Detect-and-Track: Efficient Pose Estimation in Videos

TL;DR

This paper introduces a lightweight, two-stage method for human pose estimation and tracking in videos, combining frame-based keypoint detection with temporal tracking to improve accuracy and efficiency.

Contribution

The paper presents a novel two-stage approach that integrates frame-level pose estimation with lightweight tracking, utilizing a 3D extension of Mask R-CNN for enhanced robustness.

Findings

Achieves 55.2% MOTA on PoseTrack validation set

State-of-the-art performance on ICCV 2017 PoseTrack challenge

Effective use of temporal information for improved pose estimation

Abstract

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information over small clips to generate more robust frame predictions. We conduct extensive ablative experiments on the newly released multi-person video pose estimation benchmark, PoseTrack, to validate various design choices of our model. Our approach achieves an accuracy of 55.2% on the validation and 51.8% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric, and achieves state of the art performance on the ICCV 2017 PoseTrack keypoint tracking challenge.