scholarly journals A Novel Approach of Intelligent Computing for Multiperson Pose Estimation with Deep High Spatial Resolution and Multiscale Features

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Haiquan Wang ◽  
Xiangyang Wang ◽  
Yijie Shi ◽  
Yanping Li ◽  
Chunhua Qian ◽  
...  
Keyword(s):  
Spatial Resolution ◽  
Pose Estimation ◽  
Spatial Information ◽  
High Spatial Resolution ◽  
Human Pose Estimation ◽  
Body Parts ◽  
Low Resolution ◽  
Feature Maps ◽  
Intelligent Computing ◽  
Human Pose

Currently, human pose estimation (HPE) methods mainly rely on the design framework of Convolutional Neural Networks (CNNs). These CNNs typically consist of high-to-low-resolution subnetworks (encoder) to learn semantic information and low-to-high subnetworks (decoder) to raise the resolution for keypoint localization. Because too low-resolution feature maps in encoder will inevitably lose some spatial information, which cannot be recovered in the upsampling stages, keeping high spatial resolution features is critical for human pose estimation. On the other hand, due to scale variation of human body parts, multiscale features are also very important for human pose estimation. In this paper, a novel backbone network is proposed specifically for HPE, named High Spatial Resolution and Multiscale Networks (HSR-MSNet), which maintain high spatial resolution features in deeper layers of the encoder and meanwhile construct multiscale features within one single residual block via subgroup splitting and fusion of feature maps. Experiments show that our approach outperforms other state-of-the-art methods with more accurate keypoint locations on COCO dataset.

scholarly journals Mixing body‐parts model for 2D human pose estimation in stereo videos

2017 ◽  
Vol 11 (6) ◽  
pp. 426-433 ◽  
Author(s):  
Manuel I. López‐Quintero ◽  
Manuel J. Marín‐Jiménez ◽  
Rafael Muñoz‐Salinas ◽  
Rafael Medina‐Carnicer
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Body Parts ◽  
Human Pose

Multi-Scale Collaborative Network for Human Pose Estimation

2019 ◽  
Vol 16 (04) ◽  
pp. 1941003
Author(s):  
Chunsheng Guo ◽  
Jialuo Zhou ◽  
Wenlong Du ◽  
Xuguang Zhang
Keyword(s):  
Loss Function ◽  
Pose Estimation ◽  
Large Scale ◽  
Human Pose Estimation ◽  
Small Scale ◽  
Feature Maps ◽  
Multi Scale ◽  
Human Pose ◽  
Processing Network ◽  
Weight Coefficients

Human pose estimation is a fundamental but challenging task in computer vision. The estimation of human pose mainly depends on the global information of the keypoint type and the local information of the keypoint location. However, the consistency of the cascading process makes it difficult for each stacking network to form a differentiation and collaboration mechanism. In order to solve these problems, this paper introduces a new human pose estimation framework called Multi-Scale Collaborative (MSC) network. The pre-processing network forms feature maps of different sizes, and dispatches them to various locations of the stack network, with small-scale features reaching the front-end stacking network and large-scale features reaching the back-end stacking network. A new loss function is proposed for MSC network. Different keypoints have different weight coefficients of loss function at different scales, and the keypoint weight coefficients are dynamically adjusted from the top hourglass network to the bottom hourglass network. Experimental results show that the proposed method is competitive in MPII and LSP challenge leaderboard among the state-of-the-art methods.

scholarly journals EfficientPose: Efficient human pose estimation with neural architecture search

2021 ◽  
Author(s):  
Wenqiang Zhang ◽  
Jiemin Fang ◽  
Xinggang Wang ◽  
Wenyu Liu
Keyword(s):  
Pose Estimation ◽  
Spatial Information ◽  
Computational Cost ◽  
Multimedia Applications ◽  
Human Pose Estimation ◽  
Estimation Task ◽  
Neural Architecture ◽  
Great Performance ◽  
Human Pose ◽  
Large Model

AbstractHuman pose estimation from image and video is a key task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on lightweight devices. Nowadays, real-time multimedia applications call for more efficient models for better interaction. Moreover, most deep neural networks for pose estimation directly reuse networks designed for image classification as the backbone, which are not optimized for the pose estimation task. In this paper, we propose an efficient framework for human pose estimation with two parts, an efficient backbone and an efficient head. By implementing a differentiable neural architecture search method, we customize the backbone network design for pose estimation, and reduce computational cost with negligible accuracy degradation. For the efficient head, we slim the transposed convolutions and propose a spatial information correction module to promote the performance of the final prediction. In experiments, we evaluate our networks on the MPII and COCO datasets. Our smallest model requires only 0.65 GFLOPs with 88.1% [email protected] on MPII and our large model needs only 2 GFLOPs while its accuracy is competitive with the state-of-the-art large model, HRNet, which takes 9.5 GFLOPs.

scholarly journals Progressive Bi-C3D Pose Grammar for Human Pose Estimation

2020 ◽  
Vol 34 (07) ◽  
pp. 13033-13040 ◽  
Author(s):  
Lu Zhou ◽  
Yingying Chen ◽  
Jinqiao Wang ◽  
Hanqing Lu
Keyword(s):  
Pose Estimation ◽  
Human Body ◽  
Message Passing ◽  
Contextual Information ◽  
Human Pose Estimation ◽  
Body Parts ◽  
Multi Scale ◽  
Human Pose ◽  
Human Joints ◽  
Body Joints

In this paper, we propose a progressive pose grammar network learned with Bi-C3D (Bidirectional Convolutional 3D) for human pose estimation. Exploiting the dependencies among the human body parts proves effective in solving the problems such as complex articulation, occlusion and so on. Therefore, we propose two articulated grammars learned with Bi-C3D to build the relationships of the human joints and exploit the contextual information of human body structure. Firstly, a local multi-scale Bi-C3D kinematics grammar is proposed to promote the message passing process among the locally related joints. The multi-scale kinematics grammar excavates different levels human context learned by the network. Moreover, a global sequential grammar is put forward to capture the long-range dependencies among the human body joints. The whole procedure can be regarded as a local-global progressive refinement process. Without bells and whistles, our method achieves competitive performance on both MPII and LSP benchmarks compared with previous methods, which confirms the feasibility and effectiveness of C3D in information interactions.

scholarly journals Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images

2014 ◽  
Vol 36 (11) ◽  
pp. 2131-2143 ◽  
Author(s):  
Matthias Dantone ◽  
Juergen Gall ◽  
Christian Leistner ◽  
Luc Van Gool
Keyword(s):  
Pose Estimation ◽  
Human Pose Estimation ◽  
Body Parts ◽  
Still Images ◽  
Human Pose
Sign in / Sign up

Export Citation Format

Share Document