{"title":"基于自适应多模型切换的凸轮轴头部跟踪","authors":"Yugang Shan, Jiabao Wang, Feng Hao","doi":"10.1109/IAEAC.2017.8054469","DOIUrl":null,"url":null,"abstract":"In order to improve the accuracy and efficiency of multi-model switching Camshift head tracking, an adaptive multi-model switching Camshift head tracking method is proposed. This paper first analyzes the advantages and disadvantages of multi-model switching and multi-model combination, then presents the multi-feature description method of the object. Next, using the Bhattacharyya coefficient as the model switching condition, the update time is determined according to the switching threshold. When exceeding the switching threshold, Bhattacharyya coefficient are calculated by the various models, choosing the maximal similarity model as the object model. Image sequences are tested in the public library, the experimental results show that this algorithm can be implemented for long time head motion image sequence in the case of head translation and rotation with anti-jamming and anti-blocking. By comparing and analyzing the multiple features and RGB multi-model switching algorithm, we can get the conclusion that the proposed algorithm is superior to the latter in stability and accuracy.","PeriodicalId":432109,"journal":{"name":"2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Camshift head tracking based on adaptive multi-model switching\",\"authors\":\"Yugang Shan, Jiabao Wang, Feng Hao\",\"doi\":\"10.1109/IAEAC.2017.8054469\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In order to improve the accuracy and efficiency of multi-model switching Camshift head tracking, an adaptive multi-model switching Camshift head tracking method is proposed. This paper first analyzes the advantages and disadvantages of multi-model switching and multi-model combination, then presents the multi-feature description method of the object. Next, using the Bhattacharyya coefficient as the model switching condition, the update time is determined according to the switching threshold. When exceeding the switching threshold, Bhattacharyya coefficient are calculated by the various models, choosing the maximal similarity model as the object model. Image sequences are tested in the public library, the experimental results show that this algorithm can be implemented for long time head motion image sequence in the case of head translation and rotation with anti-jamming and anti-blocking. By comparing and analyzing the multiple features and RGB multi-model switching algorithm, we can get the conclusion that the proposed algorithm is superior to the latter in stability and accuracy.\",\"PeriodicalId\":432109,\"journal\":{\"name\":\"2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IAEAC.2017.8054469\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IAEAC.2017.8054469","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Camshift head tracking based on adaptive multi-model switching
In order to improve the accuracy and efficiency of multi-model switching Camshift head tracking, an adaptive multi-model switching Camshift head tracking method is proposed. This paper first analyzes the advantages and disadvantages of multi-model switching and multi-model combination, then presents the multi-feature description method of the object. Next, using the Bhattacharyya coefficient as the model switching condition, the update time is determined according to the switching threshold. When exceeding the switching threshold, Bhattacharyya coefficient are calculated by the various models, choosing the maximal similarity model as the object model. Image sequences are tested in the public library, the experimental results show that this algorithm can be implemented for long time head motion image sequence in the case of head translation and rotation with anti-jamming and anti-blocking. By comparing and analyzing the multiple features and RGB multi-model switching algorithm, we can get the conclusion that the proposed algorithm is superior to the latter in stability and accuracy.