检索结果-内蒙古大学图书馆

Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries

IEEE TRANSACTIONS ON image processing 2024年 33卷 2462-2476页

作者： Viviers, Christiaan G. A. Filatova, Lena Termeer, Maurice de With, Peter H. N. van der Sommen, Fons Tech Univ Eindhoven Dept Elect Engn NL-5612 AZ Eindhoven Netherlands Philips IGT NL-5684 PC Best Netherlands Tech Univ Eindhoven Elect Engn Dept NL-5612 AZ Eindhoven Netherlands

Accurate 6-DoF pose estimation of surgical instruments during minimally invasive surgeries can substantially improve treatment strategies and eventual surgical outcome. Existing deep learning methods have achieved accurate results, but they require custom approaches for each object and laborious setup and training environments often stretching to extensive simulations, whilst lacking real-time computation. We propose a general-purpose approach of data acquisition for 6-DoF pose estimation tasks in X-ray systems, a novel and general purpose YOLOv5-6D pose architecture for accurate and fast object pose estimation and a complete method for surgical screw pose estimation under acquisition geometry consideration from a monocular cone-beam X-ray image. The proposed YOLOv5-6D pose model achieves competitive results on public benchmarks whilst being considerably faster at 42 FPS on GPU. In addition, the method generalizes across varying X-ray acquisition geometry and semantic image complexity to enable accurate pose estimation over different domains. Finally, the proposed approach is tested for bone-screw pose estimation for computer-aided guidance during spine surgeries. The model achieves a 92.41% by the 0.1 center dot d ADD-S metric, demonstrating a promising approach for enhancing surgical precision and patient outcomes. The code for YOLOv5-6D is publicly available at https://***/cviviers/YOLOv5-6D-Pose.

关键词： X-ray instrument detection 6-DoF pose estimation surgical vision imaging geometry deep learning

来源：评论

学校读者我要写书评

暂无评论

Synchronous Update and Optimization Method for Large-Scale image 3D Reconstruction Technology Under Cloud-Edge Fusion Architecture

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2024年第8期15卷 1149-1160页

作者： Zhang, Jian Luo, Jingbin Chen, Yilong Guangdong Power Grid Co Ltd Guangzhou 510030 Peoples R China Guangdong Power Grid Co Ltd Guangzhou Power Supply Bur Guangzhou 510000 Peoples R China

at the problems of limited bandwidth and network delay in the traditional centralized cloud computing mode during large-scale image processing of transmission and distribution digital corridors, a synchronous updating and optimization method for large-scale image 3D reconstruction technology under cloud-edge fusion architecture is proposed. Based on the cloud-side fusion architecture, the image data of the transmission and distribution corridor is preprocessed, feature extraction is performed by deep learning, synchronous updating is performed by using the cloud-side cooperative network, and matching and 3D reconstruction are performed according to the order of the point cloud data;given the dynamically changing characteristics of the image data in the cloud-side fusion environment, the incremental learning is combined with the continuous learning and synchronous updating of the model parameters, to realize the adaptive updating mechanism. The research method utilizes the advantage of cloud-edge fusion architecture to distribute the computational tasks to the cloud and edge, realizing parallel processing and load balancing, and improving the accuracy and efficiency of 3D reconstruction. The experimental results show that the research method in this paper has an image feature point matching rate as high as 96.72%, a lower network latency rate, and a higher real-time performance, which provides strong technical support for the optimization of the transmission and distribution digital corridor 3D reconstruction technology.

关键词： Cloud-edge fusion cloud-edge collaboration 3D reconstruction synchronized update

来源：评论

学校读者我要写书评

暂无评论

deep learning based object tracking in walking droplet and granular intruder experiments

引用

JOURNAL OF real-time image processing 2023年第5期20卷 86页

作者： Kara, Erdi Zhang, George Williams, Joseph J. Ferrandez-Quinto, Gonzalo Rhoden, Leviticus J. Kim, Maximilian Kutz, J. Nathan Rahman, Aminur Spelman Coll Math Dept 350 Selman Lane S W Atlanta GA 30314 USA Univ Washington Dept Appl Math Seattle WA USA Univ Washington Dept Phys Seattle WA USA Univ Washington Dept Mech Engn Seattle WA USA Univ Washington Dept Civil & Environm Engn Seattle WA USA

We present a deep-learning based tracking objects of interest in walking droplet and granular intruder experiments. In a typical walking droplet experiment, a liquid droplet, known as walker, propels itself laterally on the free surface of a vibrating bath of the same liquid. This lateral motion stems from the interaction between the droplet and the wave it generates upon successive bounces off the vibrating liquid surface. A walker can exhibit a highly irregular trajectory over the course of its motion, including rapid acceleration and complex interactions with the other walkers present in the bath. In analogy with the hydrodynamic experiments, the granular matter experiments consist of a vibrating bath of very small solid particles and a larger solid called intruder. Like the fluid droplets, the intruder interacts with and travels the domain due to the waves of the bath but tends to move much slower and much less smoothly than the droplets. When multiple intruders are introduced, they also exhibit complex interactions with each other. We leverage the state-of-the-art object detection model YOLO (You Only Look Once) and the Hungarian Algorithm to accurately extract the trajectory of a walker or intruder in real-time. Our proposed methodology is capable of tracking individual walker(s) or intruder(s) in digital images acquired from a broad spectrum of experimental settings and does not suffer from any identity-switch issues. Thus, the deep learning approach developed in this work could be used to automatize the efficient, fast and accurate extraction of observables of interests in walking droplet, granular intruder experiments and similar particle tracking experiments. Such extraction capabilities are critically enabling for downstream tasks such as building data-driven dynamical models for the coarse-grained dynamics and interactions of the objects of interest.

关键词： Walking droplets Granular intruders Object detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

CNN based plant disease identification using PYNQ FPGA

引用

SYSTEMS AND SOFT COMPUTING 2024年 6卷

作者： Perumal, Vivek Karthick Supriyaa, T. Santhosh, P. R. Dhanasekaran, S. Sona Coll Technol Dept ECE Salem Tamil Nadu India Sri Eshwar Coll Engn Dept ECE Coimbatore India

This research presents a novel approach for plant disease identification utilizing Convolutional Neural Networks (CNNs) and the PYNQ FPGA platform. The study leverages the parallel processing capabilities of FPGAs to accelerate CNN inference, aiming to enhance the efficiency of plant disease detection in agricultural settings. The implementation involves optimizing the CNN architecture for deployment on the PYNQ FPGA, considering factors such as image size and learning rates. Through experimentation, the research refines hyper parameters, achieving improved accuracy and F1 scores. Visualizations using heat maps highlight the CNN's reliance on color, shape, and texture for feature extraction in disease identification. The integration of FPGA technology demonstrates promising advancements in real-time, high-performance plant disease classification, offering potential benefits for precision agriculture and crop management. This research contributes to the growing field of FPGA-accelerated deep learning applications in agro technology, addressing challenges in plant health monitoring and fostering sustainable agricultural practices.

关键词： CNN image processing Plant Disease FPGA PYNQ

来源：评论

学校读者我要写书评

暂无评论

Sustainable deep learning at Grid Edge for real-time High Impedance Fault Detection

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING

引用

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING 2022年第2期7卷 346-357页

作者： Sirojan, Tharmakulasingam Lu, Shibo Phung, B. T. Zhang, Daming Ambikairajah, Eliathamby Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

High impedance faults (HIFs) on overhead power lines are known to cause fires. They are difficult to detect using conventional protection relays because the fault current is insufficient to cause tripping. The delay in detecting HIFs can result in severe bushfires and energy losses;hence a high throughput, low latency detection scheme needs to be developed for HIF detection. Moreover, the complexities associated with HIF detection demands signal processing techniques combined with artificial intelligence to achieve higher detection accuracy. This paper proposes a sustainable deep learning-based approach in an edge device, that can be mounted on top of a power pole to detect HIFs in real-time. Data acquisition, feature extraction, and deep learning based fault identification are performed in an embedded edge node to achieve higher throughput, reduced latency as well as offload the network traffic. Furthermore, optimization techniques such as hardware parallelism and pipelining are adapted to achieve real-time fault identification on edge devices while ensuring the efficient usage of its limited resources. real-time implementation of the proposed system is validated through laboratory experiments and the results demonstrate the suitability of edge computing to detect HIFs in terms of reduced detection latency (115.2 ms) and higher detection accuracy (98.67 percent).

关键词： real-time systems image edge detection Edge computing Fires Cloud computing Fault detection Artificial intelligence deep learning edge computing embedded artificial intelligence real-time fault detection sensor data analytics signal processing sustainable computing

来源：评论

学校读者我要写书评

暂无评论

Fast identification of concrete cracks using 1D deep learning and explainable artificial intelligence-based analysis

引用

AUTOMATION IN CONSTRUCTION 2022年第0期143卷

作者： Geetha, Ganesh Kolappan Sim, Sung-Han Sungkyunkwan Univ Sch Civil Architectural Engn & Landscape Architect Suwon 16419 South Korea

The present paper discusses a computationally efficient deep learning (DL) model for real-time classification of concrete crack/non-crack and investigates the 'black-box' nature of the proposed DL model using eXplainable Artificial Intelligence (XAI). The state-of-the-art DL models like semantic segmentation require labor-intensive labeling for pixel-level classification. The proposed framework combines image binarization and a Fourier -based 1D DL model for fast detection and classification of concrete crack/non-crack features. image binariza-tion as a precursor to DL extracts possible Crack Candidate Regions (CCR) and eliminates the plane structural background during DL training and testing. Metadata within the 1D DL model was generated and analyzed using local XAI, wherein t-distributed Stochastic Neighborhood Embedding (t-SNE) was used to visualize the knowl-edge transfer within the hidden layers. The proposed model enables real-time pixel-level classification of crack/ non-crack at the rate of 2 images/s on a mobile platform with limited computational facilities.

关键词： 1D CNN deep learning Fast crack and non -crack classification Computer vision Concrete structures Adaptive threshold image binarization image processing eXplainable Artificial Intelligence (XAI) Mobile AI

来源：评论

学校读者我要写书评

暂无评论

deep learning Model for Cold-Rolled Plate Defect Detection Based on Omni-dimensional Dynamic Convolution and Global Attention Mechanism Enhancement

引用

METALLURGICAL AND MATERIALS TRANSACTIONS B-PROCESS METALLURGY AND MATERIALS processing SCIENCE 2025年 1-17页

作者： Xu, Wenguang Liu, Jianhua He, Yang Yang, Yuanmei Xie, Xin Yang, Xiaodong Univ Sci & Technol Beijing Natl Engn Res Ctr Adv Rolling & Intelligent Mfg Beijing 100083 Peoples R China State Key Lab Vanadium & Titanium Resources Compre Panzhihua 617000 Sichuan Peoples R China Pangang Grp Xichang Vanadium Steel Co Ltd Xichang 615000 Peoples R China

To address the issue of poor accuracy in cold-rolled sheet defect detection, a deep learning model enhanced with omni-dimensional dynamic and global attention mechanisms is proposed. First, omni-dimensional dynamic and global attention mechanisms are integrated into the backbone network. The omni-dimensional dynamic mechanism employs a multi-dimensional attention strategy through parallelism, learning complementary attention along four dimensions: spatial size, input channels, output channels, and the number of convolution kernels. This effectively enhances the network's feature extraction capability and improves its understanding and modeling of input data. The global attention mechanism captures all significant features across the channel and spatial dimensions, considering the interactions among these dimensions, thereby reducing information loss and enhancing global dimension interaction features. This leads to more comprehensive defect feature extraction, improving detection accuracy and stability. Second, we collected images of ten common types of cold-rolled sheet defects from a specific cold-rolling mill and expanded the dataset using image augmentation methods. Ablation experiments were conducted under the established cold-rolled defect dataset to compare our model with three mainstream attention mechanisms. Additionally, comparative experiments with classic two-stage models, one-stage models, and the latest state-of-the-art models were performed to validate the effectiveness of the proposed model. Attention heatmap methods were used to visualize the feature focus areas, enhancing the model's interpretability. Finally, the proposed model was validated and tested on the ten types of cold-rolled sheet defects. Results show that our model achieved a mean average precision of 97.53 pct, outperforming the comparison models. The average inference time per image was only 39.5 ms, and the model complexity was relatively low, meeting the real-time and applicability

关键词： Cold rolling

来源：评论

学校读者我要写书评

暂无评论

An application of smart visual air conditioning controller to enhance control efficiency in office environments

引用

RESULTS IN ENGINEERING 2025年 25卷

作者： Tian, Yu Zhao, Zilong Loo, Junn Yong Univ Malaya Fac Engn Dept Mech Engn Kuala Lumpur 50603 Malaysia Monash Univ Malaysia Sch Informat Technol Jalan Lagoon Selatan 47500 Bandar Sunway Selangor Darul Malaysia

Innovative solutions for sustainability and energy efficiency are crucial in green building management. This study presents a novel approach to optimizing air conditioning (AC) system operations in commercial buildings, with a focus on real-time control aimed at reducing energy consumption. We propose the Smart Visual Air Conditioning Controller (SVACC), which utilizes computer vision and deep learning-based human detection to intelligently manage AC operation, minimizing unnecessary runtime. By detecting human presence in meeting rooms, the system dynamically adjusts AC activation based on occupancy, thereby significantly reducing energy waste. A statistical analysis conducted over five months across ten conference rooms demonstrated that the SVACC reduced AC usage time by 33.60 %. We validate and optimize the SVACC across various building types, including commercial office spaces, industrial warehouses and laboratories, and residential apartments. The system achieved an optimal balance with 96.55 % precision and 93.33 % recall, resulting in an F1 score of 0.9492, demonstrating high performance across various environments. Our results underscore the effectiveness of the SVACC, which highlights the potential of integrating advanced deep learning models with HVAC systems to optimize energy consumption. This approach offers a promising solution for improving HVAC design and energy management across diverse building environments. Future work will focus on refining sensor technology and control algorithms to further optimize energy efficiency.

