检索结果-内蒙古大学图书馆

Optimized visual recognition algorithm in service robots

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2020年第3期17卷

作者： Wu, Jun W. Cai, Wei Yu, Shi M. Xu, Zhuo L. He, Xue Y. Shanghai Tiger Technol Co Ltd Shanghai Peoples R China Shanghai High Sch Int Div Shanghai Peoples R China

Vision-based detection methods often require consideration of the robot's sight. For example, panoramic images cause image distortion, which negatively affects the target recognition and spatial localization. Furthermore, the original you only look once method does not have a reasonable performance for the image recognition in the panoramic images. Consequently, some failures have been reported so far when implementing the visual recognition on the robot. In the present study, it is intended to optimize the conventional you only look once algorithm and propose the modified you only look once algorithm. Comparing the obtained results with the experiment shows that the modified you only look once method can be effectively applied in the graphics processing unit to reach the panoramic recognition speedup to 32 frames rate per second, which meets the real-time requirements in diverse applications. It is found that the accuracy of the object detection when applying the proposed modified you only look once method exceeds 70% in the studied cases.

关键词： Robot visual recognition yolo algorithm Panoramic shooting deep learning

来源：评论

学校读者我要写书评

暂无评论

Research on the Development of Object Detection algorithm in the Field of Ship Target Recognition

International Core Journal of Engineering

引用

International Core Journal of Engineering 2021年第1期7卷 233-241页

作者： Jiahao Li Jiacheng Ruan Yongquan Xie

Nowadays, with the rapid development of computer network technology, ship target detection and recognition have become an important aspect of intelligent transportation system research. In the field of maritime traffic, in order to quickly and accurately determine the location of the target in front of the ship and determine the type of the target. A series of algorithms based on convolutional neural networks (CNN) have appeared one after another, which have the characteristics of high recognition accuracy and real-time. First, the paper introduces the development process of water target detection, and then introduces target detection methods: traditional methods combining image processing with machine learning and target detection methods based on convolutional neural networks. Next, explain the development of yolo series models in the field of ship identification. Finally, compare the detection speed and accuracy of these methods. These algorithms provide help for the vision system of smart ships, the collision avoidance decision-making system of unmanned ships, unmanned water surface monitoring and patrol, and water traffic control and management.

关键词： Deep learning yolo algorithm Image recognition Target detection

来源：评论

学校读者我要写书评

暂无评论

DMAPS: An Effective and Efficient Way for the Air Purification of the Outdoors

引用

Procedia Computer Science 2020年 167卷 334-343页

作者： Pranavi Vashishtha Tanupriya Choudhury B.Tech CSE Student Amity University Noida UP India Associate Professor University of Petroleum & Energy (UPES) Dehradun Uttarakhand India

The air pollution these days is a serious environmental concern and it is not just a mere fact but a harsh reality which is creating problems for the mankind such as some serious health issues. In some parts of the world the air quality index have reached to an irrefutable level which demands for a solution now. Hence, the purpose of this paper is to tackle this problem at a large scale by providing with an artificially intelligent mobile air purifier for “outdoors”. The main problem of DMAPS is to provide with purified air in the outdoors, such as a residential colony, in apartments, office complex, etc. since most of the times people travel outdoors and stay away from their home for a long time. This ability of providing with such a smart-sensing, self-driving machine is the advantage of the paper because other air purifiers exist but they are made for indoors, they do not have mobility and also do not possess AI capabilities. The method used in this air purifier is formulated by connecting three major functions. The first one being, ‘the smart mobility’ of the machine using the approach of deep reinforcement learning, the second is the air ‘purification using the Arduino system’ and the last is, ‘the detection of humans’ so that DMAPS can be around them and provide them with purified air, based on the yolo algorithm. The whole system, works in a way that each and every function is very much connected and works simultaneously. In a nutshell, this air purifier, moves from one place (where there is low pollution content) to another place (where there is higher pollution content), purifies the environment and simultaneously have an objective to smartly detect humans to give out fresh air to them. Hence, in this way the whole methodology tries to fix the problem of air pollution by purifying the air outdoors to make it safe to inhale.

