Pavement crack measurement based on aerial 3D reconstruction and learning-based segmentation method

Abstract

Rapid inspection of urban road cracks is vital to maintain traffic smoothness and ensure traffic safety. A rapid pavement crack inspection method using low-altitude aerial images captured by the unmanned aerial system (UAS) and deep-learning aided 3D reconstruction method, learning-based object segmentation algorithm is proposed to measure road cracks automatically. The contributions include: (1) An efficient 3D reconstruction method for low-altitude aerial images captured by UAS is proposed, which applies an instance segmentation network to segment road targets from raw images with complex backgrounds first and then perform structure from motion (SFM) to reconstruct a large-scale road orthophoto from a large number of aerial images. (2) To detect cracks from the reconstructed large-size road orthophoto, the sliding window algorithm and U-Net model optimized with transformer structure are used to automatically identify and segment the cracks from the orthophoto at a pixel level. Then the connected domain feature analysis method is used to measure the road crack length. The proposed method is applied to detect road cracks in a 1.5km2 area of a city. The results show that the proposed method can effectively and accurately detect cracks and measure the length of cracks in the 6.2km-long road, which proves the practicality of the proposed method.

AIR-CNN: a lightweight automatic image rectification CNN used for barrel distortion

“…Wide-angel lenses have the advantages of large imaging angles and wide range, becoming more and more popular with the rapid development of research in automatic drive [1], video surveillance [2], and unmanned aerial vehicles [3]. However, the physical structure of the wide-angle lens determines that the magnification at the edge of its field of view is lower than that at the central part, forming the barrel distortion.…”

“…(x c , y c ) is the center of the camera distortion model and usually the center of the image. r is the Euclidean distance of the pixel point from the center of the distortion model (x c , y c ) as shown in the (2), and L(r) is the magnification function as shown in the(3)…”