Evaluation of Image Segmentation Approaches for Pavement Distress Detection
Evaluation of pavement image segmentation algorithms is one of the important process toward establishing validity and accurate applicability of an image segmentation algorithm.Since there are a large number of papers presenting segmentation algorithms for pavement distress detection,with few studying the evaluation methods on their persormance.Different evaluation of segmentation algorithm is provided in this paper.A survey of several available evaluation methods and a new compositive evaluation criterion EVAL is provided.PE.FOM,FRAG and SD are the four most important metrics.The definitions of them are then described based on the image segmentation process.The experiment results show that these method is practical and reasonable.This study gives a scientific method for the evaluation of segmentation algorithms on pavement image.Meanwhile,it points out the problems to be solved before the segmentation algorithms could be put into use in pavement distress detection.
pavement detection image segmentation segmentation evaluation
Gang Li
School of Electronic and Control Engineering,Changan University,Xian 710064,Shaanxi,China
国际会议
太原
英文
641-644
2011-02-26（万方平台首次上网日期，不代表论文的发表时间）