Welcome - Computer Vision   
Iris Images

The Computer Vision Laboratory at the University of Southern California is one of the major centers of computer vision research for thirty years. We conduct research in a number of basic and applied areas. Research topics include image and scene segmentation, stereo, motion and video analysis, range data analysis, perceptual grouping, shape analyis and object recognition. We have worked on applications to robotics, manufacturing, mobile robots, surveillance and aerial photo interpretation. Our approach emphasizes the use of segmented (part- based) symbolic descriptions of objects. Such representations have long been believed to have significant advantages over other alternatives but have been difficult to infer from the sensed data. Our group has been successful in making significant progress on this topic and is pursuing the use of these techniques for practical applications.

Use the Contacts tab to find current faculty, staff and students and links to many of the people associated with the group over the past years. The Projects tab has links to current and past research, arranged generally by research project or researc topic. Some topics may be in multiple places. The Papers tab gives links to online papers by year of publication.

Recent results, Context Tracker Recent Papers