检索结果-内蒙古大学图书馆

Implicit Diffusion Models for Continuous Super-Resolution

International Journal of Computer Vision 2025年 1-23页

作者： Liu, Xuhui Gao, Sicheng Zeng, Bohan Zhang, Luping Wang, Tian Liu, Jianzhuang Zhang, Baochang Beihang University Beijing China National Key laboratory of Automatic Target Recognition changsha China Zhongguancun Laboratory Beijing China Shenzhen Institute of Advanced Technology Shenzhen China Nanchang Institute of Technology Nanchang China

Image super-resolution (SR) has attracted increasing attention due to its widespread applications. However, current SR methods generally suffer from over-smoothing and artifacts, and most of them work only with fixed magnifications. To address these problems, this paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution. IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation. Moreover, we design a scale-adaptive conditioning mechanism that consists of a low-resolution (LR) conditioning network and a scaling factor. The LR conditioning network adopts a parallel architecture to provide multi-resolution LR conditions for the denoising model. The scaling factor further regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output, which enables the model to accommodate the continuous-resolution requirement. Furthermore, we accelerate the inference process by adjusting the denoising equation and employing post-training quantization to compress the learned denoising network in a training-free manner. Extensive experiments on six benchmark datasets validate the effectiveness of our IDM and demonstrate its superior performance over prior arts. The source code is available at https://***/Ree1s/IDM .

关键词： Image Super-Resolution Diffusion Model Implicit Neural Representation Continuous-Resolution Representation

来源：评论

学校读者我要写书评

暂无评论

Multitone Waveform Design towards Enhancing Conversion Efficiency for RF-electronics Detection

TechRxiv

引用

TechRxiv 2023年

作者： Li, Yuanzhe Hu, Weidong Fan, Hongqi Du, Xiaoyong Fan, Beichen National Key Laboratory of Automatic Target Recognition College of Electronic Science and Technology National University of Defense Technology Changsha410073 China

Nonlinear radar has attracted considerable attention in recent years due to its unique advantage in detecting nonlinear targets, such as Radio-Frequency (RF) electronics, under strong clutter conditions. However, the low nonlinear RF-to-RF conversion efficiency (RRCE) severely limits its operational range and application scenarios. So far, the research community has mainly focused on improving the RRCE from the hardware aspects while ignoring the signal design. In this paper, we study the waveform design problem that maximizes RRCE for detecting nonlinear targets. Assuming perfect channel state information and target characteristics, we develop a tractable block-oriented nonlinear model and formulate the waveform design as a constrained optimization problem. Then two iterative algorithms based on successive relaxation are proposed to solve the non-convex problem for different cases. Besides, the simulations and laboratory experiments demonstrate the effectiveness of the system model and the superiority of the proposed waveform design method over various baselines. More than 4 dB improvement in RRCE is observed for the given configurations in the experiment. The study provides a promising alternative for extending the maximum distance of nonlinear radar. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Azimuth Calibration and Data Association for a Radar-Optical Multi-Sensor System 4

Azimuth Calibration and Data Association for a Radar-Optical...

引用

4th IEEE International Conference on Electronics technology, ICET 2021

作者： Yang, Ye Da, Kai Zhu, Yongfeng Xiang, Shengwen Fu, Qiang National University of Defense Technology National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science Changsha China

ISBN: (纸本)9781728176734

Radar sensors have high false alarm rate in high density clutter and low angular measurement accuracy due to low angle resolution. This paper proposes an azimuth calibration and track association algorithm by utilizing both radar and optical sensor simultaneously to improve detection and estimation performance. First, based on 'azimuth-time' search algorithm, data calibration of radar and optical measurements is realized. Then, the nearest neighbor (NN) algorithm and the probability data association (PDA) algorithm are used to associate the calibrated data. Finally, the effectiveness of the algorithm is verified through processing and analysis of measured data. © 2021 IEEE.

关键词： Radar measurement

来源：评论

学校读者我要写书评

暂无评论

target detection and tracking algorithm based on improved Mask RCNN and LMB 10

Target detection and tracking algorithm based on improved Ma...

