Stereo Correspondence with Local Descriptors for Object Recognition

Abstract

Stereo correspondence refers to the matches between two images with different viewpoints looking at the same object or scene. It is one of the most active research topics in computer vision as it plays a central role in 3D object recognition, object categorization, view synthesis, scene reconstruction, and many other applications. The image pair with different viewpoints is known as stereo images when the baseline and camera parameters are given. Given stereo images, the approaches for finding stereo correspondences are generally split into two categories: one based on sparse local features found matched between the images, and the other based on dense pixel-to-pixel matched regions found between the images. The former is proven effective for 3D object recognition and categorization, while the latter is better for view synthesis and scene reconstruction. This chapter focuses on the former because of the increasing interests in 3D object recognition in recent years, also because the feature-based methods have recently made a substantial progress by several state-of-the-art local (feature) descriptors. The study of object recognition using stereo vision often requires a training set which offers stereo images for developing the model for each object considered, and a test set which offers images with variations in viewpoint, scale, illumination, and occlusion conditions for evaluating the model. Many methods on local descriptors consider each image from stereo or multiple views a single instance without exploring much of the relationship between these instances, ending up with models of multiple independent instances. Using such a model for object recognition is like matching between a training image and a test image. It is, however, especially interested in this chapter that models are developed integrating the information across multiple training images. The central concern is how to extract local features from stereo or multiple images so that the information from different views can be integrated in the modeling phase, and applied in the recognition phase. This chapter is composed of the following contents: