为了提高利用图象信息对沥青路面破损类型和程度识别的准确性和效率,提出了一种可减少沥青路面破损图象识别计算量的以图象分割子块模式识别结果为基础的路面破损图象特征提取方法.该方法将路面图象等分为64×64像素的子块图象,并用灰度方差值描述子块图象特征.设计了基于BP神经网络的子块图象模式分类器,利用子块图象模式分类结果所组成的矩阵作为路面破损图象分割结果.通过对典型路面破损类型的识别试验,证明了该方法的有效性,将路面破损图象子块分布特征作为路面破损图象的整体特征可以获得较好地路面破损分类识别效果.

In order to improve the aceuraey and efficieney to identify the aspha1t pavement surface distress by the image information a method of asphalt pavement surface image feature representation 15 put forward，whiceh may reduce calculation of pavement surface distress image classification. A pavement surface image 15 divided into 64X64 pixels sub-images and the intensity variances are used to represent the sub-images feature.Meanwhile，the sub-image pattern classifier 15 designed based on BP artificial neural network，all of the sub-images pattern classifying results are arra”damatrix and the pavement surface distress image segmentation 15 represented by this matrix By the experiment to identify the typical surface distress of asphalt pavement，the conelusions are as follows:(a)the average value and a minimum value of intensity variances of the image segmentation are input to BP artificial neural network，50 that the models of distress sub-images can be identified accurately.(b)the counts of horizontal and vertical projection of the distress sub-images models，sum of the distress sub-images，and convinced coefficient of the distress sub-images models may be used to deseript the main features of different the pavement surface distress，(e)the distributing features of the pavement surface distress image segmentation are used to represent a integration feature of the pavement distress image，50 that a good result for identifying Pavement surface distress may be obtained.