Vision for Longitudinal Vehicle

An important component of the drive towards intelligent vehicles is the ability to maintain a xed distance from a lead vehicle using feedback provided by range sensors. We are investigating the possibility of using stereo vision to provide the range information, in conjunction with a scanning laser radar sensor. The vision algorithms build on xation and reconstruction algorithms designed for active vision systems, and combine stereo and motion cues. We shall present preliminary results comparing the quality of range measurements provided by a vision system with the laser radar system, using data obtained oo-line. Later we will implement the tracker in real time on a network of C40 DSPs, and combine the laser and vision sensing in a cooperative manner. Note to reviewers: a longer version of this paper has been submitted to the IEEE Intelligent Transportation Systems conference in Boston. At BMVC we shall present new results from the real-time system currently under development. Abstract An important component of the drive towards intelligent vehicles is the ability to maintain a xed distance from a lead vehicle using feedback provided by range sensors. We are investigating the possibility of using stereo vision to provide the range information, in conjunction with a scanning laser radar sensor. The vision algorithms build on xation and reconstruction algorithms designed for active vision systems, and combine stereo and motion cues. We shall present preliminary results comparing the quality of range measurements provided by a vision system with the laser radar system, using data obtained oo-line. Later we will implement the tracker in real time on a network of C40 DSPs, and combine the laser and vision sensing in a cooperative manner. Note to reviewers: a longer version of this paper has been submitted to the IEEE Intelligent Transportation Systems conference in Boston. At BMVC we shall present new results from the real-time system currently under development.