The University Record, April 9, 1996

U-M-Dearborn prof design robot vehicle

Yi Lu Murphey, assistant professor of electrical and computer engineering at UM-Dearborn, is developing technology that will make it easier for unmanned military and commercial vehicles to operate in hazardous areas.

On a multiprocessor video compression system provided by the U.S. Army, Murphey applies computer vision and artificial intelligence techniques to develop real-time high rate video compression algorithms, mathematical models that reduce a video ima ge's band-width required for visual transmission. The system is designed for use aboard an unmanned, remote-controlled vehicle.

As the vehicle's video camera scans the hazardous area, the system compresses the images and transmits them to a remote location where a person can view the images, in real-time, reconstructed and displayed on a monitor. The operator who views the images also can control the vehicle's movement.

"There is a growing need for autonomous and remote-control vehicle systems for reconnaissance, mine detection and the cleaning of hazardous waste," Murphey said. "The goal of the project is to achieve a transmission rate of 16 kilo bytes per second and keep the reconstructed images in good quality."

"The compression procedure works similarly to the human eye's elementary stimulus for vision, perceiving complex patterns based on sparse contrast edges of an object being viewed," she said. "The widespread use of cartoons, sketches, blueprints and type fonts reflects this human talent."

The algorithms were developed within a system that includes a 20-inch monitor, six parallel processors and two terminals.

In the project's first stage, Murphey reduced the resolution of the image by digitizing the incoming video, splitting it into color and contrast channels.

The procedure for color-channel compression mimics the way the brain processes images. Images relayed from the retina to the brain that are high resolution in the image's center change smoothly to low resolution in the periphery of the image.

In the contrast channel, there is a compression procedure that models the human's visual capacity. The procedure works by extracting and transmitting encoded contrast edges.

There are numerous benefits of the research, in addition to improving unmanned vehicle operations.

For example, since video image compression plays a key role in teleconferencing, the project will make a contribution to multimedia classroom technology and distance learning, Murphey said.