Search

Plastic waste pollution in the aquatic environment poses a serious threat to marine ecosystems and human health. This research aims to develop a prototype of an Autonomous Underwater Robot (AUR) based on the Raspberry Pi 5 equipped with the YOLO V8 algorithm for real-time detection and classification of plastic waste. This AUR uses a PID control system for precise movement stabilization and navigation. The research methodology includes three stages: analysis, design, and implementation, with a System Development Lifecycle (SDLC) approach. The results show that YOLO V8 achieves an object detection mAP of 0.6772 at the IoU threshold of 0.5, with a detection accuracy of 89.6%. The optimal PID setting (Kp:Ki = 125:12:8) results in an object center accuracy of 96.4%, orientation stability of 90.8%, and a completion time of 2 seconds. These findings show that AUR is effective in dealing with plastic waste in waters in a sustainable manner, with implications for improving waste management solutions in the marine environment. [ABSTRACT FROM AUTHOR]

Robotic harvesting had been constrained by the low positioning accuracy of strawberry stem picking points and the significant challenge of identifying occluded strawberries. In this study, we proposed an improved YOLO v8 model combined with Pose key-point detection for enhanced strawberry recognition and localization. The accuracy of picking point localization was also improved, especially for occluded strawberries in complex environments. To optimize the YOLO v8 model, we introduced the Bidirectional Feature Pyramid Network (BiFPN) and the Generalized Attention Module (GAM), which enhanced bidirectional information flow, dynamically allocated feature weights, and focused on extracting features of small targets and enhancing the features of occluded regions. As a result, the model's ability to accurately detect and localize strawberries in complex environments was significantly improved. Experimental results showed that the improved YOLO v8- pose model outperformed the original model in several metrics: the Precision (P) increased by 6. 01 percentage points, Recall (R) by 1. 98 percentage points, mean Average Precision (mAP) by 6. 67 percentage points, and mean Average Precision for key points (mAPkp) by 7. 85 percentage points. The positioning accuracy for strawberry stem picking points, based on key-point detection, achieved errors of just 1. 4 mm in both the X and Y directions and 2. 2 mm in the Z direction. Additionally, the occlusion level was classified according to the overlap area of occluded strawberries, and the model's performance under varying occlusion conditions was assessed. Under these conditions, the mAPkp of the improved YOLO v8-pose model increased by 9. 78 percentage points compared to the original model. Field trials further validated the model's effectiveness, with the strawberry-picking robot achieving a 95% success rate, picking each strawberry within 10 seconds. The high success rate and short picking time demonstrated the practicality of the model in real-world agricultural settings, indicating its high efficiency and accuracy. The improved YOLO v8 model with key-point detection accurately and robustly recognized strawberries, leveraged multi-scale features with the BiFPN architecture, and focused attention on relevant regions with the GAM, especially for occluded strawberries. These advancements significantly improved overall performance in precision, recall, and average precision, particularly under occlusion scenarios. In conclusion, these advanced techniques were integrated into a more capable strawberry-picking robot system. The enhanced accuracy and efficiency achieved in recognizing and localizing strawberries, even in challenging occlusion scenarios, highlighted the system's potential for practical agricultural applications. The findings contributed significantly to automated strawberry harvesting in agricultural robotics, paving the way for more efficient and cost-effective farming solutions in sustainable production. [ABSTRACT FROM AUTHOR]

The purpose of this research is to address the challenges faced by visually impaired individuals, particularly in handling household appliances independently. With approximately 285 million visually impaired individuals worldwide, technological solutions are crucial to enhancing their accessibility and independence. This paper introduces a Smart Assistance System designed to empower visually impaired individuals to interact with household appliances in real-time without assistance. In this study, three Convolutional Neural Network (CNN) algorithms are compared to develop the system. The evaluation metrics include accuracy, precision, recall, F1 score, and hamming loss on validation images. The performance comparison reveals that the custom architecture CNN, MobileNetv2, and YOLO models achieve F1 scores of 0.43, 0.63, and 0.24, respectively. To enhance object detection and classification, the paper suggests implementing bounding box buttons categorization using YOLOv8, which demonstrates superior performance with a 95% classification accuracy on testing images of home appliance buttons. They face similar difficult while in public and accessing public property. Expanding upon the proposed system's capabilities, the paper introduces the concept of panic button detection and activation in a bus environment tailored for blind individuals. This system relies on various factors such as the number of people onboard, heart rate monitoring, and the detection of distress signals or SOS sounds emitted by the user. By integrating advanced sensing technologies and intelligent algorithms, this panic button detection system aims to provide prompt assistance and ensure the safety of visually impaired passengers in public transportation settings. [ABSTRACT FROM AUTHOR]

The rapid evolution of digital technology and the increasing integration of artificial intelligence in agriculture have paved the way for groundbreaking solutions in plant identification. This research pioneers the development and training of a deep learning model to identify three aromatic plants—rosemary, mint, and bay leaf—using advanced computer-aided detection within the You Only Look Once (YOLO) framework. Employing the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology, the study meticulously covers data understanding, preparation, modeling, evaluation, and deployment phases. The dataset, consisting of images from diverse devices and annotated with bounding boxes, was instrumental in the training process. The model's performance was evaluated using the mean average precision at a 50% intersection over union (mAP50), a metric that combines precision and recall. The results demonstrated that the model achieved a precision of 0.7 or higher for each herb, though recall values indicated potential over-detection, suggesting the need for database expansion and methodological enhancements. This research underscores the innovative potential of deep learning in aromatic plant identification and addresses both the challenges and advantages of this technique. The findings significantly advance the integration of artificial intelligence in agriculture, promoting greater efficiency and accuracy in plant identification. [ABSTRACT FROM AUTHOR]

Addressing the challenges in detecting surface floating litter in artificial lakes, including complex environments, uneven illumination, and susceptibility to noise and weather, this paper proposes an efficient and lightweight Ghost-YOLO (You Only Look Once) v8 algorithm. The algorithm integrates advanced attention mechanisms and a small-target detection head to significantly enhance detection performance and efficiency. Firstly, an SE (Squeeze-and-Excitation) mechanism is incorporated into the backbone network to fortify the extraction of resilient features and precise target localization. This mechanism models feature channel dependencies, enabling adaptive adjustment of channel importance, thereby improving recognition of floating litter targets. Secondly, a 160 × 160 small-target detection layer is designed in the feature fusion neck to mitigate semantic information loss due to varying target scales. This design enhances the fusion of deep and shallow semantic information, improving small target feature representation and enabling better capture and identification of tiny floating litter. Thirdly, to balance performance and efficiency, the GhostConv module replaces part of the conventional convolutions in the feature fusion neck. Additionally, a novel C2fGhost (CSPDarknet53 to 2-Stage Feature Pyramid Networks Ghost) module is introduced to further reduce network parameters. Lastly, to address the challenge of occlusion, a new loss function, WIoU (Wise Intersection over Union) v3 incorporating a flexible and non-monotonic concentration approach, is adopted to improve detection rates for surface floating litter. The outcomes of the experiments demonstrate that the Ghost-YOLO v8 model proposed in this paper performs well in the dataset Marine, significantly enhances precision and recall by 3.3 and 7.6 percentage points, respectively, in contrast with the base model, mAP@0.5 and mAP@0.5:0.95 improve by 5.3 and 4.4 percentage points and reduces the computational volume by 1.88 MB, the FPS value hardly decreases, and the efficient real-time identification of floating debris on the water's surface can be achieved cost-effectively. [ABSTRACT FROM AUTHOR]

The rapid evolution of digital technology and the increasing integration of artificial intelligence in agriculture have paved the way for groundbreaking solutions in plant identification. This research pioneers the development and training of a deep learning model to identify three aromatic plants—rosemary, mint, and bay leaf—using advanced computer-aided detection within the You Only Look Once (YOLO) framework. Employing the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology, the study meticulously covers data understanding, preparation, modeling, evaluation, and deployment phases. The dataset, consisting of images from diverse devices and annotated with bounding boxes, was instrumental in the training process. The model’s performance was evaluated using the mean average precision at a 50% intersection over union (mAP50), a metric that combines precision and recall. The results demonstrated that the model achieved a precision of 0.7 or higher for each herb, though recall values indicated potential over-detection, suggesting the need for database expansion and methodological enhancements. This research underscores the innovative potential of deep learning in aromatic plant identification and addresses both the challenges and advantages of this technique. The findings significantly advance the integration of artificial intelligence in agriculture, promoting greater efficiency and accuracy in plant identification.

