Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852812
C. Zhao, Hongbo Bi, Y. Liu, Ning Li
Traditional digital watermarking in transform domain computes complex and has limited anti-attack. Different ways of signal sparsity of compressed sensing represent different domains, which expands the embeddable space of watermarking. To take advantage of its multi-direction and multi-resolution characteristics to sparse image, Contourlet transform was analyzed. For the limitation of traditional block decision, we adopt the interleaving extraction to reduce the block artifacts. Furthermore, we presented the watermarking algorithm based on interleaving extraction block compressed sensing in Contourlet domain, simulation results verifies that the algorithm enhances the peak signal to noise ratio. Attack tests show that the proposed digital watermarking has better robustness against JPEG compression, noising, cutting etc.
{"title":"Digital watermarking based on interleaving extraction block compressed sensing in Contourlet domain","authors":"C. Zhao, Hongbo Bi, Y. Liu, Ning Li","doi":"10.1109/CISP-BMEI.2016.7852812","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852812","url":null,"abstract":"Traditional digital watermarking in transform domain computes complex and has limited anti-attack. Different ways of signal sparsity of compressed sensing represent different domains, which expands the embeddable space of watermarking. To take advantage of its multi-direction and multi-resolution characteristics to sparse image, Contourlet transform was analyzed. For the limitation of traditional block decision, we adopt the interleaving extraction to reduce the block artifacts. Furthermore, we presented the watermarking algorithm based on interleaving extraction block compressed sensing in Contourlet domain, simulation results verifies that the algorithm enhances the peak signal to noise ratio. Attack tests show that the proposed digital watermarking has better robustness against JPEG compression, noising, cutting etc.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124111687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853027
Ping Feng, Yushun Wang
Chemical pesticides security and configuration problems of low precision blending process design a kind of liquid chemical pesticide ingredient line automatic control system. System consists of Host-Computer, PLC, weighing instruments and touch-screen configuration, which use Visual Basic develop design software, with data collection, storage and query capabilities. Omron PLC as the master controller for receiving the weighing instrument collection data and by controlling the electromagnetic valves and mixers and other equipment precise to control pesticide materials intake exactly. Using FINS protocol for communication between Host-Computer and PLC real-time data exchange. Commissioning of system has been successfully applied to a liquid chemical pesticide production plant. System has the safety, accurate and efficient advantages, and low construction cost, simple structure, has great marketing value.
{"title":"Automatic control system of liquid pesticide ingredients production line","authors":"Ping Feng, Yushun Wang","doi":"10.1109/CISP-BMEI.2016.7853027","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853027","url":null,"abstract":"Chemical pesticides security and configuration problems of low precision blending process design a kind of liquid chemical pesticide ingredient line automatic control system. System consists of Host-Computer, PLC, weighing instruments and touch-screen configuration, which use Visual Basic develop design software, with data collection, storage and query capabilities. Omron PLC as the master controller for receiving the weighing instrument collection data and by controlling the electromagnetic valves and mixers and other equipment precise to control pesticide materials intake exactly. Using FINS protocol for communication between Host-Computer and PLC real-time data exchange. Commissioning of system has been successfully applied to a liquid chemical pesticide production plant. System has the safety, accurate and efficient advantages, and low construction cost, simple structure, has great marketing value.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131179258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852792
Gaojin Wen, Can Zhong, Zhe Wang, Zhaorong Lin, Yun Xu
This paper presents an infrared image processing system for monitoring and mapping the thermal distribution of regions in mobile remote sensing applications. The processing system consists of five modules: non-uniformity correction, trajectory segmentation, odd even correction, image projection and visualization. It has been designed to perform thermal mapping efficiently and meet the special requirements of fast data processing. The processing system allows for the viewing of thermal distribution in a 2-d map model. The efficiency and effectiveness of the developed system are evaluated and tested by several image processing tasks.
{"title":"An infrared image processing system for mobile remote sensing","authors":"Gaojin Wen, Can Zhong, Zhe Wang, Zhaorong Lin, Yun Xu","doi":"10.1109/CISP-BMEI.2016.7852792","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852792","url":null,"abstract":"This paper presents an infrared image processing system for monitoring and mapping the thermal distribution of regions in mobile remote sensing applications. The processing system consists of five modules: non-uniformity correction, trajectory segmentation, odd even correction, image projection and visualization. It has been designed to perform thermal mapping efficiently and meet the special requirements of fast data processing. The processing system allows for the viewing of thermal distribution in a 2-d map model. The efficiency and effectiveness of the developed system are evaluated and tested by several image processing tasks.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130978239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852780
L. Zhong, W. Luo, Lianru Gao
Spectral unmixing is an important technique for hyperspectral data exploring. Recently the nonlinear unmixing technique which considers the nonlinear mixing terms becomes an important issue of spectral unmixing. Here, we consider a particle swarm optimization technique for nonlinear unmixing. Our motivation is to make a first step to exploit the potential capability of PSO for nonlinear unmixing. The proposed algorithm does not need any prior information concerning about the gradient or hessian matrix. Therefore, it can be easily applied to characterize complex nonlinear mixtures. In addition, it provides a stochastic mechanism that can improve the probability to find a better solution. Furthermore, the experimental results indicate that our algorithm can outperform the traditional algorithm for both synthetic and real hyperspectral data.
{"title":"A particle swarm optimization algorithm for unmixing the polynomial post-nonlinear mixing model","authors":"L. Zhong, W. Luo, Lianru Gao","doi":"10.1109/CISP-BMEI.2016.7852780","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852780","url":null,"abstract":"Spectral unmixing is an important technique for hyperspectral data exploring. Recently the nonlinear unmixing technique which considers the nonlinear mixing terms becomes an important issue of spectral unmixing. Here, we consider a particle swarm optimization technique for nonlinear unmixing. Our motivation is to make a first step to exploit the potential capability of PSO for nonlinear unmixing. The proposed algorithm does not need any prior information concerning about the gradient or hessian matrix. Therefore, it can be easily applied to characterize complex nonlinear mixtures. In addition, it provides a stochastic mechanism that can improve the probability to find a better solution. Furthermore, the experimental results indicate that our algorithm can outperform the traditional algorithm for both synthetic and real hyperspectral data.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"135 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131108923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852833
Xinchao Gu, Hua Cai, Yao Zhang, Ningbo Huang, Yong Yang
NoC has redundant features, that is to say, there are multiple paths from the source node to destination node, these provided conditions for us to study fault-tolerant routing algorithm. This thesis proposes a new fault-tolerant algorithm by studying the existing fault-tolerant routing algorithm. Divide each node into edge nodes and internal nodes based on the network's position of 2D - Mesh topology structure. In view of the respective characteristics of these two types of nodes this thesis puts forward relatively fast path decision model or turning model to help more quickly determine the routing node in its own characteristics of the current task best transmission path. It can significantly reduce the repeated operation time, reduce the amount of data calculation, help to ease and restrictions on the generation of network congestion and improve the data processing efficiency of the whole piece on the network‥
{"title":"Research on network fault tolerance method on chip","authors":"Xinchao Gu, Hua Cai, Yao Zhang, Ningbo Huang, Yong Yang","doi":"10.1109/CISP-BMEI.2016.7852833","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852833","url":null,"abstract":"NoC has redundant features, that is to say, there are multiple paths from the source node to destination node, these provided conditions for us to study fault-tolerant routing algorithm. This thesis proposes a new fault-tolerant algorithm by studying the existing fault-tolerant routing algorithm. Divide each node into edge nodes and internal nodes based on the network's position of 2D - Mesh topology structure. In view of the respective characteristics of these two types of nodes this thesis puts forward relatively fast path decision model or turning model to help more quickly determine the routing node in its own characteristics of the current task best transmission path. It can significantly reduce the repeated operation time, reduce the amount of data calculation, help to ease and restrictions on the generation of network congestion and improve the data processing efficiency of the whole piece on the network‥","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131127853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853052
Hua Li, Hong Ding, Linhua Zheng
The gradient descent bit-flipping (GDBF) decoding algorithm offers an attractive tradeoff between performance and complexity compared with the other bit-flipping (BF) decoding algorithms. However, the performance of GDBF decoding is seriously effected by infinite decoding loop, which always results in decoding failure when maximal iteration number is reached. To avoid the decoding loop and improve the performance, an efficient escaping scheme is proposed for the GDBF algorithm in this paper. This scheme firstly introduces syndrome weight to detect the decoding loop. If a decoding loop is detected, the escaping mechanism works, where only the bit which can decrease the syndrome weight most efficiently is selected to be flipped. In addition, the excluding set is introduced to further prevent the local maximum. Simulation results show that the GDBF algorithm can obtain about 1 dB code gain by utilizing this scheme. Compared with noise GDBF, it has 0.1dB performance loss as well as lower complexity.
