Abstract: In order to study the influence of the acquisition method on the evaluation results of the digital image processing technology asphalt mixture evaluation method, a reasonable image acquisition condition was proposed. Digital image preprocessing was carried out on the AC-13 and AC20 grade type mixture images, the asphalt mixture images under different light intensity as well as images of different acquisition heights. Image uniformity was evaluated by four-sided static moment variation coefficient, and the results of variation coefficients were compared and analyzed. The research results show that the results of the static moment variation coefficient of 500 images of the AC-13 and AC25 asphalt mixture are concentrated in the range of 0 to 1.5%. The lower layer of AC-25 asphalt mixture is more prone to segregation than the upper layer of AC-13. In the case of sufficient light intensity, the uniformity evaluation result is not affected, but when the illumination is insufficient at night, the result will deviate, so it is necessary to compensate the illumination for the image acquisition. When the image acquisition height is 60cm, the aggregate particle surface ratio is consistent with the actual condition. As the height of the acquisition increases, the adhesion particles with large size in the preprocessed image increase, which affects the accuracy of uniformity evaluation.

Key words: highway engineering, digital image processing technology, asphalt mixture, segregation, image preprocessing, image acquisition method

摘要： 为了研究采集方法对数字图像处理技术沥青混合料离析评价方法评价结果的影响，提出合理的图像采集条件，通过对AC-13、AC-25级配类型混合料图像、不同光照强度下沥青混合料图像、不同采集高度图像进行数字图像预处理，采用四边静矩变异系数评价图像均匀性，并对比分析变异系数结果。研究结果表明：500张AC-13、AC-25级配类型沥青混合料图像静矩变异系数结果，主要集中于0~1.5%区间，下面层AC-25级配类型沥青混合料相对上面层AC-13更易产生离析；在光照强度充足情况下，不影响均匀性评价结果，但在夜间光照不足时结果出现偏差，需要对图像采集进行光照补偿；采集高度为60 cm时，集料颗粒面比与实际相符，随着采集高度的增加，预处理图像中大颗粒粘连颗粒增加，影响均匀性评价的准确性。

关键词: 道路工程, 数字图像处理技术, 沥青混合料, 离析, 图像预处理, 图像采集方法