Search results for: YOLOV8

Authors: A. Degale Desta, Cheng Jian

Abstract:

Background: Vehicle detection accuracy is critical to intelligent transportation systems and autonomous driving. The state-of-the-art object identification technology YOLOv8 has shown significant gains in efficiency and detection accuracy. This study uses the BDD100K dataset, which is renowned for its extensive and varied annotations, to assess how well YOLOv8 performs in vehicle detection. Objectives: The primary objective of this research is to assess YOLOv8's performance in intelligent transportation system vehicle identification and its ability to accurately identify cars in urban environments for safety prioritization. Methods: The primary objective of this research is to assess YOLOv8's performance in intelligent transportation system vehicle identification and its ability to accurately identify cars in urban environments for safety prioritization. Results: The results show that YOLOv8 achieves high mAP, recall, precision, and F1-score values, indicating state-of-the-art performance. This suggests that YOLOv8 can identify cars in complex urban environments with a high degree of accuracy and reliable results in a variety of traffic scenarios. Conclusion: The results indicate that YOLOv8 is a useful tool for enhancing vehicle detection accuracy in intelligent transportation systems, hence advancing urban public safety and security. The model's demonstrated performance shows how well it may be incorporated into autonomous driving applications to improve situational awareness and responsiveness.

Keywords: vehicle detection, YOLOv8, BDD100K, object detection, deep learning

Procedia PDF Downloads 14

Authors: Aysun Sezer

Abstract:

Magnetic Resonance Imaging (MRI) is one of the advanced diagnostic tools for evaluating shoulder pathologies. Proton Density (PD)-weighted MRI sequences prove highly effective in detecting edema. However, they are deficient in the anatomical identification of bones due to a trauma-induced decrease in signal-to-noise ratio and blur in the traumatized cortices. Computer-based diagnostic systems require precise segmentation, identification, and localization of anatomical regions in medical imagery. Deep learning-based object detection algorithms exhibit remarkable proficiency in real-time object identification and localization. In this study, the YOLOv8 model was employed to detect humeral head and scapular regions in 665 axial PD-weighted MR images. The YOLOv8 configuration achieved an overall success rate of 99.60% and 89.90% for detecting the humeral head and scapula, respectively, with an intersection over union (IoU) of 0.5. Our findings indicate a significant promise of employing YOLOv8-based detection for the humerus and scapula regions, particularly in the context of PD-weighted images affected by both noise and intensity inhomogeneity.

Keywords: YOLOv8, object detection, humerus, scapula, IRM

Procedia PDF Downloads 69

Authors: Pratham Madnur, Prathamkumar Shetty, Sneha Varur, Gouri Parashetti

Abstract:

In order to overcome conventional obstacles, this research paper investigates novel approaches for cricket pitch and ball detection that make use of cutting-edge technologies. The research integrates OpenCV for pitch inspection and modifies the YOLOv8 model for cricket ball detection in order to overcome the shortcomings of manual pitch assessment and traditional ball detection techniques. To ensure flexibility in a range of pitch environments, the pitch detection method leverages OpenCV’s color space transformation, contour extraction, and accurate color range defining features. Regarding ball detection, the YOLOv8 model emphasizes the preservation of minor object details to improve accuracy and is specifically trained to the unique properties of cricket balls. The methods are more reliable because of the careful preparation of the datasets, which include novel ball and pitch information. These cutting-edge methods not only improve cricket analytics but also set the stage for flexible methods in more general sports technology applications.

Keywords: OpenCV, YOLOv8, cricket, custom dataset, computer vision, sports

Procedia PDF Downloads 88

Authors: Christos Chaschatzis, Chrysoula Karaiskou, Pantelis Angelidis, Sotirios K. Goudos, Igor Kotsiuba, Panagiotis Sarigiannidis

Abstract:

Over the past few decades, the rapid growth of the global population has led to the need to increase agricultural production and improve the quality of agricultural goods. There is a growing focus on environmentally eco-friendly solutions, sustainable production, and biologically minimally fertilized products in contemporary society. Precision agriculture has the potential to incorporate a wide range of innovative solutions with the development of machine learning algorithms. YOLOv5 and YOLOv8 are two of the most advanced object detection algorithms capable of accurately recognizing objects in real time. Detecting tree diseases is crucial for improving the food production rate and ensuring sustainability. This research aims to evaluate the efficacy of YOLOv5 and YOLOv8 in detecting the symptoms of Armillaria spp. in sweet cherry trees and determining their health status, with the goal of enhancing the robustness of precision agriculture. Additionally, this study will explore Computer Vision (CV) techniques with machine learning algorithms to improve the detection process’s efficiency.

