Accelerating Arrays of Linear Classifiers Using Approximate Range Queries

Proc. Winter Conference on Applications of Computer Vision (WACV), Mar. 2014, pp. 255-260.

Modern object detection methods apply binary linear classifiers on Euclidean feature vectors. This paper shows that projecting feature vectors onto a hypersphere allows an approximate range query to accelerate these detectors within acceptable levels of accuracy. The expense of constructing the k-d tree used by these range queries is justified when many detectors are used. We demonstrate our acceleration technique on several existing detection systems, including a state of the art logo detector, and show that approximate range queries can detect logos at least half as well at 11× the speed of the full fidelity method.

Theme by Danetsoft and Danang Probo Sayekti inspired by Maksimer