Recognizing objects by matching oriented points

Abstract

We present an approach to recognition of complex objects in cluttered 3-D scenes that does not require feature extraction or segmentation. Our object representation comprises descriptive images associated with each oriented point on the surface of an object. Using a single point basis constructed from an oriented point, the position of other points on the surface of the object can be described by two parameters. The accumulation of these parameters for many points on the surface of the object results in an image at each oriented point. These images, localized descriptions of the global shape of the object, are invariant to rigid transformations. Through correlation of images, point correspondences between a model and scene data are established and then grouped using geometric consistency. The effectiveness of our algorithm is demonstrated with results showing recognition of complex objects in cluttered scenes with occlusion.

Keywords

Computer visionArtificial intelligenceObject (grammar)Cognitive neuroscience of visual object recognitionComputer scienceSegmentationInvariant (physics)Pattern recognition (psychology)Point (geometry)Matching (statistics)Representation (politics)Feature extractionPosition (finance)MathematicsGeometry

Affiliated Institutions

Carnegie Mellon University US

Related Publications

Object class recognition by unsupervised scale-invariant learning

Rob Fergus , Pietro Perona , Andrew Zisserman

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible const...

2003 2035 citations

Local feature view clustering for 3D object recognition

David Lowe

There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to...

2005 481 citations

Using spin images for efficient object recognition in cluttered 3D scenes

Andrew Johnson , Martial Hebert

We present a 3D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matchi...

1999 IEEE Transactions on Pattern Analysis... 2604 citations

Shape Matching and Object Recognition Using Low Distortion Correspondences

Alexander C. Berg , Tamara L. Berg , Jitendra Malik

We approach recognition in the framework of deformable shape matching, relying on a new algorithm for finding correspondences between feature points. This algorithm sets up corr...

2005 847 citations

Object recognition from local scale-invariant features

David Lowe

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partia...

1999 15989 citations

Publication Info

Year: 2002
Type: article
Pages: 684-689
Citations: 129
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Recognizing objects by matching oriented points

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

129

OpenAlex

Cite This

APA Style

                            
                                    Andrew Johnson, 
                                
                                    Martial Hebert
                                
                            (2002). 
                            Recognizing objects by matching oriented points. 
                            
                            , 684-689.
                            https://doi.org/10.1109/cvpr.1997.609400

Identifiers

DOI: 10.1109/cvpr.1997.609400