Keywords: Armillaria spp., machine learning, precision agriculture, smart farming, sweet cherries trees, YOLOv5, YOLOv8

Procedia PDF Downloads 117

Authors: Simiao Ren, En Wei

Abstract:

Drowning is a significant safety issue worldwide, and a robust computer vision-based alert system can easily prevent such tragedies in swimming pools. However, due to domain shift caused by the visual gap (potentially due to lighting, indoor scene change, pool floor color etc.) between the training swimming pool and the test swimming pool, the robustness of such algorithms has been questionable. The annotation cost for labeling each new swimming pool is too expensive for mass adoption of such a technique. To address this issue, we propose a domain-aware data augmentation pipeline based on Gaussian Poisson Generative Adversarial Network (GP-GAN). Combined with YOLOv8, we demonstrate that such a domain adaptation technique can significantly improve the model performance (from 0.24 mAP to 0.82 mAP) on new test scenes. As the augmentation method only require background imagery from the new domain (no annotation needed), we believe this is a promising, practical route for preventing swimming pool drowning.

Keywords: computer vision, deep learning, YOLOv8, detection, swimming pool, drowning, domain adaptation, generative adversarial network, GAN, GP-GAN

Procedia PDF Downloads 103

Authors: A. Degale Desta, Tamirat Kebamo

Abstract:

Background: Recent advances in computer vision and pattern recognition have significantly improved activity recognition through video analysis, particularly with the application of Deep Convolutional Neural Networks (CNNs). One-stage detectors now enable efficient video-based recognition by simultaneously predicting object categories and locations. Such advancements are highly relevant in educational settings where CCTV surveillance could automatically monitor academic activities, enhancing security and classroom management. However, current datasets and recognition systems lack the specific focus on campus environments necessary for practical application in these settings.Objective: This study aims to address this gap by developing a dataset and testing an automated activity recognition system specifically tailored for educational campuses. The EthioCAD dataset was created to capture various classroom activities and teacher-student interactions, facilitating reliable recognition of academic activities using deep learning models. Method: EthioCAD, a novel video-based dataset, was created with a design science research approach to encompass teacher-student interactions across three domains and 18 distinct classroom activities. Using the Roboflow AI framework, the data was processed, with 4.224 KB of frames and 33.485 MB of images managed for frame extraction, labeling, and organization. The Ultralytics YOLOv8 model was then implemented within Google Colab to evaluate the dataset’s effectiveness, achieving high mean Average Precision (mAP) scores. Results: The YOLOv8 model demonstrated robust activity recognition within campus-like settings, achieving an mAP50 of 90.2% and an mAP50-95 of 78.6%. These results highlight the potential of EthioCAD, combined with YOLOv8, to provide reliable detection and classification of classroom activities, supporting automated surveillance needs on educational campuses. Discussion: The high performance of YOLOv8 on the EthioCAD dataset suggests that automated activity recognition for surveillance is feasible within educational environments. This system addresses current limitations in campus-specific data and tools, offering a tailored solution for academic monitoring that could enhance the effectiveness of CCTV systems in these settings. Conclusion: The EthioCAD dataset, alongside the YOLOv8 model, provides a promising framework for automated campus activity recognition. This approach lays the groundwork for future advancements in CCTV-based educational surveillance systems, enabling more refined and reliable monitoring of classroom activities.

Keywords: deep CNN, EthioCAD, deep learning, YOLOv8, activity recognition

Procedia PDF Downloads 22

Authors: Zahra Alipour, Amirreza Moheb Afzali

Abstract:

In the field of human-computer interaction (HCI), hand gestures play a crucial role in facilitating communication by expressing emotions and intentions. The precise tracking of the index finger and the estimation of joint positions are essential for developing effective gesture recognition systems. However, various challenges, such as anatomical variations, occlusions, and environmental influences, hinder optimal functionality. This study investigates the performance of the YOLOv8m model for hand detection using the EgoHands dataset, which comprises diverse hand gesture images captured in various environments. Over three training processes, the model demonstrated significant improvements in precision (from 88.8% to 96.1%) and recall (from 83.5% to 93.5%), achieving a mean average precision (mAP) of 97.3% at an IoU threshold of 0.7. We also compared YOLOv8m with MediaPipe and an integrated YOLOv8 + MediaPipe approach. The combined method outperformed the individual models, achieving an accuracy of 99% and a recall of 99%. These findings underscore the benefits of model integration in enhancing gesture recognition accuracy and localization for real-time applications. The results suggest promising avenues for future research in HCI, particularly in augmented reality and assistive technologies, where improved gesture recognition can significantly enhance user experience.

Keywords: YOLOv8, mediapipe, finger tracking, joint estimation, human-computer interaction (HCI)

Procedia PDF Downloads 14

Authors: Cyrus Addy, Venkata Sriram Siddhardh Nadendla, Kwame Awuah-Offei

Abstract:

Surface robots in modern underground mine rescue operations suffer from several limitations in enabling a prompt self-rescue. Therefore, the possibility of designing and deploying in-mine robots to expedite miner self-rescue can have a transformative impact on miner safety. These in-mine robots for miner self-rescue can be envisioned to carry out diverse tasks such as object detection, autonomous navigation, and payload delivery. Specifically, this paper investigates the challenges in the design of object detection algorithms for in-mine robots using thermal images, especially to detect people in real-time. A total of 125 thermal images were collected in the Missouri S&T Experimental Mine with the help of student volunteers using the FLIR TG 297 infrared camera, which were pre-processed into training and validation datasets with 100 and 25 images, respectively. Three state-of-the-art, pre-trained real-time object detection models, namely YOLOv5, YOLO-FIRI, and YOLOv8, were considered and re-trained using transfer learning techniques on the training dataset. On the validation dataset, the re-trained YOLOv8 outperforms the re-trained versions of both YOLOv5, and YOLO-FIRI.

Keywords: miner self-rescue, object detection, underground mine, YOLO

Procedia PDF Downloads 86

Authors: Ashwini Jarali, Prajwal Lalpotu, Shreya Jadhav, Snehal Kavathekar, Sanskruti Lad

Abstract:

This paper reviews recent advancements in pothole detection technologies, comparing various methods, including deep learning models like YOLO (You Only Look Once) and SSD (Single Shot Detector) and UAV-based systems with multispectral imaging. YOLO v8 Nano emerges as a highly effective model, balancing speed and accuracy in real-time detection, while SSD demonstrates superior precision in certain scenarios. Additionally, UAVs enhance detection by providing early insights into asphalt damage. Image processing techniques and manually labeled datasets are also employed to improve model training and accuracy. The paper evaluates the strengths and limitations of these methods, examining factors like computational efficiency, environmental adaptability, and real-time application. It further explores future directions in this field, focusing on optimizing detection techniques and integrating advanced sensors to enhance road safety and maintenance.

Keywords: YOLO(You Look Only Once), Pothole Detection, YOLOV8, YOLOV5

Procedia PDF Downloads 5

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The educational system faces a significant concern with regards to Dyslexia and Dysgraphia, which are learning disabilities impacting reading and writing abilities. This is particularly challenging for children who speak the Sinhala language due to its complexity and uniqueness. Commonly used methods to detect the risk of Dyslexia and Dysgraphia rely on subjective assessments, leading to limited coverage and time-consuming processes. Consequently, delays in diagnoses and missed opportunities for early intervention can occur. To address this issue, the project developed a hybrid model that incorporates various deep learning techniques to detect the risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16, and YOLOv8 models were integrated to identify handwriting issues. The outputs of these models were then combined with other input data and fed into an MLP model. Hyperparameters of the MLP model were fine-tuned using Grid Search CV, enabling the identification of optimal values for the model. This approach proved to be highly effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention. The Resnet50 model exhibited a training accuracy of 0.9804 and a validation accuracy of 0.9653. The VGG16 model achieved a training accuracy of 0.9991 and a validation accuracy of 0.9891. The MLP model demonstrated impressive results with a training accuracy of 0.99918, a testing accuracy of 0.99223, and a loss of 0.01371. These outcomes showcase the high accuracy achieved by the proposed hybrid model in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, dyslexia, dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 67

Authors: Budhvin T. Withana, Sulochana Rupasinghe

Abstract:

