{"title":"用于视觉跟踪的非视黄变性粒子滤波","authors":"A. A. Gunawan, Ito Wasito","doi":"10.5281/ZENODO.18601","DOIUrl":null,"url":null,"abstract":"Visual tracking is the problem of using visual sensor measurements to determine location and path of target object. One of big challenges for visual tracking is full occlusion. When full occlusions are present, image data alone can be unreliable, and is not sufficient to detect the target object. The developed tracking algorithm is based on bootstrap particle filter and using color feature target. Furthermore the algorithm is modified using nonretinotopic concept, inspired from the way of human visual cortex handles occlusion by constructing nonretinotopic layers. We interpreted the concept by using past tracking memory about motion dynamics rather than current measurement when quality level of tracking reliability below a threshold. Using experiments, we found (i) the performance of the object tracking algorithm in handling occlusion can be improved using nonretinotopic concept, (ii) dynamic model is crucial for object tracking, especially when the target object experienced occlusion and maneuver motions, (iii) the dependency of the tracker performance on the accuracy of tracking quality threshold when facing illumination challenge. Preliminary experimental results are provided.","PeriodicalId":53606,"journal":{"name":"Journal of Theoretical and Applied Information Technology","volume":"14 1","pages":"104-111"},"PeriodicalIF":0.0000,"publicationDate":"2014-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Nonretinotopic Particle Filter for Visual Tracking\",\"authors\":\"A. A. Gunawan, Ito Wasito\",\"doi\":\"10.5281/ZENODO.18601\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Visual tracking is the problem of using visual sensor measurements to determine location and path of target object. One of big challenges for visual tracking is full occlusion. When full occlusions are present, image data alone can be unreliable, and is not sufficient to detect the target object. The developed tracking algorithm is based on bootstrap particle filter and using color feature target. Furthermore the algorithm is modified using nonretinotopic concept, inspired from the way of human visual cortex handles occlusion by constructing nonretinotopic layers. We interpreted the concept by using past tracking memory about motion dynamics rather than current measurement when quality level of tracking reliability below a threshold. Using experiments, we found (i) the performance of the object tracking algorithm in handling occlusion can be improved using nonretinotopic concept, (ii) dynamic model is crucial for object tracking, especially when the target object experienced occlusion and maneuver motions, (iii) the dependency of the tracker performance on the accuracy of tracking quality threshold when facing illumination challenge. Preliminary experimental results are provided.\",\"PeriodicalId\":53606,\"journal\":{\"name\":\"Journal of Theoretical and Applied Information Technology\",\"volume\":\"14 1\",\"pages\":\"104-111\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Theoretical and Applied Information Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5281/ZENODO.18601\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Theoretical and Applied Information Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5281/ZENODO.18601","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}
Nonretinotopic Particle Filter for Visual Tracking
Visual tracking is the problem of using visual sensor measurements to determine location and path of target object. One of big challenges for visual tracking is full occlusion. When full occlusions are present, image data alone can be unreliable, and is not sufficient to detect the target object. The developed tracking algorithm is based on bootstrap particle filter and using color feature target. Furthermore the algorithm is modified using nonretinotopic concept, inspired from the way of human visual cortex handles occlusion by constructing nonretinotopic layers. We interpreted the concept by using past tracking memory about motion dynamics rather than current measurement when quality level of tracking reliability below a threshold. Using experiments, we found (i) the performance of the object tracking algorithm in handling occlusion can be improved using nonretinotopic concept, (ii) dynamic model is crucial for object tracking, especially when the target object experienced occlusion and maneuver motions, (iii) the dependency of the tracker performance on the accuracy of tracking quality threshold when facing illumination challenge. Preliminary experimental results are provided.
期刊介绍:
Journal of Theoretical and Applied Information Technology published since 2005 (E-ISSN 1817-3195 / ISSN 1992-8645) is an open access International refereed research publishing journal with a focused aim on promoting and publishing original high quality research dealing with theoretical and scientific aspects in all disciplines of Information Technology. JATIT is an international scientific research journal focusing on issues in information technology research. A large number of manuscript inflows, reflects its popularity and the trust of world''s research community. JATIT is indexed with major indexing and abstracting organizations and is published in both electronic and print format.