车辆颜色和型号识别算法研究与应用

doi:10.12052/gdutxb.200051

摘要/Abstract

摘要： 针对目前基于机器学习的车辆颜色和型号识别方法的识别准确率低问题, 提出基于卷积神经网络的车辆颜色和型号识别方法。该方法使用Darknet网络中YOLOv3(You Only LookOnce Version 3)算法对车辆图片的车脸进行检测与定位, 再对车脸区域使用车辆颜色和型号识别算法同时识别车辆颜色和型号, 这是对车辆多属性同时识别的方法, 不同于车辆单一属性识别的方法。在公开车辆数据集(Peking University Vehicle Datasets, PKU-VD)上进行实验, 实验结果表明, 车辆颜色和型号同时识别准确率为93.75%, 车辆颜色单一属性识别准确率为94.98%, 车辆型号单一属性识别准确率98.38%, 明显优于基于机器学习的车辆属性识别算法, 从而验证该算法是可行且有效的。最后将车辆颜色和型号识别技术应用在智能停车场收费系统中。

关键词: 车辆颜色识别, 车型识别, 车脸, 卷积神经网络, 智能停车场收费系统

Abstract: In order to solve the problem of low recognition accuracy of current vehicle color and model recognition methods based on machine learning, a vehicle color and model recognition method based on convolutional neural network is proposed. The method uses YOLOv3(You Only LookOnce Version 3) algorithm in Darknet network to detect and locate the vehicle face, and then the vehicle color and model recognition algorithm based on convolutional neural network is used to identifythe vehicle color and model. This is a multi-attribute recognition method for vehicle, it is different from the recognition method of single vehicle attribute. On public traffic data collection of Peking University Vehicle Datasets experiment, the experimental results show that the vehicle color and model recognition accuracy of 93.75% at the same time, the recognition accuracy of vehicle color is 94.98%, the recognition accuracy of vehicle model attribute recognition is 98.38%, It is obviously better than the vehicle attribute recognition algorithm based on machine learning, the algorithm is proved to be feasible and effective. Finally, the vehicle color and model recognition technology is applied to the intelligent parking fee system.

Key words: vehicle color recognize, vehicle model recognize, vehicle face, convolutional neural networks(CNN), intelligent parking fee system

中图分类号:

TP391

战荫伟, 朱百万, 杨卓. 车辆颜色和型号识别算法研究与应用[J]. 广东工业大学学报, 2020, 37(04): 9-14.

Zhan Yin-wei, Zhu Bai-wan, Yang Zhuo. Research and Application of Vehicle Color and Model Recognition Algorithm[J]. Journal of Guangdong University of Technology, 2020, 37(04): 9-14.

