Evidential transformer for pavement distress segmentation

Abstract

Distress segmentation assigns each pixel of a pavement image to one distress class or background, which provides a simplified representation for distress detection and measurement. Even though remarkably benefiting from deep learning, distress segmentation still faces the problems of poor calibration and multimodel fusion. This study has proposed a deep neural network by combining the Dempster–Shafer theory (DST) and a transformer network for pavement distress segmentation. The network, called the evidential segmentation transformer, uses its transformer backbone to obtain pixel‐wise features from input images. The features are then converted into pixel‐wise mass functions by a DST‐based evidence layer. The pixel‐wise masses are utilized for performing distress segmentation based on the pignistic criterion. The proposed network is iteratively trained by a new learning strategy, which represents uncertain information of ambiguous pixels by mass functions. In addition, an evidential fusion strategy is proposed to fuse heterogeneous transformers with different distress classes. Experiments using three public data sets (Pavementscape, Crack500, and CrackDataset) show that the proposed networks achieve state‐of‐the‐art accuracy and calibration on distress segmentation, which allows for measuring the distress shapes more accurately and stably. The proposed fusion strategy combines heterogeneous transformers while remaining a performance not less than those of the individual networks on their respective data sets. Thus, the fusion strategy makes it possible to use the existing networks to build a more general and accurate one for distress segmentation.

Enhancing point cloud semantic segmentation in the data‐scarce domain of industrial plants through synthetic data

“…The as‐is conditions of the built environment must be captured in the field first to provide the necessary data basis for approaches associated with scan‐to‐BIM. Such data acquisition is preferably performed in 3D, using laser scanning or photogrammetry (Li et al., 2022), during the construction phase (Chern et al., 2023; Z. Wang et al., 2022) or in the context of existing projects (Tong et al., 2023; Wu et al., 2022; Zheng et al., 2022). This reality capture results in millions of points representing the object surfaces visible to the sensor in point clouds that can be very precise but are characterized by a few major shortcomings and cannot be directly used for further activities such as redesigning.…”

AI‐enabled airport runway pavement distress detection using dashcam imagery

“…Chen & He, 2022;Cheng et al, 2018;Dung & Anh, 2019;Fan et al, 2018;X. Wang & Hu, 2017;Yang et al, 2018) and transformers (Tong et al, 2023). Furthermore, recent advancements, such as spatiotemporal matching for tracking evolution over time (N. , crossscene transfer learning for enhanced adaptability (Y. , pixel-level multi-distress detection for precision (A.…”

A method of concrete damage detection and localization based on weakly supervised learning

“…This offers higher precision than previous semantic segmentation algorithms based on CNN and transformers. Tong et al (2023) proposed a Dempster Shafer theory (DST) and a transformer network for pavement distress segmentation and developed an evidence-fusion strategy to integrate heterogeneous transformers of different damage categories, enhancing the universality and accuracy of distress segmentation. Although pixel-level damage detection techniques based on semantic or instance segmentation algorithms can accurately depict the exact location and shape of the damage, they incur high manual labeling costs owing to the incorporation of the pixel-by-pixel labeling approach.…”