Applications of direct 3D motion estimation for underwater machine vision systems

Vision can provide unique capabilities under favorable visibility conditions during the operation of intelligent or autonomous underwater vehicles in deep ocean. We describe a real time vision system for positioning and station keeping, navigation, and sea floor image mosaicing. These developments exploit a direct methodology for 3D motion estimation from time varying underwater imagery. We present sample results from experiments for evaluating the performance and accuracy of the system, based on measurements from an independent sensor.

[1]  Shahriar Negahdaripour,et al.  Direct recovery of motion and range from images of scenes with time-varying illumination , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[2]  Shahriar Negahdaripour.  Revised interpretation of optical flow for dynamic scene analysis , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[3]  Xun Xu,et al.  A real-time vision-based 3D motion estimation system for positioning and trajectory following , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[4]  Shahriar Negahdaripour,et al.  Undersea optical stationkeeping: Improved methods , 1991, J. Field Robotics.

[5]  S. D. Fleischer,et al.  Global position determination and vehicle path estimation from a vision sensor for real-time video mosaicking and navigation , 1997, Oceans '97. MTS/IEEE Conference Proceedings.

[6]  S. Negahdaripour,et al.  Orientation and distance recovery of Lambertian planar surfaces in light-attenuating media from optical images , 1991 .

[7]  Shahriar Negahdaripour,et al.  Vision-based motion sensing for underwater navigation and mosaicing of ocean floor images , 1997, Oceans '97. MTS/IEEE Conference Proceedings.

[8]  Shahriar Negahdaripour,et al.  Recovery of 3D depth map from image shading for underwater applications , 1997, Oceans '97. MTS/IEEE Conference Proceedings.

[9]  Shahriar Negahdaripour,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2004 .