ArtTrack: Articulated Multi-Person Tracking in the Wild

Abstract

In this paper we propose an approach for articulated tracking of multiple people in unconstrained videos. Our starting point is a model that resembles existing architectures for single-frame pose estimation but is substantially faster. We achieve this in two ways: (1) by simplifying and sparsifying the body-part relationship graph and leveraging recent methods for faster inference, and (2) by offloading a substantial share of computation onto a feed-forward convolutional architecture that is able to detect and associate body joints of the same person even in clutter. We use this model to generate proposals for body joint locations and formulate articulated tracking as spatio-temporal grouping of such proposals. This allows to jointly solve the association problem for all people in the scene by propagating evidence from strong detections through time and enforcing constraints that each proposal can be assigned to one person only. We report results on a public "MPII Human Pose" benchmark and on a new "MPII Video Pose" dataset of image sequences with multiple people. We demonstrate that our model achieves state-of-the-art results while using only a fraction of time and is able to leverage temporal information to improve state-of-the-art for crowded scenes 1 .

Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues

“…Recent datasets for pose estimation in time focus on more challenging, multi-person videos as e.g. [17,15], but are smaller in scale -in particular due to the challenging nature of the task. Regarding establishing dense correspondences between images and surface-based body models DensePose-COCO was introduced in [12], providing annotations for 50K images of humans appearing in the COCO dataset.…”

Pose estimator and tracker using temporal flow maps for limbs

“…Multi-person pose estimation [1]- [16], [27] methods can be categorized as top-down and bottom-up approaches. The top-down approaches [5], [11]- [16] firstly detect a person's bounding box and estimate single pose on the extracted bounding box.…”

“…Several methods have been proposed to estimate and track human poses on videos [2], [4], [5], [12], [15], [16], [27]. These methods can be divided into two groups depending on whether the learned temporal information is used or not.…”

Real-time Convolutional Networks for Depth-based Human Pose Estimation

“…Spatial relationships between pairs of body parts are also considered in order to improve estimation and ease the inference stage. These relationships can be modeled by explicit regressors [16], [18], or embedded in a network architecture [29], [7]. Motivated by the cascade of detectors concept, [7] relies on recurrent detector blocks to refine predictions and encode body parts pairwise dependencies as a vector field between adjacent parts.…”