Multiple Viewpoint Recognition and Localization

This paper presents a novel approach for labeling objects based on multiple spatially-registered images of a scene. We argue that such a multi-view labeling approach is a better fit for applications such as robotics and surveillance than traditional object recognition where only a single image of each scene is available. To encourage further study in the area, we have collected a data set of well-registered imagery for many indoor scenes and have made this data publicly available. Our multi-view labeling approach is capable of improving the results of a wide variety of image-based classifiers, and we demonstrate this by producing scene labelings based on the output of both the Deformable Parts Model of [1] as well as a method for recognizing object contours which is similar to chamfer matching. Our experimental results show that labeling objects based on multiple viewpoints leads to a significant improvement in performance when compared with single image labeling.

• Type: Journal
• Year: 2010
• Where: ACCV
• Authors: Scott Helmer, David Meger, Marius Muja, James J. Little, David G. Lowe
• Keywords: ACCV 2010, Computer Vision, Image, Multi-view Labeling Approach, Single Image