International Journal of Advanced Computer Science and Applications

Показано: 1 - 2 из 2

Некоторые метрики заблокированы вашими
настройками согласия
Real-Time Road Damage Detection System on Deep Learning Based Image Analysis
(Science and Information Organization, 2024-01-01)
Bakhytzhan Kulambayev
;
Belik Gleb
;
Nazbek Katayev
;
Islam Menglibay
;
Zeinel Momynkulov
This research paper introduces a sophisticated deep learning-based system for real-time detection and segmentation of road damages, utilizing the Mask R-CNN framework to enhance road maintenance and safety. The primary objective was to develop a robust automated system capable of accurately identifying and classifying various types of road damages under diverse environmental conditions. The system employs advanced convolutional neural networks to process and analyze images captured from road surfaces, enabling precise localization and segmentation of damages such as cracks, potholes, and surface wear. Evaluation of the model's performance through metrics like accuracy, precision, recall, and F1-score demonstrated high effectiveness in real-world scenarios. The confusion matrix and loss curves presented in the study illustrate the system's ability to generalize well to unseen data, mitigating overfitting while maintaining high detection sensitivity. Challenges such as variable lighting, shadows, and background noise were addressed, highlighting the system's resilience and the need for further dataset diversification and integration of multimodal data sources. The potential improvements discussed include refining the convolutional network architecture and incorporating predictive maintenance capabilities. The system's application extends beyond mere detection, promising transformative impacts on urban planning and infrastructure management by integrating with smart city frameworks to facilitate real-time, predictive road maintenance. This research sets a benchmark for future developments in the field of automated road assessment, pointing towards a future where AI-driven technologies significantly enhance public safety and infrastructure efficiency.
Цитирования (OpenAlex) 9Цитирования (OpenCitations) 7
Некоторые метрики заблокированы вашими
настройками согласия
DamageNet: A Dilated Convolution Feature Pyramid Network Mask R‑CNN for Automated Car Damage Detection and Segmentation
(Science and Information Organization, 2025-01-01)
Nazbek Katayev
;
Zhanna Yessengaliyeva
;
Zhazira Kozhamkulova
;
Zhanel Bakirova
;
Assylzat Abuova
Automated and precise assessment of vehicle damage is critical for modern insurance processing, accident analysis, and autonomous maintenance systems. In this work, we introduce DamageNet, a unified deep instance segmentation framework that embeds a multi‑rate dilated‑convolution context module within a Feature Pyramid Network (FPN) backbone and couples it with a Region Proposal Network (RPN), RoI‑Align, and parallel heads for classification, bounding‑box regression, and pixel‑level mask prediction. Evaluated on the large‑scale VehiDE dataset comprising 5 200 high‑resolution images annotated for dents, scratches, and broken glass, DamageNet achieves a mean Average Precision (mAP) of 85.7% for damage localization and a mean Intersection over Union (mIoU) of 82.3% for segmentation, outperforming baseline Mask R‑CNN by 6.2 and 7.8 percentage points, respectively. Ablation studies confirm that the dilated‑convolution module, multi‑scale fusion in the FPN, and post‑processing refinements each contribute substantially to segmentation fidelity. Qualitative results demonstrate robust delineation of both subtle scratch lines and extensive panel deformations under diverse lighting and occlusion conditions. Although the integration of atrous convolutions introduces a modest inference overhead, DamageNet offers a significant advancement in end‑to‑end vehicle damage analysis. Future extensions will investigate lightweight dilation approximations, dynamic rate selection, and semi‑supervised learning strategies to further enhance processing speed and generalization to additional damage modalities.
Цитирования (OpenAlex) 1

International Journal of Advanced Computer Science and Applications

Фильтры

Настройки

Сортировать по

результатов на странице