检索结果-内蒙古大学图书馆

Urban road user detection and classification using 3D wire frame models

IET COMPUTER VISION 2010年第2期4卷 105-116页

作者： Buch, N. Orwell, J. Velastin, S. A. Kingston Univ London Digital Imaging Res Ctr Kingston upon Thames KT1 2EE Surrey England

This study presents a detection and classification system for vehicles and pedestrians in urban traffic scenes. This aims to guide surveillance operators and reduce human resources for observing hundreds of cameras in urban traffic surveillance. The authors perform per frame vehicle detection and classification using 3D models on calibrated cameras. Motion silhouettes (from background estimation) are extracted and compared to a projected model silhouette to identify the ground plane position and class of vehicles and pedestrians. The system is evaluated with the reference i-LIDS datasets from the UK Home Office. Performance for varying numbers of classes for three different weather conditions and for different video input filters is evaluated. The full system including detection and classification achieves a recall of 87% at a precision of 85.5% outperforming similar systems in the literature. The i-LIDS dataset is available to other researchers to compare with our results. The authors conclude with an outlook to use local features for improving the classification and detection performance.

关键词： vehicles road user classification video signal processing UK Home Office Traffic engineering computing urban traffic scenes image and video coding motion estimation motion silhouettes road vehicles i-LIDS datasets pedestrians 3D wire frame models Computer vision and image processing techniques surveillance operators road traffic urban road user detection calibrated cameras video surveillance video signal processing

来源：评论

学校读者我要写书评

暂无评论

An efficient Industrial Internet of Things video data processing system for protocol identification and quality enhancement

引用

IET CYBER-PHYSICAL SYSTEMS: THEORY & APPLICATIONS 2023年第2期8卷 63-75页

作者： Chen, Lvcheng Liu, Liangwei Zhang, Li Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou Peoples R China Hubei Univ Technol Sch Sci Wuhan Peoples R China

video has become an essential medium to monitoring, identification and knowledge sharing. For industrial applications, especially Industrial Internet of Things (IIoT), videos encoded with specific protocols are transferred to smart gateways. In a typical IIoT scenario, the protocol of the video is firstly recognised, which prepares for subsequent video tasks. Due to the constrained resources in such scenarios, the video quality can be deteriorated during encoding and compression processes, which is challenging for IIoT. Recently, there have been extensive works focussing on the protocol identification (PI) and video quality enhancement (VQE) tasks on IIoT edge devices using deep neural networks (DNNs). Since DNNs often require high computational resources, complex networks can hardly be deployed on edge devices. An IIoT system which can efficiently identify the stream protocol and enhance the video quality is proposed in this study. The light-weighted network designs and inference optimisation techniques have been proposed for PI and VQE to realise efficient deployments. Our proposed system employed on an IIoT edge device can achieve an accuracy of higher than 97.52% with fast inference speed for PI. For the VQE task, our system has demonstrated superior performance (15.230 FPS, 0.773 FPS/W) in comparison with the state-of-the-art methods.

关键词： IIoT edge device IIoT system compression processes Computer networks and techniques Multimedia communications image and video coding specific protocols efficient Industrial Internet Neural nets video coding protocols Protocols Industrial Internet of Things video data processing system video quality protocol identification neural nets encoding typical IIoT scenario subsequent video tasks video signal processing Internet of Things knowledge sharing industrial applications stream protocol Computer communications video streaming quality enhancement

来源：评论

学校读者我要写书评

暂无评论

Low memory visual saliency architecture for data reduction in wireless sensor networks

引用

IET WIRELESS SENSOR SYSTEMS 2012年第2期2卷 115-127页

作者： Ngau, C. W. H. Ang, L. -M. Seng, K. P. Univ Nottingham Dept Elect & Elect Engn Selangor 43500 Malaysia Edith Cowan Univ Sch Engn Joondalup WA 6027 Australia Sunway Univ Fac Sci & Technol Selangor 46150 Malaysia

