HPRNet: Hierarchical point regression for whole-body human pose estimation

Download

index.pdf

Date

2021-11-01

Author

SAMET, NERMİN
Akbaş, Emre

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

359
views

119
downloads

In this paper, we present a new bottom-up one-stage method for whole-body pose estimation, which we call “hierarchical point regression,” or HPRNet for short. In standard body pose estimation, the locations of ~17 major joints on the human body are estimated. Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed. To handle the scale variance among different body parts, we build a hierarchical point representation of body parts and jointly regress them. The relative locations of fine-grained keypoints in each part (e.g. face) are regressed in reference to the center of that part, whose location itself is estimated relative to the person center. In addition, unlike the existing two-stage methods, our method predicts whole-body pose in a constant time independent of the number of people in an image. On the COCO WholeBody dataset, HPRNet significantly outperforms all previous bottom-up methods on the keypoint detection of all whole-body parts (i.e. body, foot, face and hand); it also achieves state-of-the-art results on face (75.4 AP) and hand (50.4 AP) keypoint detection. Code and models are available at https://github.com/nerminsamet/HPRNet.git.

Subject Keywords

Whole-body human pose estimation, Multi-person pose estimation, Facial landmark detection, Bottom-up human pose estimation, Hand keypoint Estimation

URI

https://hdl.handle.net/11511/93836

Journal

Image and Vision Computing

DOI

https://doi.org/10.1016/j.imavis.2021.104285

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network KOCABAŞ, Muhammed; KARAGÖZ, Salih; Akbaş, Emre (2018-09-14) In this paper, we present MultiPoseNet, a novel bottom-up multi-person pose estimation architecture that combines a multi-task model with a novel assignment method. MultiPoseNet can jointly handle person detection, person segmentation and pose estimation problems. The novel assignment method is implemented by the Pose Residual Network (PRN) which receives keypoint and person detections, and produces accurate poses by assigning keypoints to person instances. On the COCO keypoints dataset, our pose estimation...
CMARS: a new contribution to nonparametric regression with multivariate adaptive regression splines supported by continuous optimization Weber, Gerhard-Wilhelm; Batmaz, İnci; Köksal, Gülser; Taylan, Pakize; Yerlikaya-Ozkurt, Fatma (2012-01-01) Regression analysis is a widely used statistical method for modelling relationships between variables. Multivariate adaptive regression splines (MARS) especially is very useful for high-dimensional problems and fitting nonlinear multivariate functions. A special advantage of MARS lies in its ability to estimate contributions of some basis functions so that both additive and interactive effects of the predictors are allowed to determine the response variable. The MARS method consists of two parts: forward an...
Parameter estimation in generalized partial linear models with Tikhanov regularization Kayhan, Belgin; Karasözen, Bülent; Department of Scientific Computing (2010) Regression analysis refers to techniques for modeling and analyzing several variables in statistical learning. There are various types of regression models. In our study, we analyzed Generalized Partial Linear Models (GPLMs), which decomposes input variables into two sets, and additively combines classical linear models with nonlinear model part. By separating linear models from nonlinear ones, an inverse problem method Tikhonov regularization was applied for the nonlinear submodels separately, within the e...
Similarity matrix framework for data from union of subspaces Aldroubi, Akram; Sekmen, Ali; Koku, Ahmet Buğra; Cakmak, Ahmet Faruk (2018-09-01) This paper presents a framework for finding similarity matrices for the segmentation of data W = [w(1)...w(N)] subset of R-D drawn from a union U = boolean OR(M)(i=1) S-i, of independent subspaces {S-i}(i=1)(M), of dimensions {d(i)}(i=1)(M). It is shown that any factorization of W = BP, where columns of B form a basis for data W and they also come from U, can be used to produce a similarity matrix Xi w. In other words, Xi w(i, j) not equal 0, when the columns w(i) and w(j) of W come from the same subspace, ...
Integrating near and long-range evidence for visual detection Samet, Nermin; Akbaş, Emre; Department of Computer Engineering (2021-9) This thesis presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby ge...

Citation Formats

N. SAMET and E. Akbaş, “HPRNet: Hierarchical point regression for whole-body human pose estimation,” Image and Vision Computing, vol. 115, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/93836.