{"title":"基于运动势能的连体追踪器","authors":"Zhao-Qian Tang, Mingyang Liu, Yun Gao","doi":"10.1109/ICSP54964.2022.9778626","DOIUrl":null,"url":null,"abstract":"Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Siamese tracker based on motion potential energy\",\"authors\":\"Zhao-Qian Tang, Mingyang Liu, Yun Gao\",\"doi\":\"10.1109/ICSP54964.2022.9778626\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.\",\"PeriodicalId\":363766,\"journal\":{\"name\":\"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)\",\"volume\":\"62 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSP54964.2022.9778626\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSP54964.2022.9778626","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Siamese trackers have been widely concerned recently. Though many trackers have obtained better performance when the target encounter fast motion or changes the direction of motion, most trackers still utilize the previous frame’s center to generate the center of the search box in the current frame, which may lead to loss of the tracked target. In this paper, we utilize the potential energy to the expended target detection region. Specially, we predict the search area of the current frame by analyzing the potential energy of the object’s historical frame. Abundant experiments show that our tracker with better robustness than most trackers on tracking benchmarks. Especially, the compared results show our tracker has an excellent performance in the fast motion challenge.