Real-Time Road Surface Damage Detection Framework based on Mask R-CNN Model

Kulambayev, Bakhytzhan; Nurlybek, Magzat; Astaubayeva, Gulnar; Tleuberdiyeva, Gulnara; Zholdasbayev, Serik; Tolep, Abdimukhan

doi:10.14569/ijacsa.2023.0140979

Cited by 5 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The limitations inherent in conventional CNN architectures, particularly for complex tasks such as lung segmentation in CT imaging, have prompted significant innovations in neural network design [23]. Advanced architectures like Highresolution networks (HR-Nets) maintain high-resolution representations through successive layers, enhancing the model's capacity to identify and delineate intricate anatomical structures.…”

Section: Advent Of Advanced Cnn Architectures For Segmentationmentioning

confidence: 99%

Enhanced U-Net Architecture for Lung Segmentation on Computed Tomography and X-Ray Images

Saimassay,

Begenov,

Sadyk

et al. 2024

ijacsa

View full text Add to dashboard Cite

In the expanding field of medical imaging, precise segmentation of anatomical structures is critical for accurate diagnosis and therapeutic interventions. This research paper introduces an innovative approach, building upon the established U-Net architecture, to enhance lung segmentation techniques applied to Computed Tomography (CT) images. Traditional methods of lung segmentation in CT scans often confront challenges such as heterogeneous tissue densities, variability in human anatomy, and pathological alterations, necessitating an approach that embodies greater robustness and precision. Our study presents a modified U-Net model, characterized by an integration of advanced convolutional layers and innovative skip connections, improving the reception field and facilitating the retention of high-frequency details essential for capturing the lung's intricate structures. The enhanced U-Net architecture demonstrates substantial improvements in dealing with the subtleties of lung parenchyma, effectively distinguishing between precarious nuances of tissues, and pathologies. Rigorous quantitative evaluations showcase a significant increase in the Dice coefficient and a decrease in the Hausdorff distance, indicating a more refined segmentation output compared to predecessor models. Additionally, the proposed model manifests exceptional versatility and computational efficiency, making it conducive for real-time clinical applications. This research underlines the transformative potential of employing advanced deep learning architectures for biomedical imaging, paving the way for early intervention, accurate diagnosis, and personalized treatment paradigms in pulmonary disorders. The findings have profound implications, propelling forward the nexus of artificial intelligence and healthcare towards unprecedented horizons.

show abstract

Section: Advent Of Advanced Cnn Architectures For Segmentationmentioning

confidence: 99%

Enhanced U-Net Architecture for Lung Segmentation on Computed Tomography and X-Ray Images

Saimassay,

Begenov,

Sadyk

et al. 2024

ijacsa

View full text Add to dashboard Cite

show abstract

“…Wang et al [33] used threshold detection in image processing technology to detect the degree of road damage at different brightness levels in the image. Kulambayev et al [34] developed a method to detect the degree of road damage in real time using a deep learning model. Maeda et al [35] and Abbas et al [36] installed cameras in cars and used CNN models to detect road cracks and abnormal conditions.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of Crack Detection and Crack Length Calculation Method using Image Processing

Oh,

Matsumoto,

Arai

2023

IJACSA

View full text Add to dashboard Cite

To evaluate the integrity of a building, many experts and engineers have evaluated the damage classification of a building based on superficial visual information through field surveys. On-site surveys are hazardous and require several years of experience and expertise. In this study, a system for detecting the presence or absence of cracks and calculating their lengths was developed using image processing technology. The accuracy of the system was examined using crack image data obtained from shear force experiments. For crack detection, a crack detection method was developed using canny edge, threshold, and HSV color detection. The detection of the presence of cracks was proposed to be coupled with image segmentation to improve detection accuracy. A method for calculating the crack length using image processing was also developed. In this study, we proposed a method to calculate cracks as straight lengths, and obtained results with 98.1% accuracy. However, for curved cracks, it was necessary to rotate or segment the image.

show abstract

“…This dataset will encompass varying road conditions, lighting scenarios, and traffic densities to ensure the robustness and generalization capability of the model. Furthermore, data augmentation techniques will be employed to simulate realworld variations and improve the model's resilience to environmental factors [8]. www.ijacsa.thesai.org…”

Section: Introductionmentioning

confidence: 99%

Real-Time Road Lane-Lines Detection using Mask-RCNN Approach

Beissenova,

Ussipbekova,

Sultanova

et al. 2024

ijacsa

View full text Add to dashboard Cite

This paper presents a novel approach to real-time road lane-line detection using the Mask R-CNN framework, with the aim of enhancing the safety and efficiency of autonomous driving systems. Through extensive experimentation and analysis, the proposed system demonstrates robust performance in accurately detecting and segmenting lane boundaries under diverse driving conditions. Leveraging deep learning techniques, the system exhibits a high level of accuracy in handling complex scenarios, including variations in lighting conditions and occlusions.Real-time processing capabilities enable instantaneous feedback, contributing to improved driving safety and efficiency. However, challenges such as model generalizability, interpretability, computational efficiency, and resilience to adverse weather conditions remain to be addressed. Future research directions include optimizing the system's performance across different geographic regions and road types and enhancing its adaptability to adverse weather conditions. The findings presented in this paper contribute to the ongoing efforts to advance autonomous driving technology, with implications for improving road safety and transportation efficiency in real-world settings. The proposed system holds promise for practical deployment in autonomous vehicles, paving the way for safer and more efficient transportation systems in the future.

show abstract

Real-Time Road Surface Damage Detection Framework based on Mask R-CNN Model

Cited by 5 publications

References 37 publications

Enhanced U-Net Architecture for Lung Segmentation on Computed Tomography and X-Ray Images

Enhanced U-Net Architecture for Lung Segmentation on Computed Tomography and X-Ray Images

Development of Crack Detection and Crack Length Calculation Method using Image Processing

Real-Time Road Lane-Lines Detection using Mask-RCNN Approach

Contact Info

Product

Resources

About