The purpose of this study was to investigate the utility of convex optimization as a decision mechanism technique to enhance negative obstacle detection performance for unmanned ground vehicle (UGV) technologies. A convex framework is established in conjunction with a unique stereo perception approach to manage the complex nature of such obstacles. The proposed stereo configuration incorporates an alignment that displaces the cameras along a vertical baseline to extract useful information pertaining to negative obstacle features for indoor and outdoor environments. The convex framework exploits these properties to evaluate depth jumps in the disparity space image and perform geometrical analysis of potential occlusion regions. Results demonstrated that consecutive processes can be structured in a convex framework to efficiently identify negative obstacle attributes at a range of distances for texture varying environments, providing insight that suggests feasible extension to real-time system implementation to improve the detection rate performance.
Negative obstacle detection via convex optimization
01.05.2016
Sonstige
Elektronische Ressource
Englisch
DDC: | 629 |
Trajectory generation for road vehicle obstacle avoidance using convex optimization
Tema Archiv | 2010
|Trajectory generation for road vehicle obstacle avoidance using convex optimization
Kraftfahrwesen | 2010
|Trajectory generation for road vehicle obstacle avoidance using convex optimization
Online Contents | 2010
|Trajectory generation for road vehicle obstacle avoidance using convex optimization
SAGE Publications | 2010
|