一种级联式神经网络框架的路标识别方法研究

Research on road sign recognition method based on a cascaded neural network framework

为了提升无人驾驶汽车对于外界环境感知的能力,本文提出了一种级联式神经网络框架对虚拟环境中的路标进行检测与分类。该框架将添加了辅助结构的全卷积神经网络与改进后的经典LeNet-5网络进行组合,在处理所提取出的路标区域边缘不平整以及产生杂项问题上使用传统的腐蚀膨胀开运算图像处理算子进行优化和解决,实现虚拟道路图像中雨雪等多种情况下的多类路标进行定位与识别。通过与经典的不变矩特征、ORB全局特征提取方法,以及YOLO,SSD人工智能方法对比试验表明,本文所提出方法具备检测准确度高,运算速度快的优势。

Automobile assisted driving system can not only reduce the driver′s mental stress during drivingdriving,but also greatly reduce the probability of traffic accidents.In order to improve the ability of driverless vehicles to perceive the external environment,this paper proposes a cascaded neural network framework to detect and classify road signs in virtual environments.The framework combines a full convolutional neural network with an auxiliary structure and a modified classic LeNet-5 network to perform traditional image processing using corrosion processing on the edges of the extracted road sign areas and the generation of miscellaneous problems.The operator is optimized and solved to realize the positioning and recognition of multiple types of road signs in various situations such as rain and snow in virtual road images.Compared with the classical invariant moment feature,ORB global feature extraction method,and YOLO,SSD artificial intelligence method,the proposed method has the advantages of high detection accuracy and fast calculation speed.