Traditionally, to reduce communication overheads because of bandwidth limitations in wireless sensor networks (WSNs), image compression techniques are used on high-resolution captures. Higher data reduction rates can be achieved by first removing redundant parts of the capture prior to the application of image compression. To locate these redundant parts, biologically plausible visual saliency processing is used to isolate parts that seemed important based on visual perception. Although visual saliency proves to be an effective method in providing a distinctive difference between important and unimportant regions, computational complexity and memory requirements often impair implementation. This study presents an implementation of a low-memory visual saliency architecture with reduced computation complexity for data reduction in WSNs through salient patch transmission. A custom softcore microprocessor-based hardware implementation on a field programmable gate array is then used to verify the architecture. Real-time processing demonstrated that data reductions of more than 50% are achievable for simple to medium scenes without the application of image compression techniques.

关键词： Computer vision and image processing techniques visual perception data compression image and video coding field programmable gate array Logic and switching circuits biologically plausible visual saliency processing salient patch transmission Logic circuits image coding Wireless sensor networks Microprocessors and microcomputers data reduction field programmable gate arrays microprocessor chips Microprocessor chips custom softcore microprocessor image compression wireless sensor networks Computational complexity redundant parts computational complexity communication overheads memory visual saliency architecture

来源：评论

学校读者我要写书评

暂无评论

Rate control strategy for embedded wavelet video coders

引用

ELECTRONICS LETTERS 1999年第21期35卷 1815-1817页

作者： Caetano, R da Silva, EAB Univ Fed Rio de Janeiro BR-21945970 Rio De Janeiro Brazil

An investigation into the use of rate-control strategies for embedded wavelet video encoders is presented. It is shown that the best model for the R-D of these encoders is piecewise linear. Also, an effective iterative procedure is proposed for dealing with the problem of frame dependency, which yields improved rate x distortion results.

关键词： wavelet transforms embedded wavelet video coders image and video coding Integral transforms in numerical analysis iterative methods rate control strategy iterative procedure video signal processing piecewise linear model Interpolation and function approximation (numerical analysis) video coding rate×distortion curve piecewise linear techniques frame dependency

来源：评论

学校读者我要写书评

暂无评论

Achieving better balance between compression and quality for JPEG-LS

引用

ELECTRONICS LETTERS 1999年第23期35卷 2019-2020页

作者： Grecos, C Jiang, J Univ Glamorgan Sch Comp Pontypridd CF37 1DL M Glam Wales

Further application of JPEG-LS for near lossless image compression reveals a balance problem when both compression efficiency and image quality are required to be high. A low-cost solution;backed up by extensive experiments, is presented by introducing different levels of information loss and by exploiting the human visual perception of image quality.

关键词： still image compression human visual perception runlength codes nonlinear prediction image quality code standards compression efficiency data compression JPEG-LS standard Codes entropy codes balance problem image coding prediction theory lossless image compression telecommunication standards image and video coding visual perception information loss levels low-cost solution

来源：评论

学校读者我要写书评

暂无评论

Texture driven quadrilateral matching motion estimation for video coding

引用

ELECTRONICS LETTERS 2000年第1期36卷 27-29页

作者： Lopes, F Ghanbari, M Univ Essex Dept Elect Syst Engn Colchester CO4 3SQ Essex England

It is shown that accurate motion and speed information extracted from the texture of the difference frame can be efficiently used to significantly improve the performance of quadrilateral matching motion estimation bu... 详细信息

关键词： speed information extraction motion estimation image and video coding texture driven quadrilateral matching motion estimation accurate motion small complexity fraction texture full search procedure quadrilateral matching motion estimation video signal processing video coding Computer vision and image processing techniques image recognition

来源：评论

学校读者我要写书评

暂无评论

Gradient-based edge detection for motion estimation in H.264/AVC

引用

IET image PROCESSING 2011年第4期5卷 323-327页

作者： Paul, A. Wu, J. Yang, J. -F. Jeong, J. Hanyang Univ Dept Elect Engn Seoul 133791 South Korea Natl Cheng Kung Univ Dept Elect Engn Tainan 70101 Taiwan

This study introduces a block-based motion estimation algorithm based on projection with adaptive window-size selection. Using one-dimensional (1D) projection, the original 2D block-matching problem is translated to a simpler 1D matching problem which eliminates the majority of potential pixel participation. The authors propose an efficient fast-motion estimation method using an intensity gradient algorithm to reduce the encoding time. The proposed algorithm estimates the texture direction of the block, and then a horizontal or vertical projection is employed for the sum of absolute difference calculation. Experimental results show that the proposed algorithm achieves a greater than 60% time reduction with negligible peak signal to noise ratio (PSNR) loss and BR increments.

关键词： gradient-based edge detection potential pixel participation image recognition Computer vision and image processing techniques image and video coding H.264-AVC adaptive window-size selection motion estimation block-based motion estimation algorithm 2D block-matching problem one-dimensional projection image matching 1D matching problem video coding Interpolation and function approximation (numerical analysis) video signal processing edge detection intensity gradient algorithm gradient methods

来源：评论

学校读者我要写书评

暂无评论

Vertex adjustment method using geometric constraint for polygon-based shape coding

引用

ELECTRONICS LETTERS 2001年第12期37卷 754-755页

作者： Yun, BJ Lee, SW Kim, SD Korea Adv Inst Sci & Technol Dept Elect Engn & Comp Sci Div Elect Engn Yusong Gu Taejon 305701 South Korea Hanbat Natl Univ Div Informat Commun & Comp Engn Yusong Gu Taejon 305719 South Korea

A new vertex selection scheme for polygon-based contour coding is proposed. The proposed method consists of 'two-step procedure'. Initial vertices are selected by using the conventional iterated refinement method (IRM) or progressive vertex selection (PVS) method. A vertex adjustment process then follows where the initial vertices are updated to produce an optimal polygon in the sense of 'error area'. In this step, the geometrical information of the partial contour and its polygon segment is used to reduce the search region for the admissible vertex position. Experimental results are presented to compare the approximation performances and the required computational burdens of the proposed and conventional methods.

关键词： image and video coding polygon shape contour coding image coding geometric constraint iterated refinement method vertex adjustment error area progressive vertex selection

来源：评论

学校读者我要写书评

暂无评论

Optical image encryption using interferometry-based phase masks

引用

ELECTRONICS LETTERS 2000年第10期36卷 874-875页

作者： Kim, JY Park, SJ Kim, CS Bae, JG Kim, SJ Kyungpook Natl Univ Dept Elect Engn Taegu 702701 South Korea Kyongju Univ Sch Comp & Informat Engn Kyungpook 780712 South Korea Kumi Coll Dept Elect Informat Kyungpook 730711 South Korea

A new and simple image encryption scheme and optical decoding technique are presented based on the principle of interference. An original image is encoded into two phase-valued images. The interference image between the two images produces a binary image, which has a two-level intensity value. The performance of the proposed technique is evaluated using computer simulations and optical experiments.

关键词： optical images light interferometry image and video coding Cryptography cryptography phase mask image coding phase shifting masks optical image encryption interferometry optical decoding

来源：评论

学校读者我要写书评

暂无评论

Improved lossless compression of general data

引用

ELECTRONICS LETTERS 2000年第25期36卷 2070-2072页

作者： Keating, S Pelly, J Sony Broadcast & Profess Europe Basingstoke RG22 4SB Hants England

New algorithms for lossless compression of general data are presented. They are based on adaptive lossless data compression (ALDC) but offer improved compression, typically 24% better for image data. The algorithms are simple to implement and are capable of high data throughput, whilst maintaining compatibility with legacy ALDC bit streams.

关键词： adaptive lossless data compression image and video coding data compression image coding high data throughput lossless compression general data Digital signal processing Signal processing and detection Signal processing theory adaptive signal processing image data Computer vision and image processing techniques

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：