Exploiting visual context and consistency for semantic segmentation

• 主要作者: Kang, Dang
• 其他作者: Ma Kai Kuang
• 格式: Theses and Dissertations
• 語言: English
• 出版: 2018
• 主題: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• 在線閱讀: https://hdl.handle.net/10356/80532; http://hdl.handle.net/10220/46581

This thesis studies the problem of semantic segmentation in both images and videos. It targets at addressing two challenges of semantic segmentation: robustness and consistency. First, assigning pixels to the corresponding semantic categories may be unreliable especially under adverse imaging condit...