Recent computer vision applications for pavement distress and condition assessment

Hakea, Ayman H. El; Fakhr, Mohamed Waleed

doi:10.1016/j.autcon.2022.104664

Cited by 29 publications

(8 citation statements)

References 128 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is already various research showing how computer vision algorithms have been developed for detecting roadside features, including guardrails, clear zones, rigid obstacles and roadside slopes. [8], but also, for pavement distress and condition assessment [9] and road network deterioration monitoring [10].…”

Section: Data Collection and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Road safety impact assessment practices and recommendations

Popova

2023

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

This article reviews the practices for conducting Road Safety Impact Assessment (RIA). An overview of current research and methodologies related to this field is presented, and various aspects of the preparation of RSIA are analysed. The DIRECTIVE OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL on road infrastructure safety management (RISM Directive) defines the procedure “road safety impact assessment” as a strategic comparative analysis of the impact of a new road or a substantial modification to the existing network on the safety performance of the road network”; The RISM Directive provides only the basic framework for conducting such analysis by just pointing out its basic elements without providing specific methodology for it. Some countries have developed their own methodologies, others not. Although the RIA is a procedure, that was included in the initial RISM Directive (2008), Bulgaria has not yet had much experience with it, nor has a developed methodology or recommendations for it. The main aim of this article is to review and analyse international experience in conducting road safety impact assessment and to present some recommendations about it for such procedures from national teams. The article draws attention to the methods and tools used in the preparation of the RIA. This includes the collection and analysis of road infrastructure and traffic data, the study of previous safety analyses, modelling and simulations of the proposed measures, and the assessment of social and economic aspects. One of the main aspects discussed in the article is the possibility of using computer models and artificial intelligence (AI) in the preparation of the RIA. AI can be applied to process large volumes of data and perform complex risk and scenario analyses. This allows practitioners to obtain more accurate and predictable results to serve as a basis for making informed road safety decisions. In conclusion, the article emphasizes the importance of preparing Road safety impact assessment and presents different practices and methodologies that can be used in this process. The use of computer models and AI can improve the efficiency and accuracy of RSIA and contribute to achieving higher standards of road safety.

show abstract

Section: Data Collection and Analysismentioning

confidence: 99%

“…These predictive models can be invaluable in identifying more efficient countermeasures and evaluating project alternatives. [9] [10]…”

Section: Data Collection and Analysismentioning

confidence: 99%

Road safety impact assessment practices and recommendations

Popova

2023

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…Tey are better than conventional ML techniques as they can automatically learn the expressive feature representation, the lexical pattern, and the sequencing pattern of a given input while generalizing the expressive data representation. Tey have demonstrated an outstanding performance in many research felds such as image processing [4], natural language processing [5], speech recognition [6], computer vision [7], human activity recognition [8][9][10][11][12], and cyber security felds [13,14]. In recent years, 1D convolutional neural networks (1D CNNs) in particular have shown an impressive performance for text classifcation [15,16].…”

Section: Limits Of Prior Atrsmentioning

confidence: 99%

MC-MLDCNN: Multichannel Multilayer Dilated Convolutional Neural Networks for Web Attack Detection

Moarref,

Sandıkkaya

2023

Security and Communication Networks

View full text Add to dashboard Cite

The explosive growth of web-based technology has led to an increase in sophisticated and complex attacks that target web applications. To protect against this growing threat, a reliable web attack detection methodology is essential. This research aims to provide a method that can detect web attacks accurately. A character-level multichannel multilayer dilated convolutional neural network (MC-MLDCNN) is proposed to identify web attacks accurately. The model receives the full text of HTTP requests as inputs. Character-level embedding is applied to embed HTTP requests to the model. Therefore, feature extraction is carried out automatically by the model, and no additional effort is required. This approach significantly simplifies the preprocessing phase. The methodology consists of multichannel dilated convolutional neural network blocks with various kernel sizes. Each channel involves several layers with exponentially increasing dilation sizes. Through the integration of multichannel and multilayer dilated convolutional neural networks, the model can efficiently capture the temporal relation and dependence of character granularity of HTTP requests at different scales and levels. As a result, the structure enables the model to easily capture dependencies over extended and long sequences of HTTP requests and consequently identify attacks accurately. The outcomes of the experiments carried out on the CSIC 2010 dataset show that the proposed model outperforms several state-of-the-art deep learning-based models in the literature and some traditional deep learning models by identifying web attacks with a precision score of 99.65%, a recall score of 98.80%, an F1 score of 99.22%, and an accuracy score of 99.36%. A useful web attack detection system must be able to balance accurate attack identification with minimizing false positives (identifying normal requests as attacks). The success of the model in recognizing normal requests is further evaluated to guarantee increased security without sacrificing web applications’ usability and availability.

show abstract

“…Previous studies predominantly focused on specific types of asphalt pavement defect detection, such as cracks or potholes 28 , typically in controlled experimental settings with relatively simple backgrounds. However, real-world asphalt pavement defect images often exhibit complex and diverse backgrounds, leading to occurrences of false positives and false negatives 29 .…”

Section: Introductionmentioning

confidence: 99%

Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning

Zhang,

Bei,

Ling

et al. 2024

Preprint

View full text Add to dashboard Cite

Accurate detection of asphalt pavement distress is crucial for road maintenance and traffic safety. However, traditional convolutional neural networks usually struggle with this task due to the varied distress patterns and complex backgrounds in the images. To enhance the accuracy of asphalt pavement distress identification across various scenarios, this paper introduces an improved model named SMG-YOLOv8, based on the YOLOv8s framework. This model integrates the space-to-depth module and the multi-scale convolutional attention mechanism, while optimizing the backbone's C2f structure with a more efficient G-GhostC2f structure. Experimental results demonstrate that SMG-YOLOv8 outperforms the YOLOv8s baseline model, achieving Pmacro and mAP@50 scores of 81.1% and 79.4% respectively, marking an increase of 8.2% and 12.5% over the baseline. Furthermore, SMG-YOLOv8 exhibits clear advantages in identifying various types of pavement distresses, including longitudinal cracks, transverse cracks, mesh cracks, and potholes, when compared to YOLOv5n, YOLOv5s, YOLOv6s, and YOLOv8n models. This enhancement optimizes the network structure, reducing the number of parameters while maintaining excellent detection performance. In real-world scenarios, the SMG-YOLOv8 model has demonstrated strong generalization capability and practical utility, providing crucial technical support for intelligent pavement distress detection.

show abstract

Recent computer vision applications for pavement distress and condition assessment

Cited by 29 publications

References 128 publications

Road safety impact assessment practices and recommendations

Road safety impact assessment practices and recommendations

MC-MLDCNN: Multichannel Multilayer Dilated Convolutional Neural Networks for Web Attack Detection

Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning

Contact Info

Product

Resources

About