Open AccessHuman Action Recognition Algorithm Based on Improved ResNet and Skeletal Keypoints in Single Image
Author(s) -
Yixue Lin,
Wanda Chi,
Wenxue Sun,
Shicai Liu,
Di Fan
Publication year - 2020
Publication title -
mathematical problems in engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.262
H-Index - 62
eISSN - 1026-7077
pISSN - 1024-123X
DOI - 10.1155/2020/6954174
Subject(s) - computer science , action (physics) , artificial intelligence , image (mathematics) , residual neural network , task (project management) , pattern recognition (psychology) , action recognition , context (archaeology) , computer vision , deep learning , engineering , paleontology , physics , systems engineering , quantum mechanics , biology , class (philosophy)
Human action recognition is an important part for computers to understand the behavior of people in pictures or videos. In a single image, there is no context information for recognition, so its accuracy still needs to be greatly improved. In this paper, a single-image human action recognition method based on improved ResNet and skeletal keypoints is proposed, and the accuracy is improved by several methods. We improved the backbone network ResNet-50 and CPN to a certain extent and constructed a multitask network to suit the human action recognition task, which not only improves the accuracy but also balances the total number of parameters and solves the problem of large network and slow operation. In this paper, the improvement methods of ResNet-50, CPN, and whole network are tested, respectively. The results show that the single-image human action recognition based on improved ResNet and skeletal keypoints can accurately identify human action in the case of different human movements, different background light, and occlusion. Compared with the original network and the main human action recognition algorithms, the accuracy of our method has its certain advantages.