In this paper, a novel two-stream architecture has been designed to improve action recognition accuracy for hockey using three main components. First, pose is estimated via the Part Affinity Fields model to extract meaningful cues from the player. Second, optical flow (using LiteFlownet) is used to extract temporal features. Third, pose and optical flow streams are fused and passed to fully-connected layers to estimate the hockey player's action. A novel publicly available dataset named HARPET (Hockey Action Recognition Pose Estimation, Temporal) was created, composed of sequences of annotated actions and pose of hockey players including their hockey sticks as an extension of human body pose. Three contributions are recognized. (1) The novel two-stream architecture achieves 85% action recognition accuracy, with the inclusion of optical flows increasing accuracy by about 10%. Thus, demonstrating the complementary nature of pose estimation and optical flow. (2) The unique localization of hand-held objects (e.g., hockey sticks) as part of pose increases accuracy by about 13%. (3) For pose estimation, a bigger and more general dataset, MSCOCO, is successfully used for transfer learning to a smaller and more specific dataset, HARPET, achieving a PCKh of 87%.
© Copyright 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. Alle Rechte vorbehalten.