检索结果-内蒙古大学图书馆

IET International Radar Conference 2020, IET IRC 2020

作者： Lu, Yue Zhang, Yue Yang, Jian Science and Technology on Automatic Target Recognition Laboratory National University of Defense Technology Changsha410073 China School of Electronic Engineering Xidian University Xi'an710071 China

ISBN: (纸本)9781839535635

Phase compensation is an essential part of inverse synthetic aperture radar imaging. Minimum entropy-based phase compensation methods have been widely applied due to their robustness under low signal-to-noise ratio (SNR) situations. However, these methods suffer from huge computation complexity and therefore, can be hardly used in real-time imaging situations. In this paper, a novel real-time phase compensation method combining Doppler centroid tracking (DCT), prominent range bins extraction, and fast minimum entropy phase compensation (FMEPC) is proposed. To achieve high efficiency, the parallel version of the proposed algorithm is implemented on Graphic Processing Unit (GPU). Experiments based on real-measured data show that almost 10 times speed-up can be realized. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Adaptive Surface Fitting Convolution for 3D Point Cloud Analysis 5

Adaptive Surface Fitting Convolution for 3D Point Cloud Anal...

引用

5th International Conference on Automation, Control and Robotics Engineering, CACRE 2020

作者： Cao, Hezhi Ma, Yanxin Zhan, Ronghui Ma, Chao Zhang, Jun National University of Defense Technology National Key Laboratory of Science and Technology on Automatic Target Recognition Changsha China National University of Defense Technology College of Meteorology and Oceanography Changsha China

ISBN: (纸本)9781728198880

Traditional Convolutional Neural Networks (CNN) are limited to extract informative local features of point clouds due to the fixed geometric structures in convolution kernel against irregular and unstructured point clouds. It usually requires data transformation such as voxelization or projection, inducing a possible loss of information. Instead of fitting the input points to the kernel by regularization, we choose to fit the kernel to input points to conduct convolution. In this paper, we present a new method to define and compute convolution directly on 3D point clouds by Adaptive Surface Fitting Convolution (ASFConv). The key idea is to utilize a set of kernel points distributed on the tangent plane and project them back to point cloud surface. After adapting to the distribution of input points, ASFConv kernel can better capture local neighborhood geometry and benefit the feature extraction. In the experiments, we evaluate our network on two public datasets: ModelNet40 and ShapeNet for classification and segmentation. The experimental results show that our method obtain competitive performances compared to the state-of-the-art. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multiple Frames Based Infrared Small target Detection Method Using CNN

Multiple Frames Based Infrared Small Target Detection Method...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Jinming Du Dongyang Li Yingjie Deng Luping Zhang Huanzhang Lu Moufa Hu Xinglin Shen Zhuoqun Liu Xuhuan Ji National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science and TechnologyNational University of Defense Technology College of Military Basic Education National University of Defense Technology

In the field of infrared, the detection of dim small target has been a challenging topic. Especially in the complex background, a large number of false alarms might appear when using traditional detection methods, this cannot meet the dual requirements of high detection rate and low false alarm rate. Therefore, in this paper,a CNN based target detection method is proposed for infrared sequence. For an image to be detected, firstly, aiming at the noise and interference which are spatially non-stationary but temporally stable, the method of registration and frame difference is used to suppress the background and extract the target, and the motion information between nearby frames is obtained;next, the extracted information is fed into the light CNN network for the extraction and fusion of different level features;finally, based on the fusion features the small target is detected. The proposed multiple frames based method relies on neural network to extract the motion information in infrared sequence to enhance the distinguishability of the target features under complex condition. Compared with the traditional methods, experimental results show that the proposed CNN method can achieve higher detection rate and lower false alarm rate, especially for the detection of dim small targets in complex background, the advantage is more obvious.

关键词： Deep learning CNN target Detection Multiple Frames

来源：评论

学校读者我要写书评

暂无评论

Infrared target Tracking Algorithm Based on Bernoulli Filter and Support Vector Machine

Infrared Target Tracking Algorithm Based on Bernoulli Filter...

