检索结果-内蒙古大学图书馆

Intelligent real-time image processing Technology of Badminton Robot via Machine Vision and Internet of Things

IEEE ACCESS 2023年 11卷 126748-126761页

作者： Liu, Bin Zheng, Yingying Taylors Univ Sch Comp Sci & Engn Subang Jaya 47500 Selangor Malaysia Wenzhou Univ Coll Phys Educ & Hlth Wenzhou 325035 Peoples R China

The development of precise detection and tracking methods for high-speed moving targets, coupled with accurate matching under varying lighting conditions, represents a formidable challenge in the realm of badminton robot creation. To tackle these intricate issues, this work introduces a suite of innovative techniques within the domain of intelligent robot image processing, offering substantial impetus to the evolution of badminton robots. Primarily, the work designs a high-precision binocular stereo vision acquisition system to enhance the accurate reconstruction of the badminton shuttlecock's trajectory in three-dimensional space, enabling real-time monitoring and in-depth analysis of shuttlecock motion. Subsequently, an inventive dynamic threshold Gaussian mixture model, underpinned by singular value decomposition, is introduced. This model dynamically adjusts the decision threshold based on background-foreground similarity while ensuring synchronized exposure between the left and right cameras and timely data retrieval. Lastly, the study addresses the impact of lighting fluctuations on target matching through a Retinex-based color histogram matching method, adapting color histogram templates according to varying lighting intensities. Experimental validation involves the utilization of an industrial digital camera with frame exposure to capture badminton images, subsequently transforming image processing into motion control to effectively realize the badminton robot's hitting action. The experimental outcomes highlight the following achievements: 1) The designed badminton robot achieves a remarkable 100% recognition rate for the shuttlecock under normal conditions, featuring a standard deviation of $\theta $ below 0.05 degrees, a position standard deviation of less than 18 millimeters in the x-axis direction, and less than 8 millimeters in the y-axis direction;2) The proposed binocular stereo vision acquisition system exhibits superior precision, profoundly suppor

关键词： Internet of Things Machine vision Target tracking machine vision badminton robots real-time image processing

来源：评论

学校读者我要写书评

暂无评论

real-time image processing in A Multi-UAV System for Structural Surveillance Through IoT Platform

Real-time Image Processing in A Multi-UAV System for Structu...

引用

Conference on real-time image processing and Deep Learning

作者： Falcon, Jose Mehrubeoglu, Mehrube Rangel, Pablo Texas A&M Univ Corpus Christi Elect Engn Program Dept Engn Corpus Christi TX 78412 USA

ISBN: (纸本)9781510650817;9781510650800

The use of location and instruction markers for multi-path planning enhancement in any set of unmanned aerial systems' tasks is crucial to the coordination and effectiveness of the individual unmanned aerial vehicles (UAVs). This research implements OpenCV algorithms that allow multiple UAVs to use ArUco markers to receive data related to location and instruction for the purposes of multi-path planning. OpenCV algorithms are utilized to develop vision-based solutions that will enhance the real-time capabilities of the UAVs. The final goal for the multi-drone system entails inspecting and surveying objects for structural damage and applying the developed image processing algorithms to collected images to determine the significance of damage. This project utilizes OpenCV and Python libraries for multi-drone pathway planning by collecting, transmitting, and displaying real-world industrially valuable data over the network infrastructure as an application of Internet of Things (IoT).

关键词： unmanned aerial vehicle UAV OpenCV ArUco marker Internet of Things real-time image processing

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent real-time image processing in fitness motion detection under internet of things

引用

JOURNAL OF SUPERCOMPUTING 2022年第6期78卷 7788-7804页

作者： Cai, Hang Nanjing Normal Univ Sch Sports Sci & Phys Educ Nanjing 210000 Jiangsu Peoples R China

The purpose is to study the applicability of digital and intelligent real-time image processing (IP) in fitness motion detection under the environment of the Internet of Things (IoT). Given the absence of real-time training standards and possible workout injury problems during fitness activities, an intelligent fitness real-time IP system based on Deep Learning (DL) is implemented. Specifically, the keyframes of the real-time images are collected from the fitness monitoring video, and the DL algorithm is introduced to analyze the fitness motions. Afterward, the performance of the proposed system is evaluated through simulation. Subsequently, the Noise Reduction (NR) performance of the proposed algorithm is evaluated from the Peak Signal-to-Noise Ratio (PSNR), which remains above 20 dB for seriously noisy images (with a noise density reaching up to 90%). By comparison, the PSNR of the Standard Median Filter (SMF) and Ranked-order Based Adaptive Median Filter (RAMF) algorithms are not higher than 10 dB. Meanwhile, the proposed algorithm outperforms other DL algorithms by over 2.24% with a detection accuracy of 97.80%;the proposed system can adaptively detect the fitness motion, with a transmission delay no larger than 1 s given a maximum of 750 keyframes. Therefore, the proposed DL-based intelligent fitness real-time IP algorithm has strong robustness, high detection accuracy, and excellent real-time image diagnosis and processing effect, thus providing an experimental reference for sports digitalization and intellectualization.

