Translator Disclaimer
27 November 2019 Action recognition based on virtual simulation for prosthetic vision
Author Affiliations +
Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113211I (2019)
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China
For now, even the state-of-the-art of retinal prostheses is limited by low resolution and image processing algorithms. In order to find suitable parameters for prosthetic vision and help visual prosthesis wearers get on well with low-resolution gray-scale image correctly and effectively, the action recognition experiments based on virtual simulation were performed in this paper. Animated videos of skeletonized walking upright were structured in 3ds Max, then the action animation video clips were pixelized by MATLAB. The actions were classified into three categories: combined actions, simple actions and difficult actions. All action clips have 6 resolutions (6×16, 24×24, 32×32, 48×48, 64×64, 128×128). Twenty observers (classified by gender and experience) were recruited to participate in the test. They were asked to recognize actions at different resolutions. The results showed that there was no significant regular pattern of gender difference on the recognition accuracy. As for experience difference, the recognition accuracy of experienced observers was higher than the unexperienced ones. The conclusion was drawing that learning experience can improve recognition accuracy, experienced observers recognized an action requires lower resolution, 48×48 was a suitable resolution which has considerable latent capacity.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dantong Xu, Ying Zhao, Aiping Yu, and Donghui Wang "Action recognition based on virtual simulation for prosthetic vision", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211I (27 November 2019);

Back to Top