Deep learning based 2D human pose estimation: A survey

Abstract

Human pose estimation has received significant attention recently due to its various applications in the real world. As the performance of the state-of-the-art human pose estimation methods can be improved by deep learning, this paper presents a comprehensive survey of deep learning based human pose estimation methods and analyzes the methodologies employed. We summarize and discuss recent works with a methodologybased taxonomy. Single-person and multi-person pipelines are first reviewed separately. Then, the deep learning techniques applied in these pipelines are compared and analyzed. The datasets and metrics used in this task are also discussed and compared. The aim of this survey is to make every step in the estimation pipelines interpretable and to provide readers a readily comprehensible explanation. Moreover, the unsolved problems and challenges for future research are discussed.

Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose tracking

“…Animal pose estimation. The proposed approach fills a void between state of the art human pose estimation algorithms, which often rely on large quantities of manually labeled samples (see [9] for a recent review), and their counterparts in animal pose estimation [37,4,6,5,38,39]. Among these animal pose estimation algorithms, Deep Lab Cut (DLC) [4], Leap Estimates Animal Pose (LEAP) [6], and Deep Pose Kit (DPK) [5], stand out as they can achieve near human-level accuracy using a modest number of labels.…”

“…Providing these labels requires significant user effort, particularly in the common case that users want to track multiple objects per frame (e.g., all the fingers on a hand or paw). Unlike HPE algorithms [9], APE algorithms are applied to a wide variety of different body structures (e.g., fish, flies, mice, or cheetahs) [10], compounding the effort required for collecting labeled datasets. Moreover, even with hundreds of labels, users still often see occasional "glitches" in the output (i.e., frames where tracking is briefly lost), which typically interfere with downstream analyses of the extracted behavior.…”

[Invited Paper] Fast and Accurate Whole-Body Pose Estimation in the Wild and Its Applications

“…In the past decade, many papers on multi-person pose estimation have been published 12) . They are usually divided into two categories: bottom-up and top-down approaches.…”

“…1) in images, and is widely used in humancomputer interactions, gaming, virtual reality, video surveillance, sports analysis, and medical assistance 1) . In the last decade, many new techniques have been proposed for human pose estimation with the development of convolutional neural networks, making it a highly popular research topic in the field of computer vision 2) . In this paper, we focused on multi-person pose estimation, which has no limitation on the number of individuals in the images.…”

“…The popular multi-person pose estimation techniques can be categorized into the bottom-up and top-down approaches 2) . The bottom-up approaches such as OpenPose 3) first detect the heatmap of keypoints in all persons from the images, then connect the body joints or keypoints for each person.…”