检索结果-南通市图书馆

A Low Complexity Distributed Multitarget Detection and Tracking Algorithm

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2023年第3期32卷 429-437页

作者： FAN Jiande XIE Weixin LIU Zongxiang ATR key laboratory Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

In this paper, we propose a low complexity distributed approach to address the multitarget detection/tracking problem in the presence of noisy and missing data. The proposed approach consists of two components: a distributed flooding scheme for measurements exchanging among sensors and a sampling-based clustering approach for target detection/tracking from the aggregated measurements. The main advantage of the proposed approach over the prevailing Markov-Bayes-based distributed filters is that it does not require any priori information and all the information required is the measurement set from multiple sensors. A comparison of the proposed approach with the available distributed clustering approaches and the cutting edge distributed multiBernoulli filters that are modeled with appropriate parameters confirms the effectiveness and the reliability of the proposed approach.

关键词： Sensor fusion Distributed multitarget tracking Constrained clustering Flooding Average consensus

Action Status Based Novel Relative Feature Representations for Interaction Recognition

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第1期31卷 168-180页

作者： LI Yanshan GUO Tianyu LIU Xing LUO Wenhan XIE Weixin ATR National key laboratory of Defense Technology Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Tencent

Skeleton-based action recognition has always been an important research topic in computer vision. Most of the researchers in this field currently pay more attention to actions performed by a single person while there is very little work dedicated to the identification of interactions between two people. However, the practical application of interaction recognition is actually more critical in our society considering that actions are often performed by multiple people. How to design an effective scheme to learn discriminative spatial and temporal representations for skeleton-based interaction recognition is still a challenging problem. Focusing on the characteristics of skeleton data for interactions, we first define the moving distance to distinguish the action status of the participants. Then some view-invariant relative features are proposed to fully represent the spatial and temporal relationship of the skeleton sequence. Further, a new coding method is proposed to obtain the novel relative feature representations. Finally, we design a three-stream CNN model to learn deep features for interaction recognition. We evaluate our method on SBU dataset, NTU RGB+D 60 dataset and NTU RGB+D 120 dataset. The experimental results also verify that our method is effective and exhibits great robustness compared with current state-of-the-art methods.

关键词： Human action analysis Interaction recognition Action status Multi-stream network Relative feature representations

Position Optimization for Mobile Relay Communications with Constrained Energy over a Whole Horizontal Plane

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2023年第5期20卷 340-350页

作者： Haijun Tan Ning Xie Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information EngineeringShenzhen UniversityShenzhen 518060China

This paper concerns the position optimization problem of a mobile relay over a whole horizontal plane.This problem is important because the position of a mobile relay directly affects the end-to-end performance,e.g.,reliability,connectivity,and data rate.In this paper,we propose a new position optimization scheme of a mobile relay over a whole horizontal plane based on the one-bit feedback information from the destination node,which improves the performance over the prior scheme whose position of the mobile relay is optimized over a fixed orbit.In the proposed scheme,the mobile relay is equipped with merely one single onboard antenna.Moreover,no prior information about the positions of both the source node and the destination node is required.Thus,the proposed scheme can work at low network resources scenario,which is particularly suitable for mobile relay communication with constrained energy,e.g.,the communications in a disaster area where the infrastructure is heavily damaged,volcano monitoring,and wireless powered communication networking.According to the characteristics of the proposed scheme,we further design two heuristic implementations to calculate the optimal position of a mobile relay over a whole horizontal plane.The first implementation has better steady performance whereas the second implementation has better convergence speed.We implement the proposed scheme and conduct an extensive performance comparison between the proposed scheme and prior schemes to verify the advantages of the proposed scheme.

关键词： mobile relay position optimization one bit feedback information whole horizontal plane energy constrained

Labeled Multi-Bernoulli Maneuvering Target Tracking Algorithm via TSK Iterative Regression Model

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第2期31卷 227-239页

作者： WANG Xiaoli XIE Weixin LI Liangqun Department of Electronics and information Guangdong Polytechnic Normal University Automatic Target Recognition (ATR) key laboratory Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

Aiming at the problem that the existing labeled multi-Bernoulli(LMB) method has a single and fixed model set, an LMB maneuvering target tracking algorithm via Takagi-Sugeno-Kang(TSK) iterative regression multiple model is proposed. In the TSK iterative regression modeling, the feature information of the targets is analyzed and represented by multiple semantic fuzzy sets. Then the state is expanded to introduce model information, thereby the adaptive multi-model idea is incorporated into the framework of the LMB method to solve the uncertain maneuverability of moving targets. Finally,the simulation results show that the proposed algorithm can effectively achieve maneuvering target tracking in the nonlinear system.

关键词： Takagi-Sugeno-Kang Iterative regression model Labeled multi-bernoulli Maneuvering target tracking

OGSRN:Optical-guided super-resolution network for SAR image

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第5期35卷 204-219页

作者： Yanshan LI Li ZHOU Fan XU Shifu CHEN ATR National key laboratory of Defense Technology Shenzhen UniversityShenzhen 518060China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen UniversityShenzhen 518060China

Although Convolutional Neural Networks(CNNs)have significantly improved the development of image Super-Resolution(SR)technology in recent years,the existing SR methods for SAR image with large scale factors have rarely been studied due to technical difficulty.A more efficient method is to obtain comprehensive information to guide the SAR image reconstruction.Indeed,the co-registered High-Resolution(HR)optical image has been successfully applied to enhance the quality of SAR image due to its discriminative characteristics.Inspired by this,we propose a novel Optical-Guided Super-Resolution Network(OGSRN)for SAR image with large scale factors.Specifically,our proposed OGSRN consists of two sub-nets:a SAR image SuperResolution U-Net(SRUN)and a SAR-to-Optical Residual Translation Network(SORTN).The whole process during training includes two stages.In stage-1,the SR SAR images are reconstructed by the SRUN.And an Enhanced Residual Attention Module(ERAM),which is comprised of the Channel Attention(CA)and Spatial Attention(SA)mechanisms,is constructed to boost the representation ability of the network.In stage-2,the output of the stage-1 and its corresponding HR SAR images are translated to optical images by the SORTN,respectively.And then the differences between SR images and HR images are computed in the optical space to obtain feedback information that can reduce the space of possible SR solution.After that,we can use the optimized SRUN to directly produce HR SAR image from Low-Resolution(LR)SAR image in the testing phase.The experimental results show that under the guidance of optical image,our OGSRN can achieve excellent performance in both quantitative assessment metrics and visual quality.

关键词： SAR image Super-resolution Optical image Attention mechanisms Convolutional Nerual Networks(CNNs)

One-bit splitting deceptive jamming against SAR

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2022年第10期18卷 1760-1777页

作者： Bo Zhao Lei Huang Bing Li Shi-qi Liu Wei-min Bao Guangdong Key Laboratory of Intelligent Information Processing College of Information EngineeringShenzhen UniversityShenzhen518060China China Aerospace Science and Technology Corporation Beijing100048China

One-bit quantization is a promising technique due to its performance retention and complexity reduction in a deceptive jammer against synthetic aperture radar(SAR).In this paper,the 1-bit quantization technology is utilized to agilely generate split false targets in the SAR imagery once the radar signal is intercepted,which reduces the complexity of the jammer significantly with guaranteed focusing quality.A single-frequency threshold is used to decompose harmonics incurred by the 1-bit quantization,and its parameters are adjusted through different pulse repetition intervals to provide steerable modulations.In this way,the SAR signal is split into coupled false scatterers during the 1-bit interception.By further deploying amplitude,time-delay,and Doppler frequency modulations on the 1-bit intercepted signal,the split false targets are created.The proposed approach is compared with different deceptive jamming methods to show its validity in effectiveness and cost,and numerical experiments are also presented for verification.

