Treffer: Investigation of Object Detection and Identification at Different Lighting Conditions for Autonomous Vehicle Application.

Ensuring the safety of autonomous vehicles requires effective detection and tracking of surrounding objects. This paper proposes the design and development of a driverless transportation system module focused on identifying obstacles around vehicles. By integrating computer vision with deep learning, the system presents a reliable and costeffective solution for autonomous driving. Utilizing Raspberry Pi 4B and a USB webcam, a compact hardware setup is created for seamless implementation in autonomous vehicles. The algorithm presented in this study enables the detection, classification, and tracking of both moving and stationary objects, including cars, buses, trucks, people, and motorcycles. TensorFlow Lite, a deep-learning network, is employed for efficient object detection and classification. Leveraging Python as the primary programming language, known for its highlevel object-oriented features and integrated semantics, the algorithm is tailored for web and application development. Experimental results demonstrate the system's capability to concurrently detect and identify multiple local objects with an accuracy ranging from 50% to 80% in day and night conditions. These findings underscore the potential of deep learning in advancing autonomous vehicle technology. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Automotive & Mechanical Engineering is the property of Universiti Malaysia Pahang, Faculty of Mechanical Engineering and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)