引用

10th International Conference on Control, Automation and Information sciences, ICCAIS 2021

作者： Liu, Zhuoqun Deng, Yingjie Ma, Feng Du, Jinming Xiong, Chao Hu, Moufa Zhang, Luping Ji, Xuhuan National University of Defense Technology National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and Technology Changsha China

ISBN: (纸本)9781665440295

This paper proposes an improved Mask RCNN and LMB algorithm for target detection and tracking in complex backgrounds, which follows the architecture of Detect-Before-Track. First, the novel algorithm adopts a two-stage neural network to improve the target positions' accuracy during the detection. Then, the label multi-Bernoulli filter, which is suitable for scenarios with an unknown number of targets and target intersection, is utilized to generate the multiple-target trajectories during the tracking stage. Experiments suggest the algorithm's effectiveness and superiority in complex backgrounds' infrared target detection and tracking. © 2021 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Center-to-Corner Vector Guided Network for Arbitrary-Oriented Ship Detection in Synthetic Aperture Radar Images 3

Center-to-Corner Vector Guided Network for Arbitrary-Oriente...

引用

3rd International Conference on Geology, Mapping and Remote Sensing, ICGMRS 2022

作者： Xiao, Man He, Zhi Lou, Anjun Li, Xinyuan Sun Yat-sen University School of Geography and Planning Guangzhou510275 China School of Geography and Planning Guangzhou510275 China National Key Laboratory of Science and Technology on Automatic Target Recognition China

ISBN: (数字)9781665485951

ISBN: (纸本)9781665485951

Recently, deep learning-based methods have gained great attention in ship detection of synthetic aperture radar (SAR) images. However, the mismatch between horizontal detection boxes and real targets poses big challenges to the improvement of detection accuracy, especially for the densely arranged ships. Therefore, how to achieve precise arbitrary-oriented ship detection is particularly important. In this paper, we propose a novel center-to-corner vector guided network named CCVNet for SAR ship detection. Different from angle regression and classification, our CCVNet adopts an anchor-free method to directly predict the vectors from center to corners, which can reduce the error accumulation caused by predicting angles and scales separately. In addition, data augmentation methods with random rotation and power transformations are put forward to keep the rotation invariance and enhance the information of SAR images, which are proved to be effective in promoting detection performance. Experimental results on the SSDD dataset demonstrate the superiority of our method. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Anti Repeater Jamming Method Based on Phase Noise Joint Time-Frequency Analysis

Anti Repeater Jamming Method Based on Phase Noise Joint Time...

引用

2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023

作者： Jiang, Hui Hu, Weidong Du, Xiaoyong Yuan, Ziqiao Hu, Yifu Zhu, Hongyu Xi'An Electronic Engineering Research Institute Xi'an China National University of Defense Technology National Key Laboratory of Automatic Target Recognition Chang Sha China Xi'An Electronic Engineering Research Institute xi'An China Xi'an China

ISBN: (纸本)9798350316728

The jammer utilizes a digital radio frequency memory (DRFM) system to generate a large number of jamming signals highly correlated with the target echo, thereby reducing the performance of radar target detection and tracking. This article establishes a model for the influence of phase noise on the interference signal of a full duplex jammer (transmitting and receiving simultaneously) forwarding system, and analyzes the differences between radar target echo and jamming signal. Perform de-chirping processing on radar received echoes and time-frequency analysis, use bandpass filtering to extract the Allan variance corresponding to jamming and target echoes, as well as the single sideband noise carrier power ratio, to identify the frequency corresponding to target echoes. Finally, the target echo signal is reconstructed after time-frequency domain filtering. The simulation experimental results show that this algorithm can accurately identify real targets and effectively suppress DRFM repeater jamming. © 2023 IEEE.

关键词： Phase noise

来源：评论

学校读者我要写书评

暂无评论

Beyond Sharing Weights in Decoupling Feature Learning Network for UAV RGB-Infrared Vehicle Re-Identification

arXiv

引用

arXiv 2023年

作者： Liu, Xingyue Qi, Jiahao Chen, Chen Bin, Kangcheng Zhong, Ping The National Key Laboratory of Automatic Target Recognition National University of Defense Technology Changsha410073 China

Owing to the capacity of performing full-time target search, cross-modality vehicle re-identification based on unmanned aerial vehicle (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the data inadequacy issue. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with 16015 RGB and 13913 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to flexibly conduct OIFS task. Comprehensive experiments are carried out to validate the effectiveness of the proposed method. The dataset and codes will be released at https://***/moonstarL/UAV-CM-VeID. Copyright © 2023, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

A Joint Detection and State Estimation Algorithm for Pulse Doppler Radar 5

A Joint Detection and State Estimation Algorithm for Pulse D...