关键词： Synthetic aperture radar(SAR) 1-Bit quantization Multi-false-target Single-frequency threshold

Pretrained Models and Evaluation Data for the Khmer Language

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第4期27卷 709-718页

作者： Shengyi Jiang Sihui Fu Nankai Lin Yingwen Fu School of information Science and Technology Guangdong University of Foreign StudiesGuangzhou 510000China Guangzhou key laboratory of Multilingual intelligent processing Guangdong University of Foreign StudiesGuangzhou 510000China

Trained on a large corpus,pretrained models(PTMs)can capture different levels of concepts in context and hence generate universal language representations,which greatly benefit downstream natural language processing(NLP)tasks.In recent years,PTMs have been widely used in most NLP applications,especially for high-resource languages,such as English and Chinese.However,scarce resources have discouraged the progress of PTMs for low-resource languages.Transformer-based PTMs for the Khmer language are presented in this work for the first time.We evaluate our models on two downstream tasks:Part-of-speech tagging and news categorization.The dataset for the latter task is self-constructed.Experiments demonstrate the effectiveness of the Khmer models.In addition,we find that the current Khmer word segmentation technology does not aid performance improvement.We aim to release our models and datasets to the community in hopes of facilitating the future development of Khmer NLP applications.

关键词： pretrained models Khmer language word segmentation part-of-speech(POS)tagging news categorization

TGSIFT: Robust SIFT Descriptor Based on Tensor Gradient for Hyperspectral Images

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2020年第5期29卷 916-925页

作者： LI Yanshan FAN Leidong XIE Weixin ATR National key Lab.of Defense Technology Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Information Engineering Shenzhen University

This paper proposes a robust sparse descriptor based on tensor theory by using the spatial and spectral information synthetically, namely the Tensor gradient SIFT(TGSIFT), for Hyperspectral image(HSI).TGSIFT integrates both spatial and spectral information and considers the natural vector feature of HSIs. Based on the HSI Gaussian scale space, a new tensor model for HSI is proposed which takes the vectorial nature of HSI into consideration and preserves all the necessary structural information distributed over all the bands.The TGSIFT descriptor is formed based on the model proposed. Experimental results of HSI matching show that the TGSIFT descriptor achieves better matching performance than other SIFT descriptors under different transformations, including illumination change, sensor noise, image rotation, viewpoint change, and scale change.

关键词： Hyperspectral image (HSI) Interest points Scale-invariant feature transform (SIFT) Sparse descriptor Tensor gradient SIFT (TGSIFT)

DeepHGNN: A Novel Deep Hypergraph Neural Network

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2022年第5期31卷 958-968页

作者： LIN Jingjing YE Zhonglin ZHAO Haixing FANG Lusheng Tibetan information processing and Machine Translation key laboratory of Qinghai Province College of Computer Qinghai Normal University Xining Urban Vocational & Technical College The State key laboratory of Tibetan intelligent information processing and Application

With the development of deep learning,graph neural networks(GNNs) have yielded substantial results in various application fields. GNNs mainly consider the pair-wise connections and deal with graph-structured data. In many real-world networks, the relations between objects are complex and go beyond pair-wise.Hypergraph is a flexible modeling tool to describe intricate and higher-order correlations. The researchers have been concerned how to develop hypergraph-based neural network model. The existing hypergraph neural networks show better performance in node classification tasks and so on, while they are shallow network because of oversmoothing, over-fitting and gradient vanishment. To tackle these issues, we present a novel deep hypergraph neural network(Deep HGNN). We design Deep HGNN by using the technologies of sampling hyperedge, residual connection and identity mapping, residual connection and identity mapping bring from graph convolutional neural networks. We evaluate Deep HGNN on two visual object datasets. The experiments show the positive effects of Deep HGNN, and it works better in visual object classification tasks.

关键词： Deep neural networks Graph neural network Hypergraph neural network Deep hypergraph neural network