Опубликована: Окт. 18, 2024
Язык: Английский
The Journal of Supercomputing, Год журнала: 2025, Номер 81(2)
Опубликована: Янв. 8, 2025
Язык: Английский
Процитировано
1
PeerJ Computer Science, Год журнала: 2025, Номер 11, С. e2519 - e2519
Опубликована: Янв. 21, 2025
Road damage often includes potholes, cracks, lane degradation, and surface shading. Potholes are a common problem in pavements. Detecting them is crucial for maintaining infrastructure ensuring public safety. A thorough assessment of pavement conditions required before planning any preventive repairs. Herein, we report the use transfer learning deep (DL) models to preprocess digital images pavements better pothole detection. Fourteen were evaluated, including MobileNet, MobileNetV2, NASNetMobile, DenseNet121, DenseNet169, InceptionV3, DenseNet201, ResNet152V2, EfficientNetB0, InceptionResNetV2, Xception, EfficientNetV2M. The study introduces modified MobileNetV2 (MMNV2) model designed fast efficient feature extraction. MMNV2 exhibits improved classification, detection, prediction accuracy by adding five-layer pre-trained network framework. It combines learning, neural networks (DNN), which resulted performance compared other models. was tested using dataset 5,000 images. rate 0.001 used optimize model. classified into ‘normal’ or ‘pothole’ categories with 99.95% accuracy. also achieved 100% recall, 99.90% precision, F1-score, 0.05% error rate. uses fewer parameters while delivering results. offers promising solution real-world applications detection assessment.
Язык: Английский
Процитировано
1
Sensors, Год журнала: 2024, Номер 24(13), С. 4373 - 4373
Опубликована: Июль 5, 2024
The search for structural and microstructural defects using simple human vision is associated with significant errors in determining voids, large pores, violations of the integrity compactness particle packing micro- macrostructure concrete. Computer methods, particular convolutional neural networks, have proven to be reliable tools automatic detection during visual inspection building structures. study’s objective create compare computer algorithms that use networks identify analyze damaged sections concrete samples from different Networks following architectures were selected operation: U-Net, LinkNet, PSPNet. analyzed images are photos obtained by laboratory tests assess quality terms defection structure. During implementation process, changes metrics such as macro-averaged precision, recall, F1-score, well IoU (Jaccard coefficient) accuracy, monitored. best demonstrated U-Net model, supplemented cellular automaton algorithm: precision = 0.91, recall 0.90, F1 0.84, accuracy 0.90. developed segmentation universal show a high highlighting areas interest under any shooting conditions volumes defective zones, regardless their localization. automatization process calculating damage area recommendation “critical/uncritical” format can used condition various types structures, adjust formulation, change technological parameters production.
Язык: Английский
Процитировано
5
Results in Engineering, Год журнала: 2024, Номер 23, С. 102745 - 102745
Опубликована: Авг. 18, 2024
Язык: Английский
Процитировано
4
Drones, Год журнала: 2025, Номер 9(3), С. 221 - 221
Опубликована: Март 19, 2025
This systematic review explores the integration of unmanned aerial vehicles (UAVs) and artificial intelligence (AI) in automating road signage inventory creation, employing preferred reporting items for reviews meta-analyses (PRISMA) methodology to analyze recent advancements. The study evaluates cutting-edge technologies, including UAVs equipped with deep learning algorithms advanced sensors like light detection ranging (LiDAR) multispectral cameras, highlighting their roles enhancing traffic sign classification. Key challenges include detecting minor or partially obscured signs adapting diverse environmental conditions. findings reveal significant progress automation, notable improvements accuracy, efficiency, real-time processing capabilities. However, limitations such as computational demands variability persist. By providing a comprehensive synthesis current methodologies performance metrics, this establishes robust foundation future research advance automated infrastructure management improve safety operational efficiency urban rural settings.
Язык: Английский
Процитировано
0
Measurement, Год журнала: 2025, Номер unknown, С. 117315 - 117315
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0
Measurement, Год журнала: 2025, Номер unknown, С. 117344 - 117344
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0
Scientific Reports, Год журнала: 2025, Номер 15(1)
Опубликована: Апрель 2, 2025
Язык: Английский
Процитировано
0
Measurement, Год журнала: 2025, Номер unknown, С. 117650 - 117650
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
0
Nature Communications, Год журнала: 2025, Номер 16(1)
Опубликована: Май 6, 2025
Язык: Английский
Процитировано
0