Pub Date : 2011-12-01DOI: 10.1109/IVSURV.2011.6157031
Shengyin Wu, Shiqi Yu, Wensheng Chen, Zhen Ji
This paper presents an implementation on image stitching system which employs a binocular camera. To obtain wide-angle images, we assemble two normal cameras by a decided angle, then stitch the images from each camera. The paremeters of the binocular camera are required initialized only once. We use a black-white chessboard to assist the paramters initialization. The costs of image stitching is very low that processing a frame only needs 10 ms.
{"title":"An implementation of image statiching based on binocular cameras","authors":"Shengyin Wu, Shiqi Yu, Wensheng Chen, Zhen Ji","doi":"10.1109/IVSURV.2011.6157031","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157031","url":null,"abstract":"This paper presents an implementation on image stitching system which employs a binocular camera. To obtain wide-angle images, we assemble two normal cameras by a decided angle, then stitch the images from each camera. The paremeters of the binocular camera are required initialized only once. We use a black-white chessboard to assist the paramters initialization. The costs of image stitching is very low that processing a frame only needs 10 ms.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"340 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123116195","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157011
Xiang Xiang
Moving object segmentation is highly beneficial to human identification and behavior analysis in intelligent video surveillance. The widely-used background subtraction works not well in dynamic scenes. In this paper, the problem is addressed by first localizing the object by tracking and then segmenting it locally via Graph cuts. We also propose a robust tracker combining the merits of two existing methods [1] and [2], and display an interactive segmentation system. Experiments verify the feasibility of our method and that the proposed tracker outperforms most state-of-the-art methods.
{"title":"Interactive tracking-based pedestrian segmentation in dynamic scenes","authors":"Xiang Xiang","doi":"10.1109/IVSURV.2011.6157011","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157011","url":null,"abstract":"Moving object segmentation is highly beneficial to human identification and behavior analysis in intelligent video surveillance. The widely-used background subtraction works not well in dynamic scenes. In this paper, the problem is addressed by first localizing the object by tracking and then segmenting it locally via Graph cuts. We also propose a robust tracker combining the merits of two existing methods [1] and [2], and display an interactive segmentation system. Experiments verify the feasibility of our method and that the proposed tracker outperforms most state-of-the-art methods.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129562511","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157022
Xiaoyi Yu, Lingyi Wu, Qingfeng Liu, Han Zhou
Tantrums exerts bad impact on children growth. It is very important to provide doctors with valid and reliable data in time to discover the abnormal behaviors of children. Children behavior analysis in video has been proposed to help; however, there are still three challenges of current implementations: caregivers' attitudes, video collecting and analysis, approaches to prove their effectiveness. In this paper we propose a prototype system, in which we exploit medical knowledge, questionnaire based attitudes investigation and Kinect based behavior analysis algorithm to address those problems. To assess the effectiveness of our system, we also design a questionnaire to interview the doctor and analyze the feedback result.
{"title":"Children tantrum behaviour analysis based on Kinect sensor","authors":"Xiaoyi Yu, Lingyi Wu, Qingfeng Liu, Han Zhou","doi":"10.1109/IVSURV.2011.6157022","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157022","url":null,"abstract":"Tantrums exerts bad impact on children growth. It is very important to provide doctors with valid and reliable data in time to discover the abnormal behaviors of children. Children behavior analysis in video has been proposed to help; however, there are still three challenges of current implementations: caregivers' attitudes, video collecting and analysis, approaches to prove their effectiveness. In this paper we propose a prototype system, in which we exploit medical knowledge, questionnaire based attitudes investigation and Kinect based behavior analysis algorithm to address those problems. To assess the effectiveness of our system, we also design a questionnaire to interview the doctor and analyze the feedback result.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948533","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157024
Lihao Cao, Yu Li, Yong Huang
In this paper, a new model of target localization based on underwater sensor networks (USN) is proposed. And several target localization algorithms used in this model are researched. The mathematical principles and the performance of these algorithms are studied in detail. And this paper has also done some research in how the target position and the number of sensors affect the localization precision which can guide the intelligent management of the sensors.
{"title":"Study of target localization based on underwater sensor networks","authors":"Lihao Cao, Yu Li, Yong Huang","doi":"10.1109/IVSURV.2011.6157024","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157024","url":null,"abstract":"In this paper, a new model of target localization based on underwater sensor networks (USN) is proposed. And several target localization algorithms used in this model are researched. The mathematical principles and the performance of these algorithms are studied in detail. And this paper has also done some research in how the target position and the number of sensors affect the localization precision which can guide the intelligent management of the sensors.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130248673","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157032
Liya Zhao, Xiaowei Jia, Hongning Tian, Limei Wang, Ke-bin Jia
An Intelligent Visual Surveillance (IVS) system based on multi SEED-VPM642 platform is proposed in this paper, including design and realization of both the hardware and software platforms. The core chip of the platform is TI multimedia Digital Signal Processor (DSP) TMS320DM642. In the system, DSP acts as a server, waiting for client PC to get connected to the Internet. In DSP, video captured by cameras is processed by algorithms in real time, then encoded, and finally sent to PC. If any event breaks the rules set by users on PC, alarm signal will be sent through the Global System for Mobile Communications (GSM) network. Experimental results show that the system works well in detecting and tracking objects. Meanwhile, PC Graphical User Interface (GUI) supports monitoring 16 video scenes at the same time and controlling Pan/Tilt/Zoom (PTZ) camera, also allows video playing back. In addition, our system supports both Client/Server (C/S) and Browser/Server (B/S) architecture.
{"title":"Multi-DSP based Intelligent Visual Surveillance System","authors":"Liya Zhao, Xiaowei Jia, Hongning Tian, Limei Wang, Ke-bin Jia","doi":"10.1109/IVSURV.2011.6157032","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157032","url":null,"abstract":"An Intelligent Visual Surveillance (IVS) system based on multi SEED-VPM642 platform is proposed in this paper, including design and realization of both the hardware and software platforms. The core chip of the platform is TI multimedia Digital Signal Processor (DSP) TMS320DM642. In the system, DSP acts as a server, waiting for client PC to get connected to the Internet. In DSP, video captured by cameras is processed by algorithms in real time, then encoded, and finally sent to PC. If any event breaks the rules set by users on PC, alarm signal will be sent through the Global System for Mobile Communications (GSM) network. Experimental results show that the system works well in detecting and tracking objects. Meanwhile, PC Graphical User Interface (GUI) supports monitoring 16 video scenes at the same time and controlling Pan/Tilt/Zoom (PTZ) camera, also allows video playing back. In addition, our system supports both Client/Server (C/S) and Browser/Server (B/S) architecture.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123389272","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 : 2011-12-01DOI: 10.1109/ivsurv.2011.6157012
Dong Wang, Xiaohui Li, Gang Yang, Huchuan Lu
{"title":"Robust tracking with spatial pyramid histogram","authors":"Dong Wang, Xiaohui Li, Gang Yang, Huchuan Lu","doi":"10.1109/ivsurv.2011.6157012","DOIUrl":"https://doi.org/10.1109/ivsurv.2011.6157012","url":null,"abstract":"","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122067514","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157023
Xiao-gang Yang, Bin-wen Chen, C. Hu, Fei Meng, Zhaohui Xia
A state recognition system based on reference information table and real-time video monitoring is designed and realized for a kind of special complex equipments in this paper. Firstly, the system general scheme is designed, including the modules of video monitoring and state recognition, reference information preparation, and video image acquisition. Then, the hardware of the system is realized and the application software is developed according to the designed scheme. At last, several application experiments demonstrate the system is efficient and practical for complex equipments video monitoring and state recognition.
{"title":"Design and realization of a video monitoring and state recognition system for complex equipments","authors":"Xiao-gang Yang, Bin-wen Chen, C. Hu, Fei Meng, Zhaohui Xia","doi":"10.1109/IVSURV.2011.6157023","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157023","url":null,"abstract":"A state recognition system based on reference information table and real-time video monitoring is designed and realized for a kind of special complex equipments in this paper. Firstly, the system general scheme is designed, including the modules of video monitoring and state recognition, reference information preparation, and video image acquisition. Then, the hardware of the system is realized and the application software is developed according to the designed scheme. At last, several application experiments demonstrate the system is efficient and practical for complex equipments video monitoring and state recognition.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121123613","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157025
Jibin Fu, Xin Bai, Baode Ju
This paper describes a screen target detection algorithm which is based on the background of Pixel texture information to judge models. The model is based on Bayesian statistical model frame, using histogram to get background reference, and lead in texture information of pixels to determine the results of the test optimization. It can quickly and accurately generate reference background, accumulating less noise during the period of updating background, and keeping longtime stability. Experimental results show that compared with the Bayesian statistical model, the screen target detection algorithm which is based on the background of Pixel texture information to judge models has greatly improved in accuracy and reduced in error rate.
{"title":"A video target detection algorithm based on pixels texture correlation background model","authors":"Jibin Fu, Xin Bai, Baode Ju","doi":"10.1109/IVSURV.2011.6157025","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157025","url":null,"abstract":"This paper describes a screen target detection algorithm which is based on the background of Pixel texture information to judge models. The model is based on Bayesian statistical model frame, using histogram to get background reference, and lead in texture information of pixels to determine the results of the test optimization. It can quickly and accurately generate reference background, accumulating less noise during the period of updating background, and keeping longtime stability. Experimental results show that compared with the Bayesian statistical model, the screen target detection algorithm which is based on the background of Pixel texture information to judge models has greatly improved in accuracy and reduced in error rate.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132000873","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157030
Congwen Gao, Kaiqi Huang, T. Tan
In this paper, we present a new people counting approach in visual surveillance scenes. The features adopted in previous methods are all extracted at pixel-level or based on local area, which are severely affected by factors such as occlusion. To cover the shortage, we introduce a new feature which describes a people crowd as a whole. Because pedestrian behaviors change when the degree of crowdedness varies, we can capture motion information to model a crowd and characterize the pedestrian behaviors based on statistic analysis. Afterwards we combine together the two kinds of features presented above as the final people counting feature. Experiments conducted in real world scenes demonstrate the superior effectiveness of the proposed method.
{"title":"People counting using combined feature","authors":"Congwen Gao, Kaiqi Huang, T. Tan","doi":"10.1109/IVSURV.2011.6157030","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157030","url":null,"abstract":"In this paper, we present a new people counting approach in visual surveillance scenes. The features adopted in previous methods are all extracted at pixel-level or based on local area, which are severely affected by factors such as occlusion. To cover the shortage, we introduce a new feature which describes a people crowd as a whole. Because pedestrian behaviors change when the degree of crowdedness varies, we can capture motion information to model a crowd and characterize the pedestrian behaviors based on statistic analysis. Afterwards we combine together the two kinds of features presented above as the final people counting feature. Experiments conducted in real world scenes demonstrate the superior effectiveness of the proposed method.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"299 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114579084","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 : 2011-12-01DOI: 10.1109/IVSURV.2011.6157033
Ming Yang, Kai Yu
Human gender and age recognition is an emerging application for intelligent video analysis. However, offline pretrained recognition models often show degraded performance in a specific application scenario. To alleviate this issue, this paper presents a client-server system design adapting gender and age recognition models for mobile platforms. Specifically, the client program on Android smart phones streams face images to a cloud computing service where the recognition models based on convolutional neural networks are adapted leveraging the face correspondences in successive frames as weak supervision. The prototype system demonstrates the proposed design effectively reduces estimation variances and enhances user experiences.
{"title":"Adapting gender and age recognition system for mobile platforms","authors":"Ming Yang, Kai Yu","doi":"10.1109/IVSURV.2011.6157033","DOIUrl":"https://doi.org/10.1109/IVSURV.2011.6157033","url":null,"abstract":"Human gender and age recognition is an emerging application for intelligent video analysis. However, offline pretrained recognition models often show degraded performance in a specific application scenario. To alleviate this issue, this paper presents a client-server system design adapting gender and age recognition models for mobile platforms. Specifically, the client program on Android smart phones streams face images to a cloud computing service where the recognition models based on convolutional neural networks are adapted leveraging the face correspondences in successive frames as weak supervision. The prototype system demonstrates the proposed design effectively reduces estimation variances and enhances user experiences.","PeriodicalId":141829,"journal":{"name":"2011 Third Chinese Conference on Intelligent Visual Surveillance","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125355314","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：