检索结果-内蒙古大学图书馆

13th Iranian/3rd International Machine Vision and Image Processing Conference (MVIP)

作者： Rahimi, Masume Mostafavi, Mohammad Arabameri, Abazar Univ Zanjan Fac Elect & Comp Engn Zanjan Iran

ISBN: (纸本)9798350350494;9798350350500

This paper presents a study on the application of transfer learning and fine-tuning techniques to a deep learning model for the purpose of detecting three specific types of brain tumors from MRI images. The proposed approach utilizes the YOLO algorithm for automatic diagnosis. Specifically, the YOLOv4-tiny model, which is a smaller version of the YOLOv4 algorithm, was trained and evaluated due to its improved performance. The dataset utilized in this research is obtained from the figshare data repository, which comprises of labeled MRI images. The division of the dataset resulted in 80% for training, 10% for validation, and 10% for testing purposes. Additionally, a pre-processing technique was devised to enhance the features in the MRI images. The outcomes of the implementation demonstrate that the YOLOv4-tiny model obtained a mean average precision (mAP) of 0.8074 for the raw data and 0.8324 for the processed data.

关键词： object detection algorithm YOLO algorithm bounding box transfer learning

来源：评论

学校读者我要写书评

暂无评论

Aerial Intelligence for Precision Monitoring and Fault Identification in Large-Scale Solar Farms Using Advanced Drone Technology and Deep Learning Technique 15

Aerial Intelligence for Precision Monitoring and Fault Ident...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Moorthy, Ponkarthika Gupta, Akshaya Rajendra Chinnadurai, Kannika Parameshwari Mustafa, Ameena Banu Arunachalam, Sivakumar Kumar, Gokul Senthil Gupta, Mirudhubasnee Rajendra Kongu Engineering College Department of Electronics and Communication Engineering Erode India Npr College of Engineering and Technology Department of Electronics and Communication Engineering Dindigul District Natham India Nandha Engineering College Department of Civil Engineering Erode India Sri Sairam Engineering College Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350370249

Solar energy is a promising source of renewable energy, and large-scale solar farms are becoming increasingly popular. However, the maintenance and monitoring of these farms can be challenging due to their size and the distributed nature of the solar panels. Traditional methods of inspection and maintenance are time-consuming, labor-intensive, and prone to human error. This project proposes an innovative solution for precision monitoring and fault identification in large-scale solar farms using advanced drone technology and image processing techniques. The methodology involves collecting high-resolution thermal images of solar panels using a drone equipped with a thermal camera. The YOLOv5 object detection algorithm is then used to detect and classify diode issues, Multi-cell hotspots, and hotspots in thermal images with high precision and recall. The proposed methodology consists of five major stages: data collection, model development, model training, model validation, and model testing. The model is trained and validated using a labeled dataset and then tested to automate the process of detecting and classifying defects or issues in real time. The use of drones and thermal imaging enables non-destructive and contactless inspection, reducing the risk of damage to the solar panels. Overall, this project demonstrates the potential of using advanced drone technology and deep learning algorithms for precision monitoring and fault identification in large-scale solar farms, contributing to the development of more sustainable and efficient solar energy systems. © 2024 IEEE.

关键词： labeled dataset object detection algorithm thermal camera

来源：评论

学校读者我要写书评

暂无评论

Wildlife Real-Time detection in Complex Forest Scenes Based on YOLOv5s Deep Learning Network

引用

REMOTE SENSING 2024年第8期16卷 1350页

作者： Ma, Zhibin Dong, Yanqi Xia, Yi Xu, Delong Xu, Fu Chen, Feixiang Beijing Forestry Univ Sch Informat Sci & Technol Beijing 100083 Peoples R China Natl Forestry & Grassland Adm Engn Res Ctr Forestry Oriented Intelligent Informa Beijing 100083 Peoples R China

With the progressively deteriorating global ecological environment and the gradual escalation of human activities, the survival of wildlife has been severely impacted. Hence, a rapid, precise, and reliable method for detecting wildlife holds immense significance in safeguarding their existence and monitoring their status. However, due to the rare and concealed nature of wildlife activities, the existing wildlife detection methods face limitations in efficiently extracting features during real-time monitoring in complex forest environments. These models exhibit drawbacks such as slow speed and low accuracy. Therefore, we propose a novel real-time monitoring model called WL-YOLO, which is designed for lightweight wildlife detection in complex forest environments. This model is built upon the deep learning model YOLOv5s. In WL-YOLO, we introduce a novel and lightweight feature extraction module. This module is comprised of a deeply separable convolutional neural network integrated with compression and excitation modules in the backbone network. This design is aimed at reducing the number of model parameters and computational requirements, while simultaneously enhancing the feature representation of the network. Additionally, we introduced a CBAM attention mechanism to enhance the extraction of local key features, resulting in improved performance of WL-YOLO in the natural environment where wildlife has high concealment and complexity. This model achieved a mean accuracy (mAP) value of 97.25%, an F1-score value of 95.65%, and an accuracy value of 95.14%. These results demonstrated that this model outperforms the current mainstream deep learning models. Additionally, compared to the YOLOv5m base model, WL-YOLO reduces the number of parameters by 44.73% and shortens the detection time by 58%. This study offers technical support for detecting and protecting wildlife in intricate environments by introducing a highly efficient and advanced wildlife detection model.

关键词： real-time detection forest wildlife object detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Improvement of High-Speed detection algorithm for Nonwoven Material Defects Based on Machine Vision

引用

Journal of Donghua University(English Edition) 2024年第4期41卷 416-427页

作者： LI Chengzu WEI Kehan ZHAO Yingbo TIAN Xuehui QIAN Yang ZHANG Lu WANG Rongwu College of Textiles Donghua UniversityShanghai 201620China

Defect detection is vital in the nonwoven material industry,ensuring surface quality before producing finished ***,deep learning and computer vision advancements have revolutionized defect detection,making it a widely adopted approach in various industrial *** paper mainly studied the defect detection method for nonwoven materials based on the improved Nano Det-Plus *** the constructed samples of defects in nonwoven materials as the research objects,transfer learning experiments were conducted based on the Nano DetPlus object detection *** this framework,the Backbone,path aggregation feature pyramid network(PAFPN)and Head network models were compared and trained through a process of freezing,with the ultimate aim of bolstering the model's feature extraction abilities and elevating detection *** half-precision quantization method was used to optimize the model after transfer learning experiments,reducing model weights and computational complexity to improve the detection *** comparisons were conducted between the improved model and the original Nano Det-Plus model,YOLO,SSD and other common industrial defect detection algorithms,validating that the improved methods based on transfer learning and semi-precision quantization enabled the model to meet the practical requirements of industrial production.

关键词： defect detection nonwoven materials deep learning object detection algorithm transfer learning halfprecision quantization

来源：评论

学校读者我要写书评

暂无评论

Breast cancer detection and classification in mammogram using a three-stage deep learning framework based on PAA algorithm

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2022年 134卷 102419-102419页

作者： Jiang, Jiale Peng, Junchuan Hu, Chuting Jian, Wenjing Wang, Xianming Liu, Weixiang Shenzhen Univ Hlth Sci Ctr Sch Biomed Engn Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Guangdong Key Lab Biomed Measurements & Ultrasound Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Natl Reg Key Technol Engn Lab Med Ultrasound Shenzhen 518060 Guangdong Peoples R China Shenzhen Univ Coll Mechatron & Control Engn Shenzhen 518060 Guangdong Peoples R China Second Peoples Hosp Shenzhen Dept Breast & Thyroid Surg Shenzhen 518035 Guangdong Peoples R China Shenzhen Univ South China Hosp Dept Breast & Thyroid Surg Shenzhen 518111 Guangdong Peoples R China

In recent years, deep learning has been used to develop an automatic breast cancer detection and classification tool to assist doctors. In this paper, we proposed a three-stage deep learning framework based on an anchor-free object detection algorithm, named the Probabilistic Anchor Assignment (PAA) to improve diagnosis performance by automatically detecting breast lesions (i.e., mass and calcification) and further classifying mammograms into benign or malignant. Firstly, a single-stage PAA-based detector roundly finds suspicious breast lesions in mammogram. Secondly, we designed a two-branch ROI detector to further classify and regress these lesions that aim to reduce the number of false positives. Besides, in this stage, we introduced a threshold-adaptive post -processing algorithm with dense breast information. Finally, the benign or malignant lesions would be classified by an ROI classifier which combines local-ROI features and global-image features. In addition, considering the strong correlation between the task of detection head of PAA and the task of whole mammogram classification, we added an image classifier that utilizes the same global-image features to perform image classification. The image classifier and the ROI classifier jointly guide to enhance the feature extraction ability and further improve the performance of classification. We integrated three public datasets of mammograms (CBIS-DDSM, INbreast, MIAS) to train and test our model and compared our framework with recent state-of-the-art methods. The results show that our proposed method can improve the diagnostic efficiency of radiologists by automatically detecting and classifying breast lesions and classifying benign and malignant mammograms.

关键词： Breast cancer Whole mammogram classification Breast lesion detection Deep learning object detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on transformer and attention in applied algorithms

Research on transformer and attention in applied algorithms

引用

作者： Junyan Zhang Department of Computer Science Wenzhou-Kean University

The transformer is an encoder-decoder-based structure and model for deep learning that completely utilizes the self-attention *** has gained remarkable success in natural language processing and computer vision and is becoming the predominant research *** study first analyzes the transformer and attention mechanism,summarizes their advantages,and explores how they help the recommendation algorithm dynamically focus on specific parts of the input that are helpful to perform the current recommendation *** analyzing the framework of the attention mechanism network and its weight computation for data *** further enhance the practicality of objects in natural situations and the precision of object recognition,a transformer detection approach based on deformable convolution is *** analyzed how the transformer works in the generative pre-trained *** algorithms illustrate the efficacy and robustness of the transformer,indicating that the transformer that incorporates the attention mechanism may satisfy the requirements of the majority of deep learning ***,the unpredictability of demands,the exponential growth of information,and other issues will continue to make it challenging to deal with global interaction mechanisms and a unified framework for multimodal data.