关键词： Deep learning real-time image processing Internet of Things Fitness motion Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Identification of malnutrition and prediction of BMI from facial images using real-time image processing and machine learning

引用

IET image processing 2022年第3期16卷 647-658页

作者： Dhanamjayulu, C. Nizhal, U. N. Maddikunta, Praveen Kumar Reddy Gadekallu, Thippa Reddy Iwendi, Celestine Wei, Chuliang Xin, Qin VIT Vellore Sch Elect Engn Vellore Tamil Nadu India VIT Vellore Sch Informat Technol & Engn Vellore Tamil Nadu India Coal City Univ Enugu Nigeria Shantou Univ Dept Elect Engn Shantou 515063 Guangdong Peoples R China Shantou Univ Key Lab Digital Signal & Image Proc Guangdong Pro Shantou Guangdong Peoples R China Univ Faroe Islands Sci & Technol Torshavn Faroe Islands

Human faces contain useful information that can be used in the identification of age, gender, weight etc. Among these biometrics, body mass index (BMI) and body weight are good indicators of a healthy person. Motivated by the recent health science studies, this work investigates ways to identify malnutrition affected people and obese people by analyzing body weight and BMI from facial images by proposing a regression method based on the 50-layers Residual network architecture. For face detection, Multi-task Cascaded Convolutional Neural Networks have been employed. A system is created to evaluate BMI along with age and gender from human facial real-time images. Malnutrition and obesity are commonly determined with the help of BMI. In the previous works, height, weight, and BMI estimation through automatic means have predominantly focused on full-body images and videos of humans. The usage of facial images for estimating such traits have been given less importance. In order to facilitate the analysis, the dataset is cleaned along with metadata containing information about the persons height, weight, age, and gender. Gender-based analysis is performed for the prediction of BMI. Finally, an email containing the persons picture along with their details is sent to the concerned health officer.

关键词： regression analysis Multitask Cascaded Convolutional Neural Networks malnutrition affected people convolutional neural nets body mass index recent health science studies body weight gender-based analysis facial images full-body images learning (artificial intelligence) human faces real-time images feature extraction face recognition 50-layers Residual network architecture image processing real-time image processing obesity BMI estimation obese people face detection

来源：评论

学校读者我要写书评

暂无评论

Detection of printed circuit board faults with FPGA-based real-time image processing

引用

Iran Journal of Computer Science 2023年第4期6卷 419-430页

作者： Aydın, Merve Kaçar, Fırat Department of Electrical and Electronics Engineering Dogus University Umraniye Istanbul Turkey Department of Electrical and Electronics Engineering Istanbul University–Cerrahpasa Avcilar Istanbul Turkey

In the electronics industry, flawless manufacturing of printed circuit boards (PCBs) is essential for producing high-quality consumer electronics products. This paper presents a real-time image processing method that uses field programmable gate arrays (FPGAs) to detect missing components, which is a critical type of failure in surface mount devices (SMDs) on PCBs. FPGAs can perform multiple parallel operations on the same clock signal, allowing for real-time image processing through high-speed data transfer. The OV7670 image sensor is used to capture the PCB image. With the VHDL code embedded in the FPGA, a PCB image in RGB444 format and a size of 320 × 240 is taken from the sensor. During the image acquisition process, median and gaussian filters are used to remove noise components and improve image quality. Additionally, an LED lighting ring is used to further reduce noise components. User keys on the FPGA allow for filter selection, the selection of the number of filters, and the display of missing components on the VGA monitor. The missing component selection displays any missing components using soldered fields. This process aims to eliminate human error and achieve faultless production without manual inspection, saving time and reducing costs in the production process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023.

关键词： FPGA Gaussian filter HSV color space Median filter PCB fault detection real-time image processing

来源：评论

学校读者我要写书评

暂无评论

Fast FPGA prototyping for real-time image processing with very high-level synthesis

引用

JOURNAL OF real-time image processing 2019年第5期16卷 1795-1812页

作者： Li, Chao Bi, Yanjing Marzani, Franck Yang, Fan Univ Bourgogne Franche Comte CNRS Lab Le2I Arts & MetiersUMR6306 F-21000 Dijon France Univ Bourgogne Franche Comte F-21000 Dijon France

Programming in high abstraction level can facilitate the development of digital signal processing systems. In the recent 20 years, high-level synthesis (HLS) has made significantly progress. This technique greatly benefits the R&D productivity of the Field Programmable Gate Array (FPGA) developments and helps for adding to the maintainability of the products by automating the C-to-RTL (register transfer language) conversion. However, due to the high complexity and computational intensity, image processing algorithms usually necessitate a higher abstraction environment than C-synthesis, and the current HLS tools do not have the ability of this kind. This paper presents a conception of very high-level synthesis method which allows fast prototyping and verifying the FPGA-based image processing designs in the MATLAB environment. We build a heterogeneous development flow by using currently available tool kits for verifying the proposed approach and evaluated it within two real-life applications. Experiment results demonstrate that it can effectively reduce the complexity of the development by automatically synthesizing the algorithm behavior from the user level into the low register transfer level and give play to the advantages of FPGA related to the other devices.

