摘要：

使用Fast RCNN方法进行特征提取存在耗时较长且检测准确率较低的问题。为此,结合Faster RCNN前方车辆检测模型与3种不同大小的卷积神经网络,提出一种改进的前方车辆检测方法,研究对比各方法在3种交通场景数据库上的前方车辆检测能力。实验结果表明,与深度卷积神经网络方法相比,该方法提高了车辆检测的准确性和鲁棒性,具有一定的泛化能力。

关键词: 智能车, 前方车辆, 深度卷积神经网络, 训练模型, 准确率

Abstract:

Using Fast RCNN method for feature extraction takes a long time and the detection accuracy is low,this paper proposes an improved forward vehicle detection method that combines the forward vehicle detection model based on Faster RCNN with Convolution Neural Network(CNN) of three different sizes.The forward vehicle detection ability of different methods on three traffic scene databases is researched and compared.Experimental results show that compared with the deep CNN,this method improves the accuracy and robustness of vehicle detection,and has a generalization ability.

Key words: intelligent vehicle, forward vehicle, deep Convolution Neural Network(CNN), training model, accuracy rate

中图分类号: 

• TP301.6