Yunyao Liu

Pavement crack detection is essential for proactive road maintenance; however, existing deep learning methods are heavily reliant on large annotated datasets and GPU computing resources, which limits their deployment in resource‐constrained environments. To address this challenge, this study proposes a novel method called Dynamic Sliding Window and Weighted Deep Forest (DSW‐WDF) for efficient and accurate crack detection. The method integrates three core components: (1) Non‐local Means (NLM) filtering for preprocessing, which suppresses noise and uneven illumination while preserving crack edges; (2) a Window Change Value (WCV)‐driven dynamic sliding window that adaptively captures multi‐scale crack features, including ultra‐fine cracks measuring less than 2 mm; and (3) a weighted cascaded forest where subtree weights are optimized through cross‐validation to enhance decision reliability. Experimental results on a small‐sample dataset consisting of 3000 original images demonstrate that DSW‐WDF achieves an Intersection over Union (IoU) of 87.2%, surpassing traditional Deep Forest, ResNet50, and mainstream segmentation models such as UNet and DeepLab‐V3+. Notably, the model operates with only 710 MB of memory and achieves a real‐time inference speed of 28.5 FPS on a CPU, while reducing training time by 21% compared to traditional Deep Forest. This work validates the potential of non‐neural network ensemble models for small‐sample crack detection, offering a cost‐effective and easily deployable solution for road maintenance departments facing challenges related to data scarcity and limited computing power.

The evaluation of in-service pavements’ performance is a complex system that encompasses a variety of uncertain factors. These uncertainties include random, fuzzy, gray, and unascertained information, and their interrelationships are intricate, making comprehensive quantification unachievable. Nonetheless, current highway management organizations rely on a comprehensive indicator, namely, the Pavement Quality Index (PQI), to assess the level of pavement performance. This paper introduces a novel approach that employs blind number theory to evaluate the reliability of pavement performance test data. The proposed method aims to enhance the representativeness of PQI and is demonstrated using detection data from highway asphalt pavements in Hunan Province. The method takes into account the probability distribution characteristics of evaluation metrics and incorporates the blind number representation format of PQI. A confidence model for pavement performance evaluation is established to assess the reliability of pavement detection results. The method also integrates expert empowerment and entropy weight to consider both the subjectivity of evaluation and the objectivity of measured data. The method presented in this study has demonstrated superior performance compared to traditional evaluation index systems. This is attributed to the effective utilization of blind information to accurately characterize the discreteness of pavement performance indexes. Consequently, pavement performance can be quantitatively graded based on anticipated issues and data.