Lati Abdelhai, M. Haitham, Benhellal Belkheir, B. Mahmoud, Achour Nouara
{"title":"基于FREAK的图像拼接和目标跟踪算法的LabVIEW实现","authors":"Lati Abdelhai, M. Haitham, Benhellal Belkheir, B. Mahmoud, Achour Nouara","doi":"10.1109/ICEE49691.2020.9249909","DOIUrl":null,"url":null,"abstract":"in this paper, we propose implementations of two important vision algorithms on LabVIEW tool; which are image mosaicing and object tracking. Features are used as a starting point for our algorithms; so the overall algorithms will only be as good as their used feature detectors and features matching techniques, for that, we propose using Harris corner detector to find key points in overlapping images, then describing the detected features using FREAK descriptors for finding correspondences, after estimating homography parameters; either the second image is transformed to the frame of the first image for image mosaicing purpose, or four corners of the tracked object are transformed for object tracking purpose. The two algorithms are tested on Matlab, and then they are implemented on LabVIEW platform; in which a sophisticated interface is created to facilitate code execution for users, the built interface on LabVIEW can be used to be executed on embedded systems. The performance of our implementation is verified on real images from different data base.","PeriodicalId":250276,"journal":{"name":"2020 International Conference on Electrical Engineering (ICEE)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Novel LabVIEW Implementation of FREAK Based Image Mosaicing and Object Tracking Algorithms\",\"authors\":\"Lati Abdelhai, M. Haitham, Benhellal Belkheir, B. Mahmoud, Achour Nouara\",\"doi\":\"10.1109/ICEE49691.2020.9249909\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"in this paper, we propose implementations of two important vision algorithms on LabVIEW tool; which are image mosaicing and object tracking. Features are used as a starting point for our algorithms; so the overall algorithms will only be as good as their used feature detectors and features matching techniques, for that, we propose using Harris corner detector to find key points in overlapping images, then describing the detected features using FREAK descriptors for finding correspondences, after estimating homography parameters; either the second image is transformed to the frame of the first image for image mosaicing purpose, or four corners of the tracked object are transformed for object tracking purpose. The two algorithms are tested on Matlab, and then they are implemented on LabVIEW platform; in which a sophisticated interface is created to facilitate code execution for users, the built interface on LabVIEW can be used to be executed on embedded systems. The performance of our implementation is verified on real images from different data base.\",\"PeriodicalId\":250276,\"journal\":{\"name\":\"2020 International Conference on Electrical Engineering (ICEE)\",\"volume\":\"127 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 International Conference on Electrical Engineering (ICEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEE49691.2020.9249909\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Electrical Engineering (ICEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEE49691.2020.9249909","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Novel LabVIEW Implementation of FREAK Based Image Mosaicing and Object Tracking Algorithms
in this paper, we propose implementations of two important vision algorithms on LabVIEW tool; which are image mosaicing and object tracking. Features are used as a starting point for our algorithms; so the overall algorithms will only be as good as their used feature detectors and features matching techniques, for that, we propose using Harris corner detector to find key points in overlapping images, then describing the detected features using FREAK descriptors for finding correspondences, after estimating homography parameters; either the second image is transformed to the frame of the first image for image mosaicing purpose, or four corners of the tracked object are transformed for object tracking purpose. The two algorithms are tested on Matlab, and then they are implemented on LabVIEW platform; in which a sophisticated interface is created to facilitate code execution for users, the built interface on LabVIEW can be used to be executed on embedded systems. The performance of our implementation is verified on real images from different data base.