Abstract Vehicle identification systems are vital components that enable many aspects of contemporary life, such as safety, trade, transit, and law enforcement. They improve community and individual well-being by increasing vehicle management, security, and transparency. These tasks entail locating and extracting license plates from images or video frames using computer vision and machine learning techniques, followed by recognizing the letters or digits on the plates. This paper proposes a new license plate detection and recognition method based on the deep learning YOLO v8 method, image processing techniques, and the OCR technique for text recognition. For this, the first step was the dataset creation, when gathering 270 images from the internet. Afterward, CVAT (Computer Vision Annotation Tool) was used to annotate the dataset, which is an open-source software platform made to make computer vision tasks easier to annotate and label images and videos. Subsequently, the newly released Yolo version, the Yolo v8, has been employed to detect the number plate area in the input image. Subsequently, after extracting the plate the k-means clustering algorithm, the thresholding techniques, and the opening morphological operation were used to enhance the image and make the characters in the license plate clearer before using OCR. The next step in this process is using the OCR technique to extract the characters. Eventually, a text file containing only the character reflecting the vehicle's country is generated. To ameliorate the efficiency of the proposed approach, several metrics were employed, namely precision, recall, F1-Score, and CLA. In addition, a comparison of the proposed method with existing techniques in the literature has been given. The suggested method obtained convincing results in both detection as well as recognition by obtaining an accuracy of 99% in detection and 98% in character recognition.

When dealing with small targets in lung cancer detection, the YOLO V8 algorithm may encounter false positives and misses. To address this issue, this study proposes an enhanced YOLO V8 detection model. The model integrates a large separable kernel attention mechanism into the C2f module to expand the information retrieval range, strengthens the extraction of lung cancer features in the Backbone section, and achieves effective interaction between multi-scale features in the Neck section, thereby enhancing feature representation and robustness. Additionally, depth-wise convolution and Coordinate Attention mechanisms are embedded in the Fast Spatial Pyramid Pooling module to reduce feature loss and improve detection accuracy. This study introduces a Minimum Point Distance-based IOU loss to enhance correlation between predicted and ground truth bounding boxes, improving adaptability and accuracy in small target detection. Experimental validation demonstrates that the improved network outperforms other mainstream detection networks in terms of average precision values and surpasses other classification networks in terms of accuracy. These findings validate the outstanding performance of the enhanced model in the localization and recognition aspects of lung cancer auxiliary diagnosis. [ABSTRACT FROM AUTHOR]

The main purpose of this study is to generate defect images of body parts using a GAN (generative adversarial network) and compare and analyze the performance of the YOLO (You Only Look Once) v7 and v8 object detection models. The goal is to accurately judge good and defective products. Quality control is very important in the automobile industry, and defects in body parts directly affect vehicle safety, so the development of highly accurate defect detection technology is essential. This study ensures data diversity by generating defect images of car body parts using a GAN and through this, compares and analyzes the object detection performance of the YOLO v7 and v8 models to present an optimal solution for detecting defects in car parts. Through experiments, the dataset was expanded by adding fake defect images generated by the GAN. The performance experiments of the YOLO v7 and v8 models based on the data obtained through this approach demonstrated that YOLO v8 effectively identifies objects even with a smaller amount of data. It was confirmed that defects could be detected. The readout of the detection system can be improved through software calibration. [ABSTRACT FROM AUTHOR]

Vehicle identification systems are vital components that enable many aspects of contemporary life, such as safety, trade, transit, and law enforcement. They improve community and individual well-being by increasing vehicle management, security, and transparency. These tasks entail locating and extracting license plates from images or video frames using computer vision and machine learning techniques, followed by recognizing the letters or digits on the plates. This paper proposes a new license plate detection and recognition method based on the deep learning YOLO v8 method, image processing techniques, and the OCR technique for text recognition. For this, the first step was the dataset creation, when gathering 270 images from the internet. Afterward, CVAT (Computer Vision Annotation Tool) was used to annotate the dataset, which is an open-source software platform made to make computer vision tasks easier to annotate and label images and videos. Subsequently, the newly released Yolo version, the Yolo v8, has been employed to detect the number plate area in the input image. Subsequently, after extracting the plate the k-means clustering algorithm, the thresholding techniques, and the opening morphological operation were used to enhance the image and make the characters in the license plate clearer before using OCR. The next step in this process is using the OCR technique to extract the characters. Eventually, a text file containing only the character reflecting the vehicle's country is generated. To ameliorate the efficiency of the proposed approach, several metrics were employed, namely precision, recall, F1-Score, and CLA. In addition, a comparison of the proposed method with existing techniques in the literature has been given. The suggested method obtained convincing results in both detection as well as recognition by obtaining an accuracy of 99% in detection and 98% in character recognition. [ABSTRACT FROM AUTHOR]

In the midst of a rapidly evolving economic landscape, the global demand for oil is steadily escalating. This increased demand has fueled marine extraction and maritime transportation of oil, resulting in a consequential and uneven surge in maritime oil spills. Characterized by their abrupt onset, rapid pollution dissemination, prolonged harm, and challenges in short-term containment, oil spill accidents pose significant economic and environmental threats. Consequently, it is imperative to adopt effective and reliable methods for timely detection of oil spills to minimize the damage inflicted by such incidents. Leveraging the YOLO deep learning network, this paper introduces a methodology for the automated detection of oil spill targets. The experimental data pre-processing incorporated denoise, grayscale modification, and contrast boost. Subsequently, realistic radar oil spill images were employed as extensive training samples in the YOLOv8 network model. The trained detection model demonstrated rapid and precise identification of valid oil spill regions. Ultimately, the oil films within the identified spill regions were extracted utilizing the simulated annealing particle swarm optimization (SA-PSO) algorithm. The proposed method for offshore oil spill survey presented here can offer immediate and valid data support for regular patrols and emergency reaction efforts. [ABSTRACT FROM AUTHOR]

Forecasting violence has become a critical obstacle in the field of video monitoring to guarantee public safety. Lately, YOLO (You Only Look Once) has become a popular and effective method for detecting weapons. However, identifying and forecasting violence remains a challenging endeavor. Additionally, the classification results had to be enhanced with semantic information. This study suggests a method for forecasting violent incidents by utilizing Yolov9 and ontology. The authors employed Yolov9 to identify and categorize weapons and individuals carrying them. Ontology is utilized for semantic prediction to assist in predicting violence. Semantic prediction happens through the application of a SPARQL query to the identified frame label. The authors developed a Threat Events Ontology (TEO) to gain semantic significance. The system was tested with a fresh dataset obtained from a variety of security cameras and websites. The VP Dataset comprises 8739 images categorized into 9 classes. The authors examined the outcomes of using Yolov9 in conjunction with ontology in comparison to using Yolov9 alone. The findings show that by combining Yolov9 with ontology, the violence prediction system's semantics and dependability are enhanced. The suggested system achieved a mean Average Precision (mAP) of 83.7 %, 88% for precision, and 76.4% for recall. However, the mAP of Yolov9 without TEO ontology achieved a score of 80.4%. It suggests that this method has a lot of potential for enhancing public safety. The authors finished all training and testing processes on Google Colab's GPU. That reduced the average duration by approximately 90.9%. The result of this work is a next level of object detectors that utilize ontology to improve the semantic significance for real-time end-to-end object detection.

The objective of this study is to develop and apply deep neural networks for the automation of crack detection in buildings. The methodology involved training the YOLO v8 network with images collected from the internet, aiming to identify and locate cracks in real time. The model obtained 80% accuracy in validation with images not used in training, despite performance limitations in Google Collab. These limitations included restrictions on the execution environment, and the model is specific to cracks. The originality of the tool lies in its relevance for the automated detection of cracks, with the potential to extend to other pathological manifestations. It is concluded that the application of deep neural networks offers an efficient solution for the identification of problems in buildings.

Insulators are crucial components of power grid systems, safeguarding against electrical conductor breaks. However, their prolonged exposure to complex outdoor environments renders them susceptible to defects. In this study, we address the importance of accurate insulator defect detection and propose an approach using the You Only Look Once (YOLO) object detection framework. In particular, we compare the performance of YOLO v8 against YOLO v7 in detecting two specific types of insulator defects—broken insulators and flashover damaged insulators. Leveraging the Insulator Defect Image Dataset, our results demonstrate that YOLO v8 achieves superior accuracy with a rate of 98.99 percent along with a mean average precision (mAP) of 99.10 percent. The findings underscore the efficacy of YOLO v8 in improving the reliability and resilience of power grid systems by allowing timely and accurate detection of insulator defects in complex outdoor environments. This research contributes to advancing the field of power grid infrastructure monitoring and maintenance, ultimately facilitating more effective strategies for mitigating the consequence of insulator defects on power grid system performance and reliability.

