检索结果-内蒙古大学图书馆

Parallelization Strategy of Non-Local Means Filtering Algorithm for real-time Denoising of Forward-Looking Multi-Beam Sonar images

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR video TECHNOLOGY 2024年第12期34卷 13226-13243页

作者： Ye, Tao Deng, Xiangpeng Cong, Xiao Zhou, Hongkun Yan, Xiangming China Univ Min & Technol Beijing Sch Mech & Elect Engn Minist Emergency Management Beijing 100083 Peoples R China China Univ Min & Technol Beijing Key Lab Intelligent Min & Robot Minist Emergency Management Beijing 100083 Peoples R China China Ship Sci Res Ctr Wuxi 214028 Peoples R China

Obtaining clear sonar images is crucial for ocean exploration applications, such as marine resource detection and underwater target searches. Traditional filtering methods cannot effectively eliminate the noise generated by the complex underwater environment in sonar images and can potentially result in problems such as image blurring. Existing methods that effectively filter sonar image noise often lack real-time performance, making them impractical for ocean exploration. To address these limitations, this study proposes a real-time denoising technique for forward-looking multi-beam sonar images based on a non-local means filtering algorithm. The integral image is used to calculate the mean square error (MSE), which improves algorithm efficiency and ensures that the runtime remains unaffected by the neighbourhood window size. To further improve real-time performance, the algorithm is migrated to a graphics processing unit (GPU) and a block-wise computation method is proposed to calculate the integral image. Simultaneously, to enhance GPU thread utilisation, the three-dimensional thread structure from the compute unified device architecture (CUDA) programming model is utilised and additional threads are allocated to enhance computation. The captured images are filtered using an M1200d sonar device manufactured by Oculus. Extensive experiments demonstrate that the proposed method achieves excellent performance regarding both denoising accuracy and efficiency. Specifically, the proposed method achieves a peak signal-to-noise ratio higher than 25 dB and a structural similarity index of more than 0.85 at 50 frames per second, thus demonstrating its significant potential for real-time sonar image denoising.

关键词： Sonar Filtering algorithms real-time systems Graphics processing units Noise reduction Filtering Mathematical models Sonar sensors non-local means filtering real-time processing GPU parallelisation

来源：评论

学校读者我要写书评

暂无评论

real-time institution video data analysis using fog computing and adaptive background subtraction

引用

JOURNAL OF real-time image processing 2023年第5期20卷 96页

作者： Amshavalli, R. S. Kalaivani, J. SRM Inst Sci & Technol Dept Comp Technol Chennai 603203 India

The increasing demand for video surveillance systems has led to a surge in research towards developing smart video surveillance systems that can combat the growing levels of insecurity. However, the massive amount of video data generated by these systems has overwhelmed the storage and processing capabilities of analytic applications. This paper proposes a fog computing-based smart video surveillance system that provides less latency, network bandwidth, and response time by localizing data to the edges of the network. The proposed system incorporates two key preprocessing steps, namely adaptive key frame extraction and adaptive contour-based background subtraction, to increase the quality of detecting abnormal motions from surveillance video streams. The adaptive key frame extraction mechanism extracts key frames from the available frames in the video sequence using a sliding window technique. The high-level semantic information of video frames is learned using the visual geometry group-16 Transfer Learning (VGG-16 TL) technique to better represent the video content. The adaptive contour-based background subtraction mechanism separates target foreground pixels from the background scenes, paving the way for easy detection of abnormal motions in the video frames. The proposed system leverages fog computing to process and store data, reducing latency and improving overall performance. The fog layer performs adaptive background subtraction, contour detection, and object analysis, ensuring timely processing of video frames and minimizing the need for transmitting large amounts of data to the cloud. The proposed system is evaluated using a real-time video dataset in terms of accuracy, compression ratio, precision, recall, processing time, latency, and network bandwidth, demonstrating the efficacy of the proposed system for abnormal motion detection and data transmission. Overall, the proposed fog computing-based smart video surveillance system provides an effective soluti

关键词： video surveillance system Keyframe extraction Background subtraction Fog computing real-time dataset

来源：评论

学校读者我要写书评

暂无评论

EdgeRelight360: Text-Conditioned 360-Degree HDR image Generation for real-time On-Device video Portrait Relighting

EdgeRelight360: Text-Conditioned 360-Degree HDR Image Genera...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lin, Min-Hui Reddy, Mahesh Berger, Guillaume Sarkis, Michel Porikli, Fatih Bi, Ning Qualcomm AI Res San Diego CA 92121 USA

