Consistent Binocular Depth and Scene Flow with Chained Temporal Profiles
Publication in refereed journal


引用次數
替代計量分析
.

其它資訊
摘要We propose a depth and image scene flow estimation method taking the input of a binocular video. The key component is motion-depth temporal consistency preservation, making computation in long sequences reliable. We tackle a number of fundamental technical issues, including connection establishment between motion and depth, structure consistency preservation in multiple frames, and long-range temporal constraint employment for error correction. We address all of them in a unified depth and scene flow estimation framework. Our main contributions include development of motion trajectories, which robustly link frame correspondences in a voting manner, rejection of depth/motion outliers through temporal robust regression, novel edge occurrence map estimation, and introduction of anisotropic smoothing priors for proper regularization.
著者Hung CH, Xu L, Jia JY
期刊名稱International Journal of Computer Vision
出版年份2013
月份3
日期1
卷號102
期次1-3
出版社SPRINGER
頁次271 - 292
國際標準期刊號0920-5691
電子國際標準期刊號1573-1405
語言英式英語
關鍵詞Chained temporal profiles; Consistent scene flow; Stereo matching; Video depth estimation
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence; COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

上次更新時間 2020-17-11 於 01:58