Fast Recognition Method of Traffic Signs Based on Fusion of Visual Image and Laser Point Cloud
Traffic signs play an important role and significance in vehicle traffic.However,in intelligent traffic,the recognition of traffic signs has poor performance due to the sign feature extraction,which leads to the features of low recognition rate and long rec-ognition time.Therefore,a new rapid recognition method of traffic signs based on the fusion of visual image and laser point cloud is proposed.Bilateral filtering method is used to preprocess the original laser point cloud data.The location ranging values of laser point cloud in target space are obtained by normalized processing.The location of the target image is obtained by the ranging value,the traffic sign visual image performs normalization processing,the k-means clustering algorithm is introduced to process the image by bi-nary clustering,the region of interest(ROI)of the image is cut by using the making cutting template,and the depth features of the traffic sign image are extracted.Combined with the convolutional neural network,the features after the second filtering are re-calibra-ted.Finally,the convolutional neural network model is used to realize the rapid recognition of traffic signs.The experimental compar-ison shows that the proposed method has a good feature extraction effect for all types of traffic signs,and the recognition rate reaches 89.74％,the recognition time is only 13.1 s,and the highest recognition time is only 15.1 s under the interference conditions,which verifies that this method can quickly and accurately identify all types of traffic signs.
visual imagelaser point cloudtraffic signquick identificationk-means clustering algorithmconvolutional neural network
万方数据
维普