The problem of Dyslexia and Dysgraphia, two learning disabilities that affect reading and writing abilities, respectively, is a major concern for the educational system. Due to the complexity and uniqueness of the Sinhala language, these conditions are especially difficult for children who speak it. The traditional risk detection methods for Dyslexia and Dysgraphia frequently rely on subjective assessments, making it difficult to cover a wide range of risk detection and time-consuming. As a result, diagnoses may be delayed and opportunities for early intervention may be lost. The project was approached by developing a hybrid model that utilized various deep learning techniques for detecting risk of Dyslexia and Dysgraphia. Specifically, Resnet50, VGG16 and YOLOv8 were integrated to detect the handwriting issues, and their outputs were fed into an MLP model along with several other input data. The hyperparameters of the MLP model were fine-tuned using Grid Search CV, which allowed for the optimal values to be identified for the model. This approach proved to be effective in accurately predicting the risk of Dyslexia and Dysgraphia, providing a valuable tool for early detection and intervention of these conditions. The Resnet50 model achieved an accuracy of 0.9804 on the training data and 0.9653 on the validation data. The VGG16 model achieved an accuracy of 0.9991 on the training data and 0.9891 on the validation data. The MLP model achieved an impressive training accuracy of 0.99918 and a testing accuracy of 0.99223, with a loss of 0.01371. These results demonstrate that the proposed hybrid model achieved a high level of accuracy in predicting the risk of Dyslexia and Dysgraphia.

Keywords: neural networks, risk detection system, Dyslexia, Dysgraphia, deep learning, learning disabilities, data science

Procedia PDF Downloads 123

Authors: Yifan Hou, Haibo Liu, Le Jiang, Wandong Su, Binqing Wang

Abstract:

Road defect detection is crucial for modern urban management and infrastructure maintenance. Traditional road defect detection methods mostly rely on manual labor, which is not only inefficient but also difficult to ensure their reliability. However, existing deep learning-based road defect detection models have poor detection performance in complex environments and lack robustness to multi-scale targets. To address this challenge, this paper proposes a distinct detection framework based on the one stage algorithm network structure. This article designs a deep feature extraction network based on RCSDarknet, which applies channel shuffling to enhance information fusion between tensors. Through repeated stacking of RCS modules, the information flow between different channels of adjacent layer features is enhanced to improve the model's ability to capture target spatial features. In addition, a multi-scale feature fusion mechanism with weighted dual flow paths was adopted to fuse spatial features of different scales, thereby further improving the detection performance of the model at different scales. To validate the performance of the proposed algorithm, we tested it using the RDD2022 dataset. The experimental results show that the enhancement algorithm achieved 84.14% mAP, which is 1.06% higher than the currently advanced YOLOv8 algorithm. Through visualization analysis of the results, it can also be seen that our proposed algorithm has good performance in detecting targets of different scales in complex scenes. The above experimental results demonstrate the effectiveness and superiority of the proposed algorithm, providing valuable insights for advancing real-time road defect detection methods.

Keywords: roads, defect detection, visualization, deep learning

Procedia PDF Downloads 17

Authors: Ezil Sam Leni, Shalen S.

Abstract:

Transport service monitoring and upkeep are essential components of smart city initiatives. The main risks to the relevant departments and authorities are the ever-increasing vehicular traffic and the conditions of the roads. In India, the economy is greatly impacted by the road transport sector. In 2021, the Ministry of Road Transport and Highways Transport, Government of India, produced a report with statistical data on traffic accidents. The data included the number of fatalities, injuries, and other pertinent criteria. This study proposes a distributed infrastructure for the monitoring, detection, and reporting of potholes to the appropriate authorities. In a distributed environment, the nodes are the edge devices, and local edge servers, and global servers. The edge devices receive the initial model to be employed from the global server. The YOLOv8 model for pothole detection is used in the edge devices. The edge devices run the pothole detection model, gather the pothole images on their path, and send the updates to the nearby edge server. The local edge server selects the clients for its aggregation process, aggregates the model updates and sends the updates to the global server. The global server collects the updates from the local edge servers, performs aggregation and derives the updated model. The updated model has the information about the potholes received from the local edge servers and notifies the updates to the local edge servers and concerned authorities for monitoring and maintenance of road conditions. The entire process is implemented in FedCV distributed environment with the implementation using the client-server model and aggregation entities. After choosing the clients for its aggregation process, the local edge server gathers the model updates and transmits them to the global server. After gathering the updates from the regional edge servers, the global server aggregates them and creates the updated model. Performance indicators and the experimentation environment are assessed, discussed, and presented. Accelerometer data may be taken into consideration for improved performance in the future development of this study, in addition to the images captured from the transportation routes.

Keywords: federated Learning, pothole detection, distributed framework, federated averaging

Procedia PDF Downloads 109