Binary Partition Trees for Object Detection
Verónica Vilaplana, Ferran Marqués, Philippe Salembier · IEEE Transactions on Image Processing · 2008
This paper discusses the use of Binary Partition Trees (BPTs) for object detection. BPTs are hierarchical region-based representations of images. They define a reduced set of regions that covers the image support and that spans various levels of resolution. They are attractive for object detection as they tremendously reduce the search space. In this paper, several issues related to the use of BPT for object detection are studied. Concerning the tree construction, we analyze the compromise between computational complexity reduction and accuracy. This will lead us to define two parts in the BPT: one providing accuracy and one representing the search space for the object detection task. Then we analyze and objectively compare various similarity measures for the tree construction. We conclude that different similarity criteria should be used for the part providing accuracy in the BPT and for the part defining the search space and specific criteria are proposed for each case. Then we discuss the object detection strategy based on BPT. The notion of node extension is proposed and discussed. Finally, several object detection examples illustrating the generality of the approach and its efficiency are reported.
Cited by 100 works. doi:10.1109/tip.2008.2002841
Authors
References
- Rapid object detection using a boosted cascade of simple features
- Robust Real-Time Face Detection
- The Laplacian Pyramid as a Compact Image Code
- Pattern Classification
- The design and analysis of spatial data structures
- Distance functions on digital pictures
- Detecting faces in images: a survey
- Pattern Classification (2nd ed.)
- Learning to detect objects in images via a sparse, part-based representation
- Hierarchical chamfer matching: a parametric edge matching algorithm