检索结果-内蒙古大学图书馆

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

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

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

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

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

3D multipath planning for UAV based on network graph

引用

Journal of Systems Engineering and Electronics 2011年第4期22卷 640-646页

作者： Xin Liu Chengping Zhou Mingyue Ding Institute for Pattern Recognition and Artificial Intelligence Key Laboratory of National Defense Science and Technology forMulti-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan 430074 R R. China School of Life Science and Technology Image Processing and Intelligence Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan 430072 P. R. China

According to the characteristic and the requirement of multipath planning, a new multipath planning method is proposed based on network. This method includes two steps： the construction of network and multipath searching. The construction of network proceeds in three phases： the skeleton extraction of the configuration space, the judgment of the cross points in the skeleton and how to link the cross points to form a network. Multipath searching makes use of the network and iterative penalty method （IPM） to plan multi-paths, and adjusts the planar paths to satisfy the requirement of maneuverability of unmanned aerial vehicle （UAV）. In addition, a new height planning method is proposed to deal with the height planning of 3D route. The proposed algorithm can find multiple paths automatically according to distribution of terrain and threat areas with high efficiency. The height planning can make 3D route following the terrain. The simulation experiment illustrates the feasibility of the proposed method.

关键词： path planning skeleton graph iterative penaltymethod (IPM) network graph.

来源：评论

学校读者我要写书评

暂无评论

A novel search coding method for generic object recognition based on shared features

A novel search coding method for generic object recognition ...

引用

MIPPR 2009 - pattern recognition and Computer Vision: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Zheng, Ping Sang, Nong 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)9780819478078

In this paper, we consider the combined problem of distinguishing classes from the background and from each other, and propose an improved framework based on the previous state-of-the-art approaches. In the process of building ECOC (Error Correcting Output Coding) matrix (also called as sharing matrix), we adopt an encoding rule of one-versus-all, and maximize Hamming distance in categories as far as possible through heuristic search in sharing-code maps (i.e., layer joint boosting). Then the final classifier is responsible for detection, and ECOC matrix for recognition. In order to make full use of the output of the final classifier and its corresponding ECOC matrix, the following measures are worth considering: Firstly, a logistic function of the output mentioned above is used for a posterior probability of each codeword. Therefore the identified class label is the one corresponding to the codeword of Maximum a posteriori (MAP). Secondly, a similarity measurement utilizing the confusion matrix is advanced to focus on the similarities between classes. Thirdly, for the purpose of adaptive adjustment in Hamming distance, we change the subsequent search coding method according to the confusion matrix until the training errors are convergent. The experimental results illustrate the effectiveness of the proposed approach. © 2009 Copyright SPIE - The International Society for Optical Engineering.

关键词： Hamming distance

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

Image compression algorithm using image restoration based on wavelet analysis

Image compression algorithm using image restoration based on...

引用

MIPPR 2009 - Remote Sensing and GIS Data processing and Other Applications: 6th International Symposium on Multispectral Image processing and pattern recognition

作者： Cheng, Zhao Zhang, Tianxu Lu, Haifeng 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)9780819478092

In this paper, we consider lossy image compression, which is based on wavelet theory. We introduce image restoration technology into the wavelet compression. By applying image restoration to the low-frequency component obtained by entropy decoding in decompression process, we retrieve a gained high-frequency component, which is the expression of reconstructed image texture in frequency domain. As a benchmark, the algorithm we present is compared to the traditional wavelet compression. The results of comparative experiments show that our method performs better than traditional algorithms. The PSNR in our method is elevated generally, and the reconstructed image is more texture-richer than the traditional approach without restoration. © 2009 Copyright SPIE - The International Society for Optical Engineering.

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：