|
Abstract : |
This paper presents a robust telerobotic system that consists of a real-time vision-based operator hand tracking system (client) and a slave robot (server) which are interconnected through a LAN. The tracking system (1) monitors the operator hand motion and (2) determines its position and orientation which are used to control the slave robot. Two digital cameras are used to monitor a four-ball based feature frame that is held by the operator hand. To determine the 3D position a tracking algorithm based on un-calibrated cameras with weak perspective projection model is used. This allows finding 3D differential position and orientation of operator hand. The features of proposed system are (1) a metric for color matching to discriminate the balls from their background, (2) a uniform and spiral search approach to speedup the detection, (3) tracking in the presence of partial occlusion, (4) consolidate detection by using shape and geometric matching, and (5) dynamic update of the reference colors. The operator can see the effects of the previous motion which enables making the necessary corrections through repetitive operator hand-eye interactions. Evaluation shows that the static and dynamic errors of tracking algorithm are 0:1% and 0:6% for a centered workspace of 203 inches3 that is 40 to 60 inches away from cameras. Running the tracking algorithm on two PCs in parallel allowed (1) a parallel image grabbing delay of 60 ms, (2) a stereo matching delay of 50 ms, and (3) a global refresh rate of 9Hz., This paper presents a robust telerobotic system that consists of a real-time vision-based operator hand tracking system (client) and a slave robot (server) which are interconnected by using a LAN. The tracking system (1) monitors the operator hand motion and (2) determine its position and orientation which are used to control the slave robot. Two digital cameras are used to monitor a four-ball called feature frame that is held by the operator hand. To determine the 3D position a tracking algorithm uses uncalibrated cameras together with the affine invariant property. This allows finding 3D differential position and orientation of operator hand. The features of proposed systems are (1) a metric for color matching to discriminate the balls from their background, (2) a uniform and spiral search approaches to speedup the detection, (3) tracking in the presence of partial occluding, (4) consolidate detection by using shape and geometric matching, and (5) dynamic update of the reference colors. The operator can see the effects of the previous motion which enables making the necessary corrections through repetitive operator hand-eye interactions. In the evaluation we study the static and dynamic errors of the tracking system as well as combined errors due to the affine invariant transformation. We also present the telerobotic real-time control scheme and its network and processing delays., |
