Deep Learning Approach for Object Detection in Autonomous Vehicles: Mitigating Weather-Related Obstacles

This paper presents a novel model designed to enhance the safety and reliability of autonomous vehicles operating in challenging environments. The proposed approach integrates the GMAN and Parallel Networks to effectively extract and process features from input images, enabling accurate object detection and classification. Extensive experiments were conducted using a diverse dataset that simulated various real-world driving conditions, including adverse weather, low visibility, and heavy traffic. The model demonstrated strong performance, achieving an accuracy of 98.03%, precision of 98.03%, recall of 98.03%, and an F1 score of 98.03%. The model’s loss was minimized to 13.26%, and it achieved an Area Under the Curve (AUC) of 98.18%, indicating its exceptional ability to differentiate between objects. These results suggest that the proposed model has significant potential for improving the safety and dependability of autonomous vehicles, particularly in complex and dynamic driving environments. Future work will explore the model’s deployment in real-world scenarios to further validate its effectiveness.