检索结果-内蒙古大学图书馆

Power line insulator defect detection using CNN with dense connectivity and efficient attention mechanism

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第10期83卷 28305-28322页

作者： Tian, Xiuxia Zhang, Mengting Lu, Guanyu Shanghai Univ Elect Power Sch Comp Sci & Technol Shanghai 200090 Peoples R China

Power line insulator defect detection is an extremely important technology to ensure the safety of power lines. In recent years, electric power enterprises often use UAVs to conduct safety inspections of power lines. This is a resource-limited terminal platform that cannot sustain the huge computational burden. In addition, insulator images taken by UAVs usually have complex background interference. All these require that the power line insulator defect detection algorithm must guarantee high detection accuracy while keeping the computational cost low. To this end, we designed a novel single-stage detection model that can be trained end-to-end based on yolov3. Our improved model replaces the backbone network of yolov3 with ResNet50 to reduce the number of model parameters. We changed the original connection structure in ResNet50 to a dense connection to improve the feature extraction capability of the backbone network. To overcome the complex background interference, we add an effective attention mechanism at the end of each layer of the backbone network to enable the model to focus effectively on the detected objects. We also use Mosaic and Random Erasing methods to enhance the dataset. Extensive experimental results show that the model achieves better prediction performance compared to other state-of-the-art methods.

关键词： Insulator defect detection yolo algorithm Attention mechanism Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Integrated yolo and CNN algorithms for Evaluating Degree of Walkway Breakage

引用

KSCE JOURNAL OF CIVIL ENGINEERING 2022年第8期26卷 3570-3577页

作者： Choi, Min Je Ku, Dong Gyun Lee, Seung Jae Univ Seoul Dept Transportat Engn Seoul 02504 South Korea Univ Seoul Dept Smart Cities Seoul 02504 South Korea

The focus of policymaking in Korea has changed from vehicle-centric road environments to people-centric environments. As the importance of walking has increased, the construction of pedestrian paths and interest in pedestrian environments have also increased. However, problem recognition and resolution require considerable time in the event of a problem in a pedestrian path. People with reduced mobility tend to resist changes in roads that they use. Thus, damaged pedestrian paths and obstacles pose a considerable risk and economic loss to transportation. In this study, we aimed to minimize the time and cost required for the evaluation of pedestrian paths by developing an automatic system for determining damage using integrated You Only Look Once (yolo) and convolutional neural network (CNN) image deep learning algorithms. We constructed a model using image deep learning by dividing the steps into walkway breakage detection and score evaluation according to the degree of breakage. The accuracy of the model was determined to be 92%. In the future, the evaluation of pedestrian path damage is expected to be automated using images and videos, thereby reducing the time required for the detection and restoration of damage.

关键词： Walkway yolo algorithm Image deep learning Breakage detection Walking environment assessment Pedestrian safety Evaluation indicators

来源：评论

学校读者我要写书评

暂无评论

Effects of Nocturnal Grazing Behavior and Stock Density on Cattle Dung in Sloped Rotational Grazing

引用

RANGELAND ECOLOGY & MANAGEMENT 2025年 99卷 18-25页

作者： Nakashima, Naohisa Kawamura, Kensuke Hirata, Masahiro Muneoka, Toshimi Kimura, Masato Shinkai, Moeka Obihiro Univ Agr & Vet Med Dept Agroenvironm Sci Obihiro Hokkaido 0808555 Japan Obihiro Univ Agr & Vet Med Dept Human Sci Obihiro Hokkaido 0808555 Japan AK Konzern Ltd Sapporo Hokkaido 0460202 Japan

