检索结果-内蒙古大学图书馆

IEEE International Conference on Information Communication and Signal processing (ICICSP)

作者： Jie xi Yulin Jiang Yifan Wang Yan Wei xingbin Tu Fengzhong Qu Ocean College Zhejiang University Zhoushan China Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province Zhejiang University Zhoushan China Hainan Institute of Zhejiang University Sanya China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

With the escalating demand for image observation and video transmission in underwater environments, real-time wireless multimedia transmission stands as the pivotal stride in the advancement of ocean exploration and observation systems. While acoustic communication remains the most dependable solution for underwater wireless communication, multimedia transmission still grapples with the challenges of limited band-width and poor channel quality. In this paper, we introduce a self-developed underwater acoustic modem especially tailored to real-time multimedia transmission. This comprehensive design spans across hardware components, the application layer, data link layer, and the physical layer. The utilization of multi-band retransmission mechanisms and sophisticated physical layer algorithms contributes to the system's resilience against the complexities of the underwater acoustic channel. Subsequent communication experiments have been conducted in both Zhoushan, Zhejiang, and the South China Sea, focusing on horizontal and vertical underwater acoustic channels respectively. Through these trials, the system's demodulation and retransmission capabilities have been duly validated, resulting in the successful transmission of multimedia video files on multiple occasions.

关键词： Wireless communication Oceans Signal processing algorithms Streaming media Signal processing Physical layer Modems Real-time systems Multimedia communication Underwater acoustics

来源：评论

学校读者我要写书评

暂无评论

Fast Total Focusing Method Based On Elliptical Arc Scanning algorithm and OpenCL Acceleration

Fast Total Focusing Method Based On Elliptical Arc Scanning ...

引用

Intelligent Control, Measurement and Signal processing and Intelligent Oil Field (ICMSP), International Conference on

作者： Yulong Pan Weizhi Tao Rui Yu Aijun He School of Electronic Science and Engineering Nanjing University Nanjing China

ISBN: (数字)9798331516550

ISBN: (纸本)9798331516567

Total focusing method (TFM), as the most effective post-processing technique for ultrasonic phased array imaging currently, can achieve focusing at any point within the detection area, possessing advantages of high resolution and signal-to-noise ratio that traditional phased array imaging methods lack. However, Total Focusing Method (TFM) imaging requires delay-and-sum processing of full matrix capture (FMC) data. If the number of elements involved in signal acquisition is N, the full matrix data will contain N A-scan signals, each containing thousands of sampling *** will result in long computation time and make it difficult to achieve real-time imaging. This paper proposes a fast total focusing method that combines elliptical arc scanning algorithm and OpenCL hardware acceleration, and deploys it to a self-developed ultrasound phased array imaging system. Results show that the fast total focusing method can generate a 512 × 512 pixel image with 32 elements in an average time of only 64 milliseconds, far surpassing the time required by conventional total focusing algorithms, providing a feasible approach for real-time high-precision non-destructive testing online.

关键词： Phased arrays Ultrasonic imaging Array signal processing Focusing Signal processing algorithms Real-time systems Arrays Velocity measurement Hardware acceleration Testing

来源：评论

学校读者我要写书评

暂无评论

Intelligent Detection of Insulator Defects on Transmission Lines in Complex Backgrounds based on Improved DETR Visual Perception Model

Intelligent Detection of Insulator Defects on Transmission L...

引用

Artificial Intelligence and Power systems (AIPS), International Conference on

作者： Songping Tang Ruifeng Zhu Chao Ji Chong Li Yuxi Dong Yun Zhang Junpeng Liu Huizhou PowerSupply Bureau of Guangdong Power Grid Co. Ltd. Huizhou China Xi'An Polytechnic University Xi'an China

ISBN: (数字)9798350392210

ISBN: (纸本)9798350392227

The problem of insulator defects in transmission lines caused by adverse environmental conditions poses a significant risk to the safe and stable operation of the power system. In order to improve upon traditional methods of inspecting transmission lines in real-time, this article proposes an optimized detection method based on the Detection Transformer (DETR) algorithm. With the aim of achieving a more intelligent detection of transmission lines, unmanned aerial vehicles (UAVs) are employed for line inspections. Firstly, the insulator images captured by UAV inspections are processed to remove fog and noise, enhancing their clarity. Subsequently, a hybrid attention mechanism module is introduced into the backbone network ResNet50 of the DETR algorithm to reduce data processing errors. Insulator defect data is annotated using LabelImg software and saved according to the Pascal VOC standard dataset. Finally, the annotated data is input into the improved DETR algorithm for feature data training, generating an optimal image neural network detection model capable of intelligently detecting insulators in transmission lines amidst complex backgrounds.

关键词： Training Power transmission lines Software algorithms Inspection Insulators Feature extraction Autonomous aerial vehicles Real-time systems Power systems Visual perception

来源：评论

学校读者我要写书评

暂无评论

Advanced image processing Techniques for Enhancing Cargo Capacity Optimization in Intelligent Logistics Vehicles

引用

TRAITEMENT DU SIGNAL 2023年第6期40卷 2433-2442页

作者： Wang, Huizhen Xian Int Univ Business Sch Xian 710077 Peoples R China

The burgeoning global logistics industry has necessitated the development of intelligent logistics systems as a crucial means to augment efficiency and curtail costs. Paramount to bolstering logistics system performance is the optimization of cargo capacity in logistics vehicles, intrinsically linked to diminishing logistics expenses and augmenting transportation efficiency. Conventional approaches for gauging vehicle cargo capacity, predominantly reliant on manual measurements, have encountered challenges of inefficiency and lack of precision. In response to these impediments, this study advocates an innovative image processing-based methodology for optimizing vehicle cargo capacity. The research initially concentrates on refining stereo matching algorithms, aiming to elevate measurement accuracy and stability amidst complex environmental conditions. This enhancement proves particularly efficacious in measuring cargos with irregular contours and diverse reflective properties, facilitating more precise volume estimations. Additionally, the study introduces a novel methodology for volume calculation, predicated on the statistical analysis of pixel heights in images. This technique, utilizing meticulous camera calibration coupled with the extraction of pixel height data, enables the swift and accurate determination of cargo volume in vehicles, thereby markedly improving measurement efficiency and precision. The progress delineated herein not only paves a novel technological path for optimizing cargo capacity in logistics vehicles but also advances the application of image processing technology within the realm of intelligent logistics. The advancements hold substantial market potential and research significance, presenting a promising avenue for future explorations in this field.

关键词： intelligent logistics cargo capacity optimization image processing stereo matching algorithms volume measurement

来源：评论

学校读者我要写书评

暂无评论

Research on Software and algorithms for Displacement Monitoring System Based on Machine Vision

Research on Software and Algorithms for Displacement Monitor...

引用

Advanced algorithms and Control Engineering (ICAACE), International Conference on

作者： Yuanding xing Yongxiang Shi Xuejie Jiao Shiqian Song xiaofei Huang Northwest Institute of Nuclear Technology Xi'an Shaanxi China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Shield tunnels excavated for urban subway construction experience complex defects since they are plagued by various factors such as rock properties, tunnel lining deformation, and erosion damage. In practical subway tunnel inspection, most measurements still hinge predominantly on traditional manual inspections and manual marking, supplemented by a limited number of inspection instruments, which is insufficient to meet modern testing requirements. To address the challenge of automated measurement during complex underground construction and subsequent operations, research was conducted on a multi-target displacement online monitoring system. The system design process is elaborated in detail from both software and image processing perspectives, encompassing the software design architecture, target capture program, image acquisition, and edge detection procedures. Considering potential target occlusion in actual monitoring environments, this study capitalizes on a triple-condition judgment method to determine target occlusion, thereby ensuring the system's field applicability and providing robust data support for the subsequent development of an automatic alarm system, a testament to a reduction in false alarm rates. Finally, the system was tested in an outdoor environment with multiple targets, and the results indicated a stable error of less than 0.05 mm, catering to field testing requirements. The research findings reveal the system's adaptability to the vibrating and dusty environments of underground construction sites, exhibiting high displacement measurement accuracy, real-time measurement, and a high degree of automation. It holds promising application prospects in displacement monitoring for complex underground engineering projects.