引用

2020 International Conference on Information science and Education, ICISE-IE 2020

作者： Tao, Huamin Shen, Xinglin Deng, Qiuqun National University of Defense Technology Natl. Key Lab. of Sci. and Technology on Automatic Target Recognition College of Electronic Science Changsha China

ISBN: (纸本)9781665422611

Infrared small target tracking algorithm is an important method to obtain the target states effectively. Support Vector Machine (SVM), a classic method in machine learning methods, is effective for target recognition. The Bernoulli filter is the optimal single-target filter for target tracking within the Bayesian framework. However, there is no related research on the joint application of the SVM and Bernoulli filter for infrared small target tracking. In this paper, the SVM and Bernoulli filter are jointly applied to the tracking and recognition of small targets in complex backgrounds. The research shows that, with the SVM, Bernoulli filter can indeed be applied to the actual multi-frame infrared target tracking scene to achieve effective tracking and recognition of infrared small targets. © 2020 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Environment-Driven Online LiDAR-Camera Extrinsic Calibration

arXiv

引用

arXiv 2025年

作者： Huang, Zhiwei Li, Jiaqi Zhong, Ping Fan, Rui The Department of Control Science & Engineering The College of Electronics & Information Engineering Tongji University Shanghai201804 China The School of Computer Science and Engineering Central South University Hunan Changsha410083 China The National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology Hunan Changsha410073 China The Department of Control Science & Engineering The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi Xi’an710049 China

LiDAR-camera extrinsic calibration (LCEC) is the core for data fusion in computer vision. Existing methods typically rely on customized calibration targets or fixed scene types, lacking the flexibility to handle variations in sensor data and environmental contexts. This paper introduces EdO-LCEC, the first environment-driven, online calibration approach that achieves human-like adaptability. Inspired by the human perceptual system, EdO-LCEC incorporates a generalizable scene discriminator to actively interpret environmental conditions, creating multiple virtual cameras that capture detailed spatial and textural information. To overcome cross-modal feature matching challenges between LiDAR and camera, we propose dual-path correspondence matching (DPCM), which leverages both structural and textural consistency to achieve reliable 3D-2D correspondences. Our approach formulates the calibration process as a spatial-temporal joint optimization problem, utilizing global constraints from multiple views and scenes to improve accuracy, particularly in sparse or partially overlapping sensor views. Extensive experiments on real-world datasets demonstrate that EdO-LCEC achieves state-of-the-art performance, providing reliable and precise calibration across diverse, challenging environments. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Sparse Aperture Based Radar Observation Resource Allocation Algorithm for Space target 3D Imaging

Sparse Aperture Based Radar Observation Resource Allocation ...

引用

IEEE International Conference on Computer and Communication Engineering technology (CCET)

作者： Qingwei Yang Libing Jiang Xiang Yu Chaoxiang Zhou Zhuang Wang National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology

ISBN: (数字)9781728188119

ISBN: (纸本)9781728188126

Radar imaging has been one of the basic functions for modern radar as well as searching, detection and tracking, especially for those ground-based space surveillance phased array radars. Due to the periodic revisiting characteristics of the in-orbit objects, multi-pass observations for space targets (e.g. satellites) within small pitching angle variation can be accumulated, which lead to the 3D inverse synthetic aperture radar (ISAR) image formation. Consequently, the strategy of allocating the limited radar observation resource for a reliable 3D ISAR imaging result is becoming a fundamental but critical issue. In this letter, a sparse aperture based radar observation resource allocating method is proposed to facilitate the space target 3D ISAR imaging. According to the sparsity estimation of the target along the azimuth dimension, the required observation resource is calculated and assigned in accordance with the imaging task priority. Furthermore, the experimental boundary of the imaging performance with different signal-to-noise ratios (SNR) and pulse extraction rates are discussed in detail, which gives an intuitive guidance for the radar observation allocation under different application scenarios. The experimental results performed on simulated data validate the feasibility and effectiveness of the proposed method.

关键词： Radar imaging Imaging Three-dimensional displays Apertures Spaceborne radar Space vehicles

来源：评论

学校读者我要写书评

暂无评论

Range migration compensation for moving targets in chirp radars with stepped frequency

Range migration compensation for moving targets in chirp rad...

