The research in computer vision described in this final report is directed towards the achievement of autonomous vehicle navigation using passive visual sensing. Navigation in both modeled and unknown environments has beer investigated; in addition, research has been carried out in related areas of static image interpretation. For a modeled environment, we have implemented a navigation system incorporating reactive planning, and based on the identification of known landmarks in the 3D scene. Also, robust algorithms have been demonstrated for the recovery of pose--the position and orientation of the camera--from model-matching between the image and known environment. For an unknown environment, a navigation system has been demonstrated in which image-based homing is used to move between neighboring target locations. We have also developed and experimentally tested techniques for acquiring a detailed environmental model automatically, starting from an unknown or partially known environment. For a completely unknown environment, multiframe structure from motion algorithms have been developed which use image sequences for the reconstruction of the camera motion and environmental structure. In a partially modeled environment, the combination of pose recovery with triangulation over image sequences yields a robust, accurate algorithm for incremental acquisition of a 3D scene model. Lastly, a new framework for obstacle detection from motion has been developed and demonstrated experimentally.... Computer vision, Autonomous vehicle and landmark-based navigation, Robust statistics, Low-level vision, Pose recovery, Stereo and motion, Kalman filtering.
Motion Analysis and Object Recognition for Autonomous Navigation
1991
40 pages
Report
Keine Angabe
Englisch
Ceramics, Refractories, & Glass , Robotics/Robots , Computer vision , Motion , Autonomous navigation , Pattern recognition , Acquisition , Addition , Algorithms , Cameras , Computers , Detection , Environments , Filtration , Homing , Identification , Images , Kalman filtering , Low level , Matching , Models , Navigation , Planning , Recovery , Sequences , Starting , Statics , Statistics , Structures , Targets , Triangulation , Vehicles , Yield
Object tracking supporting autonomous vehicle navigation
Europäisches Patentamt | 2024
|OBJECT TRACKING SUPPORTING AUTONOMOUS VEHICLE NAVIGATION
Europäisches Patentamt | 2023
|Object tracking supporting autonomous vehicle navigation
Europäisches Patentamt | 2022
|