Search

Three-section landslides are renowned for their immense size, concealed development process, and devastating impact. This study conducted physical model tests to simulate one special geological structure called a three-section-within landslide. The failure process and precursory characteristics of the tested samples were meticulously analyzed using video imagery, micro-seismic (MS) signals, and acoustic emission (AE) signals, with a focus on event activity, intensity, and frequency. A novel classification method based on AE waveform characteristics was proposed, categorizing AE signals into burst signals and continuous signals. The findings reveal distinct differences in the evolution of these signals. Burst signals appeared exclusively during the crack propagation and failure stages. During these stages, the cumulative AE hits of burst signals increased gradually, with amplitude rising and then declining. High-amplitude burst signals were predominantly distributed in the middle- and high-frequency bands. In contrast, cumulative AE hits of continuous signals escalated rapidly, with amplitude monotonously increasing, and high-amplitude continuous signals were primarily distributed in the low-frequency band. The emergence of burst signals and high-frequency AE signals indicated the generation of microcracks, serving as early-warning indicators. Notably, the early-warning points of AE signals were detected earlier than those of video imagery and MS signals. Furthermore, the early-warning point of burst signals occurred earlier than those of continuous signals, and the early-warning point of the classification method preceded that of overall AE signals. [ABSTRACT FROM AUTHOR]

The operational effectiveness of a railroad track robot that is designed for railcar undercarriage inspection is provided. Beyond describing the robot's design details and onboard imaging system, the paper analyzes the recorded video images and offers design improvements to increase their clarity. The robot is designed to be deployed trackside, traverse over the rails, and then maneuver in between the rails beneath a stopped train in a siding or a railyard. The under-carriage conditions are documented by onboard video cameras for automated or manual postprocessing. The intent is to inspect the components that are not visible to the conductor or train inspector during a walk-along inspection of a stationary train. An assessment of the existing design, followed by modification and validation, is presented. The results from a prototype unit developed by the Railway Technologies Laboratory at Virginia Tech (RTL) indicate that with proper positioning of off-the-shelf imaging systems such as cameras manufactured by GoPro® in San Mateo, CA, USA and appropriate lighting, it is possible to capture videos that are sufficiently clear for manual (by a railroad engineer), semi-automated, or fully automated (using Artificial Intelligence or Machine Learning methods) inspections of rolling stock undercarriages. Additionally, improvements to the control, mobility, and reliability of the system are documented, although reliability throughout operation and the ability to consistently climb out of the track bed remain points of future investigation. [ABSTRACT FROM AUTHOR]

For the problem of interference between shearer drum and hydraulic support guard plate, an interference state intelligent recognition method for shearer drum and hydraulic support guard plate of improved YOLOv5s algorithm is proposed. The use of boundary constraint and non-linear contextual regularization based on the group's previous proposed method of defogging and dust removal to clarify the video image, improve the quality of the monitoring video image of the comprehensive mining face. The YOLOv5s model is improved by replacing the ordinary convolutional Conv in the YOLOv5s backbone network with Ghost convolution, the improved algorithm greatly reduces the number of model parameters and improves the model recognition speed. At the same time, the coordinate attention mechanism is introduced to improve the model's ability to extract the features from the guard plate and shearer, and improve the recognition accuracy. The soft non-maximum suppression algorithm (Soft-NMS) anchor frame screening method is used to reduce the problem of missed detection due to overlapping guard plates. For the problem of determining the interference state of shearer drum and hydraulic support guard plate, the method for determining anchor box overlap degree between hydraulic support guard plate and shearer drum. The improved YOLOv5s algorithm is compared with YOLOv5s and YOLOv3-tiny algorithm. The results indicate that compared with the original YOLOv5s model, the recognition accuracy of this method has been improved by about 8.1%, and GFLOPs have been reduced by 1.86 times. mAP@.5 was increased to 97.2%, and the average recognition speed is 169 frames/s. The improved YOLOv5s algorithm is used to validate the interference state recognition effect for video images of shearer drum and hydraulic support guard plate in in actual fully mechanized mining faces, and the results show that the recognition accuracy of interference state between the coal shearer drum and the hydraulic support guard plate is 96%.

