Combining adaBoost with a Hill-Climbing evolutionary feature search for efficient training of performant visual object detector

Abstract : This paper presents an efficient method for automatic training of performant visual object detectors, and its successful application to training of a back-view car detec- tor. Our method for training detectors is adaBoost applied to a very general family of visual features (called “control-point” features), with a specific feature-selection weak-learner: evo-HC, which is a hybrid of Hill-Climbing and evolutionary-search. Very good results are obtained for the car-detection application: 95% positive car detection rate with less than one false positive per image frame, computed on an independant validation video. It is also shown that our original hybrid evo-HC weak-learner allows to obtain detection performances that are unreachable in rea- sonable training time with a crude random search. Finally our method seems to be potentially efficient for training detectors of very different kinds of objects, as it was already previously shown to provide state-of-art performance for pedestrian-detection tasks.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00435700
Contributor : Fabien Moutarde <>
Submitted on : Tuesday, November 24, 2009 - 4:14:14 PM
Last modification on : Monday, November 12, 2018 - 10:55:32 AM
Long-term archiving on : Thursday, June 17, 2010 - 6:56:55 PM

File

evoHC-Boost_FLINS06.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00435700, version 1

Citation

Yotam Abramson, Fabien Moutarde, Bogdan Stanciulescu, Bruno Steux. Combining adaBoost with a Hill-Climbing evolutionary feature search for efficient training of performant visual object detector. FLINS2006 on Applied Artificial Intelligence, Aug 2006, Genova, Italy. ⟨hal-00435700⟩

Share

Metrics

Record views

208

Files downloads

158