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning. [ABSTRACT FROM AUTHOR]

Detection of rice leaf pests is important in agriculture because it can help farmers determine appropriate preventive measures. One method that can be used to detect rice leaf pests is digital image processing technology. In this research, proof of suitability for solving this case was carried out between the Convolutional Neural Network (CNN) algorithm which was run offline with R-CNN and YOLOv8 for detecting rice leaf pests. At the data preparation stage, images of rice leaves were taken from various sources with a total of 100 images taken from website data and 10 images taken from the research site. Next, preprocessing and data augmentation are carried out to improve image quality and increase data variation. At the model training stage, a training and evaluation process is carried out using two types of algorithms, namely R-CNN and YOLOv8. The accuracy of the testing results using the same data using Yolov8 obtained 87.0% accuracy and 79% precision, while using R-CNN the results obtained were 85% for accuracy and 75% for precision with data divided into 80 training data 20 validation data and 10 testing data. Labeling the dataset uses Makesensei which has been completely standardized, with the resulting parameters being the spots on rice leaves.

The use of helmets is crucial for safeguarding the lives of construction workers. In the construction sector, computer vision technology is extensively employed to detect and monitor the correct usage of helmets by workers. Currently, there are three classical types of helmet detection algorithms: digital image processing, convolutional neural network (CNN), and Transformer. Digital images are based on manual processing of the features, which proves to be inefficient and lacks robustness. CNN exhibits high accuracy but lacks robustness, which limits its effectiveness in complex environments. This paper proposes an algorithm called the Highly Robust Helmet Detection Algorithm (HRHD), designed to attain precise detection of helmet usage at construction sites with varying conditions. The proposed model leverages the YOLO v8s architecture and incorporates the Coordinate Attention module to enhance the model’s focus on important features. It also introduces the Transformer structure to extract global features, and employs the RepConv module to diminish the model’s computational demands, thus achieving a balance between inference speed and detection accuracy. The experiments demonstrate that the proposed model in this paper significantly improves the accuracy compared to YOLO v10 and YOLO v8s. Additionally, the model maintains a rapid inference rate, suggesting substantial potential for application within the construction engineering domain.

Autonomous vehicles can transform the transportation sector by offering a safer and more effective means of travel. However, the success of self-driving cars depends on their ability to navigate complex road conditions, including the detection of potholes. Potholes pose a substantial risk to vehicles and passengers, leading to potential damage and safety hazards, making their detection a critical task for autonomous driving. In this work, we propose a robust and efficient solution for pothole detection using the "you look only once (YOLO) algorithm of version 8, the newest deep learning object detection algorithm." Our proposed system employs a deep learning methodology to identify real-time potholes, enabling autonomous vehicles to avoid potential hazards and minimise accident risk. We assess the effectiveness of our system using publicly available datasets and show that it outperforms existing state-of- the-art approaches interms of accuracy and efficiency. Additionally, we investigate different data augmentation methods to enhance the detection capabilities of our proposed system. Our results demonstrate that YOLO V8-based pothole detection is a promising solution for autonomous driving and can significantly improve the safety and reliability of self-driving vehicles on the road. The results of our study are also compared with the results of YOLO V5. [ABSTRACT FROM AUTHOR]

Implementing and monitoring traffic rules are essential for reducing accident rates and traffic rule violations. The automated traffic rule monitoring system ensures strict adherence to the traffic rules with low human effort. The system proposed identifies and acknowledges the two-wheelers violating the traffic rule regarding triple riders. The intersection points in the University Campus act as the data collection centres and collects the data through live recordings captured by surveillance cameras. The proposed system consists of detection and automatic number plate recognition. To implement this system, the Darknet framework is used, which is based on You Only Look Once (YOLO v8) for identifying two-wheelers with triple riders. The Depth estimation algorithm is used to detect vehicles and persons, which can accurately detect near and far objects. The vehicles are classified as Violator or No Violator. The Connectionist Temporal classification algorithm is used to classify the vehicles as violators or no violators. The two-wheeler classified as a Violator is stored in the database along with the vehicle license plate number, which can be penalised by traffic monitoring authorities. The implementation results show that the system is viable, efficient and reliable. Thus, make the two-wheeler follow the traffic rules properly, reducing the chance of irresponsible driving. The self-generated dataset detects the traffic rule violation and license plate number extraction. The system is trained on the considered dataset, and the best weights are used to implement the model. The proposed model achieves 94%, 96% and 97% performance for detecting triple rider, license plate and motorcycle detection. [ABSTRACT FROM AUTHOR]

When dealing with small targets in lung cancer detection, the YOLO V8 algorithm may encounter false positives and misses. To address this issue, this study proposes an enhanced YOLO V8 detection model. The model integrates a large separable kernel attention mechanism into the C2f module to expand the information retrieval range, strengthens the extraction of lung cancer features in the Backbone section, and achieves effective interaction between multi-scale features in the Neck section, thereby enhancing feature representation and robustness. Additionally, depth-wise convolution and Coordinate Attention mechanisms are embedded in the Fast Spatial Pyramid Pooling module to reduce feature loss and improve detection accuracy. This study introduces a Minimum Point Distance-based IOU loss to enhance correlation between predicted and ground truth bounding boxes, improving adaptability and accuracy in small target detection. Experimental validation demonstrates that the improved network outperforms other mainstream detection networks in terms of average precision values and surpasses other classification networks in terms of accuracy. These findings validate the outstanding performance of the enhanced model in the localization and recognition aspects of lung cancer auxiliary diagnosis.

In the midst of a rapidly evolving economic landscape, the global demand for oil is steadily escalating. This increased demand has fueled marine extraction and maritime transportation of oil, resulting in a consequential and uneven surge in maritime oil spills. Characterized by their abrupt onset, rapid pollution dissemination, prolonged harm, and challenges in short-term containment, oil spill accidents pose significant economic and environmental threats. Consequently, it is imperative to adopt effective and reliable methods for timely detection of oil spills to minimize the damage inflicted by such incidents. Leveraging the YOLO deep learning network, this paper introduces a methodology for the automated detection of oil spill targets. The experimental data pre-processing incorporated denoise, grayscale modification, and contrast boost. Subsequently, realistic radar oil spill images were employed as extensive training samples in the YOLOv8 network model. The trained detection model demonstrated rapid and precise identification of valid oil spill regions. Ultimately, the oil films within the identified spill regions were extracted utilizing the simulated annealing particle swarm optimization (SA-PSO) algorithm. The proposed method for offshore oil spill survey presented here can offer immediate and valid data support for regular patrols and emergency reaction efforts.

Autonomous vehicles can transform the transportation sector by offering a safer and more effective means of travel. However, the success of self-driving cars depends on their ability to navigate complex road conditions, including the detection of potholes. Potholes pose a substantial risk to vehicles and passengers, leading to potential damage and safety hazards, making their detection a critical task for autonomous driving. In this work, we propose a robust and efficient solution for pothole detection using the “you look only once (YOLO) algorithm of version 8, the newest deep learning object detection algorithm.” Our proposed system employs a deep learning methodology to identify real-time potholes, enabling autonomous vehicles to avoid potential hazards and minimise accident risk. We assess the effectiveness of our system using publicly available datasets and show that it outperforms existing state-of-the-art approaches in terms of accuracy and efficiency. Additionally, we investigate different data augmentation methods to enhance the detection capabilities of our proposed system. Our results demonstrate that YOLO V8-based pothole detection is a promising solution for autonomous driving and can significantly improve the safety and reliability of self-driving vehicles on the road. The results of our study are also compared with the results of YOLO V5.

In order to solve the problems of high leakage rate, high false detection rate, low detection success rate and large model volume of small targets in the traditional target detection algorithm for Unmanned Aerial Vehicle (UAV) aerial images, a lightweight You Only Look Once (YOLO) v8 algorithm model Lightweight (LW)-YOLO v8 is proposed. By increasing the channel attention mechanism Squeeze-and-Excitation (SE) module, this method can adaptively improves the model's ability to extract features from small targets; at the same time, the lightweight convolution technology is introduced into the Conv module, where the ordinary convolution is replaced by the GSConv module, which can effectively reduce the model computational volume; on the basis of the GSConv module, a single aggregation module VoV-GSCSPC is designed to optimize the model structure in order to achieve a higher computational cost-effectiveness. The experimental results show that the LW-YOLO v8 model's mAP@0.5 metrics on the VisDrone2019 dataset are more favorable than those on the YOLO v8n model, improving by 3.8 percentage points, and the computational amount is reduced to 7.2 GFLOPs. The LW-YOLO v8 model proposed in this work can effectively accomplish the task of detecting small targets in aerial images from UAV at a lower cost. [ABSTRACT FROM AUTHOR]

