Oriented Edge Forests for Boundary Detection
This work addresses boundary detection in computer vision, offering a more efficient and effective method for tasks like image segmentation, though it is incremental as it builds on existing random forest approaches.
The authors tackled boundary detection by developing a random forest-based model that uses orientation clustering and scale-dependent calibration, achieving improved performance on the BSDS500 benchmark and reducing training memory and time by a factor of 10 compared to structured forests.
We present a simple, efficient model for learning boundary detection based on a random forest classifier. Our approach combines (1) efficient clustering of training examples based on simple partitioning of the space of local edge orientations and (2) scale-dependent calibration of individual tree output probabilities prior to multiscale combination. The resulting model outperforms published results on the challenging BSDS500 boundary detection benchmark. Further, on large datasets our model requires substantially less memory for training and speeds up training time by a factor of 10 over the structured forest model.