Estimation of construction site elevations using drone-based orthoimagery and deep learning

Using deep learning to recover depth information from a single image has been studied in many situations, but there are no published articles related to the determination of construction site elevations. This paper presents the research results of developing and testing a deep learning model for estimating construction site elevations using a drone-based orthoimage. The proposed method includes an orthoimage-based convolutional neural network (CNN) encoder, an elevation map CNN decoder, and an overlapping orthoimage disassembling and elevation map assembling algorithm. In the convolutional encoder-decoder network model, the max pooling and up-sampling layers link the orthoimage pixel and elevation map pixel in the same coordinate. The experiment data sets are eight orthoimage and elevation map pairs (1,536×1,536 pixels), which are cropped into 64,800 patch pairs (128×128 pixels). Experimental results indicated that the 128×128-pixel patch had the best model prediction performance. After 100 training epochs, 21.22% of the selected 2,304 points from the testing data set were exactly matched with their ground truth elevation values; and 52.43% points were accurately matched in ±5 cm and 66.15% points in ±10 cm, less than 10% points exceeded ±25 cm. This research project advanced drone applications in construction, evaluated CNNs' effectiveness in site surveying, and strengthened CNNs to work with large-scale construction site images.