DMCA
Multiresolution models for object detection
Cached
Download Links
| Citations: | 55 - 6 self |
BibTeX
@MISC{Park_multiresolutionmodels,
author = {Dennis Park and Deva Ramanan and Charless Fowlkes},
title = {Multiresolution models for object detection},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Most current approaches to recognition aim to be scaleinvariant. However, the cues available for recognizing a 300 pixel tall object are qualitatively different from those for recognizing a 3 pixel tall object. We argue that for sensors with finite resolution, one should instead use scale-variant, or multiresolution representations that adapt in complexity to the size of a putative detection window. We describe a multiresolution model that acts as a deformable part-based model when scoring large instances and a rigid template with scoring small instances. We also examine the interplay of resolution and context, and demonstrate that context is most helpful for detecting low-resolution instances when local models are limited in discriminative power. We demonstrate impressive results on the Caltech Pedestrian benchmark, which contains object instances at a wide range of scales. Whereas recent state-of-theart methods demonstrate missed detection rates of 86%-37 % at 1 falsepositive-per-image, our multiresolution model reduces the rate to 29%. 1
Keyphrases
multiresolution model object detection pixel tall object large instance putative detection window multiresolution representation discriminative power object instance rigid template deformable part-based model caltech pedestrian benchmark low-resolution instance current approach finite resolution small instance local model whereas recent state-of-theart method demonstrate impressive result wide range detection rate