Crop yields in paddy fields can be greatly lowered by weeds and crowded places. Conventional techniques for identifying thick areas and weeds are frequently labor-and time-intensive. While machine learning-based techniques present a viable substitute, creating a single model that is capable of properly and effectively completing both jobs is difficult. This study uses image and video processing to present a multi-task machine-learning model for weed detection and dense area identification in paddy fields. The YOLO V8 deep learning architecture, which is renowned for its great accuracy and speed, serves as the foundation for the model. We gathered a sizable dataset of labeled weeds and thick areas from paddy field photos and videos in order to train the algorithm. After that, the model was trained to simultaneously identify dense areas and detect weeds. The model was assessed using a different test dataset once it had been trained. The outcomes demonstrated that even when used with video streams, the model maintained good accuracy on both tasks. The suggested model can be utilized to create other paddy field management applications, including: • Automated weed detection: The suggested model has the potential to assist farmers in increasing yields and lessening their environmental effects by automating the processes of weed detection and dense area designation. [ABSTRACT FROM AUTHOR]

The construction industry has high accident and fatality rates owing to time and cost pressures as well as hazardous working environments caused by heavy construction equipment and temporary structures. Thus, safety management at construction sites is essential, and extensive investments are made in management and technology to reduce accidents. This study aims to improve the accuracy of object recognition and classification that is the foundation of the automatic detection of safety risk factors at construction sites, using YOLO v5, which has been acknowledged in several studies for its high performance, and the recently released YOLO v8. Images were collected through web crawling and labeled into three classes to form the dataset. Based on this dataset, accuracy was improved by changing epochs, optimizers, and hyperparameter conditions. In each YOLO version, the highest accuracy is achieved by the extra-large model, with mAP50 test accuracies of 94.1% in v5 and 95.1% in v8. This study could be further expanded for application in various management tools at construction sites to improve the work process, quality control, and progress management in addition to safety management through the collection of more image data and automation for accuracy improvement. [ABSTRACT FROM AUTHOR]

In Senegal, stock recovery and fish classification are based on manual data collection, and the fish caught by the fishery are not often declared. What's more, data collection suffers from a lack of tools for monitoring and counting fish caught at fishing docks. Researchers have carried out studies on the fishery in Senegal, but data collection is almost non-existent. Moreover, there is no local fisheries database or automatic detection and counting algorithm. In this paper, a semantic segmentation algorithm is proposed using intelligent systems for the collection of fishery catches, for the formation of the local database. The data are collected by taking images of fish at the Soumbédioune fishing wharf in Senegal, and are completed with the Fishbase database. They were applied to the algorithm and resulted in a segmented dataset with masks. This constitutes our local database. The database is used with YOLO v8. The latter is very important for detecting images with bounding boxes in order to train the model. The results obtained are very promising for the proposed automatic poison detection and counting model. For example, the recall-confidence scores translate into bounding box performance with scores ranging from 0.01 to 0.75, confirming the performance of this model with bounding boxes. [ABSTRACT FROM AUTHOR]

In this work, we present a comprehensive study on fish detection in underwater environments using sonar images from the Caltech Fish Counting Dataset (CFC). We use the CFC dataset, initially designed for tracking purposes, to optimize and evaluate the performance of YOLO v7 and YOLO v8 models in fish detection. Our findings demonstrate the high performance of these deep learning models in accurately detecting fish species in sonar images. In our evaluation, YOLO v7 achieved an average precision of 68.3% (AP50) and 62.15% (AP75), while YOLO v8 demonstrated an even better performance with an average precision of 72.47% (AP50) and 66.21% (AP75) across the test dataset of 334,017 images. These high-precision results underscore the effectiveness of these models in fish detection tasks under various underwater conditions. With a dataset of 162,680 training images and 334,017 test images, our evaluation provides valuable insights into the models performance and generalization across diverse underwater conditions. This study contributes to the advancement of underwater fish detection by showcasing the suitability of the CFC dataset and the efficacy of YOLO v7 and YOLO v8 models. These insights can pave the way for further advancements in fish detection, supporting conservation efforts and sustainable fisheries management.

