Deep Reinforcement Learning for Active Human Pose Estimation

Abstract

Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing information spatially and/or temporally, whenever available. In this paper we address the problem of an active observer with freedom to move and explore the scene spatially -- in `time-freeze' mode -- and/or temporally, by selecting informative viewpoints that improve its estimation accuracy. Towards this end, we introduce Pose-DRL, a fully trainable deep reinforcement learning-based active pose estimation architecture which learns to select appropriate views, in space and time, to feed an underlying monocular pose estimator. We evaluate our model using single- and multi-target estimators with strong result in both settings. Our system further learns automatic stopping conditions in time and transition functions to the next temporal processing step in videos. In extensive experiments with the Panoptic multi-view setup, and for complex scenes containing multiple people, we show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.

arXiv commentAccepted to The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). Submission updated to include supplementary material

References in corpus (9)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Convolutional Pose Machines
• Deep Reinforcement Learning for Visual Object Tracking in Videos
• Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning
• Towards Accurate Multi-person Pose Estimation in the Wild
• General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
• Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions