Using a binocular, maneuverable visual system, a robot that holds its gaze on a visual target can enjoy improved visual perception and performance in interacting with the world. This dissertation examines the problem of holding gaze on a moving object from a moving platform, without requiring the ability to recognize the target. A novel aspect of the approach taken is the use of controlled camera movements to simplify the visual processing necessary to keep the cameras locked on the target. A gaze holding system on the Rochester robot's binocular head demonstrates this approach. Even while the robot is moving, the cameras are able to track an object that rotates and moves in three dimensions.
Real-Time Gaze Holding in Binocular Robot Vision
1992
165 pages
Report
Keine Angabe
Englisch
Robotics/Robots , Computers, Control & Information Theory , Robots , Approach , Binoculars , Cameras , Head(Anatomy) , Motors , Platforms , Processing , Targets , Theses , Tracking , Tracks , Visual perception , Visual targets , Computer vision , Visual following , Active vision , Animate vision , Precategorical vision , Gaze stabilization , Sensory-motor systems , Egomotion compensation , Mobile robots
Bicycle cleaning robot based on binocular vision recognition
Europäisches Patentamt | 2023
|Binocular Vision Sensor (Kinect)-Based Pedestrian Following Mobile Robot
Trans Tech Publications | 2014
|