Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors

Wu, Hangbin; Yao, Lianbi; Xu, Zeran; Li, Yayun; Ao, Xinran; Chen, Qichao; Li, Zhengning; Meng, Bin

doi:10.1016/j.aei.2019.100936

Cited by 78 publications

(33 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To determine whether the road is defective or not defective using the watershed algorithm, the segmentation process produces an accuracy of 82% (Chung & Khan, 2019). The location of potholes is detected with mobile mapping sensors (Wu et al, 2019), detection of potholes with 2D images using Fuzzy C-mean Clustering algorithm. The segmentation of the perforated road image using the graph cut method yields an accuracy of 81.4% (Vigneshwar & Hema Kumar, 2017) for the classification of potholed roads using the Support vector machine method (Yousaf et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

A New Watershed Algorithm for Pothole Image Segmentation

Indriyani¹,

Utoyo²,

Rulaningtyas³

2021

STUD INFORM CONTROL

View full text Add to dashboard Cite

The road casualties caused by poor road conditions, especially potholed roads, amount to a high percentage of 13% per year in Asia. In order for the government to carry out repair works, they must know the surface area of the potholed road, the depth of the potholes, and the position of the potholes. In this paper, with the purpose of determining the surface area of the potholed road, segmentation was carried out first. The segmentation method used here is a new watershed algorithm. This algorithm includes six processes: smoothing, calculating the gradient value, automatic determination of minimum flooding value, combining the catchment basins, erasing the remaining watershed lines, and creating a watershed curve. The proposed algorithm is evaluated and compared with previously analysed watershed segmentation methods. This study shows that this algorithm is effective for reducing the effects of excessive segmentation. The proposed algorithm obtained a high accuracy of 95.34%, which is higher than that of the existing watershed segmentation methods.

show abstract

Section: Related Workmentioning

confidence: 99%

A New Watershed Algorithm for Pothole Image Segmentation

Indriyani¹,

Utoyo²,

Rulaningtyas³

2021

STUD INFORM CONTROL

View full text Add to dashboard Cite

show abstract

“…erefore, the focus of road maintenance is to handle potholes [10]. Rapidly and accurately detecting potholes in cement pavement is an important prerequisite for the road management department in formulating scientific and effective maintenance strategies and implementing distress treatment [6,11,12].…”

Section: Introductionmentioning

confidence: 99%

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Gao

Wang

Zhu

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Potholes are the most common form of distress on cement concrete pavements, which can compromise pavement safety and ridability. Thus, timely and accurate pothole detection is an important task in developing proper maintenance strategies and ensuring driving safety. This paper proposes a method of integrating the processing of grayscale and texture features. This method mainly combines industrial camera to realize rapid and accurate detection of pothole. Image processing techniques including texture filters, image grayscale, morphology, and extraction of the maximum connected domain are used synergistically to extract useful features from digital images. A machine learning model based on the library for support vector machine (LIBSVM) is constructed to distinguish potholes from longitudinal cracks, transverse cracks, and complex cracks. The method is validated using data collected from agricultural and pastoral areas of Inner Mongolia, China. The comprehensive experiments for recognition of potholes show that the recall, precision, and F1-Score achieved are 100%, 97.4%, and 98.7%, respectively. In addition, the overlap rate between the extracted pothole region and the original image is estimated. Images with an overlap rate greater than 90% accounted for 76.8% of the total image, and images with an overlap rate greater than 80% accounted for 94% of the total image. A comparison discloses that the proposed approach is superior to the existing method not only from the perspective of the accuracy of pothole detection but also from the perspective of the segmentation effect and processing efficiency.

show abstract

“…On the other hand, 2D image analysis-based road damage detection methods can be grouped into two categories: computer vision-based [6], [7], [12]- [15] and machine learningbased [16]- [19]. The former typically pre-processes a 2D image, i.e., an RGB/gray-scale image or a depth/disparity map, using some image processing techniques, e.g., various image filters, to reduce image noise and enhance road damage outline [12], [13].…”

mentioning

confidence: 99%

“…In [18], the authors utilized thermal images to train a residual network (ResNet) [20] for road image classification. Furthermore, Wu et al [19] developed a robust road image segmentation system based on DeepLabv3+ [21], which employs atrous convolution along with upsampled filters to extract dense feature maps and to capture long-range context.…”

mentioning

confidence: 99%

Road Damage Detection Based on Unsupervised Disparity Map Segmentation

Fan

Liu

2020

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper presents a novel road damage detection algorithm based on unsupervised disparity map segmentation. Firstly, a disparity map is transformed by minimizing an energy function with respect to stereo rig roll angle and road disparity projection model. Instead of solving this energy minimization problem using non-linear optimization techniques, we directly find its numerical solution. The transformed disparity map is then segmented using Otus's thresholding method, and the damaged road areas can be extracted. The proposed algorithm requires no parameters when detecting road damage. The experimental results illustrate that our proposed algorithm performs both accurately and efficiently. The pixel-level road damage detection accuracy is approximately 97.56%.Index Terms-road damage detection, disparity map segmentation, stereo rig roll angle, road disparity projection model, numerical solution.

show abstract

Road pothole extraction and safety evaluation by integration of point cloud and images derived from mobile mapping sensors

Cited by 78 publications

References 35 publications

A New Watershed Algorithm for Pothole Image Segmentation

A New Watershed Algorithm for Pothole Image Segmentation

Detection and Segmentation of Cement Concrete Pavement Pothole Based on Image Processing Technology

Road Damage Detection Based on Unsupervised Disparity Map Segmentation

Contact Info

Product

Resources

About