Automated bridge surface crack detection and segmentation using computer vision-based deep learning model

Object detection from UAV thermal infrared images and videos using YOLO models

Object detection is a fundamental problem in computer vision, with applications spanning self-driving cars, surveillance systems, medical imaging, robotics, and smart cities. Among the myriad of algorithms developed for this task, the You Only Look Once (YOLO) family stands out for its ability to perform real-time and accurate object detection. This article provides a comprehensive analysis of the YOLO algorithm series, from YOLOv1 to YOLOv8, evaluating them across key performance metrics, including precision, recall, mean Average Precision (mAP), frames per second (FPS), and overall effectiveness. Unlike traditional two-stage detectors such as R-CNN, YOLO formulates object detection as a single regression problem: a single pass over the image simultaneously predicts bounding boxes and class probabilities. This end-to-end design enables YOLO to achieve high speed while maintaining a competitive accuracy-efficiency trade-off. We examine architectural innovations across YOLO versions, including batch normalization, anchor boxes, residual blocks, feature pyramid networks, and attention mechanisms, and discuss their impact on performance. Lightweight models (e.g., YOLOv5-Nano, YOLOv8-Small) are explored with a focus on their suitability for mobile and embedded systems, highlighting YOLO’s adaptability to resource-constrained environments. Challenges such as small object detection, occlusion, and domain-specific tuning are also addressed. This article serves as a practical guide for researchers, developers, and practitioners aiming to leverage YOLO for real-world object detection tasks.

The objective of this study is to examine two powerful components: the YOLO (You Only Look Once) framework for object recognition on edge devices and the MobileNet architecture. With the rising demand for real-time, efficient, and accurate object detection in constrained environments, these models offer distinct advantages suited to different applications. YOLO is renowned for its high accuracy and speed, making it ideal for complex detection tasks, whereas MobileNet is optimized for efficiency, enabling deployment on devices with limited computational resources. The paper discusses the evolution of these models, their architectural differences, and their respective strengths and limitations when implemented on edge devices. Furthermore, we explore the feasibility of integrating these frameworks into a hybrid model that leverages the lightweight feature extraction of MobileNet and the robust detection capabilities of YOLO. Such a hybrid approach could significantly enhance real-time object detection performance across a wide range of hardware platforms.  Researchers and practitioners seeking to deploy advanced object detection models in real-world applications, particularly where computational efficiency and accuracy are paramount may find this review as a valuable resource.

Advancements in image processing and deep learning offer considerable opportunities for automated defect assessment in civil structures. However, these systems cannot work interactively with human inspectors. Mixed reality (MR) can be adopted to address this by involving inspectors in various stages of the assessment process. This paper integrates You Only Look Once (YOLO) v5n and YOLO v5m with the Canny algorithm for real-time concrete crack detection and skeleton extraction with a Microsoft HoloLens 2 MR device. The YOLO v5n demonstrates a superior mean average precision (mAP) 0.5 and speed, while YOLO v5m achieves the highest mAP 0.5 0.95 among the other YOLO v5 structures. The Canny algorithm also outperforms the Sobel and Prewitt edge detectors with the highest F1 score. The developed MR-based system could not only be employed for real-time defect assessment but also be utilized for the automatic recording of the location and other specifications of the cracks for further analysis and future re-inspections.

The most important aspect of automatic driving and traffic surveillance is vehicle detection. In addition, poor road conditions caused by potholes are the cause of traffic accidents and vehicle damage. The proposed work uses deep learning models. The proposed method can detect vehicles and potholes using images. The faster region-based convolutional neural network (CNN) and the inception network V2 model are used to implement the model. The proposed work compares the performance, accuracy numbers, detection time, and advantages and disadvantages of the faster region-based convolution neural network (Faster R-CNN) with single shot detector (SSD) and you only look once (YOLO) algorithms. The proposed method shows good progress than the existing methods such as SSD and YOLO. The measure of performance evaluation is Accuracy. The proposed method shows an improvement of 5% once compared with the previous methods such as SSD and YOLO.

Thermal expansion and shrinkage of mortar and concrete surfaces under the influence of high temperatures lead to fine and irregular cracks on the surface, weakening the internal structure of mortar and adversely affecting the long‐term performance. Such cracks allow water carrying chemicals to penetrate deep into the mortar, deteriorating the internal structure of mortar. Therefore, the detection of the cracks rapidly and accurately is critical for the safety of the structure. This study aims to detect and characterize cracks occurring on the surfaces of waste PVC containing mortars exposed to high temperatures using deep learning models. For this purpose, YOLOv5, YOLOv8, and YOLOv11 models, which are popular You Only Look Once (YOLO) models in real‐time applications, were used as deep learning models. The dataset consists of 5027 images captured from mortar surfaces exposed to high temperature at 800°C, and this dataset is split into 80% training, 10% validation, and 10% test sets. Using these datasets, all sub‐models (n, s, m, l, x) of YOLOv5, YOLOv8, and YOLOv11 models were trained separately. In addition, crack area, perimeter, and width of cracks were measured from the actual and predicted images using pixel‐millimeter transformation. The results showed that the x sub‐models were the most accurate YOLO models, and the model with the highest accuracy for these models was YOLOv11x with a mean Intersection‐over‐Union (mIoU) of 81.2%. Among the YOLO models, YOLOv5x was the best model for accuracy with 0.021 mm 2 area, 0.831 mm perimeter, and 0.0008 mm width differences between actual and predicted images. In the study, the average crack width measured from the mortar surface was 0.058 mm. In addition, the YOLOv5n model is the best model for real‐time applications with a segmentation speed of 27 ms.

Sea turtles exhibit high migratory rates and occupy a broad range of habitats, which in turn makes monitoring these taxa challenging. Applying deep learning (DL) models to vast image datasets collected from citizen science programs can offer promising solutions to overcome the challenge of monitoring the wide habitats of wildlife, particularly sea turtles. Among DL models, object detection models, such as the You Only Look Once (YOLO) series, have been extensively employed for wildlife classification. Despite their successful application in this domain, detecting objects in images with complex backgrounds, including underwater environments, remains a significant challenge. Recently, instance segmentation models have been developed to address this issue by providing more accurate classification of complex images compared to traditional object detection models. This study compared the performance of two state-of-the-art DL methods namely; the object detection model (YOLOv5) and instance segmentation model (YOLOv5-seg), to detect and classify sea turtles. The images were collected from iNaturalist and Google and then divided into 64% for training, 16% for validation, and 20% for test sets. Model performance during and after finishing training was evaluated by loss functions and various indexes, respectively. Based on loss functions, YOLOv5-seg demonstrated a lower error rate in detecting rather than classifying sea turtles than the YOLOv5. According to mean Average Precision (mAP) values, which reflect precision and recall, the YOLOv5-seg model showed superior performance than YOLOv5. The mAP0.5 and mAP0.5:0.95 for the YOLOv5 model were 0.885 and 0.795, respectively, whereas for the YOLOv5-seg, these values were 0.918 and 0.831, respectively. In particular, based on the loss functions and classification results, the YOLOv5-seg showed improved performance for detecting rather than classifying sea turtles compared to the YOLOv5. The results of this study may help improve sea turtle monitoring in the future.

Productivity in mining operations is highly dependent on the efficiency of heavy equipment such as excavators. Conventional methods for measuring excavator cycle time are often manual and inefficient. This study aims to develop a real-time cycle time detection system using the You Only Look Once (YOLO) object detection algorithm. Video data from excavator operations were annotated to train the YOLO model, which was then integrated into a user-friendly application using OpenCV. The system achieved a mean Average Precision (mAP) of 94.2% and operated at 30 Frames Per Second (FPS), enabling accurate and real-time detection of excavator activities. The system enhanced monitoring efficiency and operational productivity. Its implementation in mining environments demonstrates the potential for automated cycle time analysis to support equipment management, improve safety, and reduce operational delays.

The coronavirus disease (COVID-19) is primarily disseminated through physical contact. As a precaution, it is recommended that indoor spaces have a limited number of people and at least one meter apart. This study proposes a real-time method for monitoring physical distancing compliance in indoor spaces using computer vision and deep learning techniques. The proposed method utilizes YOLO (You Only Look Once), a popular convolutional neural network-based object detection model, pre-trained on the Microsoft COCO (Common Objects in Context) dataset to detect persons and estimate their physical distance in real time. The effectiveness of the proposed method was assessed using metrics including accuracy rate, frame per second (FPS), and mean average precision (mAP). The results show that the YOLO v3 model had the most remarkable accuracy (87.07%) and mAP (89.91%). On the other hand, the highest fps rate of up to 18.71 was achieved by the YOLO v5s model. The results demonstrate the potential of the proposed method for effectively monitoring physical distancing compliance in indoor spaces, providing valuable insights for future use in other public health scenarios.

Integrating advanced technologies such as artificial intelligence (AI) with traditional agricultural practices has changed how activities are developed in agriculture, with the aim of automating manual processes and improving the efficiency and quality of farming decisions. With the advent of deep learning models such as convolutional neural network (CNN) and You Only Look Once (YOLO), many studies have emerged given the need to develop solutions to problems and take advantage of all the potential that this technology has to offer. This systematic literature review aims to present an in-depth investigation of the application of AI in supporting the management of weeds, plant nutrition, water, pests, and diseases. This systematic review was conducted using the PRISMA methodology and guidelines. Data from different papers indicated that the main research interests comprise five groups: (a) type of agronomic problems; (b) type of sensor; (c) dataset treatment; (d) evaluation metrics and quantification; and (e) AI technique. The inclusion (I) and exclusion (E) criteria adopted in this study included: (I1) articles that obtained AI techniques for agricultural analysis; (I2) complete articles written in English; (I3) articles from specialized scientific journals; (E1) articles that did not describe the type of agrarian analysis used; (E2) articles that did not specify the AI technique used and that were incomplete or abstract; (E3) articles that did not present substantial experimental results. The articles were searched on the official pages of the main scientific bases: ACM, IEEE, ScienceDirect, MDPI, and Web of Science. The papers were categorized and grouped to show the main contributions of the literature to support agricultural decisions using AI. This study found that AI methods perform better in supporting weed detection, classification of plant diseases, and estimation of agricultural yield in crops when using images captured by Unmanned Aerial Vehicles (UAVs). Furthermore, CNN and YOLO, as well as their variations, present the best results for all groups presented. This review also points out the limitations and potential challenges when working with deep machine learning models, aiming to contribute to knowledge systematization and to benefit researchers and professionals regarding AI applications in mitigating agronomic problems.

Abstract. As Artificial Intelligence (AI) technologies are developing rapidly and are widely used in various domains, it is efficient and convenient for composers to make music using AI to convert sheet music to audio. This research aims to compare the performance of different models in identifying individual notes within sheet music. Compared to traditional technologies like Optical Music Recognition (OMR), deep learning models have a significant advantage in processing blurry images with high efficiency. In the research process, three different models are used in searching for musical notes: OMR, You Only Look Once (YOLO)v5, and YOLOv8. The evaluation index consists of recognition accuracy, mean Average Precision (mAP), inference speed, and parameter quantity. After the experiment, it is found that the YOLO model performs best with high accuracy and fast speed. Based on the above analyses, the thesis finds that the YOLO model can be an efficient tool in composing music, with further research.

Ageing bridge stocks and rising traffic loads in Latin America and worldwide demand cost-effective maintenance strategies. Building Information Modelling (BIM) and its convergence with digital-twin, IoT and AI techniques have shown promise, yet their adoption for bridge upkeep remains fragmentary. This review aimed to (i) synthesise current scientific evidence on BIM-based bridge maintenance, (ii) classify methodologies and tools through a domain taxonomy, and (iii) identify research gaps that hinder large-scale implementation. A PRISMA-guided systematic literature review was conducted in Scopus and Web of Science (search cut-off = 1 February 2024). Inclusion criteria targeted peer-reviewed, open-access studies (2020–2024) that applied BIM to the maintenance of existing bridges. Twenty-five articles met the criteria and were appraised with Mixed-Methods Appraisal Tool (MMAT 2018). Seven dominant research themes were identified, with damage visualization (7 studies) and 3-D geometric modelling (6) being the most frequent, followed by information exchange/management (4). Specifically, LiDAR and photogrammetry enabled sub-centimetre models; Convolutional Neural Networks (CNN) and You Only Look Once (YOLO) algorithms reached mean average precision up to 0.91 for crack detection. Digital-twin workflows reduced operating costs while requiring higher upfront investment. A seven-domain taxonomy and a cost–technology comparison table is proposed. Key barriers reported include IFC 4.3 interoperability, high LiDAR costs ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="m1"><mml:mrow><mml:mo>&gt;</mml:mo></mml:mrow></mml:math> 10% of annual budgets), limited visual-programming skills, and cybersecurity concerns in cloud-IoT integrations. BIM supports preventive, data-driven bridge maintenance and has been linked to lower operating costs in several studies; mainstream adoption requires IFC 4.3 based interoperability, targeted training, and open-standard workflows. Future research should focus on standardised performance metrics, edge-AI monitoring and blockchain-secured data exchange.

A deep learning model to assist visually impaired in pothole detection using computer vision

Wearing masks in a crowded environment can reduce the risk of infection; however, wearing nonstandard cloud does not have a good protective effect on the virus, which makes it necessary to monitor the wearing of masks in real time. You only look once (YOLO) series models are widely used in various edge devices. The existing YOLOv5s method meets the requirements of inference time, but it is slightly deficient in terms of accuracy due to its generality. Considering the characteristics of our driver medical mask dataset, a position insensitive loss which is cloud extract shared area feature in different categories and half deformable convolution net methods with cloud concern noteworthy features were introduced into YOLOv5s to improve accuracy, with an increase of 6.7% mean average in @.5 (mAP@.5) and 8.3% in mAP@.5:.95 for our dataset. To ensure that our method can be applied in a real scenario, TensorRT and CUDA were introduced to reduce the inference time in two edge devices (Jetson TX2 and Jetson Nano) and one desktop device, whose inference time was faster than that of previous methods.

Maintaining wind turbine blades is a challenging task, often marked by high costs, safety risks, time inefficiency, and the possibility of incorrect diagnosis. A promising approach to support preventive maintenance involves the use of drones and deep learning for inspection and early fault detection. This paper offers a comparative study of five advanced deep learning models: Residual Networks (ResNet), Inception Networks (InceptionV3), YOLO (You Only Look Once), EfficientNet, and Vision Transformers (ViTs) applied to the DTU Drone Inspection Images of Wind Turbine dataset. The objective is to determine the most effective model for detecting defects in wind turbine blades, which is critical for ensuring the efficiency and safety of wind energy systems. The models were assessed using key performance metrics, such as accuracy, precision, recall, F1-score, and inference time. EfficientNet emerged as the top performer with the highest accuracy and balanced efficiency, while YOLO demonstrated the fastest inference time, making it ideal for real-time applications. ResNet and InceptionV3 also performed well, particularly in detecting subtle defects, whereas ViTs showed strong capabilities in capturing complex global features despite longer processing times. The findings provide valuable insights for selecting appropriate deep learning models in drone-based wind turbine inspections, contributing to more effective and reliable maintenance practices.