Distribution-Aware Coordinate Representation for Human Pose Estimation

Zhang, Feng; Zhu, Xiatian; Dai, Hanbin; Ye, Mao; Zhu, Ce

doi:10.1109/cvpr42600.2020.00712

Cited by 411 publications

(229 citation statements)

References 24 publications

Supporting

Mentioning

227

Contrasting

Order By: Relevance

“…If there is a moving person, the time component can be exploited, and temporal smoothness can be applied to improve the estimation accuracy [124]. Therefore, keypoint estimation methods can be divided into single-image [14], [30], [31], [111], [176], multi-frame [124], and multi-view methods [66], [73], [133] for 2D [14], [30], [31], [153], [176] or 3D [66], [73], [111], [124], [133] keypoint estimation. The keypoint estimation algorithms usually find between 14 and 21 keypoints, as shown in Fig.…”

Section: Feature Extractionmentioning

confidence: 99%

A Review of Body Measurement Using 3D Scanning

et al. 2021

View full text Add to dashboard Cite

The understanding of body measurements and body shapes in and between populations is important and has many applications in medicine, surveying, the fashion industry, fitness, and entertainment. Body measurement using 3D surface scanning technologies is faster and more convenient than measurement with more traditional methods and at the same time provides much more data, which requires automatic processing. A multitude of 3D scanning methods and processing pipelines have been described in the literature, and the advent of deep learning-based processing methods has generated an increased interest in the topic. Also, over the last decade, larger public 3D human scanning datasets have been released. This paper gives a comprehensive survey of body measurement techniques, with an emphasis on 3D scanning technologies and automatic data processing pipelines. An introduction to the three most common 3D scanning technologies for body measurement, passive stereo, structured light, and time-of-flight, is provided, and their merits w.r.t. body measurement are discussed. Methods described in the literature are discussed within the newly proposed framework of five common processing stages: preparation, scanning, feature extraction, model fitting, and measurement extraction. Synthesizing the analyzed prior works, recommendations on specific 3D body scanning technologies and the accompanying processing pipelines for the most common applications are given. Finally, an overview of about 80 currently available 3D scanners manufactured by about 50 companies, as well as their taxonomy regarding several key characteristics, is provided in the Appendix.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

A Review of Body Measurement Using 3D Scanning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Note that in all the papers mentioned above a heatmap is generated for each joint, in which the pixel value indicates the joint existence probability at that location. Zhang et al 21) regarded heatmap as the de facto standard coordinate representation in human pose estimation.…”

Section: Pose Estimationmentioning

confidence: 99%

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

Tasaka

Yamaguchi

2021

MTA

View full text Add to dashboard Cite

“…Feng Zhang et al [54] tried to improve the network performance by re-decoding the hot spot map. They decoded the hot spot map predicted by the network into the coordinates of the key points of the human body in the original image space, and proposed a more principled distributed perceptual decoding method.…”

Section: Related Workmentioning

confidence: 99%

Multi-Cascade Perceptual Human Posture Recognition Enhancement Network

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The current researches trend to adopt a low-resolution hot spot map to restore the original highresolution representation to save computing cost, resulting in unsatisfactory detection performance, especially in human body recognition with a highly complex background. Aiming at this problem, we proposed a model of parallel connection of multiple sub-networks with different resolution levels on a high-resolution main network. It can maintain the network structure of a high-resolution hot spot map in the whole operation process. By using this structure in the human key point vector field network, the accuracy of human posture recognition has been improved with high-speed operation. To validate the proposed model's effectiveness, two common benchmark data sets of COCO key point data set and MPII human posture data set are used for evaluation. Experimental results show that our network achieves the accuracy of 72.3% AP and 92.2% AP in the two data sets, respectively, which is 3%-4% higher than those of the existing mainstream researches. In our test, only the accuracy of backbone's SimpleBaseline with ResNet-152 is close to ours, yet our network realized a much lower computing cost.

show abstract

Distribution-Aware Coordinate Representation for Human Pose Estimation

Cited by 411 publications

References 24 publications

A Review of Body Measurement Using 3D Scanning

A Review of Body Measurement Using 3D Scanning

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

Multi-Cascade Perceptual Human Posture Recognition Enhancement Network

Contact Info

Product

Resources

About