Department of Computer Science and Engineering
University of Washington

Object and Activity Recognition

This research is supported by gifts from the Xerox Corporation and Adobe Research.

Object recognition is the subfield of computer vision whose goal is to recognize objects from image data and, often, to estimate the positions and orientations of the recognized objects in the 3D world. The images to be analyzed may be 2D gray-scale or color images or 3D range data images.

Activity recognition refers to analysis of videos to determine the activities that a person is engaging in during the course of the video. Our activity recognition work is motivated by the application of home health monitoring.

In the 3D domain, we have worked on the representation, recognition, and reconstruction of objects from range data. We have developed symbolic 3D object models that can be used in several different applications, including modeling the organs of the human body and modeling man-made objects for use in augmented reality environments.

People:

Linda Shapiro
Jue Wang
Shulin Yang
Bilge Soran
Jinna Lei

Publications: