All types of publications

Herout, A., Hradiš, M., Zemčík, P.: EnMS: Early non-Maxima Suppression, In: Pattern Analysis and Applications, Vol. 2012, No. 2, DE, p. 121-132, ISSN 1433-7541
Publication language:english
Original title:EnMS: Early non-Maxima Suppression
Title (cs):Časné potlačení nemaximálních odezev
Pages:121-132
Place:DE
Year:2012
Journal:Pattern Analysis and Applications, Vol. 2012, No. 2, DE
ISSN:1433-7541
Keywords
Non-Maxima Suppression, Object Detection, WaldBoost, Sequential Probability Ratio Test
Annotation
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.
BibTeX:
@ARTICLE{
   author = {Adam Herout and Michal Hradiš and Pavel Zemčík},
   title = {EnMS: Early non-Maxima Suppression},
   pages = {121--132},
   journal = {Pattern Analysis and Applications},
   volume = {2012},
   number = {2},
   year = {2012},
   ISSN = {1433-7541},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=9506}
}

Your IPv4 address: 23.22.252.150
Switch to IPv6 connection

DNSSEC [dnssec]