A Road Damage Identification Method Based on Scale-span Image and SVM
暂无分享,去创建一个
In order to improve the accuracy and efficiency of the pavement crack recognition,a precise fast pavement damage detection method is proposed based on scale-span images.In the image space domain,a pavement image is transformed into differently scaled images according to different thresholds firstly.Several damage identification scale images are selected to set up scale-span image model by superimposing according to different pavement damage image characteristics.At the same time,the road image cracks pattern identifier is designed based on support vector machine(SVM) "1 V m" to extract the fine cracks and thick cracks effectively.The test results show that the algorithm has greatly increased the accuracy and efficiency of the pavement cracks image recognition,The pavement damage degree and range can be also identified quickly and accurately.