Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks

Abstract

Models for vehicle detection, classification, and counting based on computer vision and artificial intelligence are constantly evolving. In this study, we present the Yolov4-based vehicle detection, classification, and counting model approach. The number of vehicles was calculated by generating the serial number of the identity of each vehicle. The object is detected and classified, marked by the display of bounding boxes, classes, and confidence scores. The system input is a video dataset that considers the camera position, light intensity, and vehicle traffic density. The method has counted the number of vehicles: cars, motorcycles, buses, and trucks. Evaluation of model performance is based on accuracy, precision, and total recall of the confusion matrix. The results of the dataset test and the calculation of the model performance parameters had obtained the best accuracy, precision. Total recall values when the model testing was carried out during the day where the camera position was at the height of 6 m and the loss of 500 was 83%, 93%, and 94%. Meanwhile, the lowest total accuracy, precision, and recall were obtained when the model was tested at night. The camera position was at the height of 1.5 m, and 900 losses were 68%, 77%, and 78%.