An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
A duality based approach for realtime TV-L1 optical flow
Proceedings of the 29th DAGM conference on Pattern recognition
Lateral and depth calibration of PMD-Distance sensors
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II
Time-of-Flight camera based 3D point cloud reconstruction of a car
Computers in Industry
Hi-index | 0.00 |
During the last years, Time-of-Flight sensors achieved a significant impact onto research fields in computer vision. For dynamic scenes however, most sensor's working principles lead to significant artifacts in respect to sensor or object motion --- artifacts that commonly affect distance reliability and thus affect downstream processing tasks in a negative way. We therefore introduce a compensation approach for sensors based on the Photonic Mixing Device (PMD). Out technique deals with both, lateral and axial motion artifacts. The lateral compensation tracks object motion on the level of phase images and accordingly adjusts the depth image computation in order to reduce artifacts and enhances depth reliability. The axial motion compensation is based on an axial motion estimation and a theoretical model for axial motion deviation errors. Both components utilize fast optical flow algorithms.