ISBN: (纸本)9798350365474

In this paper, we present EdgeRelight360, an approach for real-time video portrait relighting on mobile devices, utilizing text-conditioned generation of 360-degree high dynamic range image (HDRI) maps. Our method proposes a diffusion-based text-to-360-degree image generation in the HDR domain, taking advantage of the HDR10 standard. This technique facilitates the generation of high-quality, realistic lighting conditions from textual descriptions, offering flexibility and control in portrait video relighting task. Unlike the previous relighting frameworks, our proposed system performs video relighting directly on-device, enabling real-time inference with real 360-degree HDRI maps. This on-device processing ensures both privacy and guarantees low runtime, providing an immediate response to changes in lighting conditions or user inputs. Our approach paves the way for new possibilities in real-time video applications, including video conferencing, gaming, and augmented reality, by allowing dynamic, text-based control of lighting conditions.

关键词： video conferencing

来源：评论

学校读者我要写书评

暂无评论

DSP-based parallel optimization for real-time video stitching

引用

JOURNAL OF real-time image processing 2023年第2期20卷 28页

作者： Huang, Xiaofeng Tang, Ran Zhou, Yang Yin, Haibing Yan, Chenggang Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China Peking Univ Adv Inst Informat Technol Hangzhou 311215 Peoples R China Hangzhou Dianzi Univ Sch Automation Hangzhou 310018 Peoples R China

video stitching is a technique that stitches multiple overlapped videos acquired from different cameras, which is widely applied in many applications, including video surveillance, autonomous driving, and virtual reality. Feature-based stitching methods are popular in this area because of their invariance property and efficiency. However, the video stitching pipeline is relatively complicated and the amount of data calculation is large, which impedes its real-time applications. In this paper, we propose a real-time video stitching framework based on vision Digital Signal processing (DSP). real-time processing is achieved by the algorithm-level and system-level optimizations. In the algorithm of ORB feature extraction, methods, including look-up table, linear approximation, and single instruction multiple data (SIMD), are adopted to optimize its computation on DSP. In the algorithm of feature matching, the Hamming distance calculation is eliminated for some feature point pairs when their coordinates and angles are not satisfied with certain conditions. Reverse feature matching is proposed to improve registration accuracy. In system-level optimization, the directed acyclic graph (DAG)-based scheduling is proposed to improve the calculation efficiency on dual DSPs, and a ping-pong buffer is utilized to speed up the data transmission between DSP and external memory. Experimental results show that the proposed method can achieve a ten times speedup than that of the CPU, and it can achieve 1536x1024@37fps real-time processing on vision DSP.

关键词： video stitching ORB Vision DSP SIMD Pipeline

来源：评论

学校读者我要写书评

暂无评论

Integrated image processing Pipeline for Improved Vehicle Identification and Counting in video Streams 3

Integrated Image Processing Pipeline for Improved Vehicle Id...

引用

International conference on Advances in Computing, Communication and Applied Informatics (ACCAI)

作者： Shamimullah, S. Hanirex, D. Kerana Bharath Inst Higher Educ & Res Dept Comp Sci Chennai Tamil Nadu India

ISBN: (纸本)9798350389432;9798350389449;9798350389456

This study introduces a proposed integrated image processing pipeline to enhance vehicle detection and counting precision in real-time video streams. This method can accurately pinpoint areas in the videos where cars are present by using Regions of Interest (ROIs) and segmenting the frames. To ensure efficient processing of images, it is essential to optimize their quality and dimensions. Utilizing Convolutional Neural Networks (CNNs) for feature extraction enables us to impart discriminative features through hierarchical layers. Afterward, machine learning models enhance the extracted features before applying them to classify automobiles. There are two post-processing tasks: implementing vehicle counting methods that consider discovered ROIs and optimizing image size further. The primary aim is to achieve precise and effective vehicle counting and identification with this method, which is essential for tasks like traffic surveillance. Based on the experimental findings, the system effectively balances processing efficiency and accuracy in vehicle recognition and classification. With this integrated infrastructure, real-time enhancements could be made to processing traffic surveillance video streams.

关键词： image processing vehicle identification counting video streams Regions of Interest preprocessing Convolutional Neural Networks feature extraction classification traffic surveillance

来源：评论

学校读者我要写书评

暂无评论

Optimal video processing and soft computing algorithms for human hand gesture recognition from real-time video

引用

MULtimeDIA TOOLS AND APPLICATIONS 2023年第17期83卷 50425-50447页

作者： Uke, Shailaja N. Zade, Amol GHRaisoni Univ Amravati India

An essential component of building an automated hand gesture detection system is the ability to extract hand movements using a single video camera. Results for hand extraction using color cues have been encouraging utilizing local spatiotemporal approaches. When the video is recorded in real life, the color intensities are not clear. The research of hand gesture machine translation for real-world video processing has halted. video frames make it hard to recognize the hand and extract the required information for accurate identification. A new framework for real-time hand gesture detection from films is proposed using optimum video and soft computing algorithms. In the proposed system, real-time video is captured for human Hand Gesture Recognition (HGR). The framework consists of real-time video acquisition, video normalization, Hand Frames Feature Extraction (HFFE), and classification. In the video normalization phase, we first discard the redundant frames to reduce the time and space complexity using dynamic thresholding. The remaining video frames are normalized by applying the image pre-processing operations to enhance the frame's quality. The HFEF is the vital and novel phase of the proposed model as it consists of enhanced spatiotemporal-based feature extraction where we have designed a cuboid-based detector and Speeded-Up Robust Features (SURF). The HFEF phase extracts the robust hand features from the sequence of pre-processed video frames for efficient classification. Finally, the recognition of hand gestures is performed by applying different soft computing algorithms. The simulation results using the real-time research datasets prove the improvement using the proposed model over the existing solutions.

关键词： Frames Features extraction Hand gesture recognition Spatiotemporal Soft computing video processing

来源：评论

学校读者我要写书评

暂无评论

An SoC System for real-time Edge Detection

引用

JOURNAL OF ELECTRONIC MATERIALS 2024年第10期53卷 6395-6402页

作者： Yamini, Vanama Hussain, Syed Ali Sekhar, G. Chandra Kumar, P. Avinash Lehitha, P. Teja, B. Sree Venkata Samanta, Swagata Sanki, Pradyut Kumar SRM Univ AP Dept Elect & Commun Engn Amaravati 522502 India

This research work focuses on the design and implementation of a highly advanced field-programmable gate array (FPGA)-based system-on-chip (SoC) solution for real-time edge detection. By utilizing a Zynq processor and leveraging the powerful Vivado software, the aim is to overcome the significant computational challenges associated with achieving real-time edge detection. Edge detection in real-time scenarios presents several obstacles, including the possibility of missing edges due to noise and the substantial processing requirements of any edge detection technique. To address these challenges, the proposed SoC system synergistically combines the computational capabilities of an FPGA board and a Zynq processor, harnessing hardware acceleration to achieve high-performance edge detection. The OV7670 camera module serves as the primary input medium, capturing image frames for subsequent processing. These captured frames undergo initial processing before being seamlessly transferred to the FPGA fabric through customized intellectual property (IP) blocks. These IP blocks efficiently handle crucial tasks such as frame capturing, conversion to AXI Stream interface signals, and integration with the video direct memory access (VDMA) IP. The VDMA IP plays a pivotal role by facilitating high-speed data movement between the FPGA fabric and the Zynq processor IP, thereby enabling streamlined and efficient data transfer and processing. At the heart of this project lies the real-time edge detection algorithm, which is skillfully implemented on the Zynq processor. The resulting edge-detected frames are then visually presented and displayed on an output device utilizing the AXI4-Stream to video Out IP. To ensure optimal utilization of available hardware resources, the comprehensive Vivado software suite provides a wide array of tools for designing, implementing, and programming the FPGA fabric. By leveraging FPGA-based systems, this project effectively addresses the critical need f

关键词： FPGA SoC Zynq processor Computer vision image processing Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

RT3DHVC: A real-time Human Holographic video Conferencing System With a Consumer RGB-D Camera Array

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR video TECHNOLOGY 2025年第5期35卷 4226-4241页

作者： Jiang, Yuqi Li, Jing Dai, Yanran Qin, Haidong Zhou, Xiaoshi Zhang, Yong Liu, Hongwei Yan, Kefan Yang, Tao Xidian Univ Sch Telecommun Engn Xian 710071 Peoples R China Northwestern Polytech Univ Sch Comp Sci Natl Engn Lab Integrated Aerosp Ground Ocean Big D SAIIP Xian 710129 Peoples R China