引用

5th IEEE Information technology, Networking, Electronic and Automation Control Conference, ITNEC 2021

作者： Dong, Wenhao Wang, Jingyi Song, Zhiyong Fu, Qiang National University of Defense Technology National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science Changsha410073 China

ISBN: (纸本)9781665415989

In order to improve the detection sensitivity of pulse Doppler (PD) radar, a joint detection and state estimation algorithm based on random finite set is proposed. In the framework of formal Bernoulli filter, the state model and observation model of the algorithm are designed at the range-Doppler (RD) echo signal level when there is only a single target, which makes full use of the dynamic difference of phase and amplitude change between target and background. Since the state vector can be divided into linear and non-linear parts, Rao-Blackwellized particle filter (RB-PF) is used to realize the prediction and update of the state vector. The simulation results show that the algorithm can effectively improve the state estimation accuracy and detection sensitivity. © 2021 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Joint tracking and classification of extended targets with complex shapes

引用

Frontiers of Information technology & Electronic Engineering 2021年第6期22卷 839-861页

作者： Liping WANG Ronghui ZHAN Yuan HUANG Jun ZHANG Zhaowen ZHUANG National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense TechnologyChangsha 410073China

This paper addresses the problem of joint tracking and classification(JTC) of a single extended target with a complex shape. To describe this complex shape, the spatial extent state is first modeled by star-convex shape via a random hypersurface model(RHM), and then used as feature information for target classification. The target state is modeled by two vectors to alleviate the influence of the high-dimensional state space and the severely nonlinear observation model on target state estimation, while the Euclidean distance metric of the normalized Fourier descriptors is applied to obtain the analytical solution of the updated class probability. Consequently, the resulting method is called the "JTC-RHM method." Besides, the proposed JTC-RHM is integrated into a Bernoulli filter framework to solve the JTC of a single extended target in the presence of detection uncertainty and clutter, resulting in a JTC-RHM-Ber filter. Specifically, the recursive expressions of this filter are derived. Simulations indicate that:(1) the proposed JTC-RHM method can classify the targets with complex shapes and similar sizes more correctly, compared with the JTC method based on the random matrix model,(2) the proposed method performs better in target state estimation than the star-convex RHM based extended target tracking method,(3) the proposed JTC-RHM-Ber filter has a promising performance in state detection and estimation, and can achieve target classification correctly.

关键词： Extended target Fourier descriptors Joint tracking and classification Random hypersurface model Bernoulli filter

来源：评论

学校读者我要写书评

暂无评论

FCGSM: Fast Conjugate Gradient Sign Method for Adversarial Attack on Image Classification 6th

FCGSM: Fast Conjugate Gradient Sign Method for Adversarial ...

引用

6th International Conference on Innovative Computing, IC 2023

作者： Xia, Xiaoyan Xue, Wei Wan, Pengcheng Zhang, Hui Wang, Xinyu Zhang, Zhiting School of Computer Science and Technology Anhui University of Technology Maanshan243032 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Maanshan243032 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Changsha410073 China

ISBN: (纸本)9789819922864

Deep neural network is sensitive to adversarial samples that crafted by adding imperceptible perturbations to original images, and many methods of generating adversarial samples have emerged. Although existing methods based on gradient direction have good attack performance, some ill-conditioned issues may reduce their performance on occasion. In this paper, we propose a novel attack method based on three-terms conjugate gradient direction, which is effectively for improving this limitation, and its is named as fast conjugate gradient sign method (FCGSM). The proposed method FCGSM can jump from the local maximum during the process of finding the maximum value of loss function, thus generating more adversarial samples than the SOTA methods APGD and ACG. Experiments conducted on two benchmark datasets show that the FCGSM works well in attacking deep neural network-based classification models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

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：