On-line video object segmentation using illumination-invariant color-texture feature extraction and marker prediction |
| |
| Affiliation: | 1. School of Information Engineering, Guangdong University of Technology, PR China;2. Fujian Provincial Key Laboratory of Data Mining and Applications, Fujian University of Technology, Fujian, PR China;1. College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China;2. Department of Information Management, Chaoyang University of Technology, Taichung, Taiwan;1. School of Telecommunication and Information Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, PR China;2. Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, PR China;1. National Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China;2. School of Computer Science and Technology, Xidian University, Xi’an 710071, China |
| |
| Abstract: | A novel on-line video object segmentation scheme based on illumination-invariant color-texture feature extraction and marker prediction is proposed in this paper. First, the location of the object of interest is initialized based on user-specified markers. Superpixels are generated in the next available frame of the input video to extract the illumination-invariant color-texture features of the object of interest. The proposed object marker prediction scheme consists of estimating the user-specified markers and locating the object of interest in the next available frame via superpixel motion prediction using illumination-invariant optical flow, marker superpixel candidate generation using short-term superpixel affinity, and maximum likelihood computation using long-term superpixel affinity. The experimental results obtained when the proposed method is applied to several challenging video clips demonstrate that the proposed approach is competitive with several other state-of-the-art methods, especially when the illumination and object motion change dramatically. |
| |
| Keywords: | Video object segmentation Illumination invariance Region merging Marker prediction Superpixel |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
