检索结果-内蒙古大学图书馆

Hierarchical guided network for low-light image enhancement

IET image processing 2021年第13期15卷 3254-3266页

作者： Feng, Xiaomei Li, Jinjiang Fan, Hui Dalian Univ Technol Sch Software Engn Dalian Peoples R China Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai Peoples R China Inst ZhongKe Network Technol Yantai Peoples R China

Due to insufficient illumination in low-light conditions, the brightness and contrast of the captured images are low, which affect the processing of other computer vision tasks. Low-light enhancement is a challenging task that requires simultaneous processing of colour, brightness, contrast, artefacts and noise. To solve this problem, the authors apply the deep residual network to the low-light enhancement task, and propose a hierarchical guided low-light enhancement network. The key of this method is recombined hierarchical guided features through the feature aggregation module to realize low-light enhancement. The network is based on the U-Net network, and then hierarchically guided with the input pyramid branch in the encoding and decoding network. The input pyramid structure realizes multi-level receptive fields and generates a hierarchical representation. The encoding and decoding structure concatenates the hierarchical features of the input pyramid and generates a set of hierarchical features. Finally, the feature aggregation module is used to fuse different features to achieve low-light enhancement tasks. The effectiveness of the components is proved through ablation experiments. In addition, the authors are also evaluating on different data sets, and the experimental results show that the method proposed is superior to other methods in subjective and objective evaluation.

关键词： image and video coding computer vision and image processing techniques Data handling techniques

来源：评论

学校读者我要写书评

暂无评论

Multi-exposure image fusion based on feature evaluation with adaptive factor

引用

IET image processing 2021年第13期15卷 3211-3220页

作者： Huang, Li Li, Zhengping Xu, Chao Feng, Bo Anhui Univ Sch Elect Informat Engn Hefei 230000 Anhui Peoples R China

The authors present a new multi-exposure images fusion method based on feature evaluation with adaptive factor. It is noticed the existing multi-exposure fusion algorithm is not well adapted to the input images, which are overall bright or dark, the fused image quality is not pretty good, and the details are not preserved completely. So an adaptive factor to adapt the intensity of input images is presented here. First, the exposure assessment weight, texture change weight, and colour intensity weight are calculated by a sliding window. Finally, the images are fused by using a pyramid to avoid the seams. Twenty exposure input images of different scenes are selected, the subjective and objective aspects are analysed and compared with several existing multi-exposure image fusion methods. The experimental results show that the proposed method can retain more details and obtain satisfactory visual effects on static scenes.

关键词： Optical, image and video signal processing Sensor fusion computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Adaptive detection for resolvable multipath signal under heterogeneous clutter

引用

IET RADAR SONAR AND NAVIGATION 2023年第1期17卷 139-152页

作者： Cao, Chun Fan, Chongyi Du, Huagui Wang, Jian Huang, Xiaotao Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Hunan Peoples R China

In the urban environment, the radar is easily affected by multipath (MP) returns. The problem of detecting point-like targets in the urban environment with the existence of resolvable MP returns under the background of heterogeneous clutter is addressed. Two adaptive detectors have been devised with a combination of prior information on the environment and echoes of target. The detectors can use the MP echoes in all MP prediction range cells for detection or in some available paths for signal detection by the available path selection algorithm that eliminates the weak signal propagation paths. Remarkably, the proposed decision schemes exhibit the desirable constant false alarm rate property with respect to the unknown parameters of the heterogeneous interference. The performance assessment, conducted on simulated data in terms of detection probability also in comparison with conventional solutions, highlights the effectiveness of the MP exploitation, while the MP signal is strong and shows the detection performance enhancement potential.

关键词： available paths resolvable MP returns MP prediction range cells heterogeneous interference multipath channels Signal processing and detection Radar equipment, systems and applications MP echoes Signal detection radar clutter weak signal propagation paths detection probability MP signal resolvable multipath signal adaptive detection radar detection computer vision and image processing techniques desirable constant false alarm rate property heterogeneous clutter object detection signal detection multipath returns Electromagnetic compatibility and interference probability adaptive detectors available path selection MP exploitation urban environment detection performance enhancement potential Other topics in statistics point-like targets