关键词： Machine vision image edge detection Displacement measurement Manuals Inspection Software Real-time systems Monitoring Public transportation Testing

来源：评论

学校读者我要写书评

暂无评论

Indoor Visible Light Positioning Method Based on Sparse Fingerprints Using Extended Min-Max and WKNN algorithms

Indoor Visible Light Positioning Method Based on Sparse Fing...

引用

IEEE International Conference on Signal and image processing (ICSIP)

作者： Xunuo Li Zhonghua Liang Zhenyu Wang Hui Li School of Information Engineering Chang’an University Xi’an China

Indoor visible light positioning (VLP) systems based on received signal strength (RSS) fingerprint can provide high-precision indoor positioning with low complexity. However, laborious offline field measurements are required to collect RSS fingerprints, and the subsequent fingerprint matching process also needs a large computation overhead. In order to address the above problems, in this paper, we propose an indoor VLP method based on sparse fingerprints using extended Min-Max (E-Min-Max) and weighted k-nearest neighbor (WKNN) algorithms. In the proposed VLP method, bicubic interpolation is used during the offline phase to directly estimate the RSS values of virtual reference nodes. In the online phase, a coarse estimate of the position of target node (TN) is firstly obtained by using the E-Min-Max algorithm. Then, based on the coarse estimate of the TN’s position, the WKNN algorithm is used to determine the TN’s accurate position. Simulation results show that compared to the traditional WKNN algorithm, the proposed VLP method has much higher fingerprint matching efficiency while ensuring high positioning accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual-branch Approach for Tracking UAVs with the Infrared and Inverted Infrared image 7

Dual-branch Approach for Tracking UAVs with the Infrared and...

引用

7th International Conference on Intelligent Computing and Signal processing, ICSP 2022

作者： Li, Shaogang Gao, Jin Li, Liang Wang, Gang Wang, Yizheng Yang, xin University of South China Hengyang China Chinese Academy of Sciences Institute of Automation Beijing China Beijing Institute of Basic Medical Sciences Beijing China

ISBN: (纸本)9781665478571

The imaging for small unmanned aerial vehicles (UAVs) in infrared imaging systems is easily disturbed when they shuttle between different surrounding regions in a large background, resulting in target contrast inversion. Existing methods have poor tracking performance in this scenario. A dual-branch object tracking framework is proposed to tackle this problem. Firstly, the features of original and inverted infrared images are extracted by different branches. Then, a cross-correlation feature fusion module is proposed, which fuses the features of the two branches to enhance the features of the target area to obtain a more accurate bounding box regression. The proposed method achieves top performance compared with the existing state-of-the-art tracking algorithms, reaching the success rate of 78.39% and precision rate of 80.07% on the 2nd anti-UAV datasets, which are 5.84% and 4.52% higher than the SuperDiMP baseline. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Reduced CPU Workload for Human Pose Detection with the Aid of a Low-Resolution Infrared Array Sensor on Embedded systems

引用

SENSORS 2023年第23期23卷 9403页

作者： Alves, Marcos G. Chen, Gen-Lang Kang, xi Song, Guang-Hui NingboTech Univ Sch Comp & Data Engn Ningbo 315100 Peoples R China

Modern embedded systems have achieved relatively high processing power. They can be used for edge computing and computer vision, where data are collected and processed locally, without the need for network communication for decision-making and data analysis purposes. Face detection, face recognition, and pose detection algorithms can be executed with acceptable performance on embedded systems and are used for home security and monitoring. However, popular machine learning frameworks, such as MediaPipe, require relatively high usage of CPU while running, even when idle with no subject in the scene. Combined with the still present false detections, this wastes CPU time, elevates the power consumption and overall system temperature, and generates unnecessary data. In this study, a low-cost low-resolution infrared thermal sensor array was used to control the execution of MediaPipe's pose detection algorithm using single-board computers, which only runs when the thermal camera detects a possible subject in its field of view. A lightweight algorithm with several filtering layers was developed, which allowed the effective detection and isolation of a person in the thermal image. The resulting hybrid computer vision proved effective in reducing the average CPU workload, especially in environments with low activity, almost eliminating MediaPipe's false detections, and reaching up to 30% power saving in the best-case scenario.

