Journal of shanghai Jiaotong University (Science) ›› 2016, Vol. 21 ›› Issue (2): 184-191.doi: 10.1007/s12204-016-1710-7

Previous Articles     Next Articles

Consistent Depth Maps Estimation from Binocular Stereo Video Sequence

Consistent Depth Maps Estimation from Binocular Stereo Video Sequence

DUAN Fengfeng (段峰峰)   

  1. (Cultural Resources Research and Development Center of Hunan, Hunan Normal University, Changsha 410081, China; School of Computer Science, Communication University of China, Beijing 100024, China)
  2. (Cultural Resources Research and Development Center of Hunan, Hunan Normal University, Changsha 410081, China; School of Computer Science, Communication University of China, Beijing 100024, China)
  • Online:2016-04-15 Published:2016-04-26
  • Contact: DUAN Fengfeng (段峰峰) E-mail: dffeng2010@126.com

Abstract: In the paper, an approach is proposed for the problem of consistency in depth maps estimation from binocular stereo video sequence. The consistent method includes temporal consistency and spatial consistency to eliminate the flickering artifacts and smooth inaccuracy in depth recovery. So the improved global stereo matching based on graph cut and energy optimization is implemented. In temporal domain, the penalty function with coherence factor is introduced for temporal consistency, and the factor is determined by Lucas-Kanade optical flow weighted histogram similarity constraint (LKWHSC). In spatial domain, the joint bilateral truncated absolute difference (JBTAD) is proposed for segmentation smoothing. The method can smooth naturally and uniformly in low-gradient region and avoid over-smoothing as well as keep edge sharpness in high-gradient discontinuities to realize spatial consistency. The experimental results show that the algorithm can obtain better spatial and temporal consistent depth maps compared with the existing algorithms.

Key words: consistent depth maps| binocular stereo video sequence| Lucas-Kanade optical flow weighted histogram similarity constraint (LKWHSC)| joint bilateral truncated absolute difference (JBTAD)

摘要: In the paper, an approach is proposed for the problem of consistency in depth maps estimation from binocular stereo video sequence. The consistent method includes temporal consistency and spatial consistency to eliminate the flickering artifacts and smooth inaccuracy in depth recovery. So the improved global stereo matching based on graph cut and energy optimization is implemented. In temporal domain, the penalty function with coherence factor is introduced for temporal consistency, and the factor is determined by Lucas-Kanade optical flow weighted histogram similarity constraint (LKWHSC). In spatial domain, the joint bilateral truncated absolute difference (JBTAD) is proposed for segmentation smoothing. The method can smooth naturally and uniformly in low-gradient region and avoid over-smoothing as well as keep edge sharpness in high-gradient discontinuities to realize spatial consistency. The experimental results show that the algorithm can obtain better spatial and temporal consistent depth maps compared with the existing algorithms.

关键词: consistent depth maps| binocular stereo video sequence| Lucas-Kanade optical flow weighted histogram similarity constraint (LKWHSC)| joint bilateral truncated absolute difference (JBTAD)

CLC Number: