Multi-object Recognition Method Based on Improved YOLOv2 Model

Abstract

A method of vehicle multi-object identification and classification based on the YOLOv2 algorithm is proposed to solve the problems of low detection rate, poor robustness, and unsatisfactory classification effect for the classical multi-object detection and vehicle type classification on real road environment. Based on the YOLOv2 algorithm, the network structure of YOLOv2-voc is improved according to the actual road conditions. The classification training model was obtained based on the ImageNet data and fine-tuning technology, according to the analysis of training results and vehicle object characteristics. This paper proposed the improved vehicle identification classification network structure, namely called YOLOv2-voc_mul. In order to verify the validity of the detection method, experiments are performed using samples from simple backgrounds and complex backgrounds and compared with the existing YOLOv2, YOLOv2-voc, and YOLOv3 models after 70000 iterations, respectively. The results show that the proposed YOLOv2-voc_mul model has an accuracy of 98.6% under the simple background, and the mAP (mean Average Precision) of different models reaches 87.81%. Under the complex background, the improved YOLOv2-voc_mul model has an average accuracy of 92.09% and 89.64% for single and multi-object detection of four different models. In summary, our proposed method has better accuracy, a low false detection rate, and good robustness.