Laser & Optoelectronics Progress, Volume. 57, Issue 24, 241003(2020)
Human-Body Action Recognition Based on Dense Trajectories and Video Saliency
Fig. 1. Saliency-based action recognition algorithm framework
Fig. 2. Dense trajectory algorithm framework
Fig. 3. Sample frames from UCF Sports and YouTube. (a) UCF Sports; (b) YouTube
Fig. 4. Estimation of saliency detection parameters
Fig. 5. Comparison of the DT and our method. (a) UCF Sports; (b) YouTube
Fig. 6. Accuracy comparison of each class by DT and our method. (a) UCF Sports; (b) YouTube
|
|
|
Get Citation
Copy Citation Text
Deyong Gao, Zibing Kang, Song Wang, Yangping Wang. Human-Body Action Recognition Based on Dense Trajectories and Video Saliency[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241003
Category: Image Processing
Received: Mar. 30, 2020
Accepted: May. 29, 2020
Published Online: Dec. 2, 2020
The Author Email: Kang Zibing (914764692@qq.com)