A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Approximation algorithms for directed Steiner problems
Journal of Algorithms
Saliency, Scale and Image Description
International Journal of Computer Vision
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
Computers and Intractability; A Guide to the Theory of NP-Completeness
Computers and Intractability; A Guide to the Theory of NP-Completeness
Robust Real-Time Face Detection
International Journal of Computer Vision
Efficient Graph-Based Image Segmentation
International Journal of Computer Vision
Image Parsing: Unifying Segmentation, Detection, and Recognition
International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
New primal-dual algorithms for Steiner tree problems
Computers and Operations Research
Sharing Visual Features for Multiclass and Multiview Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Streetscenes: towards scene understanding in still images
Streetscenes: towards scene understanding in still images
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Robust Object Detection with Interleaved Categorization and Segmentation
International Journal of Computer Vision
Selective visual attention enables learning and recognition of multiple objects in cluttered scenes
Computer Vision and Image Understanding - Special issue: Attention and performance in computer vision
Hi-index | 0.00 |
We propose an approach to speed-up object detection, with an emphasis on settings where multiple object classes are detected. Our method uses a segmentation algorithm to select a small number of image regions on which to run a classifier. Compared to the classical sliding window approach, a significantly smaller number of rectangles is examined, which yields significantly faster object detection. Further, in the multiple object class setting, we show that the computational cost of segmentations can be amortized across objects classes, resulting in an additional speedup. At the heart of our approach is reduction to a directed Steiner tree optimization problem, which we solve approximately in order to select the segmentation algorithm parameters. The solution gives a small set of segmentation strategies that can be shared across object classes. Compared to the sliding window approach, our method results in two orders of magnitude fewer regions considered, and significant (10-15x) computational time speedups on challenging object detection datasets (LabelMe and StreetScenes) while maintaining comparable detection accuracy.