Paper
- S. Hickson, I. Essa, and H. Christensen (2015), “Semantic Instance Labeling Leveraging Hierarchical Segmentation,” in Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV), 2015. [PDF] [DOI] [BIBTEX]
@InProceedings{ 2015-Hickson-SILLHS, author = {Steven Hickson and Irfan Essa and Henrik Christensen}, booktitle = {Proceedings of IEEE Winter Conference on Applications of Computer Vision (WACV)}, doi = {10.1109/WACV.2015.147}, month = {January}, pdf = {http://www.cc.gatech.edu/~irfan/p/2015-Hickson-SILLHS.pdf} , publisher = {IEEE Computer Society}, title = {Semantic Instance Labeling Leveraging Hierarchical Segmentation}, year = {2015} }
Abstract
Most of the approaches for indoor RGBD semantic labeling focus on using pixels or superpixels to train a classifier. In this paper, we implement a higher level segmentation using a hierarchy of superpixels to obtain a better segmentation for training our classifier. By focusing on meaningful segments that conform more directly to objects, regardless of size, we train a random forest of decision trees as a classifier using simple features such as the 3D size, LAB color histogram, width, height, and shape as specified by a histogram of surface normals. We test our method on the NYU V2 depth dataset, a challenging dataset of cluttered indoor environments. Our experiments using the NYU V2 depth dataset show that our method achieves state of the art results on both a general semantic labeling introduced by the dataset (floor, structure, furniture, and objects) and a more object specific semantic labeling. We show that training a classifier on a segmentation from a hierarchy of super pixels yields better results than training directly on super pixels, patches, or pixels as in previous work.