检索结果-内蒙古大学图书馆

Adaptive tracking method for ground target of FLIR imaging

Adaptive tracking method for ground target of FLIR imaging

MIPPR 2009 - Automatic Target recognition and Image Analysis: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Li, Yun Zhang, Tianxu Zuo, Zhengrong Wan, Meijun State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478061

An adaptive tracking method for ground target in FLIR image including centric and eccentric tracking is presented in this paper. The eccentric tracking is adopted to assist ATR or manual target acquisition by stabilizing the light axis of the seeker. The tracking adaptability detection at the start of centric tracking avoids tracking bad locked point and decreases the shift, slide and jump in the subsequent tracking. Combination of periodic template-updating based on scale variance rate and interruptive template-updating based on supervision of tracking point enhances the adaptability of tracking template. Supervision, modification of current tracking point and the combination of direct and indirect tracking increase the stability of tracking system. The multi-scale and size-variable template is adopted to fit the variable target scale. The detection and adoption of occlusion mask increase the accuracy of the tracking system. The hardware system based on multi-DSP takes a real-time parallel processing. The trial results show that this method is efficient to reduce the possibility of shift, slide, and jump in ground target tracking comparing with the traditional correlation tracking method. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A novel method concerning about image transition region extraction and segmentation

A novel method concerning about image transition region extr...

引用

2nd International Conference on Multimedia Technology, ICMT 2011

作者： Wang, Fang Zhang, Tianxu Deng, Jinpeng State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781612847740

According to the feature that the gray distribution of the transition region (locating between the objects and the background) is more scattered than that of the regions of targets or background in an image, this paper proposes a novel method concerning about transition region extraction and segmentation, which is based on local variance of different areas of an image. The experiments indicate that the proposed approach can achieve better segmentation results than the local complexity method (one of the previous methods for extracting transition region).What's more, the novel approach outperforms the local complexity method about more complete and more accurate transition regions, less interference from backgrounds, more detail information of segmented targets, clearer and better segmented targets, easier calculation, and higher processing speed. © 2011 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Estimating the connection probability for 2-D mesh networks by Monte Carlo methods

Estimating the connection probability for 2-D mesh networks ...

引用

International Conference on Computer and Management

作者： Liang, Meilian Liang, Binmei Shao, Zehui Xu, Xiaodong School of Mathematics and Information Science Guangxi University Nanning 530004 China Key Laboratory of Pattern Recognition and Intelligent Information Processing School of Information Science and Technology Chengdu University Chengdu 610106 China Guangxi Academy of Sciences Nanning 530007 China

ISBN: (纸本)9781424492831

Fault tolerance is a central issue in the design and implementation of interconnection networks for large parallel systems. Connection probability of a network is a good network fault tolerance measure. For a mesh of given size and node failure probability, the gap between the known upper and lower bounds on the connection probability is often very large. In this paper we design algorithms to estimate the connection probability for 2-D meshes by Monte Carlo methods. The experiment is carefully designed and performed, and the simulation results give good estimates of the connection probability for 2-D meshes and can be used to evaluate the known lower and upper bounds on connection probability for 2-D meshes. ©2011 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Airborne target tracking algorithm against oppressive decoys in infrared imagery

Airborne target tracking algorithm against oppressive decoys...

引用

MIPPR 2009 - Automatic Target recognition and Image Analysis: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Sun, Xiechang Zhang, Tianxu State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478061

This paper presents an approach for tracking airborne target against oppressive infrared decoys. Oppressive decoy lures infrared guided missile by its high infrared radiation. Traditional tracking algorithms have degraded stability even come to tracking failure when airborne target continuously throw out many decoys. The proposed approach first determines an adaptive tracking window. The center of the tracking window is set at a predicted target position which is computed based on uniform motion model. Different strategies are applied for determination of tracking window size according to target state. The image within tracking window is segmented and multi features of candidate targets are extracted. The most similar candidate target is associated to the tracking target by using a decision function, which calculates a weighted sum of normalized feature differences between two comparable targets. Integrated intensity ratio of association target and tracking target, and target centroid are examined to estimate target state in the presence of decoys. The tracking ability and robustness of proposed approach has been validated by processing available real-world and simulated infrared image sequences containing airborne targets and oppressive decoys. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A novel multiscale recursive recognition method for flying airplane objects

A novel multiscale recursive recognition method for flying a...

引用

2012 International Conference on Image processing, Computer Vision, and pattern recognition, IPCV 2012

作者： Zhang, Tianxu Zhou, Gang Yang, Ying Weng, Wenjie Sun, Xiangdong Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology State Key Laboratory for Multispectral Information Processing Technologies Wuhan Hubei China

ISBN: (纸本)9781601322258

In actual imaging process, the projection or silhouette of a three-dimensional moving object is variable in shape, scale and resolution to make its recognizability also unstable. A remedy is suggested on concepts defined in this paper as the dynamic feature space of the pattern. The necessity of developing feature models of multi-scale characteristic view for three-dimensional moving airplane objects and the rationality of using a usual constraint on airplane object moving characteristics are discussed. Thus, a novel multi-scale intelligent recursive recognizing (MUSIRR) method for image sequences is proposed. An intelligent recognizer composed of hybrid neural networks and logic decision-making modules is constructed with the BP neural networks and RBF networks as the building blocks of the recognizer. The rationality and effectiveness of the new method proposed in this paper have been verified by results of massive simulation and actual experiments on several types of airplane object.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A novel method of aerial image classification based on attention-based local descriptors

引用

Procedia Earth and Planetary Science 2009年第1期1卷 1133-1139页

作者： Xu, Sheng Fang, Tao Huo, Hong Li, Deren Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200240 China The State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430072 China

This paper proposes a novel method for object-based classification in very high spatial resolution aerial image. It combines the saliency maps very closely to extract the conspicuous local regions for better description of object and classification. Unlike the previous work on detection of the local regions, a biologically motivated selective attention model is presented in this paper, since not all the local regions are important for describing the objects. In order to model the attention region, we propose a new attention-based local descriptor using the saliency map and relative local features to reflect the region of interest (ROI). The experimental results on the VHR aerial image dataset show that the proposed approach can obtain the state-of-the-art classifica-tion performance. © 2009.

关键词： Object recognition Image analysis Image classification Image segmentation Aerial images Bag of visual words Local descriptors Local feature Local region Novel methods Object based Region of interest Saliency map Selective attention model Very high spatial resolutions

来源：评论

学校读者我要写书评

暂无评论

MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation

引用

Medical Image Analysis 2025年 103卷 103606页

作者： Tang, Fenghe Nian, Bingkun Li, Yingtai Jiang, Zihang Yang, Jie Liu, Wei Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Suzhou Institute for Advanced Research USTC Jiangsu Suzhou215123 China Department of Automation Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology Jiangsu Suzhou215123 China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba's potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://***/FengheTan9/MambaMIM. © 2025

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Research on the method of medium wave infrared simulation based on Vega

Research on the method of medium wave infrared simulation ba...

引用

International Conference on Multimedia Technology

作者： Wang, Man Zhang, Tianxu State Key Laboratory for Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424478743

Visual Simulation, which has been applied widely to provide convenience to people from every walk of life, plays a crucial role in the field of Virtual Reality. In this thesis, 8 models representing 8 typical materials, are created by MultiGen Creator, and rendered by Vega for analysis of relation between grey values in simulated pictures and real radiance. Finally, the method of infrared simulation based on Vega is proved effective in the field of military by comparison between simulated pictures and real shot pictures at different times of the day. ©2010 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Acquisition and tracking landmarks for navigation of aircraft

Acquisition and tracking landmarks for navigation of aircraf...

引用

MIPPR 2009 - Automatic Target recognition and Image Analysis: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Yang, Xiaoyu Zhang, Tianxu Yan, Luxin Wang, Dengwei Wang, Xiaoping State Key Laboratory for Multispectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9780819478061

In this paper, we proposed a method is used to estimate an aircraft's own position in flight depending on acquisition and tracking an enlarged landmark in an image sequence. Acquisition operation is based on matching 2D template with a 2D scene of the landmark area generated by the aircraft seeker. After the landmark location is acquired, tracking the center point of the landmark maintains the slant range estimate between the sensor and the landmark which is calculated depending on data of three successive positions from the measured IMU/ GPS information. Then, we obtain the absolute position of the aircraft in the world coordinate system (WCS) with the transformation from the landmark coordinate system (LCS) into the WCS. Finally, bias errors of the Inertial Navigation are corrected for navigation of the aircraft. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

An improved algorithm of search for compressive sensing image recovery based on lp norm

An improved algorithm of search for compressive sensing imag...

引用

Chinese Automation Congress, CAC 2015

作者： Yuan, Jiang Pei, Shen Ping, Zhao Yang, Daiji Zhen, Chen Jiangxi Province Key Laboratory of Image Processing and Pattern Recognition Nanchang330063 China College of Information Engineering Nanchang Hangkong University 330063 China

Compressed sensing theory by developing a signal sparse features, under the condition of far less than the Nyquist sampling rate, the correct signal is acquired with random sampling the discrete samples, and then thro... 详细信息

ISBN: (纸本)9781467371896

关键词： Image reconstruction

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：