关键词： HVAC Building management deep learning image processing Computer vision

来源：评论

学校读者我要写书评

暂无评论

IVNet: Transfer learning Based Diagnosis of Breast Cancer Grading Using Histopathological images of Infected Cells

引用

IEEE ACCESS 2023年 11卷 127880-127894页

作者： Aziz, Sameen Munir, Kashif Raza, Ali Almutairi, Mubarak S. Nawaz, Shoaib Khwaja Fareed Univ Engn & Informat Technol Inst Informat Technol Rahim Yar Khan 64200 Pakistan Khwaja Fareed Univ Engn & Informat Technol Inst Comp Sci Rahim Yar Khan 64200 Pakistan Univ Hafr Al Batin Coll Comp Sci & Engn Hafr Alabtin 31991 Saudi Arabia Univ South Asia Lahore 54792 Pakistan

Breast cancer constitutes a significant global health concern that impacts millions of women across the world. The diagnosis of breast cancer involves categorizing grades based on the histopathological characteristics of tumor cells. While histopathological assessment remains the established benchmark for breast cancer diagnosis, it is hampered by time-consuming procedures, subjectivity, and susceptibility to human errors. This study introduces a novel approach called imageNet-VGG16 (IVNet) for the real-time diagnosis of breast cancer within a hospital environment. The research experiments are conducted using a benchmark dataset known as Jimma University Medical Center (JUMC) breast cancer grading. Advanced image processing techniques are applied to preprocess the data, enhancing performance. This preprocessing involves the utilization of Holistically Nested Edge Detection (HED) and Contrast Limited Adaptive Histogram Equalization (CLAHE) for transformation and stain normalization. We employ advanced neural network-based transfer learning techniques to analyze the preprocessed histopathological images and identify affected cells. Various pre-trained models are utilized, including convolutional neural networks (CNN) such as VGG16, ResNet50, InceptionNetv3, imageNet, MobileNetv3, and EfficientNetV3, in a comparative framework. The principal objective of this research is the accurate classification of breast cancer images into Grade-1, Grade-2 and Grade-3. Through extensive experimental research, we achieved a commendable 97% correct classification rate by utilizing a hybrid of VGG16 and imageNet as the proposed feature engineering method, IVNet. We also validate our proposed approach performance using other state-of-the-art study data and statistical t-test analysis. Furthermore, we develop a user-friendly Graphical User Interface (GUI) that facilitates real-time cell tracking in histopathological images. Our real-time diagnosing application offers valuable insights f

关键词： Breast cancer cancer grading image processing deep learning machine learning transfer learning biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

The deep Convolutional Neural Network Role in the Autonomous Navigation of Mobile Robots (SROBO)

引用

REMOTE SENSING 2022年第14期14卷 3324-3324页

作者： Esfahlani, Shabnam Sadeghi Sanaei, Alireza Ghorabian, Mohammad Shirvani, Hassan Anglia Ruskin Univ Med Technol Res Ctr MTRC Sch Engn & Built Environm Chelmsford CM1 1SQ Essex England Anglia Ruskin Univ Sch Engn & Built Environm Chelmsford CM1 1SQ Essex England

The ability to navigate unstructured environments is an essential task for intelligent systems. Autonomous navigation by ground vehicles requires developing an internal representation of space, trained by recognizable landmarks, robust visual processing, computer vision and image processing. A mobile robot needs a platform enabling it to operate in an environment autonomously, recognize the objects, and avoid obstacles in its path. In this study, an open-source ground robot called SROBO was designed to accurately identify its position and navigate certain areas using a deep convolutional neural network and transfer learning. The framework uses an RGB-D MYNTEYE camera, a 2D laser scanner and inertial measurement units (IMU) operating through an embedded system capable of deep learning. The real-time decision-making process and experiments were conducted while the onboard signal processing and image capturing system enabled continuous information analysis. State-of-the-art real-time Graph-Based SLAM (RTAB-Map) was adopted to create a map of indoor environments while benefiting from deep convolutional neural network (deep-CNN) capability. Enforcing deep-CNN improved the performance quality of the RTAB-Map SLAM. The proposed setting equipped the robot with more insight into its surroundings. The robustness of the SROBO increased by 35% using the proposed system compared to the conventional RTAB-Map SLAM.

关键词： semantic segmentation object detection autonomous navigation convolutional networks transfer learning deep learning

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：