Data augmentation method for improving the accuracy of human pose estimation with cropped images

Cited 17 time in webofscience Cited 12 time in scopus
  • Hit : 349
  • Download : 0
Neural networks have improved the accuracy of human pose estimation from a single RGB image. However, such estimation remains difficult, especially when the human body is only partially visible due to a limited field of view of the camera or occlusions. In this paper, we introduce a data augmentation method called body-cropping augmentation (BCA), which generalizes the dataset for effective training in human pose estimation. This technique includes the policies of data generation and the training strategy using the augmented data. The experiments with the COCO val2017 dataset with ground- truth bounding boxes show BCA consistently enhances accuracies of state-of-the-art neural networks by an average of 1.08% without any modification to the network architecture. Moreover, the proposed BCA technique effectively reduces the false negatives of localizing keypoints, especially in an input image with a few visible keypoints.
Publisher
ELSEVIER
Issue Date
2020-08
Language
English
Article Type
Article
Citation

PATTERN RECOGNITION LETTERS, v.136, pp.244 - 250

ISSN
0167-8655
DOI
10.1016/j.patrec.2020.06.015
URI
http://hdl.handle.net/10203/281947
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 17 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0