Background: With the increase in basketball competition intensity, video image analysis-based methods have been increasingly applied to improve the technical level of basketball players. Methods: Taking the example of one-handed set shoulder shooting (the basketball player spreads legs apart at shoulder width, holds the ball over the right shoulder, extends the right hand along with lower body movement, and releases the ball softly using fingers), this study compared the technical differences between 20 level 2 basketball players (level 2 group) and 20 basketball specialized students (specialized group) by capturing video images using a high-speed camera and conducting independent sample t-tests. Results: The level 2 group had a significantly higher shooting percentage than the specialized group (p=0.005). Additionally, the level 2 group had shorter dribbling time and longer shooting time compared to the specialized group (p=0.032; p=0.021). The amplitude of variation in the knee, hip, and elbow joints was significantly greater than that of the specialized group (p=0.008/0.016/0.031). The flexion angles of the index finger and middle finger after striking in the level 2 group were significantly higher than those of the specialized group (p=0.021/0.036). The level 2 group also had a smaller striking angle and a larger striking height and speed than the specialized group (p=0.001; p=0.005/0.006). Conclusion: Athletes of different levels show differences in phase duration and joint angles when performing one-handed set shoulder shooting, providing a basis for athletes' training.

Camera surveillance systems can record urban waterlogging processes. Objects with regular shapes and fixed sizes captured by the camera can be utilized to calculate urban waterlogging depths based on geometric principles. In this study, we propose a machine learning‐based method to measure urban waterlogging depths using wheels and traffic buckets captured in video images as reference objects. This method is validated through laboratory experiments and observed data. The results demonstrate that: (1) the urban waterlogging depths calculated using urban reference objects show high consistency with the observed water level data; (2) in the laboratory scenario, the probability of error within 3 cm for measurements based on the hub, tire, and traffic bucket are 99.07%, 99.38%, and 81.55%, respectively; (3) in the real‐world scenario, the probability of error within 3 cm for measurements based on car hubs and pickup truck hubs are 97.30% and 95.14%, respectively. In conclusion, urban waterlogging depths can be accurately measured using reference objects with regular shapes. The proposed method can help obtain waterlogging data with higher temporal and spatial resolution at lower economic costs, which is of great significance for urban flood control. [ABSTRACT FROM AUTHOR]

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology 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 operational effectiveness of a railroad track robot that is designed for railcar undercarriage inspection is provided. Beyond describing the robot’s design details and onboard imaging system, the paper analyzes the recorded video images and offers design improvements to increase their clarity. The robot is designed to be deployed trackside, traverse over the rails, and then maneuver in between the rails beneath a stopped train in a siding or a railyard. The under-carriage conditions are documented by onboard video cameras for automated or manual postprocessing. The intent is to inspect the components that are not visible to the conductor or train inspector during a walk-along inspection of a stationary train. An assessment of the existing design, followed by modification and validation, is presented. The results from a prototype unit developed by the Railway Technologies Laboratory at Virginia Tech (RTL) indicate that with proper positioning of off-the-shelf imaging systems such as cameras manufactured by GoPro® in San Mateo, CA, USA and appropriate lighting, it is possible to capture videos that are sufficiently clear for manual (by a railroad engineer), semi-automated, or fully automated (using Artificial Intelligence or Machine Learning methods) inspections of rolling stock undercarriages. Additionally, improvements to the control, mobility, and reliability of the system are documented, although reliability throughout operation and the ability to consistently climb out of the track bed remain points of future investigation.

Three-section landslides are renowned for their immense size, concealed development process, and devastating impact. This study conducted physical model tests to simulate one special geological structure called a three-section-within landslide. The failure process and precursory characteristics of the tested samples were meticulously analyzed using video imagery, micro-seismic (MS) signals, and acoustic emission (AE) signals, with a focus on event activity, intensity, and frequency. A novel classification method based on AE waveform characteristics was proposed, categorizing AE signals into burst signals and continuous signals. The findings reveal distinct differences in the evolution of these signals. Burst signals appeared exclusively during the crack propagation and failure stages. During these stages, the cumulative AE hits of burst signals increased gradually, with amplitude rising and then declining. High-amplitude burst signals were predominantly distributed in the middle- and high-frequency bands. In contrast, cumulative AE hits of continuous signals escalated rapidly, with amplitude monotonously increasing, and high-amplitude continuous signals were primarily distributed in the low-frequency band. The emergence of burst signals and high-frequency AE signals indicated the generation of microcracks, serving as early-warning indicators. Notably, the early-warning points of AE signals were detected earlier than those of video imagery and MS signals. Furthermore, the early-warning point of burst signals occurred earlier than those of continuous signals, and the early-warning point of the classification method preceded that of overall AE signals.

