Recognition of road cracks based on multi-scale Retinex fused with wavelet transform

Abstract

Cracks are the main diseases of roads and potential threats to road safety. The detection and repair of cracks is the focus of intelligent transportation system research. However, the performance of automatic crack detection is often not good enough due to the uneven illumination, low contrast between the crack and the surrounding pavement and the possible presence of shadows similar in intensity to the crack. In this paper, an improved multi-scale Retinex algorithm is proposed to enhance the crack image. The wavelet transform is integrated into the traditional multi-scale Retinex algorithm to avoid the halo generated by the Retinex algorithm, thereby reducing the image distortion. Meanwhile, the multi-scale Retinex algorithm can make up for the lack of useful information lost by wavelet transform, so the combination of the two can obtain better crack enhancement effect. In addition, the preprocessing of shadow removal is performed before crack enhancement, which effectively eliminates the interference of high-intensity shadows. Through the comparison of objective performance indicators, the newly proposed algorithm can better highlight the crack information. The method proposed in this paper can effectively realize the functions of shadow removal and crack enhancement, so that the recognition accuracy of the overall detection system reaches 95.8%, indicating that the algorithm has high research significance and engineering application value.