The purpose of the article is to develop a methodology for automating the detection and selection of moving objects. The detection and separation of moving objects based on impulse and recurrence neural networks simul...The purpose of the article is to develop a methodology for automating the detection and selection of moving objects. The detection and separation of moving objects based on impulse and recurrence neural networks simulation. The result of the work is a developed motion detector based on impulse and recurrence neural networks and an automated system developed on the basis of this detector for detecting and separating moving objects and is ready for practical application. The feasibility of integrating the developed motion detector with Emgu CV (OpenCV) image processing package, multimedia framework functions, and DirectShow application programming interface were investigated. The proposed approach and software for the detection and separating of moving objects in video images using neural networks can be integrated into more sophisticated specialized computer-aided video surveillance systems, IoT (Internet of Things), IoV (Internet of Vehicles), etc.展开更多
We propose a video image mosaic method based on multi-module cooperation. This method stitches the video into a panorama with a large field of view, divided into three modules: the key frame selection module, the imag...We propose a video image mosaic method based on multi-module cooperation. This method stitches the video into a panorama with a large field of view, divided into three modules: the key frame selection module, the image mosaic module, and the optimization module. The key frame selection module obtains key frames by comprehensively evaluating the overlap rate and image quality. The image mosaic module stitches the key frames into a panoramic image to generate an initial mosaic result. The optimization module makes the mosaic result more natural and eliminates ghosts by using object detection advantages. Our method is tested on videos taken in real scenes, and the results have a more comprehensive and natural description.展开更多
For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective cap...For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective caption locating algorithm called maximum feature score region (MFSR) based method, which mainly consists of two stages: In the first stage, up/down boundaries are attained by turning to edge map projection. Then, maximum feature score region is defined and left/right boundaries are achieved by utilizing MFSR. Experiments show that the proposed MFSR based method has superior and robust performance on news video images of different types.展开更多
Important in many different sectors of the industry, the determination of stream velocity has become more and more important due to measurements precision necessity, in order to determine the right production rates, d...Important in many different sectors of the industry, the determination of stream velocity has become more and more important due to measurements precision necessity, in order to determine the right production rates, determine the volumetric production of undesired fluid, establish automated controls based on these measurements avoiding over-flooding or over-production, guaranteeing accurate predictive maintenance, etc. Difficulties being faced have been the determination of the velocity of specific fluids embedded in some others, for example, determining the gas bubbles stream velocity flowing throughout liquid fluid phase. Although different and already applicable methods have been researched and already implemented within the industry, a non-intrusive automated way of providing those stream velocities has its importance, and may have a huge impact in projects budget. Knowing the importance of its determination, this developed script uses a methodology of breaking-down real-time videos media into frame images, analyzing by pixel correlations possible superposition matches for further gas bubbles stream velocity estimation. In raw sense, the script bases itself in functions and procedures already available in MatLab, which can be used for image processing and treatments, allowing the methodology to be implemented. Its accuracy after the running test was of around 97% (ninety-seven percent);the raw source code with comments had almost 3000 (three thousand) characters;and the hardware placed for running the code was an Intel Core Duo 2.13 [Ghz] and 2 [Gb] RAM memory capable workstation. Even showing good results, it could be stated that just the end point correlations were actually getting to the final solution. So that, making use of self-learning functions or neural network, one could surely enhance the capability of the application to be run in real-time without getting exhaust by iterative loops.展开更多