关键词： deep learning transformer attention mechanism recommendation algorithm object detection algorithm generative pre-trained transformer

来源：评论

学校读者我要写书评

暂无评论

Lead-lag Swimming Control of Robot Fish Using Color detection algorithm

引用

SENSORS AND MATERIALS 2020年第10期32卷 3491-3506页

作者： Angani, Amarnathvarma Kang, Seung Hoon Talluri, Teressa Kang, Tae Uk Seo, Myeong Jin Shin, Kyoo Jae Busan Univ Foreign Studies Dept ICT Creat Design 65Geumsaem Ro 485 Beon Gil Busan 46234 South Korea

This paper is about lead-lag robot fish swimming control by image processing. In robot fish aquariums, fish can generally move randomly in any path. This irregular movement may cause collisions between the fish, damaging them. Hence, an effective swimming control method is necessary. We thus proposed a lead-lag swimming control system for robot fish. Here, we simply study the detection of moving objects in an aquarium because we need to find the positions of moving robot fish. The locations of the robot fish are recognized using an image processing technique employing image and position sensors. This method is used to obtain the velocity for each pixel in an image and assumes a constant velocity in each video frame to obtain the positions of robot fish by comparing consecutive video frames. By using the position data, we compute the distance between robot fish and determine which robot fish is the lead fish and which fish is the lagging fish. The lead fish then waits for the lagging fish to catch up. The results of this proposed system are satisfactory in preventing collisions between robot fish. This system is exhibited in Busan Science Museum in South Korea.

关键词： robot fish lead-lag swimming control image processing object detection algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust moving object detection using compressed sensing

引用

IET IMAGE PROCESSING 2015年第9期9卷 811-819页

作者： Kang, Bin Zhu, Wei-Ping Nanjing Univ Posts & Telecommun Coll Commun & Informat Engn Nanjing 210003 Peoples R China Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada

Moving object detection plays a key role in video surveillance. A number of object detection methods have been proposed in the spatial domain. In this study, the authors propose a compressed sensing-based algorithm for the detection of moving object. They first use a practical three-dimensional circulant sampling method to yield sampled measurements. Then, they propose an object detection model to simultaneously reconstruct the foreground support, background and video sequence using the sampled measurements directly. Experimental results show that the proposed moving object detection algorithm outperforms the state-of-the-art approaches and it is robust to the movement turbulence, camera motion and video noise.

关键词： object detection compressed sensing video surveillance image sensors image sequences motion estimation compressed sensing video surveillance object detection methods spatial domain circulant sampling method object detection model video sequence object detection algorithm camera motion video noise

来源：评论

学校读者我要写书评

暂无评论

Description of shape patterns using circular arcs for object detection

引用

IET COMPUTER VISION 2013年第2期7卷 90-104页

作者： Chang, Wonil Lee, Soo-Young Elect & Telecommun Res Inst Broadcasting & Telecommun Media Res Lab Taejon 305700 South Korea Korea Adv Inst Sci & Technol Dept Bio & Brain Engn Taejon 305701 South Korea Korea Adv Inst Sci & Technol Dept Elect Engn Taejon 305701 South Korea

The authors propose a novel object detection algorithm based on shape matching using a single sketch of an object. The proposed algorithm uses circular arc segments to describe image edges;this approach is advantageous for shape description, shape expression and reconstruction. Circular arcs are initially segmented from the image contour using the split-and-merge method, and they are extended, being partially overlapped with neighbouring circular arcs. The extracted circular arcs of the object sketch constitute an attributed relational graph as a structured object model. Circular arcs in the test image are refined by the bottom-up process of circular arc extension, and matched with circular arcs in the object model by the top-down process of end-point adjustment. The authors design end-point-based shape descriptors to encode local shape information. Hough voting aggregates the detection of circular arcs to localise the object. Probabilistic relaxation verifies the detection candidates and delineate the object boundaries. The proposed object detection system benefits from reliable extraction of contour segments, efficient and discriminative shape encoding, and flexible and robust shape matching. It exhibits competitive object detection performance in experiments using real images.

关键词： edge detection graph theory Hough transforms image matching image reconstruction image segmentation object detection probability shape recognition shape pattern description object detection algorithm object sketch circular arc segmentation image edge shape expression shape reconstruction image contour attributed relational graph structured object model bottom-up process circular arc extension top-down process end point adjustment end-point-based shape descriptor shape information encoding Hough voting circular arcs detection probabilistic relaxation shape matching edge detection graph theory Hough transforms image matching image reconstruction image segmentation object detection probability shape recognition shape pattern description object detection algorithm object sketch circular arc segmentation image edge shape expression shape reconstruction image contour attributed relational graph structured object model bottom-up process circular arc extension top-down process end point adjustment end-point-based shape descriptor shape information encoding Hough voting circular arcs detection probabilistic relaxation shape matching

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：