Asphalt pavement macrotexture reconstruction from monocular image based on deep convolutional neural network

Abstract

Pavement macrotexture is one of the major factors affecting pavement functions, and it is meaningful to reconstruct the pavement macrotexture rapidly and accurately for pavement life cycle performance and quality evaluation. To reconstruct pavement macrotexture from monocular image, a novel method was developed based on a deep convolutional neural network (CNN). First, the red-greenblue (RGB) images and depth maps (RGB-D) of pavement texture were acquired by smartphone and laser texture scanner, respectively, from various asphalt mixture slab specimens fabricated in the laboratory, and the pavement texture RGB-D dataset was established from scratch. Then, an encoder-decoder CNN architecture was proposed based on residual network-101, and different training strategies were discussed for model optimization. Finally, the precision of the CNN and the three-dimensional characteristics of the reconstructed macrotexture were analyzed. The results show that the established RGB-D dataset can be used for training directly, and the established CNN architecture is plausible and effective. The mean texture depth and f 8mac of the reconstructed macrotexture both correlate with the benchmarks significantly, and the correlation coefficients are 0.88 and 0.96, respectively. It could be concluded that the proposed CNN can reconstruct the macrotexture from monocular RGB images precisely, and the reconstructed macrotexture could be further used for pavement macrotexture evaluation.

Hybrid semantic segmentation for tunnel lining cracks based on Swin Transformer and convolutional neural network

“…Recently, deep learning has also been gradually adopted to solve challenging problems in the field of infrastructure (Martins et al., 2020; Rafiei & Adeli., 2016, 2017a). Among them, the tunnel lining crack recognition algorithm based on deep learning mainly includes image classification algorithm, target detection algorithm, and semantic segmentation algorithm (Dong et al., 2022; Zheng et al., 2022).…”

“…Recently, deep learning has also been gradually adopted to solve challenging problems in the field of infrastructure (Martins et al, 2020;Rafiei & Adeli., 2016. Among them, the tunnel lining crack recognition algorithm based on deep learning mainly includes image classification algorithm, target detection algorithm, and semantic segmentation algorithm (Dong et al, 2022;Zheng et al, 2022). Image classification algorithm, such as (Visual Geometry Group, VGG) (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al, 2015), and ResNet (He et al, 2016), are often used to classify the types and severity of structural surface crack.…”

Regeneration of pavement surface textures using M‐sigmoid‐normalized generative adversarial networks

“…Pavement surface textures are known to perform a key role in determining pavement performances such as water drainage (Bawono et al., 2019), noise pollution (Tian et al., 2014), and skid resistance (Woodward et al., 2016). In this regard, numerous studies have attempted to characterize and reconstruct pavement surface textures (Dong et al., 2022; Tong et al., 2018), which are also the main focus of this study.…”

Visual–auditory learning network for construction equipment action detection

“…Computer vision enables the retrieval of meaningful information by learning visual patterns from images or videos, so various techniques have been developed for construction monitoring such as structural health monitoring and site management (Amezquita‐Sanchez & Adeli, 2019; Amezquita‐Sanchez et al., 2018; Li et al., 2017; Oh et al., 2017; Perez‐Ramirez et al., 2019). In particular, a Convolutional‐Neural‐Network (CNN)‐based computer vision model has been used to automatically detect and classify objects in an image (Choi et al., 2022; Dong et al., 2022). For example, the CNN model has been used to automatically and accurately find structural defects that are difficult to observe with the human eye (Pan & Zhang, 2021; Wang et al., 2022; Zhang & Yuen, 2021) and ensure site safety by checking workers’ helmets and informing a safe distance from construction equipment (Bang et al., 2021; Shen et al., 2020; Yan et al., 2020).…”