{"title":"An escaping scheme for gradient descent bit-flipping decoding of LDPC codes","authors":"Hua Li, Hong Ding, Linhua Zheng","doi":"10.1109/CISP-BMEI.2016.7853052","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853052","url":null,"abstract":"The gradient descent bit-flipping (GDBF) decoding algorithm offers an attractive tradeoff between performance and complexity compared with the other bit-flipping (BF) decoding algorithms. However, the performance of GDBF decoding is seriously effected by infinite decoding loop, which always results in decoding failure when maximal iteration number is reached. To avoid the decoding loop and improve the performance, an efficient escaping scheme is proposed for the GDBF algorithm in this paper. This scheme firstly introduces syndrome weight to detect the decoding loop. If a decoding loop is detected, the escaping mechanism works, where only the bit which can decrease the syndrome weight most efficiently is selected to be flipped. In addition, the excluding set is introduced to further prevent the local maximum. Simulation results show that the GDBF algorithm can obtain about 1 dB code gain by utilizing this scheme. Compared with noise GDBF, it has 0.1dB performance loss as well as lower complexity.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"79 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131175534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852964
Rui Xing, N. Dai, Yicheng Zhong, Yihua Zhang, Yi Liu
In the process of orthodontic treatment, in order to make patients adorn appropriate brackets fast and accurately, this paper proposes a new modeling method of customized brackets and individualized trays. First of all, as the straight-wire can smoothly pass through all bracket slots after orthodontic treatment, bracket bodies in the database are positioned to the tooth surfaces automatically. Then some of them may be adjusted manually in accordance with specific conditions. Subsequently, customized brackets are designed based on the teeth morphology of patient. Finally, we can create each individualized tray rapidly on the basis of isometric extrude operation and Boolean operation. Some experiments have been tested by 3D printing technology and modeling platform. The results proved that the proposed modeling method has higher efficiency and the bonded bracket positioning is accurate and reliable.
{"title":"A modeling method of customized brackets and individualized trays for orthodontic treatment","authors":"Rui Xing, N. Dai, Yicheng Zhong, Yihua Zhang, Yi Liu","doi":"10.1109/CISP-BMEI.2016.7852964","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852964","url":null,"abstract":"In the process of orthodontic treatment, in order to make patients adorn appropriate brackets fast and accurately, this paper proposes a new modeling method of customized brackets and individualized trays. First of all, as the straight-wire can smoothly pass through all bracket slots after orthodontic treatment, bracket bodies in the database are positioned to the tooth surfaces automatically. Then some of them may be adjusted manually in accordance with specific conditions. Subsequently, customized brackets are designed based on the teeth morphology of patient. Finally, we can create each individualized tray rapidly on the basis of isometric extrude operation and Boolean operation. Some experiments have been tested by 3D printing technology and modeling platform. The results proved that the proposed modeling method has higher efficiency and the bonded bracket positioning is accurate and reliable.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124984913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852929
Liang Mao, Dakun Lai, Qi Xu, Chunliu Xie
Erectile dysfunction (ED) is a frequent disorder in aging men, affecting men's physical and mental health seriously. Generally, clinical diagnosis of the physical ED need image of penile vessels to distinguish vasculogenic ED disorders from psychological disorders so as to determine an appropriate treatment. The aim of this study is to present a novel photoacoustic microscopy (PAM) for imaging of vasculogenic ED with a high resolution and a high sensitivity. In this work, a vessel phantom using a carbon pencil and ten animals' penis models isolated from health rats both were prepared carefully. A home-made PAM platform was builted for rat's penile vessels, and the corresponding two dimensional (2D) PAM image was obtained for each model. Particularly, an imaging capability of a high spatial resolution of five hundreds microns with high contrast was obtained. The preliminary imaging results of isolated penis vessel clearly indicated that the method of photoacoustic imaging would be a useful diagnostic tool for assessing vasculogenic ED and could improve the diagnosis of venous leakage visualization by combining structural and functional imaging.
{"title":"Photoacoustic imaging: A potential new tool for diagnosing vasculogenic erectile dysfunction","authors":"Liang Mao, Dakun Lai, Qi Xu, Chunliu Xie","doi":"10.1109/CISP-BMEI.2016.7852929","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852929","url":null,"abstract":"Erectile dysfunction (ED) is a frequent disorder in aging men, affecting men's physical and mental health seriously. Generally, clinical diagnosis of the physical ED need image of penile vessels to distinguish vasculogenic ED disorders from psychological disorders so as to determine an appropriate treatment. The aim of this study is to present a novel photoacoustic microscopy (PAM) for imaging of vasculogenic ED with a high resolution and a high sensitivity. In this work, a vessel phantom using a carbon pencil and ten animals' penis models isolated from health rats both were prepared carefully. A home-made PAM platform was builted for rat's penile vessels, and the corresponding two dimensional (2D) PAM image was obtained for each model. Particularly, an imaging capability of a high spatial resolution of five hundreds microns with high contrast was obtained. The preliminary imaging results of isolated penis vessel clearly indicated that the method of photoacoustic imaging would be a useful diagnostic tool for assessing vasculogenic ED and could improve the diagnosis of venous leakage visualization by combining structural and functional imaging.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126401220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853012
Yi-Ze Zhang, Hongbin Shen
Signal peptides are significant important in targeting the translocation of integral membrane proteins and secretory proteins. Due the high similarity between the transmembrane helices and signal peptides, classifiers have limit ability to discriminate the signal peptides from the transmembrane helices. To solve this problem, the protein functional domain information is applied in this method. For accurately identify the cleavage sites along the sequence, a subset of potential cleavage sites was firstly screened out by statistical machine learning rules, and then the final unique site was picked out according to its evolution conservation score. This method has been benchmarked on multiple datasets and the experimental results have shown its superiority.
{"title":"Improve signal peptide prediction by using functional domain information","authors":"Yi-Ze Zhang, Hongbin Shen","doi":"10.1109/CISP-BMEI.2016.7853012","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853012","url":null,"abstract":"Signal peptides are significant important in targeting the translocation of integral membrane proteins and secretory proteins. Due the high similarity between the transmembrane helices and signal peptides, classifiers have limit ability to discriminate the signal peptides from the transmembrane helices. To solve this problem, the protein functional domain information is applied in this method. For accurately identify the cleavage sites along the sequence, a subset of potential cleavage sites was firstly screened out by statistical machine learning rules, and then the final unique site was picked out according to its evolution conservation score. This method has been benchmarked on multiple datasets and the experimental results have shown its superiority.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"01 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127240300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852687
Zhen Gao, Guoliang Lu, Peng Yan
Sequence matching/alignment based scheme has been common for action recognition. Such a typical scheme, however, requires tremendous amounts of computation when the volume of prototypical action videos is large and easily causes mismatching for border-isolated samples in action categories. In this paper, we propose a framework of averaging video sequences based on multi-dimensional dynamic time warping (MD-DTW) and propose to use the resulting average actions, instead of prototypical action videos, for action recognition. Experimental results show that 1) average actions were shown to be more discriminative than prototypical video sequences for action modeling, and 2) action recognition using average actions rather than using prototypical action videos is much more efficient and advanced.
{"title":"Averaging video sequences to improve action recognition","authors":"Zhen Gao, Guoliang Lu, Peng Yan","doi":"10.1109/CISP-BMEI.2016.7852687","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852687","url":null,"abstract":"Sequence matching/alignment based scheme has been common for action recognition. Such a typical scheme, however, requires tremendous amounts of computation when the volume of prototypical action videos is large and easily causes mismatching for border-isolated samples in action categories. In this paper, we propose a framework of averaging video sequences based on multi-dimensional dynamic time warping (MD-DTW) and propose to use the resulting average actions, instead of prototypical action videos, for action recognition. Experimental results show that 1) average actions were shown to be more discriminative than prototypical video sequences for action modeling, and 2) action recognition using average actions rather than using prototypical action videos is much more efficient and advanced.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114474469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：