Oriented Edge Forests for Boundary Detection
icon We present a simple, efficient model for learning bound- ary detection based on a random forest classifier. Our ap- proach combines (1) efficient clustering of training exam- ples based on a simple partitioning of the space of local edge orientations and (2) scale-dependent calibration of in- dividual tree output probabilities prior to multiscale combi- nation. The resulting model outperforms published results on the challenging BSDS500 boundary detection bench- mark. Further, on large datasets our model requires sub- stantially less memory for training and speeds up training time by a factor of 10 over the structured forest model.

Download: pdf

Text Reference

Sam Hallman and Charless C. Fowlkes. Oriented edge forests for boundary detection. In CVPR. 2015.

BibTeX Reference

@inproceedings{HallmanF_CVPR_2015,
    AUTHOR = "Hallman, Sam and Fowlkes, Charless C.",
    TITLE = "Oriented Edge Forests for Boundary Detection",
    BOOKTITLE = "CVPR",
    YEAR = "2015",
    tag = "grouping"
}