Single-camera-based sand volume estimation of an excavator bucket

Abstract

For intelligent support of consruction site, it is needed to estimate the workload of excavator bucket. But, previous studies are not practical by the reason of non-real-time processing or implementation cost. In this paper, a novel method, which use only a single camera and image processing technique to estimate the workload of excavator bucket, is addressed based on the assumption of actual bucket size, uniformity of sand, and geometric model for the shape of excavator bucket and the shape of accumulated sand in the bucket. For the ease of analysis, the state of bucket was divided into three states, Under-Struck state, Struck state, and Heaped state, depending on the amount of sand accumulation. Specially, Heaped state was also divided into Sharply-Heaped state and Smoothly-Heaped state depending on the relative height of peak point of the sand pyramid in the view of photographed image. By finding the positions of bucket corner points, highest vertex of the sand pyramid and uppermost edge point of the sand region in photographed image, various geometric parameters are found by using mathematical modeling. Hereafter, the volume of sand in the bucket is estimated by using the ratio between the length of the actual bucket and the length of the bucket in the photographed image. Finally, the workload of the excavator bucket represented by the mass is obtained by multiplying the pre-defined density of sand. Experimental results show that the accuracy of the proposed method is 93.7% on average.