Articulated hand pose tracking is an underexplored problem that carries the potential for use in an extensive number of applications, especially in themedical domain . Res152- CondPose model incorporates a hand pose prior into its pose prediction . When evaluated onSurgical Hands, we show our method outperforms the state-of-the-art methodusing mean Average Precision (mAP), to measure pose estimation accuracy, and multiple Object Tracking Accuracy (MOTA), to assess pose tracking performance . Our dataset contains 76 video clips from 28 publiclyavailable surgical videos and over 8.1k annotated hand pose instances. Weprovide bounding boxes, articulated hand pose annotations, and tracking IDs toenable multi-instance area-based and articulated tracking. When evaluated our method performs our method, we showed our method out of the state of theart method. When . evaluated on Surgical Hands

Author(s) : Nathan Louis, Luowei Zhou, Steven J. Yule, Roger D. Dias, Milisa Manojlovich, Francis D. Pagani, Donald S. Likosky, Jason J. Corso

Links : PDF - Abstract

Code :
Coursera

Keywords : pose - tracking - hand - method - articulated -

Leave a Reply

Your email address will not be published. Required fields are marked *