关键词： Deep reinforcement learning Arduino yolo algorithm artificially intelligent

来源：评论

学校读者我要写书评

暂无评论

RESEARCH AND DESIGN OF MULTI-TARGET IDENTIFICATION AND LOCALISATION SYSTEMS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and Computer Science 2024年第4期86卷 209-222页

作者： Wang, Mengmei Xin, Wen Liu, Zhen School of Artificial Intelligence and Software Ke Wen College Jiangsu Normal University Jiangsu Xuzhou China School of Electricity Jiangsu University of Science and Technology Jiangsu Suzhou China

This paper designs and develops a multi-target recognition and localisation system based on shape, position and size detection, and achieves accurate recognition and localisation of multiple targets such as rectangles, triangles, circles, polygons and so on in an image by building a hardware platform and a software system. On the hardware side, this paper adopts the M2 core board and V831 chip;on the software level, by adopting the advanced yolo algorithm and DeepSort algorithm, the system successfully achieves accurate recognition and continuous tracking of multiple targets in images. To verify the recognition rate of this system, three sets of experiments were designed: one to test the effect of different recognition methods, another to test the effect of different algorithms on the recognition rate, and a third to test the effect of the number of single targets on the recognition rate. The goal was to study and analyze the impact of various factors on the system's recognition rate. The experimental results indicate that the system demonstrates good robustness. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： image recognition localisation and recognition systems target recognition yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

A grading method for Kayser Fleischer ring images based on ResNet

引用

HELIYON 2023年第5期9卷

作者： Song, Wei Xin, Ling Wang, Jiemei Anhui Univ Chinese Med Affiliated Hosp 1 Hefei 230031 Peoples R China Anhui Univ Chinese Med Dept Otolaryngol Affiliated Hosp 1 Hefei 230031 Peoples R China

The corneal K-F ring is the most common ophthalmic manifestation of WD patients. Early diagnosis and treatment have an important impact on the patient's condition. K-F ring is one of the gold standards for the diagnosis of WD disease. Therefore, this paper mainly focused on the detection and grading of the K-F ring. The aim of this study is three-fold. Firstly, to create a meaningful database, the K-F ring images are collected which contains 1850 images with 399 different WD patients, and then this paper uses the chi-square test and Friedman test to analyze the statistical significance. Subsequently, the all collected images were graded and labeled with an appropriate treatment approach, as a result, these images could be used to detect the corneal through the yolo. After the detection of corneal, image segmentation was realized in batches. Finally, in this paper, different deep convolutional neural networks (VGG, ResNet, and DenseNet) were used to realize the grading of the K-F ring images in the KFID. Experimental results reveal that the entire pre-trained models obtain excellent performance. The global accuracies achieved by the six models i.e., VGG-16, VGG-19, ResNet18, ResNet34, ResNet50, and DenseNet are 89.88%, 91.89%, 94.18%, 95.31%, 93.59%, and 94.58% respectively. ResNet34 displayed the highest recall, specificity, and F1-score of 95.23%, 96.99%, and 95.23%. DenseNet showed the best precision of 95.66%. As such, the findings are encouraging, demonstrating the effectiveness of ResNet in the automatic grading of the K-F ring. Moreover, it provides effective help for the clinical diagnosis of HLD.

关键词： HLD Wilson's disease yolo algorithm K-F ResNet

来源：评论

学校读者我要写书评

暂无评论

Detection, Recognition, and Grasping of Objects through Artificial Intelligence Using a Robotic Hand

引用

IFAC-PapersOnLine 2022年第39期55卷 443-446页

作者： V Sejdiu A Pajaziti G Rexha X Bajrami E Rrustemi J Kola

In this paper, a robotic hand can perceive surrounding objects and grasp the object of interest. This is achieved by the implementation of the yolo algorithm for the detection of everyday objects, filtering information on the presence of man-made objects, and sending that real-time information by serial communication on the robotic hand microcontroller. Upon receiving this information, commands are sent to the robotic hand motors and the latter is compressed and takes the form of the object detected by the algorithm. For objects such as bottles and cups, the adequate shape is considered the tightening of 4 fingers except for the thumb, while for thin objects such as forks, spoons, etc. the thumb and index finger are activated.

关键词： Detection Recognition Grasping Robotic Hand Image Processing yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of Safety Monitoring System Based on Visual Intelligence Technology

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第8期73卷 1384-1389页

作者： Park, Myung-Hye Kim, Young-Hyun Eun, Chang-Soo Dept. of Radio and Information Communication Engineering Chungmam National University Korea Republic of Lab. of Digital Solution KEPCO Research Institute Korea Republic of

Since the implementation of the Serious Accident Punishment Act, various attempts have been made in the field to prevent safety accidents and respond quickly when accidents occur. In particular, building a safety management operation system that monitors the site in real time using IoT technology is an issue. In this paper, we develop video inference technology using CCTV as a way to prevent worker safety accidents in high-risk industrial sites such as power plants. Based on this, we develop functions to detect worker falls, entry into hazardous areas, and fires in real time. We would like to introduce an intelligent worker safety control system implemented to control field events. © The Korean Institute of Electrical Engineers.

关键词： CCTV Monitoring System Video Inference Visual Intelligence Worker Safety yolo algorithm

来源：评论

学校读者我要写书评

暂无评论

Ocean ship detection and recognition algorithm based on aerial image

Ocean ship detection and recognition algorithm based on aeri...

引用

Image Processing, Electronics and Computers (IPEC), Asia-Pacific Conference on

作者： Dequn Zhao Xinmeng Li Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9781728160672

ISBN: (纸本)9781728160689

Because the image of UAV aerial photography is easy to be affected by light, sea area and other conditions, there are many kinds of ships. Under different conditions, the characteristics of ships are different, which makes the target recognition more difficult. In order to improve the efficiency of sea surface supervision and make the sea surface management more intelligent, an ocean ship detection algorithm based on aerial photography image is proposed. In this paper, the improved yolo algorithm is mainly used for high-efficiency ship detection of aerial video, which can achieve real-time performance and detection speed of 23fps. In order to improve the accuracy, this paper proposes a standardized mechanism of fixed frame length detection results, which uses deep learning mask RCNN algorithm for fine detection of specific frame images, and the detection map is 85%, which improves the detection speed without affecting the detection speed The accuracy of the algorithm forms an efficient and accurate algorithm for the detection of ships on the sea, which brings convenience to the management of the sea.

关键词： yolo algorithm Mask-RCNN Ocean vessel object detection Ships Object detection Seas aerial images algorithms Target recognition images aerial photography oceans sea surface

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal tracking of vehicles using Deep Learning, applied on aerial videos

Spatio-temporal tracking of vehicles using Deep Learning, ap...

引用

Moroccan Geomatics (Morgeo), 2020 IEEE International conference of

作者： Hatim Lechgar Mohamed El Imame Malaainine Hassan Rhinane FSAC-Hassan II University Casablanca-Morocco EHTP Casablanca-Morocco

ISBN: (数字)9781728158068

ISBN: (纸本)9781728158075

Deep learning methods, in their latest progress, enable key steps in object detection and recognition to be performed with convolutional neural networks (CNN). In this article, we apply yolo (You Only Look Once) algorithm on areal imagery for spatiotemporal tracking of vehicles, for GIS applications. Data augmentation technics are used to increase the number of training and test data. After augmenting the aerial images of vehicles and their corresponding labels, yolo is trained in iterations until reaching an acceptable precision. Then the trained algorithm is applied on frames of an aerial video of a parking lot, whose outputs (bounding boxes) are used in the LinktheDot algorithm in order to track vehicles in space and time.

关键词： Deep Learning yolo algorithm GIS tracking vehicle tracking geographic information systems bounding boxes Videotapes parking lots ANTENNA Object detection algorithms iterative methods observational data aerial images

来源：评论

学校读者我要写书评

暂无评论

AI Education Based on Evaluating Concentration of Students in Class: Using Machine Vision to Recognize Students’ Classroom Behavior 21

AI Education Based on Evaluating Concentration of Students i...

引用

Proceedings of the 2021 5th International Conference on Video and Image Processing

作者： Yuan Zhang Changzhen Qiu Ningze Zhong Xieyang Su Xuanrui Zhang Fuquan Huang Luping Wang Liang Wang School of Electronics and Communication Engineering Sun Yat-sen University China School of Materials Science and Engineering Sun Yat-sen University China Tandon School of Engineering New York University United States NeuroScience and Artificial Intelligence in Moral Learning Lab South China Normal University China

ISBN: (纸本)9781450385893

Attention is an indispensable part of the learning process. Currently, teachers in most of the schools judge student’ concentration only by their eyes subjectively. But this approach not only distracts teachers from the lesson but also difficult to obtain feedback on the result after class. In this paper, we introduce a method based on machine vision to evaluate students’ concentration. We apply the yolo algorithm on facial movement detection to predict whether students are engaged in class. It not only helps to differentiate instruction for students but also helps teachers to optimize their lessons. The experiments demonstrate that the method can achieve the assessment of students’ concentration within a small-size classroom.

关键词： Machine Vision yolo algorithm Students’ Concentration Object Detection

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：