A Novel Adaptive Pixels Segmentation Algorithm for Pavement Crack Detection

Abstract

<p>Cracks considerably reduce the life span of pavement surfaces. Currently, there is a need for the development of robust automated distress evaluation systems that comprise a low-cost crack detection method for performing fast and cost-effective roadway health monitoring practices. Most of the current methods are costly and have labor-intensive learning processes, so they are not suitable for small local-level projects with limited resources or are only usable for specific pavement types.</p> <p>This paper proposes a new method that uses an improved version of the weighted neighborhood pixels segmentation algorithm to detect cracks in 2-D pavement images. This method uses the Gaussian cumulative density function as the adaptive threshold to overcome the drawback of fixed thresholds in noisy environments. The proposed algorithm was tested on 300 images containing a wide range of noise representative of different noise conditions. This method proved to be time and cost-efficient as it took less than 3.15 seconds per 320 × 480 pixels image for a Xeon (R) 3.70 GHz CPU processor to determine the detection results. This makes the model a perfect choice for county-level pavement maintenance projects requiring cost-effective pavement crack detection systems. The validation results were promising for the detection of low to severe-level cracks (Accuracy = 97.3%, Precision = 79.21%, Recall= 89.18% and F<sub>1</sub> score = 83.9%).</p>

Effect of Spraying Some Nano-Fertilizers and Their Combinations on the Growth and Yield of Fenugreek (Trigonella foenum-graecum L.)

“…The fertilizers and nano-stimulators whose components are shown in Table (1) were sprayed in the early morning at an average of 400 L.ha-1. Three sprays were conducted on the plants with the same concentrations, the first when the plant reached the physiological age of 8-10 leaves, and the second and third sprays, respectively, with a difference of two weeks between them [13],The treatments that included all the expected combinations in the experiment were distributed in three replications. The data of growth traits, yield and its components were analyzed according to the analysis of variance table and the comparison between the means according to the least significant difference test at the probability level of 0.05 [14], The ready-made statistical program GenStat v.12 was used to analyze the data according to the method used by [15].…”

Efficient Crack Severity Level Classification Using Bilayer Detection for Building Structures

“…The precision, true positive rate, F score and accuracy are measured by using the expressions given in Eqs. ( 14)- (17).…”

“…Segmentation algorithm based on weighted neighborhood pixels with Gaussian cumulative density function as adaptive threshold [17], crack detection algorithm using the parabolic property on the first derivative of pixel values with SVM (Single Vector Machine) [18] and wavelet transform with Finite Element model [19] are used for identification of defects. The efficiency of these crack detection techniques depend on the quality of the input image and the lighting conditions and the complex backgrounds.…”

Automated Detection and Classification of Pavement Distresses using 3D Pavement Surface Images and Deep Learning

“…Filtering-based algorithms have been implemented to detect cracks that respond strongly to predesigned filters ( 8 ). Segmentation-based methods have divided images into small blocks and conducted detection analyses at the block level ( 9 , 10 ). However, segmentation-based methods are also not resilient to noise or illumination conditions and, since their algorithms only consider block intensity and not the relationship between pixels, pixel-level crack detection via such methods is not feasible.…”