检索结果-内蒙古大学图书馆

International conference on Unmanned Aircraft systems (ICUAS)

作者： Calvin Coopmans Richard Snider Sadikul Alim Toki Andres Sewell Steve Petruzza Emma Montgomery Department of Electrical and Computer Engineering Utah State University Logan UT USA Department of Computer Science Utah State University Logan UT USA

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

As uncrewed aerial systems continue to grow in popularity and importance, the long-term and scalable use of these systems for remote sensing and imagery data collection remains a valuable and achievable goal. To enable these systems at scale, real-time onboard imagery processing is required. To determine the feasibility of real-time remote sensing systems, many factors must be accounted for, including the ability of the sensing and processing algorithms to operate on and collect data from real-world scenes and deliver actionable intelligence to the data consumer. In this paper, a holistic simulation system based on ROS 2 and Gazebo is presented, which allows for real-time processing algorithms to be tested and proven for flight in an accurate and extensible way. By using ROS 2 and USU AggieAir's STARDOS platform, it is possible to show how the remote sensing system and onboard, real-time processing algorithms are applicable to the aerial remote sensing task (i.e. it can demonstrate feasibility for physical deployment based on accurate simulated data processing).

关键词： Accuracy Codes Data collection Autonomous aerial vehicles Real-time systems Software Hardware Sensors Remote sensing image stitching

来源：评论

学校读者我要写书评

暂无评论

Study on Optimization of Computer image Structure in Wushu Performance Training Model

引用

International Journal of High Speed Electronics and systems 2025年第2期34卷

作者： Li, Li PE Department of Shaanxi Xueqian Normal University Shaanxi Xueqian Normal University Shanxi Xi’an710100 China

With the vigorous development of computer technology, its application in various fields is increasingly deepening, especially in the application of martial arts performance training models. This paper focuses on the practical application and far-reaching impact of computer image structure optimization in martial arts performance training models. Computer image structure optimization is a multidisciplinary technique that involves image processing, computer vision, and machine learning, aiming to optimize the visual effects and quality of images through algorithms and models. In the training model of martial arts performance, computer image structure optimization technology plays a crucial role. By utilizing advanced technologies such as color management, light and shadow processing, motion estimation and compensation, the clarity, smoothness, and coherence of martial arts performance images can be effectively improved, thereby enhancing the artistic effect and viewing value of martial arts performances. The study delved into the application effect of computer image structure optimization in martial arts performance training models. Through empirical research, we have found that optimized images can not only more accurately display the details and techniques of martial arts movements, but also create a more stunning performance atmosphere. Meanwhile, computer image structure optimization technology can also provide more accurate and efficient feedback mechanisms for martial arts performance training, helping athletes better adjust and improve their movements. © World Scientific Publishing Company.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Line Sag Monitoring Using image-Based Bézier Curve Fitting

Dynamic Line Sag Monitoring Using Image-Based Bézier Curve ...

引用

IEEE SSD International Multi-conference on systems, Signals and Devices

作者： Achref Abed Hafedh Trabelsi Faouzi Derbel Faculty Engineering Sciences University of Applied Sciences Leipzig Leipzig Germany Department of Electrical Engineering and Information Technology National Engineering School of Sfax Sfax Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

This paper presents an automated system for detecting the sag of overhead transmission lines using image processing. A camera, mounted centrally between two towers, is repositioned using stepper motors to ensure symmetrical alignment with the transmission line. By detecting the lowest point of the line in the image, the system estimates the sag through Bezier curve fitting and converts the pixel-based measurements into real-world dimensions. The proposed system demonstrates high precision and accuracy, providing a reliable method for sag measurement in transmission line monitoring.

关键词： Power transmission lines Accuracy image processing Heuristic algorithms Poles and towers Transmission line measurements Real-time systems Safety Curve fitting Monitoring

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Tatsukichi Shibuya Nakamasa Inoue Rei Kawakami Ikuro Sato Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in fine-tuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO

关键词： Training Speech coding Memory management Signal processing algorithms Signal processing Classification algorithms Servers Speech processing Optimization image classification

来源：评论

学校读者我要写书评

暂无评论

Adversarial Encoder-Driven Filter for Targeted image Tagging: A Novel Approach to Visual Content Manipulation

Adversarial Encoder-Driven Filter for Targeted Image Tagging...

引用

International image processing, Applications and systems conference (IPAS)

作者： Cole Mckee Dominic Flowers Jesse Wood Ethan Shafer Department of Electrical Engineering and Computer Science United States Military Academy West Point New York

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

Computer vision, driven by artificial intelligence, has become pervasive in diverse applications such as self-driving cars and law enforcement. However, the susceptibility of these systems to attacks has raised significant concerns among researchers. This paper addresses the vulnerability of image tagging algorithms, particularly focusing on misclassifications induced by autoencoders. We present experiments conducted on Amazon Rekognition, where we developed a specialized autoencoder to manipulate the latent space, forcing it to align with specific tags. By integrating this manipulated latent space with other images, we demonstrate the ability to increase the confidence of a specific tag on Amazon Rekognition, leading to more false positives of the chosen tag. Our study showcases a practical method to exploit Amazon’s Rekognition image tagging algorithm using a black box approach.

关键词： Training Resistance Computer vision Visualization Law enforcement Military computing Computational modeling Autoencoders image annotation Closed box

来源：评论

学校读者我要写书评

暂无评论

6G XL-MIMO Channel Estimation with Sub-Nyquist Tensor Completion

6G XL-MIMO Channel Estimation with Sub-Nyquist Tensor Comple...

引用

Digital Signal processing and its Applications (DSPA), International conference on

作者： Semyon Dorokhin Vladimir Lyashev Mikhail Makurin Moscow Institute of Physics and Technology Moscow Russia Radio Transmission Technology Lab Moscow Russia

ISBN: (数字)9798331518752

ISBN: (纸本)9798331518769

Channel estimation overhead reduction is one of the main problems for 6G XL-MIMO systems. As the number of antennas and subcarriers grows, so does the overhead of traditional channel estimation methods. High overhead limits user mobility and affects the latency. Most of the popular tensor-based channel estimation algorithms combine reference signals transmission and channel tensor estimation into one problem. Such approach typically imposes limitations on reference signals, making backward-compatibility with existing 5G standard challenging. We propose to separate tensor completion and channel tensor elements estimation into different tasks. We show that tensor completion algorithms from image processing and fMRI scanning can be reused for sub-Nyquist completion of OFDM MIMO tensors to reduce the overhead. Furthermore, we extend one of these algorithms from CPD to Tensor Train (TT) and demonstrate that TT-based algorithm reduces channel estimation error up to 2 times. With the proposed approach other algorithms can be further developed based on tensor completion theory.

关键词： 6G mobile communication Tensors OFDM image processing Channel estimation Signal processing algorithms Estimation Massive MIMO Functional magnetic resonance imaging Standards

来源：评论

学校读者我要写书评

暂无评论

An Efficient image-Based Virtual Scene Generation and Stitching Algorithm

An Efficient Image-Based Virtual Scene Generation and Stitch...

引用

Multi-Agent systems for Collaborative Intelligence (ICMSCI), International conference on

作者： Luo Wei Chongqing Three Gorges Vocational College Chongqing Wanzhou China

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With the development of computer graphics and image processing, the virtual scene generation and splicing technology has been widely used in various fields of computer-aided image analysis. In this context, this study proposes a new and efficient image stitching algorithm to solve the image stitching artifacts caused by perspective changes and exposure differences in multi-camera systems, and expands it to the field of virtual images. First, as a pre-processing part, the model analyzes the image through nonlinear filtering and mesh deformation optimization to ensure image quality. Subsequently, the model presents a new image stitching algorithm based on the image matching method of minimizing projection deviation and thin plate spline theory. This algorithm further proposes an improved EIEOWF algorithm based on circular weighted fusion to achieve the task of smooth transition stitching of images. Finally, the stitching technology was extended to virtual scene generation, and OpenGL technology was used to achieve real-time 3D texture mapping. The test part is verified through experiments on the UDIS-D data set. The results show that the average splicing accuracy of the proposed algorithm in 100 sets of tests is 95%, with a standard deviation of 2%, which is significantly better than the existing comparison algorithm.

关键词： Three-dimensional displays Accuracy Splicing Heuristic algorithms Reliability theory Real-time systems Splines (mathematics) image stitching Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks (CNN) for Industrial Parts Recognition: Advancing Manufacturing Digitalization 2nd

Convolutional Neural Networks (CNN) for Industrial Parts Rec...

引用

2nd International conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Nardviriyaku, Pasavich Hajjaj, Sami Salama Hussen School of Robotics Xi’an Jiaotong-Liverpool University 111 Taicang Avenue Jiangsu Province Suzhou Taicang215400 China School of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia

ISBN: (纸本)9789819639489

In the current era of manufacturing digitalization, computer vision is an emerging field of artificial intelligence (AI) that replicates human visual system functions by enabling computers and systems to identify and interpret visual information. Convolutional Neural Networks (CNNs) have demonstrated remarkable potential in image recognition and tasks related to pixel data processing. Industrial parts recognition and classification systems play a crucial role in automating manufacturing processes, streamlining workflow, and enhancing object recognition capabilities on production lines. This research presents a CNN-based approach to industrial parts recognition and classification, offering new possibilities for efficient and accurate prediction performance. The Inception-v3 network architecture was selected for its state-of-the-art design, serving as the pre-trained model to achieve optimal performance. The TensorFlow library provided a comprehensive and flexible framework, while dropouts were employed to prevent overfitting. The trained CNN model was evaluated using key metrics such as accuracy, precision, recall, F1-score, and model loss, with a confusion matrix adopted for binary classification to assist decision-making and summarize the model’s predictions. The study results demonstrated that the model achieved an impressive accuracy of 98.83% with a model loss of 0.023084, proving highly effective in identifying industrial parts, specifically distinguishing between BJ15–860 and BJ15–870 screws. This research underscores the capabilities of artificial intelligence, particularly in CNNs, and highlights the application of industrial parts recognition and classification, contributing significantly to the digitalization of manufacturing processes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of image Recognition and processing Technology in Integrated Media Information Dissemination

Research on the Application of Image Recognition and Process...

引用

Digital Analysis and processing, Intelligent Computation (DAPIC), International conference on

作者： Shiyu Pan Jiangsu College of Tourism Yangzhou Jiangsu China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

With the rapid development of the era of integrated media, the form of information dissemination is becoming more and more diversified, in which the image as an important carrier of information dissemination, its quality and processing efficiency directly affect the dissemination effect. By virtue of its unique advantages in data analysis, image optimization and content distribution, image recognition and processing technology has become an important support means in the field of integrated media information dissemination. This paper firstly analyzes the current situation of the application of image recognition and processing technology in the information dissemination of integrated media; secondly, it discusses the core methods of image recognition and processing technology, including deep learning algorithms, feature extraction technology and real-time image processing strategies; finally, it elaborates the specific application effects of these technologies in the fields of news reporting, advertising and marketing, and live video broadcasting through practical application examples. The study shows that image recognition and processing technology not only improves the intelligent level of integrated media content production, but also provides new possibilities for the innovation of information dissemination mode. In the future, with the further improvement of algorithm performance and the technological integration of multimedia platforms, this field is expected to gain wider application.

关键词： Industries Technological innovation image recognition Face recognition Production Media Real-time systems User experience Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

Research on image Enhancement Technology and Signal processing Methods in Teaching Hydraulic systems

Research on Image Enhancement Technology and Signal Processi...

引用

Digital Analysis and processing, Intelligent Computation (DAPIC), International conference on

作者： Shijie Guan Pengpeng Liu Zhengyi Zhang Weiwei Dong xiangtong Kong High-tech Institute QingZhou Shandong China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

Hydraulic system as an important part of industrial automation, its teaching effect directly affects the quality of related technical personnel training. Hydraulic transmission course is a theoretical and practical combination of the post course offered by our non-commissioned officers' vocational and technical education in mechanical manufacturing technology, because the hydraulic system involves complex images and signal data, students often face difficulties in understanding and analyzing in the learning process. Through the course, students can systematically master the basic theoretical knowledge of the hydraulic transmission system, familiar with the structural composition and working principle of commonly used hydraulic components, and master the working principle and characteristics of common basic circuits. This paper proposes to combine image enhancement technology with signal processing methods to optimize the teaching of hydraulic system. By analyzing the application of image enhancement technology in image denoising, edge detection and brightness adjustment, as well as the practical effect of signal processing methods in frequency domain analysis, time-frequency analysis and intelligent algorithms, we explore how to enhance students' theoretical understanding and practical ability of hydraulic system. The study shows that the integration of image and signal processing technology can not only significantly improve the teaching efficiency, but also provide technical support for the construction of intelligent teaching mode in the future.

关键词： Training Time-frequency analysis image edge detection Education Brightness Hydraulic systems Virtual reality Signal processing image enhancement image denoising

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：