Evaluation of Benchmarking Pre-Trained CNN Model for Autonomous Vehicles Object Detection in Mixed Traffic

Abstract

In the next few years, the new generation of Autonomous Vehicles (AVs) promises an advanced level of self-driving experiences. One of the most challenging topics in AVs development is the readiness of object detection models in complex urban environments. Mixed traffic is a complex urban environment that contains much uncertainty and is composed of heterogeneous objects. Therefore, this paper evaluates benchmarking the pre-trained CNN model for object detection in a mixed traffic environment. The evaluation is conducted for five modern algorithms and architecture of neural networks, including Faster RCNN, SSD, YOLOv3, YOLOv4, and EfficientDet. Then, we provide a new dataset in the mixed traffic environment under night conditions for more accurate object detection. Moreover, we conduct the simulation by considering the performance parameters that are recall, precision, and F measure. The performance of our dataset is also compared to the MS-COCO dataset. The result shows that the average precision value of Faster RCNN, SSD, YOLOv3, YOLOv4, and EfficientDet is 16.70%, 8.90%, 19.67%, 43.90%, and 55.56% respectively. It shows that YOLOv4 and EfficientDet provide better object detection accuracy than other CNN models.