Paper
23 May 2023 A SlowFast behavior recognition algorithm incorporating motion saliency
Xin Zhang, Yan Zhu, Li Deng, Long Qi, Tao Zhang, Jiali Hu
Author Affiliations +
Proceedings Volume 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022); 126042Y (2023) https://doi.org/10.1117/12.2674969
Event: 2nd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 2022, Guangzhou, China
Abstract
This paper first analyzes three major problems that can be encountered in video behavior recognition tasks: sampled blocks cannot be focused on motion regions, global motion affects recognition results, and the network's spatio-temporal modeling capability is weak. To address these three problems, we propose the SlowFast behavior recognition algorithm (MASlowFast) that incorporates motion saliency as an application scenario for mine personnel safety behavior recognition. The specific solutions are the sampling method based on motion saliency, the extraction of motion boundary features, and the spatio-temporal segmentation strategy of fast and slow channels. Finally, we validated the effectiveness and accuracy of the algorithm in this paper by ablation experiments on UCF101 dataset and HMDB51 dataset.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xin Zhang, Yan Zhu, Li Deng, Long Qi, Tao Zhang, and Jiali Hu "A SlowFast behavior recognition algorithm incorporating motion saliency", Proc. SPIE 12604, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022), 126042Y (23 May 2023); https://doi.org/10.1117/12.2674969
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Detection and tracking algorithms

Video

Education and training

Mining

Motion models

Data modeling

Modeling

Back to Top