Journal of Transportation Systems Engineering and Information Technology

Journal of Transportation Systems Engineering and Information Technology ›› 2019, Vol. 19 ›› Issue (6): 45-51.

• Intelligent Transportation System and Information Technology • Previous Articles     Next Articles

Morphous Detection and Deep Learning Based Approach of Vehicle Recognition in Aerial Videos

PENG Bo1, 2, CAI Xiao-yu1, 2, TANG Ju2, XIE Ji-ming2, ZHANG Yuan-yuan2   

  1. 1. Chongqing Key Lab of Traffic System & Safety in Mountain Cities, Chongqing 400074, China; 2. College of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China
  • Received:2019-04-15 Revised:2019-05-12 Online:2019-12-25 Published:2019-12-25

基于形态检测与深度学习的高空视频车辆识别

彭博1, 2，蔡晓禹* 1, 2，唐聚2，谢济铭2，张媛媛2   

  1. 1. 山地城市交通系统与安全重庆市重点实验室，重庆 400074；2. 重庆交通大学交通运输学院，重庆 400074
  • 作者简介:彭博(1986-)，男，四川南充人，副教授.
  • 基金资助:

    国家自然科学基金/National Natural Science Foundation of China(61703064)；重庆市基础前沿与技术创新项目/ Chongqing Research Program of Basic Research and Frontier Technology Innovation(cstc2017jcyjAX0473)；城市交通管理集成优化重点实验室开放基金/Scientific Research Project of Key Laboratory of Urban ITS Technology Optimization (2017KFKT01).

PDF

Abstract:

In order to extract traffic information accurately from a regional perspective, a vehicle locating and classifying method for UAV videos was proposed combining morphous detection and deep convolutional networks. Firstly, target candidate extraction algorithm was designed based on morphous detection, thus a benchmark image library for deep learning was constructed containing 244 520 vehicle samples from UAV videos. Then, AlexNet was rebuilt by adding convolutional and pooling layers and adjusting network parameters, etc., thus a modified model AlexNet* was put forward. At last, vehicle recognition method fusing candidate extraction and AlexNet* was established. Validation analysis indicate that AlexNet* achieves an average F1 score of 85.51% in terms of image classification, outperforming AlexNet (82.54%), LeNet (63.88%), CaffeNet (46.64%), VGG16 (16.67%) and GoogLeNet (14.38%), and the proposed vehicle recognition method averagely obtains accuracy of 94.63%, repeated detection rate of 6.87% and missing detection rate of 4.40% for car and bus detection, which can effectively identify UAV objects.

Key words: intelligent transportation, vehicle recognition, deep learning, UAV video, morphous detection

摘要：

为了准确提取广域场景道路交通信息，本文融合形态检测与深度卷积网络，提出了无人机视频车辆定位及车型识别方法. 首先，基于形态检测建立候选目标提取算法，并构建了含244 520 个无人机视频车辆样本的深度学习图像基准库；然后，通过增加卷积层、池化层及调整网络参数等方法对AlexNet 进行重构，提出了改进模型AlexNet*；最后，建立了基于候选目标提取算法与AlexNet*的车辆识别方法. 验证分析显示：AlexNet*的图像分类F1 均值达 85.51% ，优于AlexNet(82.54% )、LeNet(63.88% )、CaffeNet(46.64% )、VGG16(16.67% ) 及 GoogLeNet(14.38%)；本文车辆识别方法对小汽车及公交车的正检率、重检率和漏检率均值分别达94.63%、6.87%、4.40%，可有效识别无人机视频目标.

关键词: 智能交通, 车辆识别, 深度学习, 无人机视频, 形态检测

CLC Number: