Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement

Abstract

Automated pavement crack detection and measurement are important road issues. Agencies have to guarantee the improvement of road safety. Conventional crack detection and measurement algorithms can be extremely time-consuming and low efficiency. Therefore, recently, innovative algorithms have received increased attention from researchers. In this paper, we propose an ensemble of convolutional neural networks (without a pooling layer) based on probability fusion for automated pavement crack detection and measurement. Specifically, an ensemble of convolutional neural networks was employed to identify the structure of small cracks with raw images. Secondly, outputs of the individual convolutional neural network model for the ensemble were averaged to produce the final crack probability value of each pixel, which can obtain a predicted probability map. Finally, the predicted morphological features of the cracks were measured by using the skeleton extraction algorithm. To validate the proposed method, some experiments were performed on two public crack databases (CFD and AigleRN) and the results of the different state-of-theart methods were compared. To evaluate the efficiency of crack detection methods, three parameters were considered: precision (Pr), recall (Re) and F1 score (F1). For the two public databases of pavement images, the proposed method obtained the highest values of the three evaluation parameters: for the CFD database, Pr = 0.9552, Re = 0.9521 and F1 = 0.9533 (which reach values up to 0.5175 higher than the values obtained on the same database with the other methods), for the AigleRN database, Pr = 0.9302, Re = 0.9166 and F1 = 0.9238 (which reach values up to 0.7313 higher than the values obtained on the same database with the other methods). The experimental results show that the proposed method outperforms the other methods. For crack measurement, the crack length and width can be measure based on different crack types (complex, common, thin, and intersecting cracks.). The results show that the proposed algorithm can be effectively applied for crack measurement.

Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture

“…For the proposed U-HDN, the transitional areas between non-crack and crack pixels were considered before computing , and . Considering the subjective manual labels for ground truth, the transitional areas (2 pixels distance) between crack and non-crack pixels are accepted in these papers [ 41 , 56 , 57 , 79 , 80 ]. Therefore, 2 pixels of distance is accepted in this project.…”

“…The small structured pixel images (27 × 27 pixels) was input into the neural network, which may generate overload for the computer memory. Ensemble network is proposed to perform crack detection and measure pavement cracks generated in road pavement [ 57 ]. Maeda et al on [ 58 ] adopted object detection network architecture to detect crack images, and the network architecture can be transferred to a smartphone to perform road crack detection.…”

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

“…Soloviev et al [115], Li et al [116], Tong et al [117], and Fan et al [118] demonstrated the use of DCNNs to detect and recognize cracks as defects with quantifiable properties in applications for crack detection on pavement surfaces (e.g., crack length and size). Fan et al [119] proposed a CNN-based multi-label classifier by improving the positive-to-negative ratio of samples.…”

Akıllı Şehirler için Özellik Çıkarımı ve Makine Öğrenmesi Tabanlı Asfalt Durum İzleme Yaklaşımı

“…Fan et al (Fan et al, 2020) Bu çalışmada, otomatik asfalt tespiti ve ölçümü için olasılık füzyonuna dayanan bir konvülüsyonel sinir ağı yöntemi önerilmiştir. Çalışmada 2 farklı veri seti kullanılmış olup, kullanılan veri setleri üzerinde ortalama %94 başarı sağlanmıştır.…”