Přístupnostní navigace
E-application
Search Search Close
Publication detail
HEROUT, A. HRADIŠ, M. ZEMČÍK, P.
Original Title
EnMS: Early non-Maxima Suppression
Type
journal article - other
Language
English
Original Abstract
Detection of objects in images using statistical classifiers is a well studied and documented technique. Different applications of such detectors often require selection of the image position with the highest response of the detector -- they perform non-maxima suppression. This article introduces the concept of Early non-Maxima Suppression, which aims to reduce necessary computations by making the non-Maxima Suppression decision early based on incomplete information provided by a partially evaluated classifier. We show that the error of one such speculative decision with respect to a decision made based on response of the complete classifier can be estimated by collecting statistics on unlabeled data. The article then considers a sequential strategy of multiple early non-Maxima suppression tests which follows the structure of soft-cascade detectors commonly used for object detection. We also show that an optimal (fastest for requested error rate) suppression strategy can be created by a novel variant of Wald's sequential probability ratio test (SPRT) which we call the Conditioned SPRT, CSPRT. Experimental results show that the Early non-Maxima Suppression significantly reduces amount of computation in the case of object localization while the error rates are limited to low predefined values. The proposed approach notably outperforms the state-of-the-art detectors based on WaldBoost. The potential applications of the early non-Maxima suppression approach are not limited to object localization and could be applied wherever the goal is to find the strongest response of a classifier among a set of classified samples.
Keywords
Non-Maxima Suppression, Object Detection, WaldBoost, Sequential Probability Ratio Test
Authors
HEROUT, A.; HRADIŠ, M.; ZEMČÍK, P.
RIV year
2012
Released
1. 5. 2012
ISBN
1433-7541
Periodical
PATTERN ANALYSIS AND APPLICATIONS
Year of study
Number
2
State
United Kingdom of Great Britain and Northern Ireland
Pages from
121
Pages to
132
Pages count
12
BibTex
@article{BUT76262, author="Adam {Herout} and Michal {Hradiš} and Pavel {Zemčík}", title="EnMS: Early non-Maxima Suppression", journal="PATTERN ANALYSIS AND APPLICATIONS", year="2012", volume="2012", number="2", pages="121--132", issn="1433-7541" }