PoseTrack: A Benchmark for Human Pose Estimation and Tracking

Abstract

Figure 1: Sample video from our benchmark. We select sequences that represent crowded scenes with multiple articulated people engaging in various dynamic activities and provide dense annotations of person tracks, body joints and ignore regions. AbstractExisting systems for video-based pose estimation and tracking struggle to perform well on realistic videos with multiple people and often fail to output body-pose trajectories consistent over time. To address this shortcoming this paper introduces PoseTrack which is a new large-scale benchmark for video-based human pose estimation and articulated tracking. Our new benchmark encompasses three tasks focusing on i) single-frame multi-person pose estimation, ii) multi-person pose estimation in videos, and iii) multi-person articulated tracking. To establish the benchmark, we collect, annotate and release a new dataset that features videos with multiple people labeled with person tracks and articulated pose. A public centralized evaluation server is provided to allow the research community to evaluate on a held-out test set. Furthermore, we conduct an extensive experimental study on recent approaches to articulated pose tracking and provide analysis of the strengths and weaknesses of the state of the art. We envision that the proposed benchmark will stimulate productive research both by providing a large and representative training dataset as well as providing a platform to objectively evaluate and compare the proposed methods. The benchmark is

Pose estimator and tracker using temporal flow maps for limbs

“…In order to prove the efficiency of the proposed method, experiments on the PoseTrack 2017 and 2018 datasets [17] have been performed. PoseTrack datasets are large-scale benchmarks for human pose estimation and tracking.…”

“…We evaluated the proposed method on the PoseTrack 2017 and 2018 datasets [17]. To prove the effectiveness of the proposed method, we made a comparison of our work with state-of-the-art algorithms.…”

NADS-Net: A Nimble Architecture for Driver and Seat Belt Detection via Convolutional Neural Networks

“…Most of the pose estimation models are trained and validated on publicly available data set such as MS COCO [19] and PoseTrack [2] data sets. These data sets are, however, mostly images taken in daytime or bright indoor scenes, whereas the illumination in vehicles can vary drastically.…”

FollowMeUp Sports: New Benchmark for 2D Human Keypoint Recognition

“…The PoseTrack dataset [13] includes both multi-person pose estimation and tracking annotations in videos. It can perform not only pose estimation in single frames, but also temporal tracking across frames.…”

“…Since the pose estimation results of the same person in the standing posture are correct, we argue the false predictions are caused by the abnormal postures. Current datasets lack the corresponding samples [12] [13].…”