360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos

arXiv:2404.13953v1 Announce Type: new
Abstract: Visual object tracking and segmentation in omnidirectional videos are challenging due to the wide field-of-view and large spherical distortion brought by 360{\deg} images. To alleviate these problems, we introduce a novel representation, extended bounding field-of-view (eBFoV), for target localization and use it as the foundation of a general 360 tracking framework which is applicable for both omnidirectional visual object tracking and segmentation tasks. Building upon our previous work on omnidirectional visual object tracking (360VOT), we …

arxiv cs.cv object segmentation tracking type videos visual