To solve the problem that the production of Mahu conglomerate reservoir is not up to expectation after the multi-cluster plus temporary plugging fracturing technology is applied in horizontal wells, stages 2–6 in the...To solve the problem that the production of Mahu conglomerate reservoir is not up to expectation after the multi-cluster plus temporary plugging fracturing technology is applied in horizontal wells, stages 2–6 in the test well MaHW6285 are selected to carry out erosion tests with different pumping parameters. The downhole video imaging technology is used to monitor the degree of perforations erosion, and then the fracture initiation and proppant distribution of each cluster are analyzed. The results showed that proppant entered 76.7% of the perforations. The proppant was mainly distributed in a few perforation clusters, and the amount of proppant entered in most of the clusters was limited. The proppant distribution in Stage 4 was relatively uniform, and the fracture initiation of each cluster in the stage is more uniform. The proppant distribution in stages 2, 3, 5, and 6 was significantly uneven, and the uniform degree of fracture initiation in each cluster is low. More than 70% of the proppant dose in the stage entered clusters near the heel end, so the addition of diverters did not promote the uniform initiation of hydraulic fractures. There was a positive correlation between the amount of proppant added and the degree of perforations erosion, and the degree of perforations erosion ranged from 15% to 352%, with an average value of 74.5%, which was far higher than the statistical results of shale reservoir tests in North America. The use of 180° phase perforation(horizontal direction) can reduce the “Phase Bias” of perforations erosion, promote uniform perforations erosion and fluid inflow. The research results provide the basis for optimizing the pumping procedure, reducing the perforation erosion and improving the success rate of diversion.展开更多
A novel temporal shape error concealment technique is proposed, which can he used in the context of object-based video coding schemes. In order to reduce the effect of the shape variations of a video object, the curva...A novel temporal shape error concealment technique is proposed, which can he used in the context of object-based video coding schemes. In order to reduce the effect of the shape variations of a video object, the curvature scale space (CSS) technique is adopted to extract features, and then these features are used for boundary matching between the current frame and the previous frame. Because the temporal, spatial and sta- tistical video contour information are all considered, the proposed method can find the optimal matching, which is used to replace the damaged contours. The simulation results show that the proposed algorithm achieves better subjective, objective qualities and higher efficiency than those previously developed methods.展开更多
Discrete Cosine Transform(DCT)is the most widely used technique in image and video compression.In this paper,the structure of DCT and Inverse DCT(IDCT)algorithm is split in the form of COordinate Rotation DIgital Comp...Discrete Cosine Transform(DCT)is the most widely used technique in image and video compression.In this paper,the structure of DCT and Inverse DCT(IDCT)algorithm is split in the form of COordinate Rotation DIgital Computer(CORDIC)rotation matrix.The two-dimensional(2-D)8×8 DCT/IDCT units based on the improved rotation CORDIC algorithm is proposed.The shift and addition operations of the CORDIC algorithm are used to replace the cosine multiplication operations in the algorithm.The design does not contain any multiplier unit,which reduces the complexity of the hardware unit.The row-column transform unit composed of register arrays connects two 1-D 8-point DCT units to complete the calculation of 2-D 8×8 DCT.The pipeline latency of proposed architecture is 28 clock cycles.The proposed efficient two-dimensional DCT architecture has been synthesized on the Xilinx’s Kintex-7 FPGA.The resource utilization is 17.36%for Slice LUTs,3.49%for Slice Registers,and the maximum operating frequency is 172 MHz.It takes only 0.161μs to complete a process of block of 8×8 samples.A frame of image is processed by the designed DCT unit and then reconstructed by the IDCT unit to verify the function.The Peak Signal to Noise Ratio(PSNR)can reach 51.99 dB.展开更多
Avoiding lameness or leg weakness in pig production is crucial to reduce cost, improve animal welfare and meat quality. Detection of lameness detection by the use of vision systems may assist the farmer or breeder to ...Avoiding lameness or leg weakness in pig production is crucial to reduce cost, improve animal welfare and meat quality. Detection of lameness detection by the use of vision systems may assist the farmer or breeder to obtain a more accurate and robust measurement of lameness. The paper presents a low-cost vision system for measuring the locomotion of moving pigs based on motion detection, frame-grabbing and multivariate image analysis. The first step is to set up a video system based on web camera technology and choose a test area. Secondly, a motion detection and data storage system are used to build a processing system of video data. The video data are analyzed measuring the properties of each image, stacking them for each animal and then analyze these stacks using multivariate image analysis. The system was able to obtain and decompose information from these stacks, where components could be extracted, representing a particular motion pattern. These components could be used to classify or score animals according to this pattern, which might be an indicator of lameness. However, further improvement is needed with respect to standardization of herding, test area and tracking of animals in order to have a robust system to be used in a farm environment.展开更多
In the present study, a generalized active contour model of gradient vector flow is combined with the video techniques of Argus system to delineate and track sequential nearshore wave crest profiles in the shoaling pr...In the present study, a generalized active contour model of gradient vector flow is combined with the video techniques of Argus system to delineate and track sequential nearshore wave crest profiles in the shoaling process, up to their breaking on the shoreline. Previous applications of active contour models to water wave problems are limited to controllable wave tank experiments. By contrast, our application in this study is in a nearshore field environment where oblique images obtained under natural and varying condition of ambient light are employed. Existing Argus techniques produce plane image data or time series data from a selected small subset of discrete pixels. By contrast, the active contour model produces line image data along continuous visible curves such as wave crest profiles. The combination of these two existing techniques, the active contour model and Argus methodologies, facilitates the estimates of the direction wave field and phase speeds within the whole area covered by camera. These estimates are useful for the purpose of inverse calculation of the water depth. Applications of the present techniques to Hsi-tzu bay where a beach restoration program is currently undertaken are illustrated. This extension of Argus video techniques provides new application of optical remote sensing to study the hydrodynamics and morphology of a nearshore environment.展开更多
As the fiat panel displays (Liquid Crystal Displays, AMOLED, etc.) reach near perfection in their viewing qualities and display areas, it is natural to seek the next level of displays, including 3D displays. There i...As the fiat panel displays (Liquid Crystal Displays, AMOLED, etc.) reach near perfection in their viewing qualities and display areas, it is natural to seek the next level of displays, including 3D displays. There is a strong surge in 3D liquid crystal displays as a result of the successful movie Avatar. Most of these 3D displays involve the employment of special glasses that allow one view perspective for each of the eyes to achieve a depth perception. Such displays are not real 3D displays. In fact, these displays can only provide one viewing perspective for all viewers, regardless of the viewer's position. In addition, a fundamental viewing problem of focusing and accommodation exist that can lead to discomfort and fatigue for many viewers. In this paper, the authors review the current status of stereoscopic 3D displays and their problems. The authors will also discuss the possibility of using fiat panels for the display of both phase and intensity of video image information, leading to the ultimate display of 3D holographic video images. Many of the fundamental issues and limitations will be presented and discussed.展开更多
Improving the quality of equipment training for the Heavy Equipment Operators(HEO)is a critical task in improving safety and eliminating equipment-related injuries in mining.One of major responsibilities for the HEOs ...Improving the quality of equipment training for the Heavy Equipment Operators(HEO)is a critical task in improving safety and eliminating equipment-related injuries in mining.One of major responsibilities for the HEOs is proper machine inspection.Traditional miner safety training includes the use of hardcopy documents and video instructions.However,modern mobile and computer technology offers tremendous potential to improve the training process.In this study,we apply a 360-degree camera,opensource platform WordPress^(TM),and the software Unity3D in order to create materials and tools for the HEOs safety training to help trainees better understand the pre-shift safety machine inspection.The computer-based safety task training developed in this research is tested and implemented at a surface mine in the southern United States.展开更多
Current investigations on visual information retrieval are generally content-based methods. The significant difference between similarity in low-level features and similarity in high-level semantic meanings is still a...Current investigations on visual information retrieval are generally content-based methods. The significant difference between similarity in low-level features and similarity in high-level semantic meanings is still a major challenge in the area of image retrieval. In this work, a scheme for constructing visual ontology to retrieve art images is proposed. The proposed ontology describes images in various aspects, including type & style, objects and global perceptual effects. Concepts in the ontology could be automatically derived. Various art image classification methods are employed based on low-level image features. Non-objective semantics are introduced, and how to express these semantics is given. The proposed ontology scheme could make users more naturally find visual information and thus narrows the “semantic gap”. Experimental implementation demonstrates its good potential for retrieving art images in a human-centered manner.展开更多
This study investigates the different aspects of multimedia computing in Video Synthetic Aperture Radar(Video-SAR)as a new mode of radar imaging for real-time remote sensing and surveillance.This research also conside...This study investigates the different aspects of multimedia computing in Video Synthetic Aperture Radar(Video-SAR)as a new mode of radar imaging for real-time remote sensing and surveillance.This research also considers new suggestions in the systematic design,research taxonomy,and future trends of radar data processing.Despite the conventional modes of SAR imaging,Video-SAR can generate video sequences to obtain online monitoring and green surveillance throughout the day and night(regardless of light sources)in all weathers.First,an introduction to Video-SAR is presented.Then,some specific properties of this imaging mode are reviewed.Particularly,this research covers one of the most important aspects of the Video-SAR systems,namely,the systematic design requirements,and also some new types of visual distortions which are different from the distortions,artifacts and noises observed in the conventional imaging radar.In addition,some topics on the general features and high-performance computing of Video-SAR towards radar communications through Unmanned Aerial Vehicle(UAV)platforms,Internet of Multimedia Things(IoMT),Video-SAR data processing issues,and real-world applications are investigated.展开更多
A laboratory study of the turbulence front initiated by the Rayleigh-Taylor instabilities was conducted by overturning a two-layer stratified flow in a tank. Dye was introduced to the upper layer and the concentration...A laboratory study of the turbulence front initiated by the Rayleigh-Taylor instabilities was conducted by overturning a two-layer stratified flow in a tank. Dye was introduced to the upper layer and the concentration of the dye was determined using a video imaging method. The mass center of the heavier upper layer moved continuously to a lower elevation because of the intrusion of the heavier fluid into the lower layer and the lighter fluid into the upper layer. The downward movement of the mass center was accurately determined from the dye concentration profile. It is concluded that the initial advancement of the mass center follows a quadratic relation with time and the final advancement obeys a linear relation with time.展开更多
Virtual reality(VR)offers an artificial,computer generated simulation of a real life environment.It originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and intelligence.B...Virtual reality(VR)offers an artificial,computer generated simulation of a real life environment.It originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and intelligence.Because deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion,they can build very powerful models which leverage large quantities of visual media data.Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques.VR content creation and exploration relates to image and video analysis,synthesis and editing,so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed,designed specifically to handle panoramic images and video and virtual 3 D scenes.This article surveys recent research that uses such deep learning methods for VR content creation and exploration.It considers the problems involved,and discusses possible future directions in this active and emerging research area.展开更多
文摘The purpose of the article is to develop a methodology for automating the detection and selection of moving objects. The detection and separation of moving objects based on impulse and recurrence neural networks simulation. The result of the work is a developed motion detector based on impulse and recurrence neural networks and an automated system developed on the basis of this detector for detecting and separating moving objects and is ready for practical application. The feasibility of integrating the developed motion detector with Emgu CV (OpenCV) image processing package, multimedia framework functions, and DirectShow application programming interface were investigated. The proposed approach and software for the detection and separating of moving objects in video images using neural networks can be integrated into more sophisticated specialized computer-aided video surveillance systems, IoT (Internet of Things), IoV (Internet of Vehicles), etc.
基金supported by the National Natural Science Foundation of China (Nos.61906135, 62020106004 and 92048301)the Tianjin Science and Technology Plan Project (No.20JCQNJC01350)。
文摘We propose a video image mosaic method based on multi-module cooperation. This method stitches the video into a panorama with a large field of view, divided into three modules: the key frame selection module, the image mosaic module, and the optimization module. The key frame selection module obtains key frames by comprehensively evaluating the overlap rate and image quality. The image mosaic module stitches the key frames into a panoramic image to generate an initial mosaic result. The optimization module makes the mosaic result more natural and eliminates ghosts by using object detection advantages. Our method is tested on videos taken in real scenes, and the results have a more comprehensive and natural description.
基金supported by National Natural Science Foundation of China(Nos.61272394,61201395 and61472119)the program for Science&Technology Innovation Talents in Universities of Henan Province(No.13HASTIT039)+1 种基金Henan Polytechnic University Innovative Research Team(No.T2014-3)Henan Polytechnic University Fund for Distinguished Young Scholars(No.J2013-2)
文摘For news video images, caption recognizing is a useful and important step for content understanding. Caption locating is usually the first step of caption recognizing and this paper proposes a simple but effective caption locating algorithm called maximum feature score region (MFSR) based method, which mainly consists of two stages: In the first stage, up/down boundaries are attained by turning to edge map projection. Then, maximum feature score region is defined and left/right boundaries are achieved by utilizing MFSR. Experiments show that the proposed MFSR based method has superior and robust performance on news video images of different types.