In this paper, we present an end-to-end holographic video conferencing system that enables real-time high-quality free-viewpoint rendering of participants in different spatial regions, placing them in a unified virtual space for a more immersive display. Our system offers a cost-effective, complete holographic conferencing process, including multiview 3D data capture, RGB-D stream compression and transmission, high-quality rendering, and immersive display. It employs a sparse set of commodity RGB-D cameras that capture 3D geometric and textural information. We then remotely transmit color and depth maps via standard video encoding and transmission protocols. We propose a GPU-parallelized rendering pipeline based on an image-based virtual view synthesis algorithm to achieve real-time and high-quality scene rendering. This algorithm uses an on-the-fly Truncated Signed Distance Function (TSDF) approach, which marches along virtual rays within a computed precise search interval to determine surface intersections. We then design a multiweight projective texture mapping method to fuse color information from multiple views. Furthermore, we introduce a method that uses a depth confidence map to weight the rendering results from different views, which mitigates the impact of sensor noise and inaccurate measurements on the rendering results. Finally, our system places conference participants from different spaces into a virtual conference environment with a global coordinate system through coordinate transformation, which simulates a real conference scene in physical space, providing an immersive remote conferencing experience. Experimental evaluations confirm our system's real-time, low-latency, high-quality, and immersive capabilities.

关键词： Rendering (computer graphics) real-time systems Three-dimensional displays Cameras Streaming media image color analysis videoconferences Point cloud compression image reconstruction Hardware 3D video conferencing holographic telepresence multiview RGB-D video view-dependent rendering

来源：评论

学校读者我要写书评

暂无评论

Zooming Into video Conferencing Privacy

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第1期11卷 933-944页

作者： Kagan, Dima Alpert, Galit Fuhrmann Fire, Michael Ben Gurion Univ Negev Dept Software & Informat Syst Engn Beer Sheva Israel

The unprecedented growth in video conferencing usage is accompanied by multiple security and privacy threats. Importantly, protecting users' privacy is not always in their own hands. Posting meeting images affects all participants, leading to an easy collection of personal data including age, gender and linkage with participation in other meetings. Here, we explored privacy issues that may be at risk by attending virtual meetings. We extracted private information from collage images of meeting participants that are publicly posted online. We used image processing, text recognition tools, as well as social network analysis to explore our curated dataset of over 15 700 collage images, and over 142 000 face images of meeting participants. We demonstrate that video conference users are facing prevalent security and privacy threats. Our results indicate that it is relatively easy to collect thousands of publicly available images of video conference meetings and extract personal information about the participants, including their face images, age, gender, usernames, and even full names. This type of data can vastly and easily jeopardize people's security and privacy both in the online and real-world, affecting not only adults but also more vulnerable segments of society, such as children and older adults. Finally, we show that cross-referencing facial image data with social network data may put participants at additional privacy risks they may not be aware of and that it is possible to identify users that appear in several video conference meetings, thus providing a potential to maliciously aggregate different sources of information about a target individual.

关键词： Data science image processing security and privacy video conference video conference applications

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of real-time Object Detection in Edge Device Through Concurrent Multi-Frame processing

引用

IEEE ACCESS 2025年 13卷 1522-1533页

作者： Kim, Seunghwan Kim, Changjong Kim, Sunggon Seoul Natl Univ Sci & Technol Dept Comp Sci & Engn Seoul 01811 South Korea

As the performance and accuracy of machine learning and AI algorithms improve, the demand for adopting computer vision techniques to solve various problems, such as autonomous driving and AI robots, increases. To meet such demand, IoT and edge devices, which are small enough to be adopted in various environments while having sufficient computing capabilities, are being widely adopted. However, as devices are utilized in IoT and edge environments, which have harsh restrictions compared to traditional server environments, they are often limited by low computational and memory resources, in addition to the limited electrical power supply. This necessitates a unique approach for small IoT devices that are required to run complex tasks. In this paper, we propose a concurrent multi-frame processing scheme for real-time object detection algorithms. To do this, we first divide the video into individual frames and group the frames according to the number of cores in the device. Then, we allocate a group of frames per core to perform the object detection, resulting in parallel detection of multiple frames. We implement our scheme in YOLO (You Only Look Once), one of the most popular real-time object detection algorithms, on a state-of-the-art, resource-constrained IoT edge device, Nvidia Jetson Orin Nano, using real-world video and image datasets, including MS-COCO, imageNet, PascalVOC, DOTA, animal videos, and car-traffic videos. Our evaluation results show that our proposed scheme can improve the diverse aspect of edge performance and improve the runtime, memory consumption, and power usage by up to 445%, 69%, and 73%, respectively. Additionally, it demonstrates improvements of $2.10\times $ over state-of-the-art model optimization.

关键词： YOLO image edge detection Performance evaluation Computational modeling Streaming media real-time systems Load modeling Runtime Parallel processing Memory management Edge devices machine learning object detection performance optimization

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：