参考文献

[1] 邓柳. 基于深度卷积神经网络的车型识别[D]. 成都: 西南交通大学, 2015.
[2] REDMON J, FARHADI A. YOLOv3: an incremental improvement[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE Computer Society, 2018: 89-95.
[3] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedi ng of the 3rd International Conference on Learning Representations. SanDiego: ICLR, 2015: 1409-1556.
[4] 陈旭, 张军, 陈文伟, 等. 卷积网络深度学习算法与实例[J]. 广东工业大学学报, 2017, 34(6): 20-26
CHEN X, ZHANG J, CHEN W W, et al. Convolutional neural network algorithm and case [J]. Journal of Guangdong University of Technology, 2017, 34(6): 20-26
[5] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[C]//26th Annual Conference on Neural Information Processing Systems. Lake Tahoe: Neur al Information Processing System Foundation, 2012: 1097-1105.
[6] HEK, ZHANG X, REN S, et al. Deep residual learning for imagerecognition[C]//2016 IEEE Conference on Compute rVision and Pattern Recognition. Las Vegas: IEEE Computer Society, 2016: 770-778.
[7] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolueons[C]//2015 IEEE Conference on Computer Visi onand Pattern Recognition. Boston: IEEE Computer Society, 2015: 1-9.
[8] HowarD A G, ZHU M, CHEN B, et al. Mobile Nets: efficient convolutional neural networks for mobile vision applications [J]. arXiv preprint, 2017, 32(9): 100-108
[9] 尹宏鹏, 陈波, 柴毅, 等. 基于视觉的目标检测与跟踪综述[J]. 自动化学报, 2016, 42(10): 1466-1489
YIN H P, CHEN B, CHAI Y, et al. Vision-based object detection and tracking: a review [J]. Acta Automatica Sinica, 2016, 42(10): 1466-1489
[10] 李旭冬, 叶茂, 李涛. 基于卷积神经网络的目标检测研究综述[J]. 计算机应用研究, 2017, 34(10): 2881-2886
LI X D, YE M, LI T. Review of object detection based on convolutional neural networks [J]. Application of Computer Research, 2017, 34(10): 2881-2886
[11] LAOPRACHA N, SUNAT K. Comparative study of computational time that HOG-Based features used forvehicle detection[C]//2017 International Conference on Computing and Information Technology. Helsinki: IEEE Computer Society, 2017: 275-284.
[12] El-KHOREBY MOHAMED, ABU-BAKAR SYED. Vehicle detection and counting for complex weather conditions[C]//2017 IEEE International Conference on Signal and Image Processing Applications. Beijing: IEEE Computer Society, 2017: 425-428.
[13] MAQBOOL S, KHAN M, TAHIR J, et al. Vehicle Detection, Tracking and Counting[C]// 2018 IEEE 3rd International Conference on Signal and Image Processing (ICSIP). Shenzhen: IEEE, 2018: 126-132.
[14] 张红兵, 李海林, 黄晓婷, 等. 基于车前脸HOG特征的车型识别方法研究与实现[J]. 计算机仿真, 2015, 32(12): 119-123
ZHANG H B, LI H L, HUANG X T, et al. Research and implementation of vehicle-type recognition method based on HOG features of vehicle frontal face [J]. Computer Simulation, 2015, 32(12): 119-123
[15] PAN C, SUN M, YANZ. The study on vehicle detection based on DPM in traffic scenes[C]//2016 International Conference on Frontier Computing. Tokyo: FC, 2016: 19-27.
[16] SANG J, GUO P, XIANGZ, et al. Vehicle detection based on faster-RCNN [J]. Journal of Chongqing University, 2017, 40(7): 32-36
[17] 张鹏, 陈湘军, 阮雅端, 等. 采用稀疏SIFT特征的车型识别方法[J]. 西安交通大学学报, 2015, 49(12): 137-143
ZHANG P, CHEN X J, RUAN Y D, et al. A vehicle classification technique based on sparse coding [J]. Journal of Xi'an Jiaotong University, 2015, 49(12): 137-143
[18] 贾晓. 套牌车辆的车型识别与检索技术研究[D]. 大连: 大连海事大学, 2016.
[19] TANG Y, ZHANG C Z, GU R S, et al. Vehicle detection and recognition for intelligent traffic surveillance system [J]. Multimedia Tools & Applications, 2017, 76(4): 5817-5832
[20] 李慧, 利齐律, 程良伦, 等. 基于多颜色空间卷积神经网络的车辆颜色分类[J]. 工业控制计算机, 2019, 32(11): 78-82
LI H, LI Q L, CHENG L L, et al. Convolutional neural network based on multi-color space for vehicle color classification [J]. Industrial Control Computer, 2019, 32(11): 78-82
[21] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE Computer Society, 2016: 779-788.
[22] 陈正斌, 叶东毅, 朱彩霞, 等. 基于改进YOLOv3的目标识别方法[J]. 计算机系统应用, 2020, 29(1): 49-58
CHEN Z B, YE D Y, ZHU C X, et al. Object recognition method based on improved YOLOv3 [J]. Computer Systems and Applications, 2020, 29(1): 49-58
[23] YAN K, TIAN Y, WANG Y, et al. Exploiting multi-grain ranking constraints for precisely searching visually-similar vehicles[C]//2017 IEEE Conference on Computer Vision. Venice: IEEE, 2017: 562-570.
[24] PASZKE A, GROSS S, MASSA F, et al. PyTorch: an imperative style, high-performance deep learning library[C]//33rd Conference on Neural Information Processing Systems (NeurIPS 2019). Vancouver: Curran Associates, 2019: 8024-8035.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed