检索结果-内蒙古大学图书馆

YOLOFig detection model development using deep learning

IET image PROCESSING 2021年第13期15卷 3071-3079页

作者： Lawal, Olarewaju Mubashiru Zhao, Huamin Shanxi Agr Univ Coll Agr Engn Jinzhong 030801 Peoples R China

The detection of fruit, including accuracy and speed is of great significance for robotic harvesting. Nevertheless, attributes such as illumination variation, occlusion, and so on have made fruit detection a challenging task. A robust YOLOFig detection model was proposed to solve detection challenges and to improve detection accuracy and speed. The YOLOFig detection model incorporated Leaky activated ResNet43 backbone with a new 2,3,4,3,2 residual block arrangement, spatial pyramid pooling network (SPPNet), feature pyramid network (FPN), complete (CIoU) loss, and distance DIoU-NMS to improve the fruit detection performance. The obtained average precision (AP) and speed (frames per second or fps) respectively under 2,3,4,3,2 residual block arranged backbone for YOLOv3b is 78.6% and 69.8 fps, YOLOv4b is 87.6% and 57.1 fps, and YOLOFig is 89.3% and 96.8 fps;under 1,2,8,8,4 residual block arranged backbone for YOLOv3 is 77.1% and 56.3 fps, YOLOv4 is 87.1% and 52.5 fps, and YOLOResNet70 is 87.3% and 79 fps;and under 3,4,6,3 residual block arranged backbone for YOLOResNet50 is 85.4% and 77.1 fps. An indication that the new residual block arranged backbone of 2,3,4,3,2 outperformed 1,2,8,8,4 on an average AP of 1.33% and detection speed of 15.2%. Finally, the compared results showed that the YOLOFig detection model performed better than other models at the same level of residual block arrangement. It can better generalize and is highly suitable for real-time harvesting robots.

关键词： Optical, image and video signal processing image and video coding Computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Classified image compression using optimally structured auto-association networks

引用

IET image PROCESSING 2007年第2期1卷 189-196页

作者： Abbas, H. M. Mentor Graphics Corp Cairo 11341 Egypt

Here, an application of a set of auto-association networks with linear output neurons and sigmoidal hidden neurons for classified image compression is carried out. Simulations and statistical analysis of this type of network have shown that, at convergence, the hidden neurons operate mainly in their linear region. The nearly linear behaviour of the hidden neurons is exploited in finding out the minimum number of hidden neurons needed to reconstruct image data within a certain error threshold. Four optimally structured auto-association networks are set up so that each network is trained to encode a certain variance-based class of image blocks. Results have shown excellent performance of the proposed architecture in reproducing high-quality images at a low bit rate.

关键词： sigmoidal hidden neurons optimally structured auto-association networks linear output neurons statistical analysis Computer vision and image processing techniques image classification image and video coding image coding image data reconstruction image blocks classified image compression Other topics in statistics image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Real-time video object segmentation in H.264 compressed domain

引用

IET image PROCESSING 2009年第5期3卷 272-285页

作者： Mak, C. -M. Cham, W. -K. Chinese Univ Hong Kong Shatin Hong Kong Peoples R China

In this study the authors proposed a real-time video object segmentation algorithm that works in the H.264 compressed domain. The algorithm utilises the motion information from the H.264 compressed bit stream to identify background motion model and moving objects. In order to preserve spatial and temporal continuity of objects, Markov random field (MRF) is used to model the foreground field. Quantised transform coefficients of the residual frame are also used to improve segmentation result. Experimental results show that the proposed algorithm can effectively extract moving objects from different kinds of sequences. The computation time of the segmentation process is merely about 16 ms per frame for CIF size frame, allowing the algorithm to be applied in real-time applications.

关键词： residual frame background motion model motion information Computer vision and image processing techniques real-time video object segmentation image and video coding Markov processes image coding moving objects Markov random field spatial continuity temporal continuity H.264 compressed bit stream quantised transform coefficients data compression H.264 compressed domain image segmentation

来源：评论

学校读者我要写书评

暂无评论

Acceleration of fractal image compression using fuzzy clustering and discrete-cosine-transform-based metric

引用

IET image PROCESSING 2012年第7期6卷 1024-1030页

作者： Jaferzadeh, K. Kiani, K. Mozaffari, S. Semnan Univ Elect & Comp Dept Semnan Iran

The encoding step in a fractal image compression is very time consuming, because a large numbers of sequential search through a list of domains are needed to find the best match for a given range block. Adaptive domain clustering is one solution to overcome this computational burden. The use of a new metric with fewer operations for domain-range blocks comparison is fruitful. In this study, range and domain blocks are categorised by fuzzy c-mean-clustering approach and compared with the use of new metric based on discrete cosine transform coefficient. Experimental results show that by clustering image pixels into five clusters, the encoding step was 8.88 times faster than the full-search method (no clustering) at the expense of some reduction in the decoded image's quality. But the proposed method with the same number of clusters speeds up the encoding process by 45 with lower PSNR decay.

