Structured Forests for Fast Edge Detection

• Published in: 2013 IEEE International Conference on Computer Vision pp. 1841 - 1848
• Main Authors: Dollar, Piotr, Zitnick, C. Lawrence
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.12.2013
• Subjects: Algorithms; Computer vision; Decision trees; Detectors; Edge detection; Image color analysis; Image edge detection; Image segmentation; Learning; realtime vision; Segmentation; State of the art; structure learning; Training; Vegetation
• ISSN: 1550-5499
• DOI: 10.1109/ICCV.2013.231

Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computationally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests. Our novel approach to learning decision trees robustly maps the structured labels to a discrete space on which standard information gain measures may be evaluated. The result is an approach that obtains real time performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge detection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets.