检索结果-内蒙古大学图书馆

Defect object detection algorithm for electroluminescence image defects of photovoltaic modules based on deep learning

引用

ENERGY SCIENCE & ENGINEERING 2022年第3期10卷 800-813页

作者： Meng, Ziyao Xu, Shengzhi Wang, Lichao Gong, Youkang Zhang, Xiaodan Zhao, Ying Minist Educ Engn Res Ctr Thin Film Photoelect Technol Tianjin 300350 Peoples R China Nankai Univ Inst Photoelect Thin Film Devices & Technol Tianjin Peoples R China Nankai Univ Key Lab Photoelect Thin Film Devices & Technol Ti Tianjin Peoples R China

Visual inspection of photovoltaic modules using electroluminescence (EL) images is a common method of quality inspection. Because human inspection requires a lot of time, object detection algorithm to replace human inspection is a popular research direction in recent years. To solve the problem of low accuracy and slow speed in EL image detection, we propose a yolo-based object detection algorithm yolo-PV, which achieves 94.55% of AP (average precision) on the photovoltaic module EL image data set, and the interference speed exceeds 35 fps. The improvement of speed and accuracy benefits from the targeted design of the network architecture according to the characteristics of EL image. First, we weaken the backbone's ability to extract deep-level information so that it can focus on extracting the low-level defect information. Second, the PAN network is used for feature fusion in the Neck part. But, only the single-size feature map output is retained, which significantly reduces the amount of calculation. Also, we analyze the impact of data enhancement methods on model overfitting and performance. Finally, we give effective data enhancement methods. The results show that the object detection algorithm in this paper can meet the requirements for high-precision and real-time processing on the PV module production line.

关键词： deep learning electroluminescence image object detection photovoltaic modules yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

An Automatic Search Image Augmentation algorithm for UAV Identification

An Automatic Search Image Augmentation Algorithm for UAV Ide...

引用

International Conference on Autonomous Unmanned Systems (ICAUS)

作者： Zeng, Guoqi Pan, Shengrui Jia, Huiwen Li, Jie Niu, Zifan Fan, Zheng Zheng, Lili Beihang Univ Inst Unmanned Syst Beijing 100191 Peoples R China Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China

ISBN: (纸本)9789819904815;9789819904792;9789819904785

Currently, it is difficult to obtain a large amount of training data for UAV identification, so data augmentation is needed, which is an effective method to improve the accuracy of object detection. However, current data augmentation implementations are manually designed commonly. In this paper, we describe a data augmentation strategy for an automated search. Specifically, we design a search space where each policy consists of N operations, each of which is an image processing function such as translation, rotation, and the probability and magnitude of applying these operations. In the actual automatic search process, an evolutionary algorithm is used to find the optimal operation combination. In addition, to further improve the recognition rate of the algorithm under the condition of a few samples, we also use an improved genetic algorithm to tune the hyperparameters. Experiments show that after using the hybrid strategy, the mAP of the network increases from 71.45% to 78.61%, and the recognition accuracy is also significantly improved.

关键词： Hyperparameter tuning Automatic search Image augmentation Genetic algorithm UAV identification yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

MULTI-SMALL TARGET DETECTION AND TRACKING BASED ON IMPROVED yolo AND SIFT FOR DRONES

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2021年第1期17卷 205-224页

作者： Lu, Pancheng Ding, Yong Wang, Changjian Nanjing Univ Aeronaut & Astronaut Coll Automat 29 Jiangjun Ave Nanjing 210016 Peoples R China

Multi-target tracking algorithms applied to drones often face more detection algorithm, while achieving active tracking of small targets and fast-moving targets. In response to these problems, this paper proposes a multi-small target detection and tracking method based on improved yolo and SIFT for drones. First, we prune the network of the yolo algorithm. Through sparse training, channel pruning, and network adjustment, the drone can deploy a target detection network with a smaller model. Secondly, we propose a method of adaptive threshold and minimum distance and optimize SIFT feature extraction, achieve effective detection of small targets, and improve tracking accuracy and success rate. Finally, we consider the needs of the UAV to track fast-moving targets, we use scale and position information to complete the data association, and the UAV can effectively track fast-moving targets. The algorithm of this paper is evaluated by the VisDrone 2019 MOT benchmark data set. The leading evaluation indicators MOTA and MOTP are 38.7 and 75.7. The secondary evaluation indicators IDF1, ML, and FN, etc. all perform better. The algorithm meets the complex task requirements of multi-target tracking for UAVs.

关键词： Drone yolo algorithm Network pruning SIFT features Data association Multi-target tracking

来源：评论

学校读者我要写书评

暂无评论

Lateral distance measurement technology of driverless vehicle based on machine vision

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2022年第4期22卷 1373-1384页

作者： Wang, Yeqing Changzhou Coll Informat Technol Sch Elect Engn Changzhou 213164 Jiangsu Peoples R China

In order to solve the problems of large measurement errors and long time consuming in the measurement of the lateral distance between driverless vehicles, this paper proposes to design a lateral distance measurement technology of driverless vehicles based on machine vision. According to the preview following theory and model basis, the lateral movement process of driverless vehicles is determined, the lateral displacement deviation change rate and heading angle deviation change rate between vehicle and preview point in local coordinates are calculated, and the lateral motion dynamic model of unmanned vehicle is designed. With the help of yolo algorithm, the boundary frame is drawn up to determine the position of the lateral moving vehicle, and the detection error is corrected with the help of loss function to complete the lateral moving target detection of the unmanned vehicle. The relationship between the machine coordinate system and the world coordinate system is determined. According to the internal and external parameter matrix of the relationship between the lateral distances of the driverless vehicle, the machine vision position is set, and the lateral distance is determined by the pitch angle between the horizontal planes. The experimental results show that the measurement error of this method is always less than 5%. This method has small measurement error, small error between test distance and actual distance, and has certain application performance.

关键词： Machine vision driverless vehicles transverse distance between vehicles yolo algorithm coordinate system

来源：评论

学校读者我要写书评

暂无评论

ROI Image Encryption using yolo and Chaotic Systems

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2021年第7期12卷 466-474页

作者： Kang, Sung Won Choi, Un Sook Pukyong Natl Univ Dept Informat Secur Busan South Korea Tongmyong Univ Sch Artificial Intelligence Busan South Korea

In this paper, we design a cellular automata (CA)-based ROI (region of interest) image encryption system that can effectively reduce computational cost and maintain an appropriate level of security. The proposed image encryption system obtains a cryptographic image through three steps. First, a region of interest with high importance is extracted from the entire image using deep learning. We use the yolo (You Only Look Once) algorithm to extract the ROI from a given original image. Next, the detected ROI is encrypted using the Chen system, a chaotic-based function with high security. Finally, the execution time is effectively reduced by encrypting the entire image using a hardware-friendly CA. The safety of the proposed encryption system is verified through various statistical experiment results and analyses.

关键词： Image encryption cellular automata yolo algorithm deep learning Chen system region of interest

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Management using Machine Learning

Intelligent Traffic Management using Machine Learning

引用

2025 International Conference on Intelligent Computing and Control Systems, ICICCS 2025

作者： Vasumathi, A. Dharshini, P. Jagath, M. Krishna Raj, R. Mahalakshmi, S. Karpagam College of Engineering Department Of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331512088

A smart traffic control system that gives priority to emergency vehicles like ambulances and adjusts traffic signals dynamically according to vehicle density is the primary focus of the project. To accurately measure vehicle density in real time and change traffic signals accordingly, the system utilizes a yolo (You Only Look Once) object detection model. By sending green lights to the most congested lanes, it relieves traffic congestion and facilitates better flow of traffic. In addition, an RF module is installed in ambulances to provide real-time detection of emergency vehicles. The RF technology prioritizes the ambulance automatically by altering the light green as it comes near within a given distance from the traffic signal. This enables the ambulance to move through traffic without any hindrances. In case of emergency, this automated clearance system ensures a faster response time for ambulances, potentially leading to saving lives. The adaptive divider control in the system is another critical element. Real-time traffic density information from the yolo model can be utilized for adjusting road lane widths, allocating more space to lanes with higher traffic densities. This enhances use of roads and reduces congestion points. By adapting to evolving traffic conditions, this adaptive approach optimizes traffic flow and works toward offering an efficient and responsive urban traffic solution. Overall, this technology ensures a smarter, real-time reaction to traffic conditions, enhancing emergency response times in addition to traffic flow efficiency. © 2025 IEEE.

关键词： adjust traffic signals emergency prioritizing image processing lane adjustment real time application RF module Vehicle density detection yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive Traffic Signal Management Using Real-Time Vehicle Detection and Tracking 3

Adaptive Traffic Signal Management Using Real-Time Vehicle D...

引用

3rd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025

作者： Shirulkar, Sarvesh Makode, Rishabhdev Khandelwal, Richa Shri Ramdeobaba College of Engineering and Management Dept. of Electronics and Computer Science Nagpur India Ramdeobaba University Dept. of Electronics Engineering Nagpur India

ISBN: (纸本)9798331521691

Traffic congestion is a significant issue in urban cities, as it restricts traffic flow, increases fuel consumption, and produces high emissions. Traditional traffic signal systems work on fixed timing without considering real-time variations in traffic and often worsen the problem. This paper describes an adaptive traffic signal control system based on the yolo (You Only Look Once) algorithm, using object detection for real-time signal timing in response to real-time traffic. The system applies real-time vehicle detection and tracking at intersections for dynamic management of green light time according to volume and vehicle type. The proposed approach makes vehicle recognition significantly efficient and responds quickly to the change in traffic situation. The paper discusses the design, implementation, and evaluation of performance in a simulated environment. The results demonstrate improved traffic management and reduced congestion, offering a promising solution to smart city traffic control. © 2025 IEEE.

关键词： Adaptive traffic signal control Real-time traffic management Smart city traffic control Traffic congestion Vehicle detection and tracking yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Object Detection using Learning algorithm and IoT

Object Detection using Learning Algorithm and IoT

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： SenthilPandi, S. Mithun, D. Naresh Kumar, A. Paulraj, D. Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering R.M.K. Engineering College Chennai India

ISBN: (纸本)9798350305708

To reduce accidents and safeguard the lives of drivers, it is crucial to ensure road safety. Helmets are essential for preventing brain injuries during car accidents and must be worn properly. In this research, we offer a Helmets Detection device for Road Safety that makes use of IoT (Internet of Things) and the cutting-edge object detection algorithms yolo (You Only Look Once).The proposed system makes use of the Raspberry Pi 3 and the IoT (Internet of Things) to gather real-time information from the camera. If the driver is wearing a helmet, the camera will gather an image of the helmet and if the ignition is successful, the engine will start. If the driver is not wears a helmet, our camera will capture an image and the engine fails to ignite. After being submitted into a reliable CNN (Convolutional Neural Network) model that was trained on an extensive collection of annotated helmet photos, the gathered data is then used. On a real-world dataset, we analysed this, and we were able to reach a high detection reliability of over 95%. The outcomes show that the suggested strategy is beneficial in enhancing road by recognising motorcyclists who neglect to put on helmets, accidents and injuries can be avoided. This information is sent to a central computer, where the yolo technique is used to locate and identify motorcyclists' helmets from collected photos. © 2023 IEEE.

关键词： Convolutional Neural Networks (CNN) IoT (Internet of Things) Raspberry Pi 3 Real-time detection Safety Helmet Detector yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Automated steel corrosion detection and damage assessment using yolov5 algorithm

引用

SHIPS AND OFFSHORE STRUCTURES 2025年

作者： Mu, Jianwu Yang, Yang Chu, Jinze Lv, Wanyang Hu, Kaixuan Dalian Univ Technol Sch Naval Architecture & Ocean Engn Dalian Liaoning Peoples R China

Current ship corrosion inspections rely heavily on manual observation, which is subjective, inefficient, and difficult in inaccessible areas. This paper proposes a method for identifying steel corrosion and determining damage levels using the yolov5 (You Only Look Once, Version 5) algorithm and its enhancements. The method increases the steel corrosion dataset and applies yolo for corrosion image recognition. Converting images to greyscale reduces the impact of colour on corrosion detection, while Gaussian filtering eliminates noise. A segmented linear transformation enhances contrast between corroded and non-corroded areas. To detect corrosion, a Otsu's method is used, and expansion operations reduce noise in small corrosion regions. The 8-neighborhood method then counts and analyses corrosion areas, providing details on number, size, and location. By combining these techniques with the DOP (Degree of Pitting Corrosion) index and damage classification, the method quantitatively evaluates corrosion damage on ship surfaces. Significantly improving detection efficiency and accuracy.

关键词： Corrosion damage identification convolutional neural networks yolo algorithm feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing autonomous pavement crack detection: Optimizing yolov5s algorithm with advanced deep learning techniques

引用

MEASUREMENT 2025年 240卷

作者： Zhou, Shuangxi Yang, Dan Zhang, Ziyu Zhang, Jinwen Qu, Fulin Punetha, Piyush Li, Wengui Li, Ning Guangzhou Maritime Univ Sch Civil & Engn Management Guangzhou 510725 Peoples R China East China Jiaotong Univ Sch Civil Engn & Architecture Nanchang 330013 Peoples R China Univ New South Wales Ctr Infrastruct Engn & Safety Sch Civil & Environm Engn Sydney NSW 2052 Australia Univ Technol Sydney Sch Civil & Environm Engn Ultimo NSW 2007 Australia Univ Manchester Dept Solids & Struct Manchester M13 9PL England

To enhance the safety and comfort of vehicle travel, detecting pavement cracks is a critical task in road management. This article introduces an advanced single-stage target detection method utilizing the yolov5s algorithm to enhance real-time performance and accuracy. Initially, Squeeze-and-Excitation Networks are integrated into the model to facilitate self-learning for improved crack characterization. Subsequently, anchors computed through the K-means clustering algorithm are closely aligned with the fracture dataset, achieving an adaptation rate of 99.9 % and enhancing the recall rate of the model. Furthermore, the inclusion of the SimSPPF module from yolov6 diminishes memory usage and expedites detection speed. By replacing the original nearest up- sampling method with transposed convolution, optimization of up-sampling for crack datasets is achieved. Performance assessments reveal that the refined yolov5s algorithm attains an F1 score of 91 %, a mean Average Precision (mAP) of 93.6 %, and a 1.54 % increase in frames per second (fps) for pavement crack detection. This enhancement in detection technology signifies a substantial advancement in the maintenance and longevity of road infrastructure.

关键词： Road maintenance Crack detection yolo algorithm AI integration Advanced image processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：