Name
Abstract | ||
|---|---|---|
The goal of this paper is to develop a robust depth estimation method from a single-view video sequence. We utilize an estimated initial depth to establish a reference depth for further obtaining the reliable depth information, and then it is refined with a temporal-spatial filter. At first, we use adaptive support-weight block matching to extract disparity information from consecutive video frames. The disparity is compensated with the camera motion and then transformed to the initially estimated depth. Based on the initial depth, two kinds of depth maps, the propagation depth and the optical flow depth can be established. Finally, these three depth maps are fused together by using voting merger, and then applied with the superpixel segmentation and a temporal-spatial smoothing filter to improve the noisy depth estimation in the textureless region. The experiments show that the proposed method could achieve visually pleasing and temporally consistent depth estimation results without additional pre-processing and time-consuming iterations as required in other works. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ISCE.2013.6570130 | Consumer Electronics |
Keywords | Field | DocType |
image matching,image segmentation,image sensors,image sequences,spatial filters,video signal processing,camera motion,depth maps,initial depth,noisy depth estimation,optical flow depth,propagation depth,reference depth,reliable depth information,robust depth estimation method,single view video sequence,superpixel segmentation,support weight block matching,temporal spatial filter,temporal spatial smoothing filter,textureless region,video frames,2d-to-3d,dibr,single-view video,adaptive support-weight,depth estimation,depth propagation,optical flow,estimation,optical imaging,computer vision,2d to 3d,optical filters | Computer vision,Pattern recognition,Image sensor,Range segmentation,Computer science,Image matching,Smoothing filter,Image segmentation,Artificial intelligence,Depth map,Optical flow,Superpixel segmentation | Conference |
ISSN | ISBN | Citations |
0747-668X | 978-1-4673-6198-9 | 1 |
PageRank | References | Authors |
0.37 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tien-Ying Kuo | 1 | 148 | 19.24 |
| Cheng-Hong Hsieh | 2 | 1 | 0.71 |
| Yi-Chung Lo | 3 | 32 | 5.06 |