L. Mirisola, J. Lobo, and J. Dias (Portugal)
Autonomous Airships, Artificial Vision, Inertial, 3D Registration.
A depth map registration method is proposed in this arti cle, and experimental results are presented for long three dimensional map sequences obtained from a moving ob server. In vision based systems used in mobile robotics the perception of self-motion and the structure of the environ ment is essential. Inertial and earth field magnetic pose sen sors can provide valuable data about camera ego-motion, as well as absolute references for structure feature orien tations. In this work we explore the fusion of stereo tech niques with data from the inertial and magnetic sensors, enabling registration of 3D maps aquired by a moving ob server. The article reviews the camera-inertial calibration used, other works on registering stereo point clouds from aerial images, as well as related problems as robust image matching. The map registration approach is presented and validated with experimental results on ground outdoor en vironments.
Important Links:
Go Back
