Mingming Lv, Li Wang, Yuan-long Hou, Q. Gao, Run-min Hou
{"title":"基于灰色预测的均值漂移跟踪器视觉目标跟踪","authors":"Mingming Lv, Li Wang, Yuan-long Hou, Q. Gao, Run-min Hou","doi":"10.1109/CJECE.2018.2875142","DOIUrl":null,"url":null,"abstract":"In this paper, the mean shift (MS) tracker embedded with grey prediction is proposed for visual object tracking. As the basic model of grey prediction, grey model [GM(1,1)] is employed to predict object location with few historical information. The predicted location is taken as the initial point of MS iteration instead of the previous tracking result in the original MS tracker. The prediction equation of GM(1,1) is simplified to reduce computation, and the occlusion degree is determined by the Bhattacharyya coefficient and a set threshold. If the degree exceeds a certain limit, the MS iteration may not converge to the true result and the object location is replaced with the predicted location to prevent failure tracking. The experimental results show that the proposed approach can effectively deal with the problems of fast-moving and serious occlusion and has a better performance than the original MS tracker and the MS tracker with particle filter.","PeriodicalId":55287,"journal":{"name":"Canadian Journal of Electrical and Computer Engineering-Revue Canadienne De Genie Electrique et Informatique","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2018-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CJECE.2018.2875142","citationCount":"2","resultStr":"{\"title\":\"Mean Shift Tracker With Grey Prediction for Visual Object Tracking\",\"authors\":\"Mingming Lv, Li Wang, Yuan-long Hou, Q. Gao, Run-min Hou\",\"doi\":\"10.1109/CJECE.2018.2875142\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, the mean shift (MS) tracker embedded with grey prediction is proposed for visual object tracking. As the basic model of grey prediction, grey model [GM(1,1)] is employed to predict object location with few historical information. The predicted location is taken as the initial point of MS iteration instead of the previous tracking result in the original MS tracker. The prediction equation of GM(1,1) is simplified to reduce computation, and the occlusion degree is determined by the Bhattacharyya coefficient and a set threshold. If the degree exceeds a certain limit, the MS iteration may not converge to the true result and the object location is replaced with the predicted location to prevent failure tracking. The experimental results show that the proposed approach can effectively deal with the problems of fast-moving and serious occlusion and has a better performance than the original MS tracker and the MS tracker with particle filter.\",\"PeriodicalId\":55287,\"journal\":{\"name\":\"Canadian Journal of Electrical and Computer Engineering-Revue Canadienne De Genie Electrique et Informatique\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2018-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1109/CJECE.2018.2875142\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Canadian Journal of Electrical and Computer Engineering-Revue Canadienne De Genie Electrique et Informatique\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CJECE.2018.2875142\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"Engineering\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Canadian Journal of Electrical and Computer Engineering-Revue Canadienne De Genie Electrique et Informatique","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CJECE.2018.2875142","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Engineering","Score":null,"Total":0}
Mean Shift Tracker With Grey Prediction for Visual Object Tracking
In this paper, the mean shift (MS) tracker embedded with grey prediction is proposed for visual object tracking. As the basic model of grey prediction, grey model [GM(1,1)] is employed to predict object location with few historical information. The predicted location is taken as the initial point of MS iteration instead of the previous tracking result in the original MS tracker. The prediction equation of GM(1,1) is simplified to reduce computation, and the occlusion degree is determined by the Bhattacharyya coefficient and a set threshold. If the degree exceeds a certain limit, the MS iteration may not converge to the true result and the object location is replaced with the predicted location to prevent failure tracking. The experimental results show that the proposed approach can effectively deal with the problems of fast-moving and serious occlusion and has a better performance than the original MS tracker and the MS tracker with particle filter.
期刊介绍:
The Canadian Journal of Electrical and Computer Engineering (ISSN-0840-8688), issued quarterly, has been publishing high-quality refereed scientific papers in all areas of electrical and computer engineering since 1976