测绘学报 ›› 2018, Vol. 47 ›› Issue (9): 1228-1237.doi: 10.11947/j.AGCS.2018.20170506

• 摄影测量学与遥感 • 上一篇    下一篇

利用无人机多源影像检测车辆速度

姜尚洁1, 罗斌1, 贺鹏2, 杨国鹏2, 顾亚平3, 刘军1, 张云1, 张良培1   

  1. 1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079;
    2. 解放军 95899部队, 北京 100085;
    3. 淮安市水利勘测设计研究院有限公司, 江苏 淮安 223000
  • 收稿日期:2017-09-07 修回日期:2018-04-28 出版日期:2018-09-20 发布日期:2018-09-26
  • 通讯作者: 罗斌 E-mail:luob@whu.edu.cn
  • 作者简介:姜尚洁(1993-),男,硕士,研究方向为图像处理,目标检测与无人机控制。E-mail:shangjiejiang@whu.edu.cn

Vehicle Speed Detection by Multi-source Images from UAV

JIANG Shangjie1, LUO Bin1, HE Peng2, YANG Guopeng2, GU Yaping3, LIU Jun1, ZHANG Yun1, ZHANG Liangpei1   

  1. 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. 95899 Troops, People's Liberation Army, Beijing 100085, China;
    3. Huai'an Surveying and Design Institute of Water Resources Co., Ltd., Huai'an 223000, China
  • Received:2017-09-07 Revised:2018-04-28 Online:2018-09-20 Published:2018-09-26

摘要: 交通在人民生活和社会经济中有着举足轻重的作用。车辆速度检测是智能交通管理系统的重要组成部分。本文提出了一种基于无人机(UAV)多源影像数据进行车辆速度检测的方法,首先,搭建小型无人机多源数据采集平台,获取可见光影像与热红外影像。然后,针对采集的多源数据,采用深度学习框架YOLO(you only look once)进行车辆检测。最后,基于卡尔曼滤波进行车辆跟踪,并根据跟踪结果计算车辆速度。本文利用无人机平台增加监测车辆的灵活性,同时综合使用多源数据,不仅提高车辆检测精度,还可以不依赖光照条件跟踪车辆。试验结果表明,本文方法具有有效性和稳健性,为道路监控管理部门提供一种高效率、机动灵活的监测模式。

关键词: 无人机, 车辆速度检测, 深度学习, 热红外影像

Abstract: Traffic plays a vital role in people's life and social economy.Vehicle speed detection is an important part of intelligent transportation system.This paper focus on the vehicle speed detection based on multi-source data from autonomous unmanned aerial vehicle (UAV).Firstly,we build a multi-source data acquisition system on UAV for visible image and thermal infrared image.Secondly,we utilize "You only look once" (YOLO),which is a deep learning framework for vehicle detection.Finally,we track the vehicle based on Kalman filter and calculated the vehicle speed according to the result of vehicle tracking.This paper adopts the UAV platform to increase the flexibility.While the use of multi-source data improves the accuracy of the vehicle detection and tracks the vehicle in different illumination.The result of experiments shows that the strategy is effective and robust,which provides an efficient and flexible monitoring mode for traffic management department.

Key words: unmanned aerial vehicle, vehicle speed detection, deep learning, thermal infrared image

中图分类号: