In an effort to increase efficiency and safety, the automobile industry is undergoing a rapid transformation thanks to the integration of machine learning and artificial intelligence. In this study, computer vision and deep learning techniques are utilized to predict encounters between vehicles and pedestrians by analysing data captured by dash cam. Specifically, YOLO v8 is employed for detecting cyclists and pedestrians, focusing on six categories: person, car, bike, motorcycle, bus, and truck. By equipping autonomous vehicles with sensors and ML capabilities, significant benefits such as safer roads, reduced traffic congestion, lower emissions, and enhanced mobility can be achieved. Moreover, the implementation of night vision technology enables the detection of pedestrians, animals and cyclists in low-light conditions, thereby addressing specific risks. Overall, these advancements in vision-based technology and autonomous vehicles are leading to a transformative shift in the transportation industry, offering improved safety and efficiency. The methodology followed in this paper is inclined more towards the detection followed by prevention in collision of automobiles.
Collision Detection and Prevention for Automobiles using Machine Learning
2024-03-22
2518929 byte
Conference paper
Electronic Resource
English
Collision forces in automobiles
Engineering Index Backfile | 1906
|Collision Avoidance System for Automobiles
Automotive engineering | 1978
|Collision Avoidance System for Automobiles
SAE Technical Papers | 1978
|Collision avoidance system for automobiles
Tema Archive | 1978
|