As autonomous driving technology evolves, ensuring car dependability and safety is crucial. The versatile Quanser Car (Q-car) platform provides an ideal testing ground for driverless vehicles. This research focuses on enhancing self-driving car safety by implementing an effective obstacle detection system. The study aims to improve obstacle recognition in self-driving Q-Cars by integrating depth cameras with MATLAB Simulink. Depth cameras offer advantages over yolo v5, providing vital three-dimensional environmental data essential for accurate obstacle detection and distance measurement. The research explores depth camera usage in driverless cars, detailing their integration into the Q-Car platform via Simulink. Additionally, it investigates how depth cameras can enhance safety features, especially collision avoidance. By leveraging depth cameras and MATLAB Simulink, the project aims to significantly boost autonomous vehicle safety and reliability on the Q-car platform, potentially advancing autonomous driving technology and fostering the development of safer self-driving cars.
Obstacle Detection and Enhanced Safety for Self-driving Automobiles (ODESSA)
Communic.Comp.Inf.Science
International Conference on Computer Vision and Image Processing ; 2024 ; Chennai, India December 20, 2024 - December 22, 2024
2025-07-20
9 pages
Article/Chapter (Book)
Electronic Resource
English
Self-driving Automobiles: Are We Ready?
Springer Verlag | 2024
|Optical Detection for Space Situational Awareness (ODESSA)
British Library Conference Proceedings | 2018
|Engineering Index Backfile | 1937
|Engineering Index Backfile | 1937
|British Library Online Contents | 2015