Efficient Use of Geometric Constraints for Sliding-Window Object Detection in Video
Lists
Only you see this
Abstract
We systematically investigate how geometric constraints can be used for efficient sliding-window object detection. Starting with a general characterization of the space of sliding-window locations that correspond to geometrically valid object detections, we derive a general algorithm for incorporating ground plane constraints directly into the detector computation. Our approach is indifferent to the choice of detection algorithm and can be applied in a wide range of scenarios. In particular, it allows to effortlessly combine multiple different detectors and to automatically compute regions-of-interest for each of them. We demonstrate its potential in a fast CUDA implementation of the HOG detector and show that our algorithm enables a factor 2-4 speed improvement on top of all other optimizations.
BibTeX
@inproceedings{sudowe2011efficient,
author = {Patrick Sudowe and Bastian Leibe},
title = {{Efficient Use of Geometric Constraints for Sliding-Window Object Detection in Video}},
booktitle = {ICVS},
year = {2011},
doi = {10.1007/978-3-642-23968-7\_2},
}Loading related content...