{"title":"基于倾斜菱形搜索的交通监控实时运动估计","authors":"T. Johri, V. Bahri, R. Sahu","doi":"10.1109/SECON.2008.4494348","DOIUrl":null,"url":null,"abstract":"This paper focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.","PeriodicalId":188817,"journal":{"name":"IEEE SoutheastCon 2008","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A real time motion estimation for traffic monitoring using sloped diamond search\",\"authors\":\"T. Johri, V. Bahri, R. Sahu\",\"doi\":\"10.1109/SECON.2008.4494348\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.\",\"PeriodicalId\":188817,\"journal\":{\"name\":\"IEEE SoutheastCon 2008\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE SoutheastCon 2008\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SECON.2008.4494348\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE SoutheastCon 2008","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SECON.2008.4494348","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A real time motion estimation for traffic monitoring using sloped diamond search
This paper focus on fast block based motion estimation for traffic monitoring using a stationary camera. As the traffic needs to be monitored continuously a real time motion estimation algorithm is required which could provide good match as well. Most of the existing block matching algorithms fail to give good match when the speed of motion varies too much. This algorithm (RTME-SDS) overcomes this problem by estimating the initial position to be searched using the motion vector of previous frame. At this position we apply sloped diamond search. Since the traffic move along a fixed path at different speed, this algorithm gives a good initial position to continue with the estimation. RTME-SDS improves over the above mentioned algorithm by more than 45% in terms of complexity giving a match close to above mentioned algorithm.