基金financial support from the Brazilian Federal Agency for Support and Evaluation of Graduate Education(Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior—CAPES,scholarship process no BEX 0506/15-0)the Brazilian National Agency of Petroleum,Natural Gas and Biofuels(Agencia Nacional do Petroleo,Gas Natural e Biocombustiveis—ANP),in cooperation with the Brazilian Financier of Studies and Projects(Financiadora de Estudos e Projetos—FINEP)the Brazilian Ministry of Science,Technology and Innovation(Ministério da Ciencia,Tecnologia e Inovacao—MCTI)through the ANP’s Human Resources Program of the State University of Sao Paulo(Universidade Estadual Paulista—UNESP)for the Oil and Gas Sector PRH-ANP/MCTI no 48(PRH48).
文摘Important in many different sectors of the industry, the determination of stream velocity has become more and more important due to measurements precision necessity, in order to determine the right production rates, determine the volumetric production of undesired fluid, establish automated controls based on these measurements avoiding over-flooding or over-production, guaranteeing accurate predictive maintenance, etc. Difficulties being faced have been the determination of the velocity of specific fluids embedded in some others, for example, determining the gas bubbles stream velocity flowing throughout liquid fluid phase. Although different and already applicable methods have been researched and already implemented within the industry, a non-intrusive automated way of providing those stream velocities has its importance, and may have a huge impact in projects budget. Knowing the importance of its determination, this developed script uses a methodology of breaking-down real-time videos media into frame images, analyzing by pixel correlations possible superposition matches for further gas bubbles stream velocity estimation. In raw sense, the script bases itself in functions and procedures already available in MatLab, which can be used for image processing and treatments, allowing the methodology to be implemented. Its accuracy after the running test was of around 97% (ninety-seven percent);the raw source code with comments had almost 3000 (three thousand) characters;and the hardware placed for running the code was an Intel Core Duo 2.13 [Ghz] and 2 [Gb] RAM memory capable workstation. Even showing good results, it could be stated that just the end point correlations were actually getting to the final solution. So that, making use of self-learning functions or neural network, one could surely enhance the capability of the application to be run in real-time without getting exhaust by iterative loops.
基金Supported by the PetroChina–China University of Petroleum (Beijing) Strategic Cooperation Project (ZLZX2020-04)。
文摘To solve the problem that the production of Mahu conglomerate reservoir is not up to expectation after the multi-cluster plus temporary plugging fracturing technology is applied in horizontal wells, stages 2–6 in the test well MaHW6285 are selected to carry out erosion tests with different pumping parameters. The downhole video imaging technology is used to monitor the degree of perforations erosion, and then the fracture initiation and proppant distribution of each cluster are analyzed. The results showed that proppant entered 76.7% of the perforations. The proppant was mainly distributed in a few perforation clusters, and the amount of proppant entered in most of the clusters was limited. The proppant distribution in Stage 4 was relatively uniform, and the fracture initiation of each cluster in the stage is more uniform. The proppant distribution in stages 2, 3, 5, and 6 was significantly uneven, and the uniform degree of fracture initiation in each cluster is low. More than 70% of the proppant dose in the stage entered clusters near the heel end, so the addition of diverters did not promote the uniform initiation of hydraulic fractures. There was a positive correlation between the amount of proppant added and the degree of perforations erosion, and the degree of perforations erosion ranged from 15% to 352%, with an average value of 74.5%, which was far higher than the statistical results of shale reservoir tests in North America. The use of 180° phase perforation(horizontal direction) can reduce the “Phase Bias” of perforations erosion, promote uniform perforations erosion and fluid inflow. The research results provide the basis for optimizing the pumping procedure, reducing the perforation erosion and improving the success rate of diversion.
基金the National Natural Science Foundation of China (60532070)
文摘A novel temporal shape error concealment technique is proposed, which can he used in the context of object-based video coding schemes. In order to reduce the effect of the shape variations of a video object, the curvature scale space (CSS) technique is adopted to extract features, and then these features are used for boundary matching between the current frame and the previous frame. Because the temporal, spatial and sta- tistical video contour information are all considered, the proposed method can find the optimal matching, which is used to replace the damaged contours. The simulation results show that the proposed algorithm achieves better subjective, objective qualities and higher efficiency than those previously developed methods.
文摘Discrete Cosine Transform(DCT)is the most widely used technique in image and video compression.In this paper,the structure of DCT and Inverse DCT(IDCT)algorithm is split in the form of COordinate Rotation DIgital Computer(CORDIC)rotation matrix.The two-dimensional(2-D)8×8 DCT/IDCT units based on the improved rotation CORDIC algorithm is proposed.The shift and addition operations of the CORDIC algorithm are used to replace the cosine multiplication operations in the algorithm.The design does not contain any multiplier unit,which reduces the complexity of the hardware unit.The row-column transform unit composed of register arrays connects two 1-D 8-point DCT units to complete the calculation of 2-D 8×8 DCT.The pipeline latency of proposed architecture is 28 clock cycles.The proposed efficient two-dimensional DCT architecture has been synthesized on the Xilinx’s Kintex-7 FPGA.The resource utilization is 17.36%for Slice LUTs,3.49%for Slice Registers,and the maximum operating frequency is 172 MHz.It takes only 0.161μs to complete a process of block of 8×8 samples.A frame of image is processed by the designed DCT unit and then reconstructed by the IDCT unit to verify the function.The Peak Signal to Noise Ratio(PSNR)can reach 51.99 dB.
基金The Norwegian Re-search Council is gratefully acknowledged for providing financial support for this research as part of the Robust Pig project.
文摘Avoiding lameness or leg weakness in pig production is crucial to reduce cost, improve animal welfare and meat quality. Detection of lameness detection by the use of vision systems may assist the farmer or breeder to obtain a more accurate and robust measurement of lameness. The paper presents a low-cost vision system for measuring the locomotion of moving pigs based on motion detection, frame-grabbing and multivariate image analysis. The first step is to set up a video system based on web camera technology and choose a test area. Secondly, a motion detection and data storage system are used to build a processing system of video data. The video data are analyzed measuring the properties of each image, stacking them for each animal and then analyze these stacks using multivariate image analysis. The system was able to obtain and decompose information from these stacks, where components could be extracted, representing a particular motion pattern. These components could be used to classify or score animals according to this pattern, which might be an indicator of lameness. However, further improvement is needed with respect to standardization of herding, test area and tracking of animals in order to have a robust system to be used in a farm environment.
基金supported by the Science Council,Taiwan,under Grant No.NSC95-2221-E-006-475-MY2
文摘In the present study, a generalized active contour model of gradient vector flow is combined with the video techniques of Argus system to delineate and track sequential nearshore wave crest profiles in the shoaling process, up to their breaking on the shoreline. Previous applications of active contour models to water wave problems are limited to controllable wave tank experiments. By contrast, our application in this study is in a nearshore field environment where oblique images obtained under natural and varying condition of ambient light are employed. Existing Argus techniques produce plane image data or time series data from a selected small subset of discrete pixels. By contrast, the active contour model produces line image data along continuous visible curves such as wave crest profiles. The combination of these two existing techniques, the active contour model and Argus methodologies, facilitates the estimates of the direction wave field and phase speeds within the whole area covered by camera. These estimates are useful for the purpose of inverse calculation of the water depth. Applications of the present techniques to Hsi-tzu bay where a beach restoration program is currently undertaken are illustrated. This extension of Argus video techniques provides new application of optical remote sensing to study the hydrodynamics and morphology of a nearshore environment.
文摘As the fiat panel displays (Liquid Crystal Displays, AMOLED, etc.) reach near perfection in their viewing qualities and display areas, it is natural to seek the next level of displays, including 3D displays. There is a strong surge in 3D liquid crystal displays as a result of the successful movie Avatar. Most of these 3D displays involve the employment of special glasses that allow one view perspective for each of the eyes to achieve a depth perception. Such displays are not real 3D displays. In fact, these displays can only provide one viewing perspective for all viewers, regardless of the viewer's position. In addition, a fundamental viewing problem of focusing and accommodation exist that can lead to discomfort and fatigue for many viewers. In this paper, the authors review the current status of stereoscopic 3D displays and their problems. The authors will also discuss the possibility of using fiat panels for the display of both phase and intensity of video image information, leading to the ultimate display of 3D holographic video images. Many of the fundamental issues and limitations will be presented and discussed.
文摘Improving the quality of equipment training for the Heavy Equipment Operators(HEO)is a critical task in improving safety and eliminating equipment-related injuries in mining.One of major responsibilities for the HEOs is proper machine inspection.Traditional miner safety training includes the use of hardcopy documents and video instructions.However,modern mobile and computer technology offers tremendous potential to improve the training process.In this study,we apply a 360-degree camera,opensource platform WordPress^(TM),and the software Unity3D in order to create materials and tools for the HEOs safety training to help trainees better understand the pre-shift safety machine inspection.The computer-based safety task training developed in this research is tested and implemented at a surface mine in the southern United States.
基金China-American Digital Academic Library (CADAL) project, partially supported by the Research Project on Context-Based Multiple Digital Media Semantic Organization and System Development,中国科学院'百人计划',the One-Hundred Talents Plan of CAS
文摘Current investigations on visual information retrieval are generally content-based methods. The significant difference between similarity in low-level features and similarity in high-level semantic meanings is still a major challenge in the area of image retrieval. In this work, a scheme for constructing visual ontology to retrieve art images is proposed. The proposed ontology describes images in various aspects, including type & style, objects and global perceptual effects. Concepts in the ontology could be automatically derived. Various art image classification methods are employed based on low-level image features. Non-objective semantics are introduced, and how to express these semantics is given. The proposed ontology scheme could make users more naturally find visual information and thus narrows the “semantic gap”. Experimental implementation demonstrates its good potential for retrieving art images in a human-centered manner.
文摘This study investigates the different aspects of multimedia computing in Video Synthetic Aperture Radar(Video-SAR)as a new mode of radar imaging for real-time remote sensing and surveillance.This research also considers new suggestions in the systematic design,research taxonomy,and future trends of radar data processing.Despite the conventional modes of SAR imaging,Video-SAR can generate video sequences to obtain online monitoring and green surveillance throughout the day and night(regardless of light sources)in all weathers.First,an introduction to Video-SAR is presented.Then,some specific properties of this imaging mode are reviewed.Particularly,this research covers one of the most important aspects of the Video-SAR systems,namely,the systematic design requirements,and also some new types of visual distortions which are different from the distortions,artifacts and noises observed in the conventional imaging radar.In addition,some topics on the general features and high-performance computing of Video-SAR towards radar communications through Unmanned Aerial Vehicle(UAV)platforms,Internet of Multimedia Things(IoMT),Video-SAR data processing issues,and real-world applications are investigated.
文摘A laboratory study of the turbulence front initiated by the Rayleigh-Taylor instabilities was conducted by overturning a two-layer stratified flow in a tank. Dye was introduced to the upper layer and the concentration of the dye was determined using a video imaging method. The mass center of the heavier upper layer moved continuously to a lower elevation because of the intrusion of the heavier fluid into the lower layer and the lighter fluid into the upper layer. The downward movement of the mass center was accurately determined from the dye concentration profile. It is concluded that the initial advancement of the mass center follows a quadratic relation with time and the final advancement obeys a linear relation with time.
基金supported by the National Natural Science Foundation of China(Grant Nos.61902012,61932003)supported by a Victoria Early-Career Research Excellence Award.
文摘Virtual reality(VR)offers an artificial,computer generated simulation of a real life environment.It originated in the 1960 s and has evolved to provide increasing immersion,interactivity,imagination,and intelligence.Because deep learning systems are able to represent and compose information at various levels in a deep hierarchical fashion,they can build very powerful models which leverage large quantities of visual media data.Intelligence of VR methods and applications has been significantly boosted by the recent developments in deep learning techniques.VR content creation and exploration relates to image and video analysis,synthesis and editing,so deep learning methods such as fully convolutional networks and general adversarial networks are widely employed,designed specifically to handle panoramic images and video and virtual 3 D scenes.This article surveys recent research that uses such deep learning methods for VR content creation and exploration.It considers the problems involved,and discusses possible future directions in this active and emerging research area.