来源：评论

学校读者我要写书评

暂无评论

3D imaging of moving targets for ultra-wideband MIMO through-wall radar system

引用

IET RADAR SONAR AND NAVIGATION 2021年第3期15卷 261-273页

作者： Pan, Jun Ye, Shengbo Shi, Cheng Yan, Kun Liu, Xin Ni, Zhikang Yang, Guangyao Fang, Guangyou Chinese Acad Sci Aerosp Informat Res Inst 9 Dengzhuang South Rd Beijing Peoples R China Chinese Acad Sci Key Lab Electromagnet Radiat & Sensing Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Ultra-wideband (UWB) radar is widely used in static through-wall imaging (TWI). There are still many imaging problems of motion through-wall targets for complex system structure and unknown wall environment. Herein, a motion compensation method based on the reference channel and a modified Kirchhoff migration imaging algorithm are proposed for Ultra-wideband (UWB) MIMO sparse array, which is used for high-precision 3D TWI of moving targets. The channels of the MIMO radar are time-division multiplexing based on microwave switch. Besides, a reference channel is added for motion compensation of moving targets. Performing motion compensation on the target before 3D imaging can effectively avoid the problems of defocus and position deviation caused by target motion. In the proposed imaging method, the backward Green function is used to replace the forward Green function to solve the problem of a large field of view with small arrays. The experiment with a static through-wall target proves that the proposed imaging algorithm can suppress sidelobes well compared with the traditional back-projection algorithm (BPA). Through-wall experiments are carried out for targets with different speeds, and results show that the positioning accuracy and sidelobe level of the proposed compensation method is better than previously proposed methods.

关键词： computer vision and image processing techniques moving targets MIMO radar TWI through-wall imaging Ultra-wideband radar radar imaging target motion ultra wideband communication motion compensation method Optical, image and video signal processing modified Kirchhoff migration imaging algorithm complex system structure Radar equipment, systems and applications UWB imaging problems motion compensation high-precision 3D performing motion compensation through-wall experiments ultra wideband radar through-wall target unknown wall environment Green's function methods reference channel imaging method motion through-wall targets Ultra-wideband MIMO sparse array ultra-wideband MIMO through-wall radar system

来源：评论

学校读者我要写书评

暂无评论

MPI: Multi-receptive and parallel integration for salient object detection

引用

IET image processing 2021年第13期15卷 3281-3291页

作者： Sun, Han Cen, Jun Liu, Ningzhong Liang, Dong Zhou, Huiyu Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China Nanjing Univ Aeronaut & Astronaut MIIT Key Lab Pattern Anal & Machine Intelligence Nanjing Peoples R China Univ Leicester Sch Informat Leicester Leics England

The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object detection. This paper proposes a novel method called multi-receptive and parallel integration, for salient object detection. Firstly, a multi-receptive enhancement module is designed to effectively expand the receptive fields of features from different layers and generate features with different receptive fields. Multi-receptive enhancement module can enhance the semantic representation and improve the model's perception of the image context, which enables the model to locate the salient object accurately. Secondly, in order to reduce the reuse of redundant information in the complex top-down fusion method and weaken the differences between semantic features, a relatively simple but effective parallel fusion strategy is proposed. It allows multi-scale features to better interact with each other, thus improving the overall performance of the model. Experimental results on multiple datasets demonstrate that the proposed method outperforms state-of-the-art methods under different evaluation metrics.

关键词： image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Adaptive combination of linear predictors for lossless image compression

引用

IEE PROCEEDINGS-SCIENCE MEASUREMENT AND TECHNOLOGY 2000年第6期147卷 414-419页

作者： Deng, G Ye, H Cahill, LW La Trobe Univ Dept Elect Engn Bundoora Vic 3083 Australia

Lossless image coding is an essential requirement for medical imaging applications. Lossless image compression techniques usually have two major components: adaptive prediction and adaptive entropy coding. The paper is concerned with adaptive prediction. Recently, several researchers have studied prediction schemes in which the final prediction is formed by a combination of a group of subpredictors. The authors present an overview of this new type of prediction technique. They show that the basic principle of adaptive predictor combination has been extensively studied and applied to many science and engineering problems. They then describe their own combination scheme, which is based on the estimation of the local prediction error variance. Experimental results show that the compression performance of the algorithms that employ this new type of predictor is consistently better than that of state-of-the-art algorithms.

关键词： adaptive prediction adaptive signal processing adaptive entropy coding data compression Biology and medical computing error variance Patient diagnostic methods and instrumentation health physics medical diagnostic imaging computer vision and image processing techniques image coding Biomedical measurement and imaging adaptive combination final prediction Optical, image and video signal processing algorithms linear predictors lossless image compression state-of-the-art algorithms Medical and biomedical uses of fields, radiations, and radioactivity medical image processing

来源：评论

学校读者我要写书评

暂无评论

Social graph convolutional LSTM for pedestrian trajectory prediction

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2021年第3期15卷 396-405页

作者： Zhou, Yutao Wu, Huayi Cheng, Hongquan Qi, Kunlun Hu, Kai Kang, Chaogui Zheng, Jie Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan Peoples R China China Univ Geosci Wuhan Sch Geog & Informat Engn Wuhan Peoples R China Jiangnan Univ Sch Internet Things Wuxi Peoples R China NYU Ctr Urban Sci Progress Brooklyn NY USA

Understanding the movement of pedestrians and predicting their future trajectory can be very important in intelligent transportation systems because accurate pedestrian trajectory prediction will improve the level of autonomous driving technology and reduce traffic accidents. The authors address this problem with a social graph convolutional long short-term memory neural network architecture by considering the movement information of each pedestrian and its interaction with neighbours. Specifically, the authors use a graph to model pedestrian walking state where nodes denote the pedestrian movement information, and edges represent the interactions between pairwise pedestrians. An end-to-end architecture that combines a sequence-to-sequence model with a graph convolutional network to learn the movement features and interaction features is used. To capture the interaction influence on different pedestrians, an emotion gate to refine the learned features and filter out useless information is introduced. A companion loss function to increase the ability of the network to capture 'walking in groups' behaviour is further proposed. Through experiments on two public datasets (ETH and UCY), the authors prove that our method outperforms the previous methods.

关键词： computer vision and image processing techniques Traffic engineering computing Other topics in statistics Combinatorial mathematics

来源：评论

学校读者我要写书评

暂无评论

Iterative multi-scale residual network for deblurring

引用

IET image processing 2021年第8期15卷 1583-1595页

作者： Zhang, Tianlin Li, Jinjiang Hua, Zhen Shandong Technol & Business Univ Sch Informat & Elect Engn Yantai Peoples R China Coinnovat Ctr Shandong Coll & Univ Future Intelli Yantai 264005 Peoples R China

In dynamic scene deblurring, recent neural network-based methods have been very successful. But with the improvement of deep deblurring performance, network structure and learning become more complicated. Compared with large-scale network parameters and complex network structures, an iterative multi-scale residual network to achieve a more effective parameter sharing scheme is proposed. In each iterative unit, fast multi-scale residual blocks to replace superimposed convolutional layers or classic residual blocks are used. On the basis of preventing model overfitting, the receptive field of the network is increased. At the same time, the gated recurrent unit is introduced to connect modules of different stages. The model does not rely on the estimation of the blur kernel and directly generates sharp images in an end-to-end manner. The experimental structure on the benchmark dataset and real-world images showed that this method has better quality than the existing methods in terms of large-scale blur and subjective perception effects, both in quantitative and qualitative terms.

关键词： Interpolation and function approximation (numerical analysis) Optical, image and video signal processing Interpolation and function approximation (numerical analysis) computer vision and image processing techniques Neural nets

来源：评论

学校读者我要写书评

暂无评论

image quality-augmented intramodal palmprint authentication

引用

IET image processing 2012年第6期6卷 668-676页

作者： Prasad, S. M. Govindan, V. K. Sathidevi, P. S. Natl Inst Technol Calicut Dept Comp Sci & Engn Calicut 673601 Kerala India Natl Inst Technol Calicut Dept Elect & Commun Engn Calicut 673601 Kerala India

This study serves dual objectives. First, as an efficient, in terms of speed and accuracy, wavelet-based intramodal palmprint authentication approach. Second, quantification of illumination, quality of palmprints and its incorporation in the score fusion for the classification performance enhancement. The later objective is realised using localised contrast measurement and quality-augmented fusion based on illumination sensitiveness of the features. The former objective is realised through intramodal feature extraction and fusion exploiting the multi-scale analysis of palmprint using wavelet transform. The intramodal features (energy, principal lines, dominant wrinkles and high-scale spatial patterns) are extracted in the wavelet domain thus significantly minimising the computational disadvantage of intramodal approach. Significant reduction in the equal error rate (EER) is observed upon match score fusion. Experimental results on PolyU-Online-Palmprint-Database (PolyU) of 386 classes show a relative improvement index of 71.75% with an overall EER of 0.14%;better than the state-of-the-art intramodal and wavelet-based approaches.

关键词： Sensor fusion multiscale analysis image enhancement wavelet-based intramodal palmprint authentication approach image recognition wavelet transform computer vision and image processing techniques image quality-augmented intramodal palmprint authentication image fusion intramodal feature extraction Integral transforms classification performance enhancement quality-augmented fusion palmprint recognition equal error rate localised contrast measurement wavelet transforms feature extraction PolyU-online-palmprint-database

来源：评论

学校读者我要写书评

暂无评论

Digital watermarking: applications, techniques and challenges

引用

ELECTRONICS & COMMUNICATION ENGINEERING JOURNAL 1999年第4期11卷 173-183页

作者： Barnett, R Synteny Syst Maldon CM9 6SL Essex England

The explosive growth in the use of the Internet has made it an attractive medium for the distribution of multimedia material. However, it has become apparent that the digital nature of such material makes enforcement and proof of copyright ownership virtually impossible. Another problem with digital images and video is that undetectable modifications can be made with very simple and widely available equipment. As a result, the use of digital material for evidential purposes has been called into question at a time when the video surveillance industry is moving towards digital rather than analogue systems. Digital watermarking promises to address these issues. Different types of watermarking systems exist for different applications robust watermarks for copyright protection and fragile watermarks for integrity checking applications. The question is just how good are current digital watermark techniques and what are the issues surrounding their use in real-life situations?.

关键词： copyright ownership digital watermarking watermarking systems fragile watermarks Internet integrity checking applications security of data robust watermarks multimedia material distribution image coding Data security copyright protection surveillance computer vision and image processing techniques image and video coding copyright digital images Video signal processing video surveillance industry video coding digital video

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：