Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Abstract
This paper proposes an approach to simultaneously detect and segment objects of a known category. Edgelet features are used to capture the local shape of the objects. For each feature a pair of base classifiers for detection and segmentation is built. The base segmentor is designed to predict the per-pixel figure-ground assignment around a neighborhood of the edgelet based on the feature response. The neighborhood is represented as an effective field which is determined by the shape of the edgelet. A boosting algorithm is used to learn the ensemble classifier with cascade decision strategy from the base classifier pool. The simultaneousness is achieved for both training and testing. The system is evaluated on a number of public image sets and compared with several previous methods.Keywords
This publication has 15 references indexed in Scilit:
- Rapid object detection using a boosted cascade of simple features2005
- Robust Object Detection via Soft Cascade2005
- Pedestrian Detection in Crowded Scenes2005
- Contour-based learning for object detection2005
- LOCUS: learning object classes with unsupervised segmentation2005
- Integrating representative and discriminant models for object category detection2005
- Learning to detect objects in images via a sparse, part-based representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Fusion of global and local information for object detection2003
- Improved Boosting Algorithms Using Confidence-rated PredictionsMachine Learning, 1999
- Real-time object detection for "smart" vehicles1999