Automatic Road Crack Detection Using Random Structured Forests

TLDR

Cracks pose a growing threat to road conditions and are a key focus of intelligent transportation systems, yet automatic detection is hampered by intensity inhomogeneity, complex topology, and noise. The authors introduce CrackForest, a random structured forest framework designed to overcome these challenges in road crack detection. CrackForest employs integral channel features to represent cracks, random structured forests to detect arbitrarily complex cracks, and a novel crack descriptor to distinguish cracks from similar textures. The method is faster, easily parallelizable, and experimentally outperforms competing approaches in detection precision.

Abstract

Cracks are a growing threat to road conditions and have drawn much attention to the construction of intelligent transportation systems. However, as the key part of an intelligent transportation system, automatic road crack detection has been challenged because of the intense inhomogeneity along the cracks, the topology complexity of cracks, the inference of noises with similar texture to the cracks, and so on. In this paper, we propose CrackForest, a novel road crack detection framework based on random structured forests, to address these issues. Our contributions are shown as follows: 1) apply the integral channel features to redefine the tokens that constitute a crack and get better representation of the cracks with intensity inhomogeneity; 2) introduce random structured forests to generate a high-performance crack detector, which can identify arbitrarily complex cracks; and 3) propose a new crack descriptor to characterize cracks and discern them from noises effectively. In addition, our method is faster and easier to parallel. Experimental results prove the state-of-the-art detection precision of CrackForest compared with competing methods.