关键词： edge computing thermal image MediaPipe pose detection power optimization power saving

来源：评论

学校读者我要写书评

暂无评论

Autofocus-Coupled UTAMP for Sparse Aperture ISAR Imaging

Autofocus-Coupled UTAMP for Sparse Aperture ISAR Imaging

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Hailong Kang Liang Xu Tuoyu Shen Jun Li Marco Martorella The Hangzhou Institute of Technology Xidian University Hangzhou China The National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Radar and Surveillance Systems (RaSS) Laboratory (CNIT) Pisa Italy Department of Electronic Electrical and Systems Engineering University of Birmingham Birmingham UK

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Autofocusing is an important step for inverse synthetic aperture radar (ISAR) imaging, while traditional autofocusing algorithms often fail in sparse aperture (SA) case. The residual phase error due to the imperfect motion compensation cannot be ignored for the compressive sensing (CS) based SA ISAR imaging. To tackle this issue, an autofocus-coupled approximate message passing with unitary transformation (AFUTAMP) algorithm for SA ISAR imaging is proposed in this paper. The phase error estimation process is introduced to the UTAMP framework for autofocusing, which enable UTAMP to simultaneously complete ISAR image reconstruction and autofocus, thereby leading to excellent performance of imaging and autofocusing. The effectiveness and superiority of the proposed algorithm are verified by the simulation results and experimental results based on measured data.

关键词： Simulation Message passing Imaging Geoscience and remote sensing Apertures Radar imaging Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Road Safety: Constrained Device Utilization for Accident Prevention in Traffic Congestion

Enabling Smart Road Safety: Constrained Device Utilization f...

引用

Multimedia University Engineering Conference (MECON)

作者： Amna Khatoon Asad Ullah Ishfaq Ahmed Ayesha Aslam Mardeni Bin Roslee Shabeer Ahmad School of Information Engineering Chang'an University Xi'an China School of Information Engineering Xi’ an Eurasia University Xi’ an Shaanxi China School of Marine Science Northwestern Polytechnical University Xi’ an China Faculty of Engineering Multimedia Multimedia University University Cyberjaya Malaysia School of Electronic Engineering Beijing University of posts and Telecommunications

ISBN: (数字)9798331530747

ISBN: (纸本)9798331530754

Computer Vision (CV) analysis on constrained devices plays a crucial role in enhancing road safety and mitigating traffic congestion. This study demonstrates the integration of image segmentation and classification techniques into traffic monitoring systems on devices with limited computational power, such as dashboard cameras, smartphones, and IoT sensors. These technologies enable efficient real-time data collection and processing in densely populated urban areas, facilitating the immediate detection of irregular traffic patterns and potential collision points by leveraging edge computing and optimized algorithms. By implementing these analyses directly on constrained devices strategically placed within traffic systems, our approach provides timely responses to dynamic conditions, significantly reducing accident risks through early warnings and adaptive route suggestions. Our research also shows that CV systems can monitor driver behavior, detect attention or weariness, and give timely signals to improve driver response times. The data supports improving traffic signal timings, which might reduce vehicle idle times and improve traffic flow, thus increasing road safety and reducing environmental impact. The study provides a comprehensive methodology for implementing high-quality CV technologies in resource-constrained environments, highlighting advancements in edge computing and energy-efficient hardware. These advances underscore the importance of CV in building sustainable, resilient transport networks and its versatility in municipal and vehicle traffic management, enabling proactive measures to reduce accidents.

关键词： Computer vision Data collection Road safety Real-time systems Vehicle dynamics Traffic congestion Monitoring Edge computing Accidents Vehicles

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：