Year: 2012
Type: report
Abstract: In this work we use bounding-based techniques, such as Branch-and-Bound (BB) and Cascaded Detection (CD) to efficiently detect objects with Deformable Part Models (DPMs). Instead of evaluating the classifier score exhaustively over all image locations and scales, we use bounding to focus on promising image locations. The core problem is to compute bounds that accommodate part deformations; for this we adapt the Dual Trees data structure to our problem. We evaluate our approach using DPMs. We obtain exactly the same results but can perform the part combination substantially faster; for a conservative threshold the speedup can be double, for a less conservative we can have tenfold or higher speedups. These speedups refer to the part combination process, after the unary part scores have been computed. We also develop a multiple-object detection variation of the system, where hypotheses for 20 categories are inserted in a common priority queue. For the problem of finding the strongest category in an image this can result in more than 100-fold speedups.
Source: HAL
Author: Kokkinos, Iasonas
Institution: École Centrale Paris
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
Awards: G7240651115, G8979309407
OpenAlex ID: W2601116187