研究方向
基于视觉的场景理解与自动交互,具体研究内容包括场景语义理解、语义SLAM、交互语义分析等。基于场景理解获取的几何、语义、affordance构建机器人对工作环境的认知模型,提高机器人对新工作环境的适应性及其在环境中提供服务的自主性。
基于中国手语表达的人机交互,具体研究内容包括基于虚拟人模型的3D中国手语合成(相关成果被2008年北京奥运会信息无障碍服务计划采纳)、基于视频的2D中国手语合成、中国手语光场获取、基于光场数据的中国手语识别等。
代表性论文
1.Wang Lichun, Li Shuang, Wang Shaofan, Kong Dehui, Yin Baocai, Hardness-Aware Dictionary Learning: Boosting Dictionary for Recognition, IEEE Transactions on Multimedia, DOI 10.1109/TMM.2020.3017916.
2. Wang Yuping,Wang Lichun, Kong Dehui, Yin Baocai, High-resolution Light Field Capture with Coded Aperture. IEEE Transactions on Image Processing, 24(12): 5609-5618, 2015.
3.Wang Lichun, Wang Ru, Kong Dehui, Yin Baocai, Similarity Assessment Model for Chinese Sign Language Videos. IEEE Transactions on Multimedia, 16(3): 751-761, 2014.
4. Shuo Li,Lichun Wang, Dehui Kong, Synthesis of sign language co-articulation based on key frames. Multimedia Tools and Applications, 74(6):1915-1933, 2015.
5. Ru WANG,Lichun WANG, Dehui KONG, Baocai Yin, Making Smooth Transitions Based on Multi-dimensional Transition database for Chinese Sign Videos Joining,Multimedia Tools and Applications, 60(3):483-493, 2012.