检索结果-内蒙古大学图书馆

ENGINEERING RESEARCH EXPRESS 2025年第2期7卷

作者： Zhang, Xinghua Heilongjiang Polytech Harbin 150080 Peoples R China

With the increasing level of modern computer technology and the rapid development of artificial intelligence, various industries have begun to adopt intelligent devices in large quantities to reduce the waste of human resources. In the field of garbage disposal, sweepers use image acquisition devices to obtain street and road images, and recognize and detect street garbage through image information. The 'You Only Look Once' (yolo) algorithm is used to deploy and optimize the garbage recognition and detection software. The results showed that in the brightness balanced scene, the research method had a grayscale mean of 2108, with a slightly lower proportion of poorly exposed pixels at 6.7 parts per thousand. By reducing the exposure time, the grayscale mean was lowered to 1978, significantly reducing the proportion of poorly exposed pixels to 12.7%. For high contrast scenes, this research method faced a high exposure pixel ratio of 146.8 parts per thousand, which was 146.8 parts per thousand of the saturation threshold. It increased the gray mean to 1748 and greatly reduced the proportion of poorly exposed pixels to an extremely low level. After single frame calculation, the research method time increased to 1.643 ms, and after stabilization, the research method time was 1.886 ms, with a distance ratio of only 12.2%, which was more stable. Compared with the yolo real-time garbage detection method, the yolov5s+TensorRT proposed in this study could detect garbage in near real time on low-cost embedded devices in terms of FPS or inference speed, with the yolo real-time garbage detection method exceeding 32fps. In terms of accuracy, yolov5+TensorRT optimization could maintain a good accuracy of 99%, and had certain advantages in comprehensive performance, making it easier to promote and apply in practical applications. It can be seen that the methods proposed in the study have solved the limitations of traditional garbage cleaning methods, improved the efficiency and qua

关键词： region segmentation algorithm yolo algorithm street garbage identification detection software

来源：评论

学校读者我要写书评

暂无评论

A Review of yolo algorithm and The Research in Garbage Classification Target Detection 24

A Review of YOLO Algorithm and The Research in Garbage Class...

引用

4th International Joint Conference on Robotics and Artificial Intelligence, JCRAI 2024

作者： Zhang, Juan Blancaflor, Eric B. Mapua University Makati City Philippines

ISBN: (纸本)9798400710100

Target detection is an important research direction in computer vision, how to real-time accurate object detection of objects is the focus of research. In recent years, deep learning technology has developed rapidly and are widely used in various fields. Firstly, this paper summarizes the idea of yolo series detection algorithm and its improvement process, analyzes the advantages and disadvantages of yolo series algorithm;then, expounds the application status of yolo algorithm in garbage classification target detection, summarizes the public garbage classification dataset and commonly used evaluation indicators in target detection;finally, summarizes the problems in garbage classification identification, and forecast the future development direction. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Target detection Garbage classification Real-time detection yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

The performance of You Only Look Once (yolo) algorithm in differentiating hunger, feeding, and post-feeding behaviours in hybrid grouper juveniles (Epinephelus fuscoguttatus ♀ x Epinephelus lanceolatus ♂)

引用

APPLIED ANIMAL BEHAVIOUR SCIENCE 2025年 282卷

作者： Tan, Karsoon Tan, Kianann Tan, Zi-Kai Au, Hsein-Loong Ebi, Isaac Teo, Kenneth Tze Kin Alfred, Rayner Shapawi, Rossita Lim, Leong-Seng Beibu Gulf Univ Coll Marine Sci Beibu Gulf Ocean Dev Res Ctr Guangxi Key Lab Beibu Gulf Biodivers Conservat Qinzhou Guangxi Peoples R China Univ Malaysia Sabah Fac Engn Kota Kinabalu Sabah Malaysia Univ Malaysia Sabah Higher Inst Ctr Excellence HICoE Borneo Marine Res Inst Kota Kinabalu Sabah Malaysia Univ Malaysia Sabah Fac Comp & Informat Creat Adv Machine Intelligence Res Ctr Kota Kinabalu Sabah Malaysia

Digital aquaculture technologies are playing an increasingly important role in enhancing resource management efficiency and reducing environmental pollution. Given the high feed cost of hyrbid grouper (Epinephelus fuscoguttatus female x Epinephelus lanceolatus male) aquaculture, the present study aimed to classify the feeding behaviour of hybrid grouper using yolo and to compare the accuracy of the random forest model, decision tree model, and logistic regression model in distinguishing grouper behaviour during the hunger, feeding, and post-feeding phases. Overall, groupers displayed distinct behaviors across these phases. During the hunger phase, they displayed active, dynamic swimming and foraging behaviors while searching for food. This vigorous movement made it challenging for a 60-second heatmap to accurately capture their movement patterns in the cumulative movement distribution. In contrast, during the feeding and post-feeding phases, their movements became more predictable. The cumulative movement distribution and 60-second heatmap showed high similarity, with most groupers congregating near the food source and feeding actively during the feeding phase, followed by more sedentary behavior post-feeding, as they settled at the bottom of the tank. Moreover, the random forest model outperformed the decision tree and linear regression models, achieving superior accuracy (0.95), F1-score (0.89), precision (0.96), and recall (0.86). These findings contribute to the development of intelligent feeding systems for hybrid grouper farming and offer valuable insights for improving the cost-efficiency of grouper aquaculture.

关键词： Hybrid grouper Feeding behaviour yolo algorithm Random forest model Decision tree model Logistic regression model

来源：评论

学校读者我要写书评

暂无评论

Application of Improved yolo algorithm in the Design of FSAC Racing Real-time Target Detection System 5

Application of Improved Yolo algorithm in the Design of FSAC...

引用

5th International Conference on Advances in Image Processing (ICAIP)

作者： Sun, Jie Jianghan Univ Sch Phys Educ Wuhan Hubei Peoples R China

ISBN: (纸本)9781450385183

In order to further improve the accuracy of FSAC racing target detection, this paper explores the modified method of yolo algorithm, puts it into the design of target detection system, and puts forward the application scheme of system design. The scheme uses k-means algorithm to design clustering processing scheme. By reducing the detection target specification, the control algorithm is developed in ROS system to realize high-precision target detection. The test results show that the target detection accuracy of the system is significantly improved compared with the original algorithm, and the processing efficiency is accelerated.

关键词： yolo algorithm Target detection FSAC racing

来源：评论

学校读者我要写书评

暂无评论

The Real-Time Detection of Traffic Participants Using yolo algorithm 26

The Real-Time Detection of Traffic Participants Using YOLO A...

引用

26th Telecommunications Forum (TELFOR)

作者： Corovic, Aleksa Ilic, Velibor Duric, Sinisa Marijan, Malisa Pavkovic, Bogdan RT RK Inst Comp Based Syst Novi Sad Serbia

ISBN: (纸本)9781538671719

Object detection is one of the key software components in the next generation of autonomous cars. Classical computer vision and machine learning approaches for object detection usually suffer from the slow response time. Modern algorithms and architectures based on artificial neural networks, such as yolo (You Only Look Once) algorithm, solve this problem without precision losses. In this paper we provide the demonstration of the usage of the newest yolov3 algorithm for the detection of traffic participants. We have trained the network for 5 object classes (car, truck, pedestrian, traffic signs, and lights) and have demonstrated the effectiveness of the approach in the variety of the driving conditions (bright and overcast sky, snow, fog, and night).

关键词： Advanced Driver Assistance Systems (ADAS) Convolutional Neural Networks Deep Learning Machine Learning Object Detection yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

A Model for Real-Time Traffic Signs Recognition Based on the yolo algorithm - A Case Study Using Vietnamese Traffic Signs 6th

A Model for Real-Time Traffic Signs Recognition Based on the...

引用

6th International Conference on Future Data and Security Engineering (FDSE)

作者： An Cong Tran Duong Lu Dien Hiep Xuan Huynh Nguyen Huu Van Long Nghi Cong Tran Can Tho Univ Can Tho Vietnam

ISBN: (纸本)9783030356538;9783030356521

The rapid development of the automobile resulted in the traffic infrastructure becomes more and more complicated. Both type and the number of traffic signs on the streets are increasing. Therefore, there is a need for applications to support drivers to recognize the traffic signs on the streets to help them avoid missing traffic signs. This paper proposes an approach to detecting and classifying Vietnamese traffic signs based on the yolo algorithm, a unified deep learning architecture for real-time recognition applications. An anchor boxes size calculation component based on the k-means clustering algorithm is added to identify the anchor boxes size for the yolo algorithm. A Vietnamese traffic sign dataset including 5000 images containing 5704 traffic signs of types was collected and used for evaluation. The F1 score of the tiny model (the fastest but the most inaccurate model) achieved is about more than 92% and the detection time is approximately 0.17 s (in our testing environment: laptop CPU Intel 3520M, 8GB RAM, no GPU). In comparison with similar research in Vietnamese traffic sign recognition, the proposed approach in this paper shows a potential result that provides a good trade-off between the recognition accuracy and recognition time as well as the feasibility for real applications.

关键词： Vietnamese traffic signs Detection yolo algorithm Deep learning K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Detection of Harmful Snakes Using yolo algorithm

