Object-based RGBD Image Co-segmentation with Mutex Constraint

Object-based RGBD Image Co-segmentation with Mutex Constraint
Title:
Object-based RGBD Image Co-segmentation with Mutex Constraint
Other Titles:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI:
10.1109/CVPR.2015.7299072
Keywords:
Publication Date:
01 June 2015
Citation:
Huazhu Fu; Dong Xu; Lin, S.; Jiang Liu, "Object-based RGBD image co-segmentation with mutex constraint," in Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on , vol., no., pp.4428-4436, 7-12 June 2015
Abstract:
We present an object-based co-segmentation method that takes advantage of depth data and is able to correctly handle noisy images in which the common foreground object is missing. With RGBD images, our method utilizes the depth channel to enhance identification of similar foreground objects via a proposed RGBD co-saliency map, as well as to improve detection of object-like regions and provide depth-based local features for region comparison. To accurately deal with noisy images where the common object appears more than or less than once, we formulate co-segmentation in a fully-connected graph structure together with mutual exclusion (mutex) constraints that prevent improper solutions. Experiments show that this object-based RGBD co-segmentation with mutex constraints outperforms related techniques on an RGBD co-segmentation dataset, while effectively processing noisy images. Moreover, we show that this method also provides performance comparable to state-of-the-art RGB co-segmentation techniques on regular RGB images with depth maps estimated from them.
License type:
PublisherCopyrights
Funding Info:
Description:
ISBN:

Files uploaded: