and GFLOPS are reduced by 38% and 49.7%, respectively. Additionally, the F1 of the proposed GC-YOLO is improved by 10% on the PASCAL VOC dataset. Moreover, the proposed GC-YOLO achieved mAP of 90% on the custom dataset. [ABSTRACT FROM AUTHOR]

In recent years, remote sensing image processing technology has developed rapidly, and the variety of remote sensing images has increased. Solving a geographic problem often requires multiple remote sensing images to be used together. For an image processing analyst, it is difficult to become proficient in the image processing of multiple types of remote sensing images. Therefore, it is necessary to have multiple image processing analysts collaborate to solve geographic problems. However, as a result of the naturally large volumes of data and the computer resources they consume for analysis, remote sensing images present a barrier in the collaboration of multidisciplinary remote sensing undertakings and analysts. As a result, during the development of the collaborative analysis process, it is necessary to achieve the online processing and analysis of remote sensing images, as well as to standardize the online remote sensing image collaborative analysis process. To address the above issues, a hierarchical collaborative online processing and analysis framework was developed in this paper. This framework defined a clear collaborative analysis structure, and it identifies what kinds of online image processing and analysis activities participants can engage in to successfully conduct collaborative processes. In addition, a collaborative process construction model and an online remote sensing image processing analysis model were developed to assist participants in creating a standard collaborative online image processing and analysis process. In order to demonstrate the feasibility and effectiveness of the framework and model, this paper developed a collaborative online post-disaster assessment process that utilizes radar images and optical remote sensing images for a real forest fire event. This process was based on the BPMN2.0 and OGC dual standards. Based on the results, the proposed framework provides a hierarchical collaborative remote sensing image processing and analysis process with well-defined stages and activities to guide the participants' mutual collaboration. Additionally, the proposed model can help participants to develop a standardized collaborative online image processing process in terms of process structure and information interactions. [ABSTRACT FROM AUTHOR]

The airlift pump is a key part of wastewater treatment and is employed as an innovative and feasible collection tool. However, as one of the key factors in the lifting capability of airlift pumps, film thickness in the gas–liquid two-phase flow operating in pumps is still an unknown topic because it is difficult to measure. This paper proposes a visualization method for measuring film thickness and investigates the film thickness when operating under gas flow with a high rate in airlift pumps using experiments. Firstly, a simulation experiment platform was built, and the images of the film structure were acquired by a high-speed camera. Then, image-processing technology and an image distortion correction were proposed to extract the gas–liquid interface for studying the thickness of the film. The experimental results demonstrated that a large film thickness ranging from 0.15 D to 0.24 D was found in airlift pumps and that its film thickness kept a constant value, even under a high gas superficial velocity, maintaining a large output liquid flow from airlift pumps. As wastewater was carried by wastewater treatment, a larger film thickness of the annular film will benefit the high lifting rate of wastewater. The works in this paper offer valuable insights for the higher performance of working airlift pumps and wastewater treatment efficiency. [ABSTRACT FROM AUTHOR]

Vitiligo is a dermatological condition characterized by depigmentation of the skin, resulting from the loss of melanocytes. Automatic image analysis methods are essential for diagnosing vitiligo and tracking its development. Because it is good at defining object boundaries, watershed segmentation is a frequently used technique for segmenting medical images. However, traditional watershed segmentation may produce oversegmentation and under-segmentation issues in vitiligo images due to their complex and irregular patterns. This research paper proposes a modified watershed segmentation approach tailored specifically for vitiligo image analysis. The proposed method incorporates pre-processing steps to enhance image contrast and reduce noise, followed by a novel marker-based watershed segmentation algorithm. In this algorithm, markers are strategically placed based on local intensity and texture features to guide the segmentation process and improve boundary delineation. Annotated ground truth images from a collection of vitiligo images are used to assess the effectiveness of the suggested technique. Several quantitative indicators, including accuracy, the Jaccard index, and the Dice similarity coefficient, are used to compare the segmentation outcomes produced by the suggested method with those produced by advanced techniques. Experimental results demonstrate that the modified watershed segmentation method outperforms existing approaches in accurately segmenting vitiligo lesions while minimizing over-segmentation and undersegmentation errors. The proposed method shows promising potential for aiding dermatologists in diagnosing and monitoring vitiligo progression, facilitating timely treatment interventions, and improving patient confidence. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is rapidly advancing, aiming to mimic human cognitive abilities, and is addressing complex medical challenges in the field of biological science. Over the past decade, AI has experienced exponential growth and proven its effectiveness in processing massive datasets and optimizing decision-making. The main content of this review paper emphasizes the active utilization of AI in the field of stem cells. Stem cell therapies use diverse stem cells for drug development, disease modeling, and medical treatment research. However, cultivating and differentiating stem cells, along with demonstrating cell efficacy, require significant time and labor. In this review paper, convolutional neural networks (CNNs) are widely used to overcome these limitations by analyzing stem cell images, predicting cell types and differentiation efficiency, and enhancing therapeutic outcomes. In the biomedical sciences field, AI algorithms are used to automatically screen large compound databases, identify potential molecular structures and characteristics, and evaluate the efficacy and safety of candidate drugs for specific diseases. Also, AI aids in predicting disease occurrence by analyzing patients' genetic data, medical images, and physiological signals, facilitating early diagnosis. The stem cell field also actively utilizes AI. Artificial intelligence has the potential to make significant advances in disease risk prediction, diagnosis, prognosis, and treatment and to reshape the future of healthcare. This review summarizes the applications and advancements of AI technology in fields such as drug development, regenerative medicine, and stem cell research. [ABSTRACT FROM AUTHOR]

Agriculture plays a crucial role in fostering sustainable growth through the integration of various technological advancements such as image processing, artificial intelligence, deep learning, and the Internet of Things (IoT). The global population is increasing on a daily basis. The increasing demand within the agriculture industry has necessitated the collective enhancement of plant cultivation and field productivity. This paper emphasizes the significance of effectively managing the crop during its initial growth phase as well as during the harvesting era. Image processing and artificial neural networks are employed as distinct methodologies for detecting illnesses on leaves. When capturing images using drones, the resulting images undergo a process of segmentation and transformation, resulting in the identification of three distinct vectors that represent diseases. These vectors include colour, texture, and morphology. This paper reviews on various disease classification strategies that can be utilized for the detection of plant diseases. [ABSTRACT FROM AUTHOR]