引用

SN Computer Science 2024年第1期5卷 52页

作者： Naresh, E. Babu, J. Ananda Darshan, S. L. Shiva Murthy, S.V.N. Srinidhi, N.N. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Information Science and Engineering Malnad College of Engineering Karnataka Malnad India Department of Computer Science and Engineering National Institute of Technology Warangal Warangal India Department of CSE SJC Institute of Technology Chikkaballapur India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The spotlight of our discussion here is on developing a model for detecting snakes present in the agricultural fields using cameras and machine learning algorithms. The idea is to construct a machine learning model to identify the snakes, which will be trained on a vast set of images of snakes. These images will be carefully selected to include the snake patterns, skin color of different species of snakes (extraction of the unique features). This is done to train the model properly to identify different types of snakes that the farmer encounters in the fields. Most famers are unaware and have a need for a way to detect these snakes so that they can either avoid them or get rid of them. Hence, this system can be implemented to prevent thousands of deaths and can help famers alleviate the repercussions of snake bites. Mistakes in recognizing potentially harmful animal species based only on visual cues are major contributors to the high death toll from venomous animal attacks. Since they spend so much time in the fields, where rice and wheat are cultivated, farmers are at a higher risk of being bitten by a snake than the general population. Because of their ignorance, illiterate farmers are more inclined to believe in superstitions, which can lead to their untimely deaths from snakebites despite medical intervention. Animals that would normally pose no threat to humans are responsible for the deaths of thousands of people every year because of environmental factors. However, because it is hard for humans to recognize these dangers, a new design paradigm has been developed to make it simpler. Researchers in the field of animal biology can use it to search for endangered species. Predators may enter gardens and green areas like tea and coffee plantations. There is not yet a plan in place to implement automated sorting for discovering distinctions. By applying the suggested framework to photographs of potentially dangerous animals, several factors useful for studying anim

关键词： Classifier training Convolutional neural network Farmer deaths Feature extraction Snake detection yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Surveillance Systems with yolo algorithm for Real-Time Object Detection and Tracking 2

Enhancing Surveillance Systems with YOLO Algorithm for Real-...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Anish, A. Sharan, R. Hema Malini, A. Archana, T. Department of ECE Saveetha Engineering College Chennai India

ISBN: (纸本)9798350340235

A Virtually Impaired Person (VIP) is unable to identify objects when they cannot recognize where the object is placed. The researchers are working on it to enhance object detection and help VIP. The challenges faced by researchers are performing detection under low-resolution images, insufficient sensors, portability, and cost. Making a compact device and alerting them is required. By considering the above-mentioned difficulties, an innovative solution is described in this research work. The growth of image processing and deep learning techniqueshas simplifiedthe complexity of processing data and provided accurate results within a limited time period. The suggested technique presented is a deep learning algorithm calledthe yolo algorithm, which is combined with the web to predict objects accurately. For this approach, a dataset with a total of 500 images was chosen and trained. The proposed classifier result is satisfactory, and it achieved an overall accuracy of 94%. Furthermore, this proposed technique provides enough output in comparison with several other machine learning and image processing algorithms. © 2023 IEEE.

关键词： Deep Learning Image Processing Object Detection Visually Impaired Person (VIP) yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Attitude Control of Steel Structure Damage Detection under yolo algorithm and PID

Attitude Control of Steel Structure Damage Detection under Y...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Wang, Yanhui Co. Ltd Zhejiang Hangzhou China The Third Construction Co. Ltd of China Construction Third Engineering Bureau Hubei Wuhan China

ISBN: (纸本)9798350315455

Strengthening the real-time monitoring and diagnosis of steel structure buildings is very important for timely detection of structural damage, evaluation of its safety, and guidance on its maintenance. Based on fuzzy fractional order PID control, yolo algorithm is used to adjust the fractional order PID order effectively. Based on the mathematical model and the controller, the pitch angle of the flexible robot is taken as input and the rotational torque is output to control the motion of the flexible robot, so as to realize the real-time control of the motion attitude of the flexible robot. The adjustment time of the ordinary PID controller is 20s, that of the fuzzy PID controller is 15s, and that of the fuzzy frit-order PID controller is 5s. The method presented in this paper can make the flexible damage detection robot quickly reach the desired motion posture, and can effectively suppress the jitter, and the reaction speed is fast and the stability is good. © 2023 IEEE.

关键词： attitude control damage detection robot fuzzy fractional order proportional integral differential steel structure yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Control System Using yolo algorithm for Traffic Congested Cities

Intelligent Traffic Control System Using YOLO Algorithm for ...

引用

2023 Congress in Computer Science, Computer Engineering, and Applied Computing, CSCE 2023

作者： Mou, Afsana Rahman Milanova, Mariofanna Piya, Sumaiya Sharmin University of Arkansas at Little Rock Department of Computer Science Little RockAR United States Chittagong University of Engineering & Technology Department of Electrical & Electronic Engineering Chittagong Bangladesh

ISBN: (纸本)9798350327595

The number of vehicles on the road has increased in recent years, and many countries now require reliable and sophisticated control of the traffic signal system. By accurately calculating the traffic density based on the images captured by cameras installed on the traffic posts, this research aims to resolve this dilemma. The technique uses a simple algorithm that first processes a fuzzy controller to recognize vehicles using a yolo classifier. It could be developed further for hardware implementation using specialized CPUs. Our method entails periodically capturing photos and processing them further with a cascade classifier. The classifier is retained for use in calibration. With the help of this method, the system can deduce the traffic density, which a fuzzy controller then evaluates to decide when to turn on the traffic signals. The output function of the fuzzy controller, which compares the vehicle density of the most recent photos, adjusts the output dynamically. © 2023 IEEE.

关键词： fuzzy logic object detection traffic control yolo algorithm

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：