摘要
目的在传统车辆目标检测问题中,需要针对不同图像场景选择适合的特征。为此提出一种基于快速区域卷积神经网络(Fast R-CNN)的场景图像车辆目标发现方法,避免传统车辆目标检测问题中需要设计手工特征的问题。方法该方法基于深度学习卷积神经网络思想。首先使用待检测车辆图像定义视觉任务。利用选择性搜索算法获得样本图像的候选区域,将候选区域坐标与视觉任务示例图像一起输入网络学习。示例图像经过深度卷积神经网络中的卷积层,池化层计算,最终得到深度卷积特征。在输入时没有规定示例图像的规格,此时得到的卷积特征规格不定。然后,基于Fast R-CNN网络结构,通过感兴趣区域池化层规格化特征,最后将特征输入不同的全连接分支,并行回归计算特征分类,以及检测框坐标值。经过多次迭代训练,最后得到与指定视觉任务强相关的目标检测模型,具有训练好的权重参数。在新的场景图像中,可以通过该目标检测模型检测给定类型的车辆目标。结果首先确定视觉任务包含公交车,小汽车两类,背景场景是城市道路。利用与视觉任务强相关的测试样本集对目标检测模型进行测试,实验表明,当测试样本场景与视觉任务相关度越高,且样本中车辆目标的形变越小,得到的车辆目标检测模型对车辆目标检测具有良好的检测效果。结论本文提出的车辆目标检测方法,利用卷积神经网络提取卷积特征代替传统手工特征提取过程,通过Fast R-CNN对由示例图像组成定义的视觉任务训练得到了效果良好的车辆目标检测模型。该模型可以对与视觉任务强相关新场景图像进行效果良好的车辆目标检测。本文结合深度学习卷积神经网络思想,利用卷积特征替代传统手工特征,避免了传统检测问题中特征选择问题。深层卷积特征具有更好的表达能力。基于Fast R-CNN网络,最�
Objective The traditional vehicle target detection problem is typically divided into two steps： the first step is generating assumptions, that is, the image may exist in the vehicle target, thus reducing the need to calculate the area ; the second step is verifying the hypothesis, that is, testing to verify whether there is a vehicle target in the image. In the first step, different features must be designed for different scenes. Among the features commonly used in vehicle detection problems are symmetry, color, shadows, corners, edges, textures, and lights. In the second step, verifying the hypothesis is typically based on the template method or on the appearance of the characteristics of the method. In addition to the above basic features, HOG, Harris, SIFT, and other manual features are also typically used. Finally, the test results are obtained through the support vector machine and other classifiers that classify the feature matrix. The whole process appears to be very detrimental to the generalization of detection problems; thus, it is necessaDT to select suitable characteristics for the case of unreasonable samples. This paper proposes a vehicle detection method based on Fast R-CNN, which can find vehicle objects in scene images. Method The method is based on the idea of deep learning convolution neural network. First, define the visual task using the vehicle image to be detected. The candidate region of the sample image is obtained by the selective search algorithm, and the candidate region coordinates are inputted to the network learning together with the visual task sample image. The sample image is calculated by the convolution layer and the pool layer in the deep convolution neu- ral network. Finally, the deep convolution feature is obtained. The specifications of the sample image are not specified at the time of input, and the convolution characteristics obtained at this time are variable. Subsequently, the feature is nor-malized by the pooling region of the region of interest based on the Fast R-C
出处
《中国图象图形学报》
CSCD
北大核心
2017年第5期671-677,共7页
Journal of Image and Graphics
基金
国家自然科学基金项目(91120009)~~
关键词
快速区域卷积神经网络
深度学习
车辆
视觉任务
目标检测
fast region convolutional neural network （Fast R-CNN）
deep learning
vehicle
vision tasks
object detection