In view of the low accuracy and high cost of existing urban flooding monitoring methods, this study proposed a method for measuring the depth of urban flooding using a combination of surveillance cameras and intentionally designed rulers. The method includes the binocular method and the subruler method, two implementation approaches based on a self-designed floating ruler to measure urban flooding depth. First, floating rulers were installed in the test area. Then, the pixel position of the floating rulers was obtained through surveillance cameras and the YOLOv5s object detection model. Finally, the water depth of urban flooding was obtained using two-pixel position to water depth transfer functions of the binocular method and the subruler method. The results showed that our proposed method precisely measured the depth of urban flooding in surveillance video frames, exhibiting an average relative measurement error of 8.541% and 5.250% and an average frame processing duration of 0.397 and 0.468 s. Compared with the existing method using machine vision and the binocular method, the subruler method can provide a low-cost and high-accuracy urban flooding monitoring solution, which has the potential for deployment in the field. The subruler method is recommended for use in areas prone to deep water accumulation. [ABSTRACT FROM AUTHOR]

Copyright of Rolling Stock (1002-7602) is the property of Rolling Stock Editorial Office 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 Camera surveillance systems can record urban waterlogging processes. Objects with regular shapes and fixed sizes captured by the camera can be utilized to calculate urban waterlogging depths based on geometric principles. In this study, we propose a machine learning‐based method to measure urban waterlogging depths using wheels and traffic buckets captured in video images as reference objects. This method is validated through laboratory experiments and observed data. The results demonstrate that: (1) the urban waterlogging depths calculated using urban reference objects show high consistency with the observed water level data; (2) in the laboratory scenario, the probability of error within 3 cm for measurements based on the hub, tire, and traffic bucket are 99.07%, 99.38%, and 81.55%, respectively; (3) in the real‐world scenario, the probability of error within 3 cm for measurements based on car hubs and pickup truck hubs are 97.30% and 95.14%, respectively. In conclusion, urban waterlogging depths can be accurately measured using reference objects with regular shapes. The proposed method can help obtain waterlogging data with higher temporal and spatial resolution at lower economic costs, which is of great significance for urban flood control.

Target tracking is a core working mode of airborne photoelectric reconnaissance and aiming system, and its performance directly determines the mission efficiency of the airborne system. Aiming at the outstanding problems and technical difficulties in the application of target tracking, according to the multi-sensor configuration and application characteristics of the system, an intelligent target tracking strategy based on inertial measurement and video image information fusion is proposed, which integrates multi-dimensional information such as inertial navigation, motion mea-surement, servo control, geography and image coordinates. Simulation analysis and flight test show that the strategy can effectively improve the anti-jamming performance of target tracking, realize the robust and persistent target tracking in full dynamic complex scenes, and improve the combat ability of reconnaissance and surveillance, target positioning, weapon guidance of the airborne system.

Copyright of Aero Weaponry is the property of Aero Weaponry Editorial Office 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.)

In order to solve the problems of poor image quality, low definition and loss of image information in traditional algorithms, a modeling research of fractional differential equation in cloud computing image fusion algorithm is proposed. Firstly, the method of image denoising and enhancement under the framework of fractional calculus theory and the improved algorithm based on it are discussed. A series of difficult problems in the image processing method based on fractional calculus are discussed. Then, the large data video image in cloud computing environment is fused in scale space through fractional differential equation, and the fused image is decomposed by lifting fractional differential equation to obtain the low-frequency subband coefficients and high-frequency subband coefficients in different scale space. For the low-frequency subband coefficients and high-frequency subband coefficients, their respective fusion schemes are given to obtain the lifting static small transform coefficients of the fused image. The fusion effect of the proposed algorithm is tested from both subjective and objective aspects.The results show that the entropy value of this algorithm is 7.1450, slightly higher than sparse coding algorithm and random walk algorithm, which shows that the fusion processing by this algorithm will not lose the amount of information contained in the image. Therefore, the image denoising and enhancement algorithm of fractional differential equation proposed in this paper has good subjective fusion effect, good clarity and quality of the fused image, and will not lose the information contained in the image.

Remote network teaching has gained significant importance in recent times, with video images serving as a crucial medium for delivering educational content. Ensuring accurate face recognition in these video images is a key challenge. To address this, we present a face recognition algorithm based on an improved frame difference method. The algorithm focuses on enhancing the accuracy of face recognition specifically in remote network teaching video images. By leveraging a generative adversarial network method, we enhance image resolution as a preprocessing step. Subsequently, our proposed image target detection algorithm effectively identifies the face region through foreground and background segmentation. We employ an improved local three-value pattern for face feature extraction, concentrating on the face target region. These features are then input into an integrated neural network face recognition model. Experimental results demonstrate the algorithm's efficacy in enhancing clarity processing, facial object detection, and feature extraction for remote teaching video images. Notably, the proposed method achieves an average gradient of details below 0.1 and attains a facial feature matching degree of 0.98, establishing the high accuracy of facial recognition results in remote teaching video images. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology 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 article shows one of the factors influencing the formation of corrosion of hollow reinforced concrete structures — leakage currents in insulators. The development of corrosion depends on the amount of electricity that has passed through the reinforced concrete. A method for controlling the corrosion state by changing the color parameters on the video image of the reinforced concrete surface is proposed. A full-scale experiment is carried out on samples simulating various degrees of corrosion, as well as on a sample with an unknown level of corrosion. The images are obtained using an industrial endoscope.

Tracking the trajectory of dribble directional shooting in the video image is beneficial to improve the basketball training skills. In this paper, the trajectory tracking method of dribble directional shooting based on the symmetrical algorithm is proposed. The symmetric differential algorithm is used to segment the video image of the dribble directional shooting. In the segmented image sequence, the range of motion of the dribble directional shooting is detected every three consecutive frames. Through the maximum variance ratio threshold method, the motion area of the dribble directional shot is divided. The initial motion coordinates and feature vectors of the dribble directional shooting are calculated, and the characteristic affine transformation equation of the shooting action pixel information is constructed. The Camshift method is used to mark the trajectory contour of the dribble directional shooting. According to the result of the contour extraction, the gray pixel value feature points of the video sequence are fitted, and the trajectory tracking model of the dribble directional shooting is established to accurately track the trajectory of the dribble directional shooting. It is verified that the trajectory of the dribble directional shooting tracked by the proposed method is consistent with the actual situation, and the tracking error average is about 1.9%, that is the reliable trajectory tracking method of dribble directional shooting. [ABSTRACT FROM AUTHOR]

In this paper, an accurate segmentation algorithm of video dynamic background image (VDBI) based on improved wavelet transform is proposed. Based on the smooth processing of VDBI, the traditional wavelet transform process is improved, and the two-layer decomposition of dynamic image is realized by using twodimensional wavelet transform. On the basis of decomposition results and information enhancement processing, image features are detected, feature points are extracted, and quantum ant colony algorithm is adopted to complete accurate segmentation of the image. The maximum SNR of the output results of the proposed algorithm can reach 73.67 dB, the maximum time of the segmentation process is only 7 seconds, the segmentation accuracy shows a trend of decreasing first and then increasing, and the global maximum value can reach 97%, indicating that the proposed algorithm effectively achieves the design expectation. [ABSTRACT FROM AUTHOR]

The article provides a general description of the problems of information support for critical infrastructure management systems in modern conditions using remote mobile sensors on aviation platforms. The basis here is the imbalance between the reliability of the information received and the speed of its receipt, taking into account the on-board video data transmission channels. The increase in the information load on the channels of information transmission about the objects of monitoring is justified. The requirements for time delays for the delivery of video information and its reliability in accordance with the requirements of the QoS system and the standards STANAG 4545: 2013, STANAG 4586: 2012 are briefly given. The direction of implementation of such requirements is proposed by resolving the issue of increasing the likelihood of channel errors during data transmission through communication channels and the occurrence of information losses in the process of compressing the volumes of video images. The disadvantages of existing noise-resistant coding technologies are briefly revealed, which make it possible to increase the reliability of video information in the process of its transmission. And also reveals the shortcomings of existing technologies for reducing the information intensity of video data. Among these disadvantages are: the additional use of redundant binary sequences, and therefore an increase in the initial volumes of video data; the gain in efficiency is compensated by the destruction of the semantic component of the video image, and therefore the risks of loss of reliability of information increase. Solving the imbalance of video data delivery is proposed to be solved by developing methods for encoding transformed video images to increase their compression in conditions of ensuring the required reliability. The improvement of coding technologies for transformed video segments through the use of their preliminary clustering is justified. taking into account the number of series of units in the binary syntactic description of the components of the transformer. The method of formation of structural clusters of clustered components of transforms is proposed on the basis of the content of their binary description – the number of series of units. The main stages of the developed method of coding transformed video segments in the structural space are outlined. [ABSTRACT FROM AUTHOR]

This paper describes an intelligent video surveillance system for human behavior and provides a brief overview of systems with similar functional characteristics. We present a collection of methods and algorithms for automatic recognition of human images, their identification, and analysis of behavior based on motor activity using a cascade of neural networks. A technology for capturing a person's image and tracking their movements between video cameras is proposed. [ABSTRACT FROM AUTHOR]

Due to weather conditions, brightness conditions, capture equipment and other factors, leads to video unclear or even abnormally confused, which is not conducive to monitoring, and can not meet the needs of applications. Based on the actual data of night video surveillance, this paper proposes a new low illumination video image enhancement algorithm, which overcomes the existing problems. We analyze the characteristics of low illumination video image, and use HSV color space instead of traditional RGB space to enhance the robustness of video contrast and color distortion. At the same time, we use wavelet image fusion to highlight the details of video image, so the enhanced video has higher clarity and visual effect. Compared with other four algorithms, the proposed algorithm outperforms the above algorithms in subjective evaluation and objective evaluation. At the same time, compared with other algorithms, the proposed algorithm has faster processing time for each frame. Experiments show that the algorithm can effectively improve the overall brightness and contrast of video images, and avoid the over-enhancement of bright areas near the light source, which can meet the practical application requirements of video surveillance.

Excessive psychological pressure, long working hours, and excessive labor intensity can make people exhausted and affect people's cognition and motor function. Detecting the fatigue state of athletes can prevent excessive fatigue and sports injuries. This article chooses the adaptive median filter method to smooth the image and remove the noise, and uses the adaptive threshold light equalization method to adjust the image's light equalization. According to the admission and rejection criteria of the Sequential Forward Floating Selection (SFFS) algorithm, different feature parameter combinations are used to build a fatigue motion detection model based on Support Vector Machine (SVM). Taking the classification performance of the built SVM detection model as the evaluation criterion, and using the sequence floating forward selection algorithm as the search strategy, the fatigue characteristic parameter optimization selection algorithm is established. The algorithm is used to reduce the dimensionality of the full set of fatigue feature parameters, and the optimal feature subset of fatigue motion is extracted. Based on the paired sample t-test and the analysis of variance method, it analyzes and quantifies the comprehensive influence of individual athlete differences and fatigue exercise on sports behavior and eye movement characteristics. An adaptive detection model is built based on personality parameters, and the design idea of the fatigue feature extraction network is analyzed. In order to make full use of the information of the feature vector output by the fully connected layer, the new network designs two fully connected layers to extract feature vectors. Two types are output by the Softmax loss function, which can directly determine whether the athlete is in a fatigue state. Based on the PERCLOS (Percentage of Eyelid Closure Over the Pupil over time) criterion, this article completes the construction of the fatigue motion sample set, and classifies the face images with more than 80% eyes closed as fatigue samples. This method can apply the PERCLOS criterion to the training of the convolutional neural network, so that it can recognize the fatigue state of the face based on the comprehensive facial features and improve the robustness of the algorithm.

Extracting the fuzzy feature of the mobile video image can effectively improve the low illumination image quality. Traditional methods are used to construct fuzzy feature indexes of mobile terminal video images, and the detailed information of video images is divided, but the bidirectional matching of feature points is ignored, which leads to low extraction accuracy. Therefore, this paper proposes a method for extracting fuzzy features of mobile terminal video images based on SURF-based virtual reality technology. First, perform video image grayscale extraction on the input mobile terminal video image, and detect the closed area in the mobile terminal video image as the radiation invariant area of the terminal video image. Secondly, Hessian matrix is used to detect the feature points of the image, and the non-maximum suppression method and interpolation operation are used to find and locate the extreme value points. Then, the main direction of feature points was determined, and SURF description operator was used for matching to obtain initial matching point pairs. Finally, the obtained fuzzy feature one-way matching result of the video image is matched in two directions, the closest distance ratio is used to match the feature points, and the full constraint condition is used to filter out the wrong matching point pairs, thereby completing the mobile terminal video image fuzzy feature extraction. The experimental results show that the proposed algorithm is effective in feature extraction and matching, stability and speed. The misrecognition rate of the algorithm in this paper is 0.101, and the time used is only 0.41 s, which fully meets the real-time requirements.

In order to effectively extract image features highly related to visual perception quality, improve the image quality evaluation method, under the framework of deep learning, combining the optical flow method and the edge detection algorithm, a multi-feature fusion motion based on improved optical flow is proposed target detection algorithm. First, a video fluid model is proposed. The fluid model decomposes the video object area changes into sub-area zoom, rotation and translation movements. The rigid body area and the area hierarchy describe the spatial relationship of pixels, and the rigid body motion describes the time domain relationship of pixels. It provides a region-based video processing. The associated spatiotemporal is association method. Secondly, a video fluid model is proposed. The video fluid model treats all pixels of the same surface imaged in the video as a fluid, using streamlines to represent the regional motion of the object, and streamlines to represent the pixel motion of the video object, using rotators and translation lines to simplify the streamlines when necessary. The streamline of the same fluid is smooth in the time domain, and the flow pattern is smooth in both the time domain and the space domain. Finally, the top-down deep learning generation model conversion is carried out, and finally through continuous adjustment between different levels, the generation model can reconstruct the original sample with lower error, so that the essential characteristics of this sample are obtained, namely the highest abstract representation of the depth model. After processing the deep learning model, the sample features after dimensionality reduction can be obtained, and the recognition module is used on this basis. Experiments show that the optical flow estimation method based on deep learning and multi-grid, optical flow field estimation method based on variational model and desiccation method proposed in this paper are effective, and it is suitable for moving image analysis, target tracking and 3D reconstruction Such research has certain theoretical significance and practical application value.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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 In order to improve the motion recognition effect of sports athletes based on image recognition technology, this study takes the current common diving athletes as the research material in the actual research, and combines the research status of image recognition to study the athlete’s motion recognition from image processing. Simultaneously, in this study, the gradient segmentation method is used to segment the image, the research object is segmented from the video image, the traditional image grayscale method is improved, and the image segmentation algorithm adapted to the diving motion is obtained. On this basis, this study combines Gaussian mixture background modeling and background subtraction to achieve the detection and extraction of target human body regions, and uses morphological operators to deal with noise and void phenomena in foreground images. The example analysis shows that the proposed method has certain practicality and can provide theoretical reference for subsequent related research.

Objectives: In order to solve the problems of the low accuracy and the slow speed of the existing video image flame detection methods, we propose a real-time video flame detection algorithm based on im- proved Yolo-v3 to achieve real-time and efficient detection of flames in the video. Methods: Firstly, in the feature extraction stage, the multi - scale detection network is improved. We add a new - scale feature and then improved the network's ability to learn the shallow information of the images by further integrating multi-scale features. Using this method, the accurate identification of small flame is achieved . Secondly, in the target detection stage, we use the improved K-means clustering algorithm to optimize the multi - scale prior frames, and make them adapt to the changing posture and shape of the flame. Finally, after detecting video flames based on improved Yolo-v3, we use the unique flicker characteristics of the flame to check the video again, and eliminate the false detection frame in the detection result. And in this method the detection accuracy is further improved. Results: In order to prove the effectiveness of our method, the video flames are detected from both accuracy and speed, and the results are compared with the advanced flame detection methods in recent years. The results show that the average accuracy rate of our method can reach 98.5%, the false detection rate is as low as 2.3%, and the average detection rate is 52 frames/s, so our method has better performance in terms of accuracy and speed. Conclusions: The effectiveness of this method is proved through multiple sets of experiments. Comparing with the existing flame detection methods, our method can be more effectively applied to video flame detection [ABSTRACT FROM AUTHOR]

Turbidity currents are the main drivers behind the transportation of terrestrial sediments to the deep sea, and turbidite deposits from such currents have been widely used in geological studies. Nevertheless, the contribution of turbidity currents to vertical displacement of seawater has rarely been discussed. This is partly because until recently, deep-sea turbidity currents have rarely been observed due to their unpredictable nature, being usually triggered by meteorological or geological events such as typhoons and earthquakes. Here, we report a direct observation of a deep-sea turbidity current using the recently developed Edokko Mark 1 monitoring system deployed in 2019 at a depth of 1,370 m in Suruga Bay, central Japan. A turbidity current occurred two days after its probable cause, the Super Typhoon Hagibis (2019), passed through Suruga Bay causing devastating damage. Over aperiod of 40 hours, we observed increased turbidity with turbulent conditions confirmed by a video camera. The turbidity exhibited two sharp peaks around 3:00 and 11:00 on October 14 (Japan Standard Time). The temperature and salinity characteristics during these high turbidity events agreed with independent measurements for shallow water layers in Suruga Bay at the same time, strongly suggesting that the turbidity current caused vertical displacement in the bay's water column by transporting warmer and shallower waters downslope of the canyon. Our results add to the previous few examples that show meteorological and geological events may have significant contributions in the transportation of shallower seawater to the deep sea. Recent technological developments pertaining to the Edokko Mark 1 and similar devices enable straightforward, long-term monitoring of the deep-seafloor and will contribute to the understanding of similar spontaneous events in the deep ocean. [ABSTRACT FROM AUTHOR]

Background: Although optimal treatment of superficial esophageal squamous cell carcinoma (SCC) requires accurate evaluation of cancer invasion depth, the current process is rather subjective and may vary by observer. We, therefore, aimed to develop an AI system to calculate cancer invasion depth. Methods: We gathered and selected 23,977 images (6857 WLI and 17,120 NBI/BLI images) of pathologically proven superficial esophageal SCC from endoscopic videos and still images of superficial esophageal SCC taken in our facility, to use as a learning dataset. We annotated the images with information [such as magnified endoscopy (ME) or non-ME, pEP-LPM, pMM, pSM1, and pSM2-3 cancers] based on pathologic diagnosis of the resected specimens. We created a model using a convolutional neural network. Performance of the AI system was compared with that of invited experts who used the same validation video set, independent of the learning dataset. Results: Accuracy, sensitivity, and specificity with non-magnified endoscopy (ME) were 87%, 50%, and 99% for the AI system and 85%, 45%, 97% for the experts. Accuracy, sensitivity, and specificity with ME were 89%, 71%, and 95% for the AI system and 84%, 42%, 97% for the experts. Conclusions: Most diagnostic parameters were higher when done by the AI system than by the experts. These results suggest that our AI system could potentially provide useful support during endoscopies. [ABSTRACT FROM AUTHOR]

This paper investigates the field of Video image analysis depending on texture for detecting a goal and tracing its movement in a video series. Analysing images depending on texture is better than depending on colour or shape , for the goal sometimes depends on different features . The aim of this study is to propose a method for tracing a goal within a video series after detecting it in each video frame. This study exhibits one of the techniques of extracting the image features depending on the signal frequency through using Gabor filter and in different trends for each frame. Then the histogram is taken for each frame and the frame given the best description for the goal is selected , in which case the threshold is depended . Then it is transformed into the binary form of the video frame ,to decrease time consumed short in detecting the object target . The algorithm is applied to part of the video frame . The location of the object target is determined through calculating the centre for part of the frame and the operation is applied to the series of the frames of the video film . Two films have been adopted as a research sample ,The first is a person„s movement by the traffic lights in al-Nabi Yunus area and the other are the students movement at the university of Mosul in the College of Education.

Due to weather conditions, brightness conditions, capture equipment and other factors, leads to video unclear or even abnormally confused, which is not conducive to monitoring, and can not meet the needs of applications. Based on the actual data of night video surveillance, this paper proposes a new low illumination video image enhancement algorithm, which overcomes the existing problems. We analyze the characteristics of low illumination video image, and use HSV color space instead of traditional RGB space to enhance the robustness of video contrast and color distortion. At the same time, we use wavelet image fusion to highlight the details of video image, so the enhanced video has higher clarity and visual effect. Compared with other four algorithms, the proposed algorithm outperforms the above algorithms in subjective evaluation and objective evaluation. At the same time, compared with other algorithms, the proposed algorithm has faster processing time for each frame. Experiments show that the algorithm can effectively improve the overall brightness and contrast of video images, and avoid the over-enhancement of bright areas near the light source, which can meet the practical application requirements of video surveillance. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Zhengzhou University: Engineering Science is the property of Editorial Office of Journal of Zhengzhou University: Engineering Science 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.)