引用

IET International Radar Conference 2018, IRC 2018

作者： Sen, Wang Qinglong, Bao Zengping, Chen Science and Technology on Automatic Target Recognition Laboratory National University of Defense Technology Changsha China

Long-time coherent pulse integration method has been extensively used in detecting weak targets, but the detection performance is affected by range migration (RM) due to high radial velocity. This study proposes a new modulation format of chirp radars with stepped frequency and a corresponding coherent integration method based on adjacent cross-correlation operation (ACCO) to compensate RMs of moving targets with, respectively, arbitrary unknown constant velocity. Simulation results show that the method has higher range resolution compared with bandwidth variation modulation and shorter blind distance compared with duration variation modulation. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Modulation

来源：评论

学校读者我要写书评

暂无评论

Radiation pattern design of Perovskite light-emitting diodes by nanostructures 4

Radiation pattern design of Perovskite light-emitting diodes...

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Ci, Qing Ren, Xingang Huang, Zhixiang Wu, Xianliang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan237000 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei230039 China Anhui University Key Laboratory of Electromagnetic Environmental Sensing Department of Education of Anhui Province Hefei230039 China

ISBN: (纸本)9781733509619

Perovskite light-emitting diodes (PeLEDs) are drawing great interest due to its promising applications in both high-quality display and lighting. The incorporations of nanostructures into the device have widely used to enhance the light extraction efficiency (LEE). Besides, the spatial emission pattern of PeLEDs can also be modified, which is useful in a range of scientific and industrial applications. Herein, we studied the characteristics of PeLEDs with incorporation of perovskite or Ag nanogratings into electron transport layer with finite difference-time domain (FDTD) numerical simulation method. The results clearly demonstrated that the LEE has enhanced more than three times compared with conventional planar PeLEDs. We further found that the horizontal location of emission source can greatly manipulate the radiation pattern of Ag patterned PeLEDs. The results suggest that the employment of nanostructures opens the possibility of controlling emission light. Moreover, the findings shown here will be useful to performance enhancement of other optoelectronic devices. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Infrared target Tracking Algorithm Based on Bernoulli Filter and Support Vector Machine

Infrared Target Tracking Algorithm Based on Bernoulli Filter...

引用

Information science and Education (ICISE-IE), International Conference on

作者： Huamin Tao Xinglin Shen Qiuqun Deng National Key Laboratory of Science and Technology on Automatic Target Recognition College of Electronic Science National University of Defense Technology Changsha China

关键词： Support vector machines Information science target tracking Machine learning algorithms target recognition Education Machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Surface Fitting Convolution for 3D Point Cloud Analysis

Adaptive Surface Fitting Convolution for 3D Point Cloud Anal...

引用

Automation, Control and Robotics Engineering (CACRE), International Conference on

作者： Hezhi Cao Yanxin Ma Ronghui Zhan Chao Ma Jun Zhang National Key Laboratory of Science and Technology on Automatic Target Recognition National University of Defense Technology College of Meteorology and Oceanography National University of Defense Technology National Key Laboratory of Science and echnology on Automatic Target Recognition National University of Defense Technology College of Electronic Science and Technology National University of Defense Technology

ISBN: (数字)9781728198880

ISBN: (纸本)9781728198897

Traditional Convolutional Neural Networks(CNN)are limited to extract informative local features of point clouds due to the fixed geometric structures in convolution kernel against irregular and unstructured point clouds. It usually requires data transformation such as voxelization or projection, inducing a possible loss of information. Instead of fitting the input points to the kernel by regularization, we choose to fit the kernel to input points to conduct convolution. In this paper, we present a new method to define and compute convolution directly on 3 D point clouds by Adaptive Surface Fitting Convolution(ASFConv). The key idea is to utilize a set of kernel points distributed on the tangent plane and project them back to point cloud *** adapting to the distribution of input points, ASFConv kernel can better capture local neighborhood geometry and benefit the feature extraction. In the experiments, we evaluate our network on two public datasets: ModelNet40 and ShapeNet for classification and segmentation. The experimental results show that our method obtain competitive performances compared to the state-of-the-art.

关键词： CNN point cloud convolution operation tangent plane

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：