Research on uniformity detection method of asphalt mixture during paving process based on digital image technology

Focused on the problem of continuous real-time monitoring of aggregate distribution uniformity during asphalt pavement paving process, an asphalt mixture identification and segmentation method based on image processing technology was developed and a uniformity evaluation method based on static moment theory was proposed. Firstly, original true colour images were converted to binary images. And then the watershed segmentation method based on extended-maxima transform was developed, which could significantly eliminate the over-segmentation of particles. Seventy images of particles were tested, and experimental results showed that the segmentation was satisfactory by the improved algorithm; the accuracy of segmentation was as high as 98%. Considering the influence of aggregate size and distribution position on the uniformity, the computational model based on four-side static moment theory was established, and then the uniformity judging criteria was determined by analyzing 1,000 randomly on-site collected images. The remaining 85 images were used to verify the plausibility of the uniformity judging criterion. The results indicated that when the value of UA is greater than or equal to 0.91, loose asphalt mixtures could be considered as uniform, vice versa.