检索结果-内蒙古大学图书馆

conference on sensor fusion: architectures, algorithms, and applications IV

作者： Sintes, C Solaiman, B GESMA F-29240 Brest France

ISBN: (纸本)0819436771

This paper concerns the possibilities of sea bottom imaging and altitude determining of each imaged point. The performances of new side scan sonars which are able to image the sea bottom with a high definition and are able to evaluate the relief with the same definition derived from an interferometric multisensor system. The drawbacks concern the precision of the numerical altitude model. One way to improve the measurements precision is to merge all the information issued from the multi-sensors system. This leads to increase the Signal to Noise Ratio (SNR) and the robustness of the used method. The aim of this paper is to clearly demonstrate the ability to derive benefits of all information issued from the three arrays side scan sonar by merging : a. the three phase signals obtained at the output of the sensors, b. this same set of data after the application of different processing methods, and c, the a priori relief contextual information. The key idea the proposed fusion technique is to exploit the strength and the weaknesses of each data element in the fusion of process so that the global SNR will be improved as well as the robustness to hostile noisy environments.

关键词： Interferometry Image fusion sensors Electronic filtering Data fusion Image filtering Signal to noise ratio Gaussian filters Signal processing Wavefronts

来源：评论

学校读者我要写书评

暂无评论

Edge detection through information fusion using fuzzy and evidential reasoning concepts

Edge detection through information fusion using fuzzy and ev...

引用

conference on sensor fusion: architectures, algorithms, and applications IV

作者： Solaiman, B Lecornu, L Roux, C ENST Bretagne Dpt ITI F-29285 Brest France

ISBN: (纸本)0819436771

The main topic of this study concerns edge detection using information fusion approaches. Edge detection methods are based on first and second order local operations followed by a thresholding and edge tracking techniques. In this study, an intermediate fuzzy-evidential conceptual level is introduced between the gray level and edge detection symbolic information level. From the image, evidences concerning edges and regions are extracted using fuzzy membership functions as well as contextual information. The proposed approach can be decomposed into two steps: 1) application of evidential reasoning approach in order to compute a basic masse function, 2) edge detection process based on the use of an iterative algorithm, exploiting the contextual information and a belief masse function. Masse function computation is based of the use of edge and region fuzzy membership functions of each pixel in the analyzed scene. The main interest of this step is to consider membership functions as being observed evidences instead of image gray level values. The key idea of the second step is to use all the information about regions, edges and contextual data in the edge extraction process. Obtained results are encouraging and the proposed methodology is shown to be robust to different noisy environments.

关键词： evidential reasoning fuzzy edge detection evidential fusion information fusion

来源：评论

学校读者我要写书评

暂无评论

Decision forgetting and decision smoothing for diagnostic decision fusion in systems with redundant information

Decision forgetting and decision smoothing for diagnostic de...

引用

conference on sensor fusion: architectures, algorithms, and applications IV

作者： Goebel, K GR Corp Res & Dev Niskayuna NY 12309 USA

ISBN: (纸本)0819436771

This paper introduces techniques to deal with temporal aspects of fusion systems with redundant information. One of the challenges of a fusion system is that individual information is not necessarily announced at the same time. While some decisions (or features or data) are produced at a high sampling frequency, other decisions are generated at a much lower rate, perhaps only once during the operation of the system or only during certain operating conditions. This means that some information will be outdated when the actual information fusion task is performed. An event may have occurred in the meantime leading to a decision discord. We tackle this challenge by introducing the concept of "information or decision forgetting". In other words, in case of an information discord, more recent information is evaluated with higher confidence than older information. Another difficulty is distinguishing between outliers and actual system state changes. If tools perform their task at a high sampling frequency we can employ "decision smoothing". That is, we factor out the occasional outlier and generally reduce the noise of the system. To that end, we introduce an adaptive smoothing algorithm that evaluates the system state and changes the smoothing parameter if it encounters suspicious situations, i.e., situations that might indicate a changed system state. We show the concepts introduced in the diagnostic realm where we aggregate the output of several different diagnostic tools.

关键词： diagnostic information fusion decision forgetting decision smoothing diagnosis classification decision making

来源：评论

学校读者我要写书评

暂无评论

Finite band-depth information extraction

Finite band-depth information extraction

引用

conference on sensor fusion: architectures, algorithms, and applications IV

作者： Miettinen, K Bailey, J Eastman Kodak Co Rochester NY 14653 USA

ISBN: (纸本)0819436771

We present a system for extraction of information bands from imagery that combines properties of subband/wavelet decomposition and factor analysis to achieve uniform presentations of ground truth from a variety of sensor inputs. Some unique information-regularizing features of the system are invariance to scaling, sorting, and skewing of the input data, as well as robustness to blurring or sharpening, nonlinear intensity remapping, and to the differences between literal and nonliteral input imagery. These features enhance both visual interpretability of an RGB color image and machine exploitability of regularized information bands. Three specific problems in multi-modality data fusion addressed by our information extraction technology are: How to display three bands of color information on an RGB output device given an arbitrarily large number of bands of source data. How to display literal and specular imagery, e.g., infrared and synthetic aperture radar (SAR), together in a single fused image without prior knowledge of which source image bands come from what sensors. How to present regularized inputs to an automated imagery exploitation algorithm without prior knowledge of the available sensors. Our method for solving these three problems stems from an information theoretic treatment of the image fusion problem: treating the derived final exploitation product with constrained band depth (e.g., three bands for color imagery or perhaps ten to twelve bands for automated exploitation) as a communication channel, and coding information from the multi-modal image stack onto the channel, subject to statistical constraints corresponding to an a priori image model. New methods and results introduced in this work are: A novel directional wavelet methodology producing six complex-valued subbands per level of decomposition. Application of factor analysis to multi-band inter-sensor analysis of covariance. An extension of traditional factor analysis to augment the vector of spe

关键词： sensor fusion image fusion factor analysis principal component wavelet subband decomposition

来源：评论

学校读者我要写书评

暂无评论

Self-organized integration of adaptive visual cues for face tracking

Self-organized integration of adaptive visual cues for face ...

引用

conference on sensor fusion: architectures, algorithms, and applications IV

作者： Triesch, J Univ Rochester Dept Comp Sci Rochester NY 14627 USA

ISBN: (纸本)0819436771

The integration of information stemming from different sensors, cues, or modalities is among the most fundamental problems of perception in biological and artificial systems. Due to frequent changes in complex environments, the integration has to be adaptive. However, there usually is no teacher available to guide the adaptation. An agent has to figure out on his own which cues are reliable for a given task in the current context - self-organization is required. We have recently proposed a new integration scheme for such situations(1,2): In "Democratic Integration" the cues agree on a result and the result agreed upon serves as the basis for individual adaptations. A system with this property will automatically try to keep maximal coherence among its different cues. A technical formulation of this scheme has been employed in a face tracking system. The self-organized adaptation leads to suppression and recalibration of discordant cues, i.e., cues which do not agree with the overall result. Experiments show that the system is robust to sudden changes in the environment as long as the changes disrupt only a minority of the currently used cues at the same time, although all cues may be affected in the long run. The system relies partly on cues for which there was no a priori knowledge about the task available. These cues are bootstrapped by the others and can then keep the system on the right track during situations in which the original cues fail. In this paper we test and compare different measures of agreement between the overall result and individual cues' opinions, which serve as the basis for adapting a cue's weight in computing the overall result. Our results suggest, that adjusting a cue's weight in accordance to its current agreement to the overall result can only help if there is sufficient continuity in the cue's performance and may even be harmful otherwise.

关键词： computer vision sensor fusion sensory integration face tracking face detection self-organization adaptation Democratic Integration

来源：评论

学校读者我要写书评

暂无评论

sensor fusion: architectures, algorithms and applications iii

Sensor Fusion: Architectures, Algorithms and Applications II...

引用

1999年

作者： Belur V Dasarathy

来源：评论

学校读者我要写书评

暂无评论

Multifeature fusion using Pulse Coupled Neural Networks

Multifeature fusion using Pulse Coupled Neural Networks

引用

conference on sensor fusion - architectures, algorithms, and applications iii

作者： Inguva, R Johnson, JL Schamschula, MP East West Enterprises Huntsville AL 35805 USA

We propose an unbiased multifeature fusion Pulse Coupled Neural Network (PCNN) algorithm. The method shares linking between several PCNNs running in parallel. We illustrate the PCNN fusion technique with a clean and n... 详细信息

ISBN: (纸本)0819431931

关键词： Image fusion Neural networks Image processing Modulators Convolution Evolutionary algorithms Feature extraction Modulation Pulse generators Transform theory

来源：评论

学校读者我要写书评

暂无评论

sensor management in an ASW data fusion system

引用

Proceedings of SPIE - The International Society for Optical Engineering 1999年 3719卷 418-429页

作者： Penny, Dawn E. Defence Evaluation and Research Agency Worcestershire United Kingdom

The Multi-sensor fusion Management (MSFM) algorithm is extended to admit a richer variety of behavior. More realistic sensor characteristic models are used such as detection-plus-bearing sensors and false alarm probabilities commensurate with actual sonar sensor systems. The performance of the modified MSFM algorithm is illustrated on a realistic anti-submarine warfare (ASW) application.

关键词： sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Virtual associative networks: a new paradigm for sensor fusion

引用

Proceedings of SPIE - The International Society for Optical Engineering 1999年 3719卷 43-50页

作者： Malhotra, Raj P. Yufik, Yan M. Air Force Research Lab Wright-Patterson Air Force Base United States

We discuss Virtual Associative Networks (VANs) and their relevance for addressing computationally prohibitive sensor fusion problems (with results in Dynamic sensor Management). To our knowledge, this discussion of VAN technology for sensor fusion is unique and our current result involving VANs for Dynamic sensor Management is the first of its kind. The following provides methodology, results, and extensions.

关键词： sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

Feature and data level fusion of infrared and visual images

Feature and data level fusion of infrared and visual images

引用

conference on sensor fusion - architectures, algorithms, and applications iii

作者： Ulug, ME McCullough, CL Intelligent Neurons (United States) U.S. Army Space and Missile Defense Command (United States)

ISBN: (纸本)0819431931

In both military and civilian applications, increasing interest is being shown in fusing infrared and vision images for improved situational awareness. In previous work, the authors have developed a fusion method for combining the thermal and vision images into a single image emphasizing the most salient features of the surrounding environment. This approach is based on the assumption that although the thermal and vision data are uncorrelated, they are complementary and can be fused using a suitable disjunctive function. This paper, as a continuation of that work, will describe the development of an information based real-time data level fusion method. In addition, applicability of the algorithms thar we developed for data level fusion to feature level techniques (e.g., shapes, lines, and edges) will be investigated.

关键词： data level fusion sensor fusion infrared

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：