In this study, we investigated the effects of nocturnal variation in grazing behavior and stock density on the distribution of cattle dung in a sloped rotational grazing system in Japan. The specific objectives were to determine the influence of watering sites on dung distribution at night and the relationship between stock density and dung distribution. The study was conducted on a 2.56-ha steeply sloped pasture that was divided into four sub-paddocks for rotational grazing. Drone imagery and the yolo deep learning algorithm were used to automate the mapping of more than 400 cattle dung pats per grazing session, with a mean average precision of 0.75. The yolo algorithm demonstrated high accuracy in identifying dung that was up to 4 days old. Our analyses revealed that the distance to a watering site influenced fecal distribution during the day, but had a weaker and insignificant effect at night. With low-density grazing, dung pats showed a clumped distribution across the entire pasture, whereas at higher stock density the distribution approached randomness. The formation of four dung hotspots was observed in the pasture, although these spots were not consistently used throughout subsequent grazing periods. The cattle tended to migrate from more elevated foraging areas to more level grazing areas for rest, resulting in a loose connection between foraging and resting sites, and this behavior may have a bearing on the lack of successive utilization of these fecal hotspots. Subsequent research must examine whether these patterns persist across seasonal variations and different grazing lands. Despite this need for validation, our findings can provide insights for guiding sustainable nutrient redistribution and grassland management on sloped terrain through the management of stock density and grazing schedules. (c) 2024 The Society for Range Management. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar

关键词： Automated identification Cattle dung Pasturing Sloped pasture Stock density yolo algorithm

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

Smart Waste Manager: yolo-driven Medical Waste Detection and Classification System 1

Smart Waste Manager: YOLO-driven Medical Waste Detection and...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Bobe, Srushti Adhav, Priyanka Bhalerao, Omkar Chaware, Sandeep JSPM's Rajarshi Shahu College of Engineering Department of Information Technology Pune India

ISBN: (纸本)9798350377002

In the realm of healthcare waste management, the improper handling of medical waste poses significant threats to public health and the environment. The reliance on manual sorting procedures not only proves ineffective but also introduces risks for waste handlers and garbage collectors. To address these challenges and improve safety, efficiency, and ecological sustainability, this study proposes an innovative solution. We introduce a dedicated software system leveraging the yolo (You Only Look Once) algorithm for precise detection and classification of medical waste items. The envisioned system, while foregoing specific accuracy metrics, promises potential cost savings and plays a pivotal role in mitigating the hazards associated with manual sorting. This research advances a software solution for efficient medical waste detection and classification, bridging gaps in existing literature regarding accuracy issues, limited datasets, and the need for real-time detection capabilities, contributing to a safer and more sustainable waste management landscape. © 2024 IEEE.

关键词： Classification Deep learning Detection Garbage collectors Medical waste Management Safety 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

Analysis, Design and Implementation of a Ripe Mango Detection Program in Burkina Faso 15th

Analysis, Design and Implementation of a Ripe Mango Detectio...

引用

15th International Conference on e Infrastructure and e Services for Developing Countries

作者： Bikienga, Moustapha Tougma, Roland Manegaouinde Ouedraogo, Soumaila Norbert ZONGO Univ Avce Maurice Yameogo BP376 Koudougou Burkina Faso Joseph KI ZERBO Univ Ouagadougou CFX2 7R6 Burkina Faso

ISBN: (纸本)9783031815720;9783031815737

The analysis, concept, and implementation of a computer program capable of detecting ripe mangoes are at the core of this study. Traditional methods are often faced with calibration errors. Recently, deep learning has shown promising performance in visually guided agricultural applications. Faced with these constraints, it is necessary to establish an automatic system for robust and efficient detection of mangoes in orchards. In this study, a fast implementation system of a mango detector, distinguishing between ripe and unripe mangoes based on deep learning using the yolov5 algorithm, was developed. From a simple photo, the algorithm detects and counts the number of mangoes on a tree. This artificial intelligence system (deep neural network) was trained on a dataset of over 500 annotated mango images. Experimental results show that the algorithm achieves 98% precision, 98% recall, and an F1-score of 98%. This satisfactory precision in mango detection offers significant advantages in terms of efficiency and accuracy compared to traditional methods. However, it should be noted that our system has certain limitations. Nevertheless, our study demonstrates promising results in the field of ripe mango detection.

关键词： Deep learning yolo algorithm Mangoes Performance metrics Computer vision

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detection of Safety Hazards in Coal Mines Utilizing an Enhanced yolov3 algorithm

引用

TRAITEMENT DU SIGNAL 2023年第4期40卷 1565-1572页

作者： Zheng, Junhui Wang, Deyong Geng, Zexun Pingdingshan Univ Sch Informat Engn Pingdingshan 467000 Peoples R China

In coal mining environments, both complexity and potential hazards are inherently present. Responding to the critical need for improved coal mine safety, a method was developed for the real-time surveillance of these hazards using an adapted yolo algorithm. Initially, an algorithm, which amalgamates attention mechanisms and multi-feature fusion for the detection of safety hazards in coal mines, was presented. Utilizing the yolov3 framework, the Gc Net attention module was integrated, a reverse feature fusion pathway was established, and a three-scale prediction module was constructed. Such modifications were designed to identify hazards of various dimensions and configurations, thus augmenting the approach's robustness in intricate situations. Further, the model's loss function underwent optimization to address the imbalances observed in the distribution of positive and negative samples concerning their numbers and complexities. Through experimentation, the efficacy of the proposed method was demonstrated.

关键词： yolo algorithm safety hazards in coal mines real-time monitoring model

来源：评论

学校读者我要写书评

暂无评论

Insulator Defects Detection for Aerial Photography of the Power Grid Using You Only Look Once algorithm

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2023年第4期18卷 3287-3300页

作者： Wang, Shanshan Zou, Xinyi Zhu, Wei Zeng, Liang Hubei Univ Technol Hubei Engn Res Ctr Safety Monitoring New Energy & Sch Elect & Engn Wuhan Hubei Peoples R China

The safe operation of the power grid system depends partly on regular inspections of transmission lines, in which the insulator is one of the most important inspections objects. The manual inspection of transmission lines is a chaotic process that is both time and cost-consuming since it involves an accurate manual inspection by an expert. For insulator defect detection, an improved yolov4 algorithm is proposed. First, a new data augmentation method is proposed to solve the problem of insufficient sample size. Then, the size of the anchor boxes is redesigned base on the K-means algorithm to further improve the detection precision. Finally, an insulator defects detection network is constructed based on yolov4. Experimental results show that the detection precision of the improved network is 37.2% higher after data enhancement and anchor boxes redesign. In addition, the detection method proposed in this paper is superior to other popularity detection algorithms, including the single shot detector, region-convolutional neural networks (Faster-RCNN) and released version of you only look once (yolo). The value of mean average precision is 99.08% and frame per second is 56. The robustness test results demonstrate that our proposed algorithm performs well under different light intensities and complex environmental backgrounds, and can accurately detect all targets, which is significantly better than other comparative algorithms. In terms of detection accuracy, test speed and robustness, our proposed algorithm meets the requirements of industrial field applications of insulator defect detection.

关键词： Insulator defects detection yolo algorithm Data augmentation Object detection Aerial images

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence as a Mechanism for Transparency and Trust in e-Government: algorithm for the Detection of Peruvian Marine Species in High Seas During Closed Season 13th

Artificial Intelligence as a Mechanism for Transparency and ...

引用

13th International Conference on Electronic Government and the Information Systems Perspective (EGOVIS)

作者： Palma, Carlos Tupia, Manuel Cueva, Rony Pontificia Univ Catolica Peru Ave Univ 1801 San Miguel Lima Peru

ISBN: (纸本)9783031682100;9783031682117

One of the main problems that arise in the process of extracting marine species during the closed seasons is the indiscriminate loading of marine species that are prohibited because they are in spawning season. These problems are often aggravated by the lack of transparency in inspection process, where inspectors receive bribes when they intervene with vessels on the high seas [1]. In addition to that, [2] details how the process of identifying marine species does not have rigorous verification due to not having the appropriate tools and control mechanisms. For those reasons, this paper has the general objective of the implementation of a technological solution based on a Artificial Intelligence and mobile application integrated into the identification and control processes of marine species in closed seasons by providing an adequate classification of the species detected by those devices. To achieve this, yolo algorithm has been trained and used in an integrated app. yolo is an algorithm whose architecture is based on convolutional neural networks. This algorithm, unlike other CNN-based architectures, seeks to perform detection in a single run, which allows it to be an extremely fast alternative by performing two fundamental tasks at the same time: identifying a region of interest and classifying it.

关键词： Fish Recognition Deep Learning yolo algorithm Mobile Closed Season Computer Vision Marine species

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：