Object detection via boosted deformable features. Hussein, M., Porikli, F., & Davis, L. In 2009 16th IEEE International Conference on Image Processing (ICIP), pages 1445–1448, 2009. doi abstract bibtex It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable features adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.
@inproceedings{hussein_object_2009,
title = {Object detection via boosted deformable features},
rights = {All rights reserved},
doi = {10.1109/ICIP.2009.5414561},
abstract = {It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable features adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.},
eventtitle = {2009 16th {IEEE} International Conference on Image Processing ({ICIP})},
pages = {1445--1448},
booktitle = {2009 16th {IEEE} International Conference on Image Processing ({ICIP})},
author = {Hussein, M. and Porikli, F. and Davis, L.},
date = {2009-11},
year = {2009},
keywords = {Biological system modeling, boosted ensembles, Boosting, Computer science, Computer vision, Context modeling, deformable features, Deformable Features, Deformable models, Educational institutions, feature extraction, Head, human detection, Human Detection, Humans, object detection, Object detection, statistics, visual evidence},
file = {IEEE Xplore Abstract Record:C\:\\Users\\Mohamed Hussein\\Zotero\\storage\\I28BE5Y4\\5414561.html:text/html}
}
Downloads: 0
{"_id":"4Tef7vzNAFRydyNdd","bibbaseid":"hussein-porikli-davis-objectdetectionviaboosteddeformablefeatures-2009","author_short":["Hussein, M.","Porikli, F.","Davis, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Object detection via boosted deformable features","rights":"All rights reserved","doi":"10.1109/ICIP.2009.5414561","abstract":"It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable features adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.","eventtitle":"2009 16th IEEE International Conference on Image Processing (ICIP)","pages":"1445–1448","booktitle":"2009 16th IEEE International Conference on Image Processing (ICIP)","author":[{"propositions":[],"lastnames":["Hussein"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Porikli"],"firstnames":["F."],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["L."],"suffixes":[]}],"date":"2009-11","year":"2009","keywords":"Biological system modeling, boosted ensembles, Boosting, Computer science, Computer vision, Context modeling, deformable features, Deformable Features, Deformable models, Educational institutions, feature extraction, Head, human detection, Human Detection, Humans, object detection, Object detection, statistics, visual evidence","file":"IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Mohamed Hussein\\\\Zotero\\\\storage\\\\I28BE5Y4\\\\5414561.html:text/html","bibtex":"@inproceedings{hussein_object_2009,\n\ttitle = {Object detection via boosted deformable features},\n\trights = {All rights reserved},\n\tdoi = {10.1109/ICIP.2009.5414561},\n\tabstract = {It is a common practice to model an object for detection tasks as a boosted ensemble of many models built on features of the object. In this context, features are defined as subregions with fixed relative locations and extents with respect to the object's image window. We introduce using deformable features with boosted ensembles. A deformable features adapts its location depending on the visual evidence in order to match the corresponding physical feature. Therefore, deformable features can better handle deformable objects. We empirically show that boosted ensembles of deformable features perform significantly better than boosted ensembles of fixed features for human detection.},\n\teventtitle = {2009 16th {IEEE} International Conference on Image Processing ({ICIP})},\n\tpages = {1445--1448},\n\tbooktitle = {2009 16th {IEEE} International Conference on Image Processing ({ICIP})},\n\tauthor = {Hussein, M. and Porikli, F. and Davis, L.},\n\tdate = {2009-11},\n\tyear = {2009},\n\tkeywords = {Biological system modeling, boosted ensembles, Boosting, Computer science, Computer vision, Context modeling, deformable features, Deformable Features, Deformable models, Educational institutions, feature extraction, Head, human detection, Human Detection, Humans, object detection, Object detection, statistics, visual evidence},\n\tfile = {IEEE Xplore Abstract Record:C\\:\\\\Users\\\\Mohamed Hussein\\\\Zotero\\\\storage\\\\I28BE5Y4\\\\5414561.html:text/html}\n}\n\n","author_short":["Hussein, M.","Porikli, F.","Davis, L."],"bibbaseid":"hussein-porikli-davis-objectdetectionviaboosteddeformablefeatures-2009","role":"author","urls":{},"keyword":["Biological system modeling","boosted ensembles","Boosting","Computer science","Computer vision","Context modeling","deformable features","Deformable Features","Deformable models","Educational institutions","feature extraction","Head","human detection","Human Detection","Humans","object detection","Object detection","statistics","visual evidence"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/2bJzYjCLapWTtM86s/mehussein-2023.bib","dataSources":["kYvtZ54PgkXqjbteW","mhdykGczo2jDicE3X","havAjNnaG4BxhYWyb"],"keywords":["biological system modeling","boosted ensembles","boosting","computer science","computer vision","context modeling","deformable features","deformable features","deformable models","educational institutions","feature extraction","head","human detection","human detection","humans","object detection","object detection","statistics","visual evidence"],"search_terms":["object","detection","via","boosted","deformable","features","hussein","porikli","davis"],"title":"Object detection via boosted deformable features","year":2009}