学术论文

      基于多传感器融合的前方车辆识别方法研究

      Recognition of front vehicle based on multi-sensor fusion

      摘要:
      为提高汽车安全辅助驾驶系统对前方车辆识别的准确性和实时性,提出了一种基于摄像头和毫米波雷达信息融合的前方车辆检测方法.首先将毫米波雷达和摄像头进行联合标定,并确定两个传感器坐标系之间的相互转化关系,对毫米波雷达数据进行预处理快速分割图像,以获得前方车辆识别的感兴趣区域;然后采用自适应阈值对感兴趣区域内的图像进行二值化处理以获得车辆底部阴影信息,利用边缘检测和霍夫变换得到车辆上下边界的位置信息;通过底部阴影和上下边界信息获得车辆识别的高度与宽度,最后根据车辆对称性特征建立识别窗口.试验验证表明,该方法前方车辆检测准确率为90.2%,单帧图像的处理速度为32 ms,能够满足智能汽车应用中的实时性和准确性的要求.
      Abstract:
      In order to improve the accuracy and real-time performance of vehicle safety driving system, a vehicle detection method based on camera and millimeter wave radar information fusion is proposed.Firstly, joint calibration of the millimeter wave radar and camera are conducted.Mutual transformation relationship between two sensors coordinate systems is determined.The millimeter wave radar data is preprocessed to segment the image to obtain the interested region of the vehicle in front.Then the adaptive threshold is used to binarize the image in the interested region to obtain the shadow information of the vehicle bottom.The position information of the upper and lower boundary of the vehicle is obtained by edge detection and Hough transform.The height and width of vehicle are identified by bottom shadow and upper and lower boundary information.Finally, recognition window is established according to vehicle symmetry characteristic.Experimental results show that the detection accuracy of the proposed method is 90.2%, and the processing speed of single frame image is 32 ms, which can meet the requirements of real-time and accuracy of intelligent vehicle applications.
      Author: WANG Zhan-gu SHAO Jin-ju GAO Song SUN Liang YU Jie TAN De-rong
      作者单位: 山东理工大学交通与车辆工程学院,山东淄博,255049
      年,卷(期): 2017, 42(2)
      分类号: TP212.9
      在线出版日期: 2017年5月16日
      基金项目: 国家重点研发计划项目,山东省自然科学基金