2.1 depth estimation of frames in image sequences using motion occlusions

Authors:
Guillem Palou;Philippe Salembier
Affiliations:
Dept. of Signal Theory and Communications, Technical University of Catalonia (UPC), Barcelona, Spain;Dept. of Signal Theory and Communications, Technical University of Catalonia (UPC), Barcelona, Spain
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 10
Cited 0

Transformation of Optical Flow by Camera Rotation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to algorithms

Introduction to algorithms
Symmetrical Dense Optical Flow Estimation with Occlusions Detection

International Journal of Computer Vision
Occlusion boundaries: low-level detection to high-level reasoning

Occlusion boundaries: low-level detection to high-level reasoning
Consistent Depth Maps Recovery from a Video Sequence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Region merging techniques using information theory statistical measures

IEEE Transactions on Image Processing
Occlusion boundary detection using pseudo-depth

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Occlusion boundary detection and figure/ground assignment from optical flow

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval

IEEE Transactions on Image Processing
Binary Partition Trees for Object Detection

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a system to depth order regions of a frame belonging to a monocular image sequence. For a given frame, regions are ordered according to their relative depth using the previous and following frames. The algorithm estimates occluded and disoccluded pixels belonging to the central frame. Afterwards, a Binary Partition Tree (BPT) is constructed to obtain a hierarchical, region based representation of the image. The final depth partition is obtained by means of energy minimization on the BPT. To achieve a global depth ordering from local occlusion cues, a depth order graph is constructed and used to eliminate contradictory local cues. Results of the system are evaluated and compared with state of the art figure/ground labeling systems on several datasets, showing promising results.