Modified -Vehicle Detection and Localization model for Autonomous Vehicle Traffic System 

The modification of vehicles for financial gain is an evolving tendency observed in India. These modified vehicles are riskier than other automobiles that are allowed. Recognizing and detecting of these modified illicit cars is an important but critical task in autonomous vehicles. In a real-world traffic scenario, it is always possible for a cyclist or pedestrian to traverse obstacles or other fixed objects that appear in front of any moving vehicle. Vehicles that are autonomous or self-driving require a different system to quickly identify both stationary and moving objects. A deep learning model named YOLOv5-CBAM is proposed here for the Indian traffic System which is based on YOLOv5m. The algorithm is applied to the vehicle dataset collected from different regions of Uttarakhand. The proposed algorithm, YOLOv5-CBAM, has three major components. The first module, the backbone module is employed for feature extraction. The second module is to detect static as well as dynamic objects at the same time and the third CBAM module is adopted in the backbone and neck part, which mainly focuses on the more prominent features. Two CSP modules were used after every convolutional layer resulting in an additional head to the proposed model. Four head modules equipped with anchor boxes performed the final detection. For the present dataset, the proposed model showed 98.2% mAP, 98.4% precision, and 94.8% recall as compared to the original YOLOv5m.