Mastering a lightweight method for the identification of pavement surface cracks plays a vital role in enhancing the efficiency and accuracy of pavement crack detection. However, the existing crack detection methods typically concentrate on improving model performance while neglecting the study of lightweight identification methods, causing inefficient crack detection. Therefore, this study aims to investigate a lightweight identification method for pavement cracks. High-definition vehicle-mounted cameras were employed to collect pavement crack images across multiple districts in Shenzhen, China, resulting in a dataset containing 20256 images. In addition, a pavement crack detection method based on the You Only Look Once version 8 (YOLO v8) model was proposed. On this basis, a knowledge distillation model enhanced by multiple teacher-assistants (KDMTA) was established to explore the impact of different teacher assistants and distillation paths on model performance. The results indicate that in the proposed KDMTA model, each level of teacher-assistant (TA) model can absorb diverse aspects of knowledge from the teacher models, thus broadening the range of insights. Subsequently, the information is imparted to lower-level TA models and the student model, expanding the perspective from which the student model acquires knowledge. Therefore, this improves the model's generalization performance and its effectiveness in target detection. The type and number of teacher assistant models, as well as the distillation path, influence the model performance. The random learning strategy enriches the combination and transfer of knowledge among teacher models, TA models, and student models, achieving lightweight identification for pavement crack. According to the results, the crack identification accuracy reaches 95.79 %, the mAP reaches 81.07 %, and the image processing speed has been improved by 79.6 %. This study enhances the efficiency and accuracy of pavement crack detection, providing methodological support for the rapid and accurate identification of pavement cracks. This study offers a novel method for the rapid and accurate identification of pavement cracks, which can assist management authorities to timely identify and repair pavement defects, reducing maintenance costs, and extending the lifespan of roads. Moreover, it can also facilitate the development of road safety management and intelligent transportation systems. [Display omitted] • Establish a large-scale and high-quality dataset suitable for pavement crack recognition. • Clarify the performance evolution pattern of YOLOv8 model. • Determine the impact of the teacher-assistant models on knowledge distillation. • Develop knowledge distillation model enhanced by multiple teacher-assistant and random learning. [ABSTRACT FROM AUTHOR]

In order to solve the problems of high leakage rate, high false detection rate, low detection success rate and large model volume of small targets in the traditional target detection algorithm for Unmanned Aerial Vehicle (UAV) aerial images, a lightweight You Only Look Once (YOLO) v8 algorithm model Lightweight (LW)-YOLO v8 is proposed. By increasing the channel attention mechanism Squeeze-and-Excitation (SE) module, this method can adaptively improves the model’s ability to extract features from small targets; at the same time, the lightweight convolution technology is introduced into the Conv module, where the ordinary convolution is replaced by the GSConv module, which can effectively reduce the model computational volume; on the basis of the GSConv module, a single aggregation module VoV-GSCSPC is designed to optimize the model structure in order to achieve a higher computational cost-effectiveness. The experimental results show that the LW-YOLO v8 model’s mAP@0.5 metrics on the VisDrone2019 dataset are more favorable than those on the YOLO v8n model, improving by 3.8 percentage points, and the computational amount is reduced to 7.2 GFLOPs. The LW-YOLO v8 model proposed in this work can effectively accomplish the task of detecting small targets in aerial images from UAV at a lower cost.

In order to address the challenges of inefficiency and insufficient accuracy in the manual identification of young citrus fruits during thinning processes, this study proposes a detection methodology using the you only look once for complex backgrounds of young citrus fruits (YCCB-YOLO) approach. The method first constructs a dataset containing images of young citrus fruits in a real orchard environment. To improve the detection accuracy while maintaining the computational efficiency, the study reconstructs the detection head and backbone network using pointwise convolution (PWonv) lightweight network, which reduces the complexity of the model without affecting the performance. In addition, the ability of the model to accurately detect young citrus fruits in complex backgrounds is enhanced by integrating the fusion attention mechanism. Meanwhile, the simplified spatial pyramid pooling fast-large kernel separated attention (SimSPPF-LSKA) feature pyramid was introduced to further enhance the multi-feature extraction capability of the model. Finally, the Adam optimization function was used to strengthen the nonlinear representation and feature extraction ability of the model. The experimental results show that the model achieves 91.79% precision (P), 92.75% recall (R), and 97.32% mean average precision (mAP)on the test set, which were improved by 1.33%, 2.24%, and 1.73%, respectively, compared with the original model, and the size of the model is only 5.4 MB. This study could meet the performance requirements for citrus fruit identification, which provides technical support for fruit thinning., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Ang, Zhiwei, Wei, Yuepeng, Longlong, Yuliang, Jianping and Lijia.)