关键词： High-level synthesis FPGA Fast prototyping real-time image processing Computer-aided design

来源：评论

学校读者我要写书评

暂无评论

The role of film and television big data in real-time image detection and processing in the Internet of Things era

引用

JOURNAL OF real-time image processing 2021年第4期18卷 1115-1127页

作者： Tong, Yangfan Sun, Wei Wuhan Univ Sch Art Wuhan 430072 Peoples R China Hunan Univ Technol & Business Sch Literature & Journalism Changsha 410205 Peoples R China

With the rapid development of the Internet, images play an increasingly critical role as an important data source in the Internet of Things (IoT). To meet the low-latency and high-efficiency transmission method of the IoT platform, the current problems in the image processing are analyzed from the perspective of real-time image processing in this study. The image features are extracted with the back propagation neural network (BPNN), and the images are classified with the support vector machines (SVM). A real-time image detection and processing platform (RT-IDPP) is constructed using the Adaboost framework based on the IoT, and the real-time image transmission and processing is realized based on different databases. It is found that the RT-IDPP proposed for the IoT realizes the image detection and tracking. The proposed method can not only run effectively on different cloud platforms for use, but also meet the real-time requirements in the image detection and tracking process, ensuring that the image detection rate is higher than 97%. Thus, the detection effect is better. Compared with the traditional image detection methods, the proposed method has higher detection rate and lower false-negative rate (FNR) and false-positive rate (FPR). The experimental detection effect on the film and television big data (FTBD) database is significantly better than that of other databases. This research can provide a theoretical basis for related researches on real-time image processing in the environment of IoT.

关键词： Internet of Things Film and television big data real-time image processing Deep learning Adaboost framework

来源：评论

学校读者我要写书评

暂无评论

Radar real-time image processing for Machine Perception

Radar Real-time Image Processing for Machine Perception

引用

Conference on real-time image processing and Deep Learning

作者： Saponara, Sergio Univ Pisa Dept Informat Engn Via G Caruso 16 I-56122 Pisa Italy

The paper reviews real-time image processing techniques for machine perception with a specific focus on radar image processing for autonomous vehicles. Both algorithms and real-time computing platforms for range-doppl... 详细信息

ISBN: (纸本)9781510626584

关键词： Radar image processing real-time image processing Doppler signal processing Continuous Waves Radar Waveform design

来源：评论

学校读者我要写书评

暂无评论

Special issue on heterogeneous real-time image processing

引用

JOURNAL OF real-time image processing 2018年第3期14卷 513-515页

作者： Fey, Dietmar Hannig, Frank Friedrich Alexander Univ Erlangen Nurnberg FAU Dept Comp Sci Comp Architecture Martensstr 3 D-91058 Erlangen Germany Friedrich Alexander Univ Erlangen Nurnberg FAU Dept Comp Sci Hardware Software Codesign Cauerstr 11 D-91058 Erlangen Germany

Another trend is to use new 3D integrated circuit technologies that allow for tighter integration of processor cores, memory, and sensors to reduce communication latency and improve bandwidth, leading to lower energy consumption, see, for example, the work by Dudek et al. [...]in the last years, several model-based design methods [4, 12, 17] and approaches based on domain-specific programming languages for programming heterogeneous image systems and corresponding compilers have been proposed [2]—prominent examples include Halide [13], HIPAcc [10, 14], and Darkroom [8]. The next two articles propose systematic analysis, synthesis, and mapping methods for heterogeneous system-on-chip (SoC) architectures. The authors propose an efficient nonlinear filter to suppress high-density fixed-value impulse noise—also known as salt-and-pepper noise—in large-size grayscale images.

关键词： real-time image processing Heterogeneous

来源：评论

学校读者我要写书评

暂无评论

High-level synthesis for FPGAs: code optimization strategies for real-time image processing

引用

JOURNAL OF real-time image processing 2018年第3期14卷 701-712页

作者： Li, Chao Bi, Yanjing Benezeth, Yannick Ginhac, Dominique Yang, Fan Chinese Acad Sci Inst Acoust Stat Key Lab Acoust Beijing 100190 Peoples R China Univ Bourgogne Franche Comte Arts & Metiers CNRS LE2I FRE2005 F-21000 Dijon France Univ Bourgogne Franche Comte Lab CPTC F-21000 Dijon France

High-level synthesis (HLS) is a potential solution to increase the productivity of FPGA-based real-time image processing development. It allows designers to reap the benefits of hardware implementation directly from the algorithm behaviors specified using C-like languages with high abstraction level. In order to close the performance gap between the manual and HLS-based FPGA designs, various code optimization forms are made available in today's HLS tools. This paper proposes a HLS source code and directive manipulation strategy for real-time image processing by taking into account the applying order of different optimization forms. Experiment results demonstrate that our approach can improve more effectively the test implementations comparing to the other optimization strategies.

关键词： Code optimization High-level synthesis FPGA real-time image processing

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：