Abstract: Vehicle object detection based on computer vision is an important application field. In recent years, with the great progress of deep learning in image classification, vehicle object detection algorithm combining machine vision technology with deep learning method has gradually become the research priority and hotspot in this field. This paper introduces the tasks, difficulties and current development status of vehicle detection based on machine vision technology. Several?representative convolutional neural network in deep learning is also introduced, as well as two-stage and one-stage object detection algorithms derived from these networks. In the next place, it is followed by vehicle detection?and?the relevant data sets and evaluation criteria for the detection results. The existing problems and future development direction are finally discussed.

Key words: deep learning, computer vision, vehicle detection, object detection algorithm

摘要： 车辆目标检测是基于计算机视觉的目标检测领域的一个重要应用领域，近年来随着深度学习在图像分类方面取得的巨大进展，机器视觉技术结合深度学习方法的车辆目标检测算法逐渐成为该领域的研究重点和热点。介绍了基于机器视觉的车辆目标检测的任务、难点与发展现状，以及深度学习方法中几种具有代表性的卷积神经网络模型，通过这些网络模型衍生出的two stage、one stage车辆目标检测算法和用于模型训练的相关数据集与检测效果评价标准，对其存在的问题及未来可能的发展方向进行了讨论。

关键词: 深度学习, 计算机视觉, 车辆检测, 目标检测算法