RMPE: Regional Multi-person Pose Estimation
It improves pose estimation accuracy for applications like surveillance or sports analysis, but is incremental as it builds on existing detection-based methods.
The paper tackles the problem of multi-person pose estimation in the wild by addressing errors from human detectors, proposing the RMPE framework to handle inaccurate bounding boxes and redundant detections, resulting in a 17% increase in mAP over state-of-the-art methods on the MPII dataset.
Multi-person pose estimation in the wild is challenging. Although state-of-the-art human detectors have demonstrated good performance, small errors in localization and recognition are inevitable. These errors can cause failures for a single-person pose estimator (SPPE), especially for methods that solely depend on human detection results. In this paper, we propose a novel regional multi-person pose estimation (RMPE) framework to facilitate pose estimation in the presence of inaccurate human bounding boxes. Our framework consists of three components: Symmetric Spatial Transformer Network (SSTN), Parametric Pose Non-Maximum-Suppression (NMS), and Pose-Guided Proposals Generator (PGPG). Our method is able to handle inaccurate bounding boxes and redundant detections, allowing it to achieve a 17% increase in mAP over the state-of-the-art methods on the MPII (multi person) dataset.Our model and source codes are publicly available.