NDLI: Multi-person pose estimation using atrous convolution

Content Provider	IET Digital Library
Author	Lin, Lu Wang, Yifei Wang, Lianghao Zhang, Ming Li, Dongxiao
Abstract	The technology of human keypoint localisation has been greatly improved with the development of deep neural network. In particular, recent methods that exploit multi-scale features and cascaded networks have achieved the accurate prediction of multi-person keypoints. These methods typically extract small-resolution feature maps with classical backbone and then generate heatmaps through upsampling. However, consecutive striding is harmful for keypoint localisation since detail information is decimated. In this Letter, the authors present a novel network structure that uses atrous spatial pyramid pooling to generate keypoint prediction. First, atrous convolution is used in the backbone to expand the receptive field and maintain the scale of the feature map. Thus, the size of the feature map can be guaranteed to avoid too many details being removed. Second, multi-scale features are extracted using an atrous spatial pyramid pooling module to enrich the scale information of the obtained features. Finally, instead of upsampling, deconvolutional layers are applied to construct the output heatmaps. State-of-the-art results are achieved on the MS COCO 2017 keypoint database.
Starting Page	533
Ending Page	535
Page Count	3
ISSN	00135194
Volume Number	55
e-ISSN	1350911X
Issue Number	Issue 9, May (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/el/55/9
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/el.2019.0351
Journal	Electronics Letters
Publisher Date	2019-03-15
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Atrous Convolution Atrous Spatial Pyramid Pooling Module Cascaded Network Classical Backbone Computer Vision Computer Vision And Image Processing Technique Deep Neural Network Feature Extraction Feature Map Human Keypoint Localisation Image Recognition Image Representation Image Resolution Keypoint Prediction MS COCO 2017 Keypoint Database Multiperson KeyPoint Multiscale Feature Network Structure Neural Computing Technique Neural Nets Object Detection Object Recognition Particular Method Pose Estimation Scale Information Small-resolution Feature Maps
Content Type	Text
Resource Type	Article
Subject	Electrical and Electronic Engineering

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

OCPAN: multi-person pose estimation with more attention on residual information

Multi-scale object detection by bottom-up feature pyramid network

Multi-scale feature fusion network for person re-identification

Edge gradient feature and long distance dependency for image semantic segmentation

Crowd counting using a self-attention multi-scale cascaded network

CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution

Multi-scale deep neural network for salient object detection

Adaptive learning feature pyramid for object detection

Automatic drug pills detection based on enhanced feature pyramid network and convolution neural networks

Multi-person pose estimation using atrous convolution

Similar Documents

OCPAN: multi-person pose estimation with more attention on residual information

Multi-scale object detection by bottom-up feature pyramid network

Multi-scale feature fusion network for person re-identification

Edge gradient feature and long distance dependency for image semantic segmentation

Crowd counting using a self-attention multi-scale cascaded network

CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution

Multi-scale deep neural network for salient object detection

Adaptive learning feature pyramid for object detection

Automatic drug pills detection based on enhanced feature pyramid network and convolution neural networks

Multi-person pose estimation using atrous convolution