关键词： adaptive domain clustering discrete cosine transforms domain-range blocks comparison fractal image compression acceleration sequential search image quality decoding encoding process Computer vision and image processing techniques image and video coding image coding fuzzy set theory Integral transforms pattern clustering discrete-cosine-transform-based metric fuzzy clustering decoding image pixels clustering encoding step Combinatorial mathematics fuzzy c-mean-clustering approach domain blocks fractals

来源：评论

学校读者我要写书评

暂无评论

Performance of an efficient heuristic scheduling algorithm for MPEG-4 traffic in high data rate wireless personal area network

引用

IET COMMUNICATIONS 2011年第8期5卷 1090-1095页

作者： Yang, G. Hu, H. Rong, L. Du, Y. Zhejiang Univ Dept Informat Sci & Elect Engn Hangzhou 310058 Zhejiang Peoples R China Shanghai Res Ctr Wireless Commun Shanghai 200050 Peoples R China Huawei Technol Co Ltd Shanghai 200050 Peoples R China

In this research, the authors study the impact of a controlling parameter on system performances of our previously proposed heuristic channel-aware scheduling algorithm. In addition, parameter optimisation for a combined performance measure is also discussed. The investigation is carried out through numerical simulations via ns-2. When compared with other algorithms, the proposed algorithm uniformly shows the best performance, with the performance gain being more evident for bad channel. The findings are useful for system designers.

关键词： image and video coding heuristic channel-aware scheduling algorithm video coding video signal processing Radio links and equipment Other computer networks MPEG-4 traffic wireless personal area network video communication Computer communications personal area networks ns-2 simulations scheduling

来源：评论

学校读者我要写书评

暂无评论

Cross-point regions on multiple bit planes for lossless images compression

引用

IET image PROCESSING 2011年第5期5卷 466-471页

作者： Dang, T. T. Nguyen, S. K. Vu, T. D. Higuchi, S. Hochiminh City Univ Technol Fac Elect & Elect Engn Ho Chi Minh City Vietnam Osaka Sangyo Univ Fac Engn Osaka Japan

This study presents cross-point regions for lossless image compression on multiple bit planes (CRICM), an algorithm for losslessly encoding and decoding images, especially medical images, by optimising on the probability of bits on different bit planes of cross points that are neighbour points of grey levels 2(n). Based on Gray coding, Gray codes of cross points are determined on an adjacent data set because images characteristically contain data that do not change much in a specific area, then this effect is generalised for real data without losing generality for their statistical properties. This is especially true for medical images that have many regions with the same grey levels. The Gray code transformation makes the bit states of cross points change from the original data bits, so firstly the probabilities of data bits on specific bit planes in cross-point regions and then the entropies of the messages are changed. These probabilities are estimated and compared with the probabilities of the original data bits. This change of probability has important effects on the encoding and decoding processes in lossless medical image compression.

关键词： probability encoding Codes multiple bit planes entropies lossless medical image compression grey levels image coding image and video coding Other topics in statistics Gray codes cross-point regions data compression decoding Gray coding

来源：评论

学校读者我要写书评

暂无评论

A novel decoder based on Bayesian rules for task-driven object segmentation

引用

IET image PROCESSING 2023年第3期17卷 832-848页

作者： Cai, Yuxiang Yu, Yuanlong Jiang, Weijie Chen, Rong Zheng, Weitao Wu, Xi Su, Renjie Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China State Grid Fujian Infotmat & Telecommun Co Technol Dept Fuzhou Peoples R China Fuzhou Univ Coll Comp & Data Sci Fuzhou 350108 Peoples R China

As a challenging problem in computer vision, salient object segmentation has attracted increasing attention in recent years. Though a lot of works based on encoder-decoder have been made, these methods can only recognize and segment one class of objects, but cannot segment the other classes of objects in the same image. To address this issue, this paper proposes a novel decoder based on Bayesian rules to perform task-driven object segmentation, in which a control signal is added to the decoder to determine which class of objects need to be segmented. What's more, a Bayesian rule is established in the decoder, in which the control signal is set as the prior, and the latent features learned in encoder is transferred to the corresponding layer of decoder as observation, thus the posterior probability of each object with respect to the specific-class can be calculated, and the objects belonging to this class can be segmented. This proposed method is evaluated for task-driven salient object segmentation on several benchmark datasets, including MS COCO, DUT-OMRON, ECSSD etc. Experimental results show that the approach tends to segment accurate, detailed, and complete objects, and improves the performance compared with the previous state-of-the-art.

关键词： image coding image segmentation feature extraction encoder-decoder Machine learning (artificial intelligence) object detection image and video coding computer vision control signal Other topics in statistics task-driven salient object segmentation complete objects Bayesian rule image recognition learning (artificial intelligence) Bayes methods Computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Dynamic convolutional capsule network for In-loop filtering in HEVC video codec

引用

IET image PROCESSING 2023年第2期17卷 439-449页

作者： Su, LiChao Cao, Mengqing Yu, Yue Chen, Jian Yang, XiuZhi Wu, Dapeng Fuzhou Univ Coll Software Coll Comp & Data Sci Fuzhou Fujian Peoples R China Fuzhou Univ Coll Phys & Informat Engn Qi Shan Campus2 Xue Yuan Rd Fuzhou Fujian Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

Recently, several in-loop filtering algorithms based on convolutional neural network (CNN) have been proposed to improve the efficiency of HEVC (High Efficiency video coding). Conventional CNN-based filters only apply a single model to the whole image, which cannot adapt well to all local features from the image. To solve this problem, an in-loop filtering algorithm based on a dynamic convolutional capsule network (DCC-net) is proposed, which embeds localized dynamic routing and dynamic segmentation algorithms into capsule network, and integrate them into the HEVC hybrid video coding framework as a new in-loop filter. The proposed method brings average 7.9% and 5.9% BD-BR reductions under all intra (AI) and random access (RA) configurations, respectively, as well as, 0.4 dB and 0.2 dB BD-PSNR gains, respectively. In addition, the proposed algorithm has an outstanding performance in terms of time efficiency.

关键词： Codecs, coders and decoders HEVC hybrid video coding framework convolutional neural network image and video coding dynamic convolutional capsule network CNN-based filters Neural nets video coding HEVC video codec video codecs dynamic routing in-loop filtering algorithm video signal processing dynamic segmentation algorithms high efficiency video coding convolutional neural nets

来源：评论

学校读者我要写书评

暂无评论

Emergency TeleOrthoPaedics m-health system for wireless communication links

引用

IET COMMUNICATIONS 2009年第8期3卷 1284-1296页

作者： Hadjinicolaou, M. G. Nilavalan, R. Itagaki, T. Voskarides, S. Ch. Pattichis, C. S. Schizas, A. N. Brunel Univ Sch Engn & Design Uxbridge UB8 3PH Middx England Cyprus Univ Technol Elect & Informat Technol Dept Limassol Cyprus Univ Cyprus Dept Comp Sci Nicosia Cyprus Paphos Gen Hosp Orthopaed Clin Paphos Cyprus

For the first time, a complete wireless and mobile emergency TeleOrthoPaedics system with field trials and expert opinion is presented. The system enables doctors in a remote area to obtain a second opinion from doctors in the hospital using secured wireless telecommunication networks. Doctors can exchange securely medical images and video as well as other important data, and thus perform remote consultations, fast and accurately using a user friendly interface, via a reliable and secure telemedicine system of low cost. The quality of the transmitted compressed (JPEG2000) images was measured using different metrics and doctors opinions. The results have shown that all metrics were within acceptable limits. The performance of the system was evaluated successfully under different wireless communication links based on real data.

关键词： mobile radio image coding medical image processing Biomedical measurement and imaging data compression image and video coding medical images wireless communication links Mobile radio systems telemedicine system Biomedical communication radio links image compression emergency teleorthopaedics m-health system mobile emergency system telemedicine medical video

来源：评论

学校读者我要写书评

暂无评论

Analysis of the error susceptibility of a field programmable gate array-based image compressor through random event injection simulation

引用

IET COMPUTERS AND DIGITAL TECHNIQUES 2012年第3期6卷 160-165页

作者： Lopes Filho, A. d'Amore, R. Natl Inst Space Res INPE Div Eletron Aeroespacial Sao Jose Dos Campos SP Brazil ITA Dept Eletron Aplicada Sao Jose Dos Campos SP Brazil

The successful use of commercial-off-the-shelf (COTS) devices on board space applications requires the use of fault mitigation methods because of the effects of space radiation in microelectronics devices. This study describes a scheme for the random injection of single event transients/upsets to evaluate the viability of employing COTS field programmable gate array for an onboard, low-complexity, remote-sensing image data compressor. The fault injection features are added to the application to be tested by modifying its hardware description language source code. Then the tests are executed by simulation, with or without the inclusion of fault mitigation methods, so that comparative evaluations can be quickly obtained. The evaluation results (robustness enhancement against area) of different fault mitigation methods are presented, with good estimates of the behaviour of the hardware implementation of the application in a space radiation environment.

关键词： COTS device image compressor random event injection simulation single event transient Logic and switching circuits image and video coding hardware description languages commercial-off-the-shelf single event upset error susceptibility Logic circuits field programmable gate arrays Logic design methods fault injection features Computer vision and image processing techniques field programmable gate array image coding radiation effects Radiation effects (semiconductor technology) board space application space radiation Digital circuit design, modelling and testing microelectronics device hardware description language source code fault mitigation method

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：