Object recognition in high clutter images using line features
- 1 January 2005
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15505499), 1581
- https://doi.org/10.1109/iccv.2005.173
Abstract
We present an object recognition algorithm that uses model and image line features to locate complex objects in high clutter environments. Finding correspondences between model and image features is the main challenge in most object recognition systems. In our approach, corresponding line features are determined by a three-stage process. The first stage generates a large number of approximate pose hypotheses from correspondences of one or two lines in the model and image. Next, the pose hypotheses from the previous stage are quickly ranked by comparing local image neighborhoods to the corresponding local model neighborhoods. Fast nearest neighbor and range search algorithms are used to implement a distance measure that is unaffected by clutter and partial occlusion. The ranking of pose hypotheses is invariant to changes in image scale, orientation, and partially invariant to affine distortion. Finally, a robust pose estimation algorithm is applied for refinement and verification, starting from the few best approximate poses produced by the previous stages. Experiments on real images demonstrate robust recognition of partially occluded objects in very high clutter environmentsKeywords
This publication has 14 references indexed in Scilit:
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- SoftPOSIT: Simultaneous Pose and Correspondence DeterminationInternational Journal of Computer Vision, 2004
- Shape recognition with edge-based featuresPublished by British Machine Vision Association and Society for Pattern Recognition ,2003
- New algorithms for 2D and 3D point matchingPattern Recognition, 1998
- Local grayvalue invariants for image retrievalIeee Transactions On Pattern Analysis and Machine Intelligence, 1997
- A graduated assignment algorithm for graph matchingIeee Transactions On Pattern Analysis and Machine Intelligence, 1996
- Optimal Geometric Model Matching under Full 3D PerspectiveComputer Vision and Image Understanding, 1995
- Aligning pictorial descriptions: An approach to object recognitionCognition, 1989
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional ObjectsIeee Transactions On Pattern Analysis and Machine Intelligence, 1986