计算机与现代化

• 图像处理 • 上一篇    下一篇

基于深度学习的车辆检测方法

  

  1. 1.军事交通学院研究生管理大队,天津300161;2.军事交通学院军用车辆系,天津300161
  • 收稿日期:2017-03-15 出版日期:2017-08-31 发布日期:2017-09-01
  • 作者简介:王德宇(1992-),男,辽宁庄河人,军事交通学院硕士研究生,研究方向:无人驾驶,深度学习; 徐友春(1972-),男,军事交通学院军用车辆系教授,博士,研究方向:无人驾驶,人工智能; 李永 乐(1984-),男,助教,博士,研究方向:无人驾驶,人工智能; 陆峰(1993-),男,硕士研究生,研究方向:无人驾驶,传感器融合; 郑凯文(1991-),男,硕士研究生,研究方向:无人驾驶,智 能控制。
  • 基金资助:
    国家自然科学基金资助项目(91220301); 国家973计划项目(2016YFB0100903)

Vehicle Detection Based on Deep Learning

  1. 1. Postgraduate Training Bridge, Military Transportation University, Tianjin 300161, China; 
    2. Military Vehicle Department, Military Transportation University, Tianjin 300161, China
  • Received:2017-03-15 Online:2017-08-31 Published:2017-09-01

摘要:

针对一般道路行驶条件下无人驾驶汽车检测前方车辆问题,将车辆检测问题转化为图像中的目标检测,利用深度学习方法进行车辆目标检测。通过无人驾驶汽车采集真实的车辆图像数据,构建车
辆检测训练数据集,用大量实验验证检测系统的可行性。该检测系统是一个端到端的检测系统,输入为无人驾驶汽车视觉系统的图像,输出为图像中的车辆的位置及类别。

关键词: 深度学习, 车辆, 目标检测

Abstract:

Aiming at the detection problem of the vehicle in the general detection environment for selfdriving cars, the vehicle detection is transformed into the object
detection in the image, and the object detection algorithm based on deep learning is applied to the detection of the vehicle. A lot of experiments have been carried out to
verify the validity of the detection system by building the image data set of the vehicle. The detection system is an end to end detection system, only needs to input images,
which can quickly and accurately locate the position of the vehicle in the image and predict class probabilities.

Key words: deep learning, vehicle, object detection

中图分类号: