Efficient Road Crack Detection Based on an Adaptive Pixel-Level Segmentation Algorithm

Abstract

Cracks considerably reduce the life span of pavement surfaces. Currently, there is a need for the development of robust automated distress evaluation systems that comprise a low-cost crack detection method for performing fast and cost-effective roadway health monitoring practices. Most of the current methods are costly and have labor-intensive learning processes, so they are not suitable for small local-level projects with limited resources or are only usable for specific pavement types. This paper proposes a new method that uses an adapted version of the weighted neighborhood pixels segmentation algorithm to detect cracks in 2-D pavement images. The method uses the Gaussian cumulative density function (CDF) as the adaptive threshold to overcome the drawback of fixed thresholds in noisy environments. The proposed algorithm was tested on 300 images containing a wide range of noise representative of various pavement noise conditions. The method proved to be time and cost-efficient as it took less than 3.15 s per 320 × 480 pixels image for a Xeon (R) 3.70 GHz CPU processor to generate the detection results. This makes the proposed method a perfect choice for county-level pavement maintenance projects requiring cost-effective pavement crack detection systems. The validation results were promising for the detection of medium to severe-level cracks (precision = 79.21%, recall = 89.18%, and F1 score = 83.90%).

Road damage detection and classification using deep neural networks

“…Image processing technology, known for its high efficiency and low cost, has seen increasing recognition accuracy with technological development, leading many researchers to employ these techniques for pavement damage detection. Traditional crack detection methods depend on manual inspection or feature extraction [3], using image segmentation techniques [4]. However, these methods encounter difficulties with model generalization and robustness in practical engineering due to the complexity of the road environment and limitations of manually designed feature extraction.…”

Crack image generation algorithm based on deep convolutional generative adversarial network

“…However, it only determines the degree of damage that cracks have, not where they are located.With the application of yolov3 for crack detection in pavements, Nie [6] et al address the issues of low accuracy and real-time weakness in the conventional road crack detection method. The experimental results can reach 88% accuracy and quick detection speed.In order to extract pavement cracks, Safaei N [7] et al proposed an adaptive version of pixel segmentation with weighted domain. Its method of obtaining adaptive thresholds using a Gaussian cumulative density function (CDF) effectively resolves the issue of a single threshold for image background noise, and the processing time is less than 4 seconds.Yang F [8] et al proposed a new network model architecture that combines feature pyramids and augmented networks to incorporate the contextual background information extracted by the network into the low-level feature layer.…”

Detection Method of Cracks in Expressway Asphalt Pavement Based on Digital Image Processing Technology

“…There are many factors in daily life that cause damage to roadways in various forms, such as cracks, pits, et cetera. That damage brings hidden dangers to people's traffic safety [3]. Therefore, timely and effective pavement damage detection has become the most important part of highway maintenance, in which crack detection of expressway asphalt pavement is a key part.…”