Multi-object Recognition Method Based on Improved YOLOv2 Model

In this paper, a method of vehicle multi-object identification and classification based on the YOLOv2 algorithm is proposed, which is used to solve the classical multi-object classification problems of low detection rate, poor robustness and unsatisfactory effect on real road environment. We analyzed vehicle objective and training results. The network structure of YOLOv2-voc is improved according to the actual road conditions based on the YOLOv2 algorithm, and the classification training model was obtained by the ImageNet data which is came from many tweaks. A classification network structure YOLOv2-voc_mul is obtained for sensitive vehicle type changing. 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, YOLOv2-tiny, YOLOv3 and YOLOv3-tiny 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.

Automated summary

This paper proposes a method of vehicle multi-object identification and classification based on the YOLOv2 algorithm, effectively solving classical multi-object classification problems. The improved algorithm achieved high accuracy and mAP values in both simple and complex backgrounds.