Class-specific Hough forests for object detection
- 1 June 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1022-1029
- https://doi.org/10.1109/cvpr.2009.5206740
Abstract
We present a method for the detection of instances of an object class, such as cars or pedestrians, in natural images. Similarly to some previous works, this is accomplished via generalized Hough transform, where the detections of individual object parts cast probabilistic votes for possible locations of the centroid of the whole object; the detection hypotheses then correspond to the maxima of the Hough image that accumulates the votes from all parts. However, whereas the previous methods detect object parts using generative codebooks of part appearances, we take a more discriminative approach to object part detection. Towards this end, we train a class-specific Hough forest, which is a random forest that directly maps the image patch appearance to the probabilistic vote about the possible location of the object centroid. We demonstrate that Hough forests improve the results of the Hough-transform object detection significantly and achieve state-of-the-art performance for several classes and datasets.Keywords
This publication has 23 references indexed in Scilit:
- Learning an Alphabet of Shape and Appearance for Multi-Class Object DetectionInternational Journal of Computer Vision, 2008
- Object Class Segmentation using Random ForestsPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Efficiently Combining Contour and Texture Cues for Object RecognitionPublished by British Machine Vision Association and Society for Pattern Recognition ,2008
- Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian DetectionLecture Notes in Computer Science, 2008
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- Sampling Strategies for Bag-of-Features Image ClassificationLecture Notes in Computer Science, 2006
- Learning to detect objects in images via a sparse, part-based representationIeee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Interleaved Object Categorization and SegmentationPublished by British Machine Vision Association and Society for Pattern Recognition ,2003
- Shape Quantization and Recognition with Randomized TreesNeural Computation, 1997
- Induction of decision treesMachine Learning, 1986