Abstract:Panoramic vision has developed greatly in the field of computer vision during these years. The tracking of moving objects is one of the most classic subjects, which has a wide application prospect. Du...Panoramic vision has developed greatly in the field of computer vision during these years. The tracking of moving objects is one of the most classic subjects, which has a wide application prospect. Due to the influence of panorama image distortion, it brings a serious error to the target feature extraction, and it is hard to track the target precisely. The existing method of panoramic vision tracking still has some limitations. Therefore, based on the particle filter tracking, this paper proposes a panoramic visual tracking algorithm based on adaptive extraction of the fused features of color and shape features, and included the particle weights into the tracking process. The target tracking accuracy is significantly improved. Experimental results show that the proposed algorithm can solve the problem of change in object's appearance, which caused by the translation, rotation, external illumination and occlusion of the target object, effectively improve the robustness of panoramic visual tracking.Read More
Publication Year: 2018
Publication Date: 2018-10-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 1
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot