Implicit Hierarchical Boosting for Multi-view Object Detection

Abstract :

Multi-view object detection is a fundamental problem in computer vision. Current approaches generally require an explicit partition between different views with or without sharing descriptors. We present a novel boosting based learning approach which automatically learns a multi-view detector without using intra-class sub-categorization based on prior knowledge. To avoid multiplying the false alarm rate by the number of classifiers, which happens on the classical approach where one classifier per view is considered, we build a single cascade of weak classifiers which contains an implicit hierarchical structure. In details, a partition of positive samples is automatically computed in order to build an adequate weak classifier based on one specific descriptor per subset. By adapting iteratively the number of descriptors at each stage, the so-defined hierarchical structure enables both a precise modelling and an efficient sharing of descriptors between views. Experimental results demonstrate the relevance and efficiency of this new approach.

Document type :
Conference papers
Complete list of metadatas

https://hal.telecom-paristech.fr/hal-02286717
Contributor : Telecomparis Hal <>
Submitted on : Friday, September 13, 2019 - 4:05:29 PM
Last modification on : Saturday, September 14, 2019 - 1:38:46 AM

Identifiers

Collections

Citation

X. Perrotton, M. Sturzel, Michel Roux. Implicit Hierarchical Boosting for Multi-view Object Detection. The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, Jun 2010, San Francisco, CA, United States. pp.958-965, ⟨10.1109/CVPR.2010.5540115⟩. ⟨hal-02286717⟩

Share

Metrics

Record views

2