A Method to Improve the Accuracy of Pavement Crack Identification by Combining a Semantic Segmentation and Edge Detection Model

Abstract

In recent years, deep learning-based detection methods have been applied to pavement crack detection. In practical applications, surface cracks are divided into inner and edge regions for pavements with rough surfaces and complex environments. This creates difficulties in the image detection task. This paper is inspired by the U-Net semantic segmentation network and holistically nested edge detection network. A side-output part is added to the U-Net decoder that performs edge extraction and deep supervision. A network model combining two tasks that can output the semantic segmentation results of the crack image and the edge detection results of different scales is proposed. The model can be used for other tasks that need both semantic segmentation and edge detection. Finally, the segmentation and edge images are fused using different methods to improve the crack detection accuracy. The experimental results show that mean intersection over union reaches 69.32 on our dataset and 61.05 on another pavement dataset group that did not participate in training. Our model is better than other detection methods based on deep learning. The proposed method can increase the MIoU value by up to 5.55 and increase the MPA value by up to 10.41 when compared to previous semantic segmentation models.

Estimation of Degradation Degree in Road Infrastructure Based on Multi-Modal ABN Using Contrastive Learning

“…The main purpose of those methods is the streamlining inspection operations to detect damages in infrastructures for preventing serious accidents. In previous studies [ 5 , 6 , 7 , 24 , 25 , 26 , 27 , 28 , 29 ], models were built to detect distresses in the taken image. In particular, the studies [ 7 , 25 , 28 , 29 ] attempted to visualize the corresponding regions of cracks in distress images as the segmentation task.…”

“…In previous studies [ 5 , 6 , 7 , 24 , 25 , 26 , 27 , 28 , 29 ], models were built to detect distresses in the taken image. In particular, the studies [ 7 , 25 , 28 , 29 ] attempted to visualize the corresponding regions of cracks in distress images as the segmentation task. The studies [ 5 , 6 , 7 , 24 , 25 , 26 , 27 , 28 , 29 ] achieved their tasks by extracting the features of distress images by introducing CNNs.…”

“…In particular, the studies [ 7 , 25 , 28 , 29 ] attempted to visualize the corresponding regions of cracks in distress images as the segmentation task. The studies [ 5 , 6 , 7 , 24 , 25 , 26 , 27 , 28 , 29 ] achieved their tasks by extracting the features of distress images by introducing CNNs. Other previous studies [ 5 , 8 , 9 , 10 , 30 ] target the classification of distresses (e.g., crack, efflorescence or corrosion) that have occurred in infrastructures.…”

“…The above studies [ 5 , 6 , 7 , 8 , 9 , 10 , 24 , 25 , 26 , 27 , 28 , 29 , 30 ] constructed supervised learning models by using the label information of images as ground truth. For general object recognition in the field of computer vision, the performance improvement is rapid, and the contribution of large image datasets, such as ImageNet [ 13 ] and Microsoft common object in context [ 31 ], has been significant.…”

Scale-Adaptive Deep Matching Network for Constrained Image Splicing Detection and Localization

“…In recent years, deep learning algorithms [14][15][16] represented by convolutional neural networks [17][18][19], recurrent neural networks [20] and generative adversarial networks have been widely used in many fields such as image classification [21,22], object detection [23], semantic segmentation [24,25], image retrieval [26], scene understanding [27], etc. and have made a leap forward compared with traditional methods.…”