A Top-down Approach to Articulated Human Pose Estimation and Tracking

Guanghan Ning, Ping Liu, Xiaochuan Fan, Chi Zhang; Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018, pp. 0-0

Both the tasks of multi-person human pose estimation and pose tracking in videos are quite challenging. Existing methods can be categorized into two groups: top-down and bottom-up approaches. In this paper, following the top-down approach, we aim to build a strong baseline system with three modules: human candidate detector, singleperson pose estimator and human pose tracker. Firstly, we choose a generic object detector among state-of-the-art methods to detect human candidates. Then, cascaded pyramid network is used to estimate the corresponding human pose. Finally, we use a flow-based pose tracker to render keypoint-association across frames, i.e., assigning each human candidate a unique and temporally-consistent id, for the multi-target pose tracking purpose. We conduct extensive ablative experiments to validate various choices of models and configurations. We take part in two ECCV’18 PoseTrack challenges1: pose estimation and pose tracking.