Several assignment methods are compared in terms of problem size, computational complexity and misassignment as a function of sparsity and gating. Specific real world applications include multi-target multi-sensor tra...
详细信息
ISBN:
(纸本)0819424838
Several assignment methods are compared in terms of problem size, computational complexity and misassignment as a function of sparsity and gating. Specific real world applications include multi-target multi-sensor tracking/fusion and resource management with sparse cost matrices. The cost matrix computational complexity is also addressed. Both randomly generated cost matrices and measured data sets are used to test the algorithms. It is shown that, both standard and some new greedy, assignment algorithms significantly degrade in performance with fully gated columns and/or rows. However, it is shown that it is possible to modify specific algorithms to regain the lost optimality.
Continuing dramatic improvements in semiconductor manufacturing processes are enabling radical new signal-processing architectures at the chip level. The development of these new architectures must be coupled, a fusio...
详细信息
Continuing dramatic improvements in semiconductor manufacturing processes are enabling radical new signal-processing architectures at the chip level. The development of these new architectures must be coupled, a fusion, with clearly defined target applications, a thorough analysis of applicable signal processing algorithms, and significant advancements in code-generation technology. The TMS320C6x development program involved the codevelopment of the VelociTI architecture, a new code-generation environment, and a large set of representative benchmarks.
Two major factors that could limit successful implementations of image restoration and superresolution algorithms in missile seeker applications ate, (i) lack of accurate knowledge of sensor point spread function (PSF...
详细信息
ISBN:
(纸本)0819425923
Two major factors that could limit successful implementations of image restoration and superresolution algorithms in missile seeker applications ate, (i) lack of accurate knowledge of sensor point spread function (PSF) parameters, and (ii) noise-induced artifacts in the restoration process. The robustness properties of a recently developed blind iterative Maximum Likelihood (ML) restoration algorithm to inaccuracies in sensor PSF are established in this paper. Two modifications to this algorithm that successfully equip it to suppress artifacts resulting from the presence of high frequency noise components are outlined. Performance evaluation studies with one-dimensional and two-dimensional signals are included to demonstrate that these algorithms have superresolution capabilities while possessing also attractive robustness and artifact suppression properties. The algorithms developed here hence contribute to efficient designs of intelligent integrated processing architectures for smart weapon applications.
In this paper we propose a robust method of data fusion for the classification of multispectral images. The approach is novel in that it attempts to remove blurring of the images in conjunction with fusing the data. T...
详细信息
The potential application of neural networks in manufacturing scenarios is increasingly becoming feasible. Typical of such a manufacturing scenario is the integration of metal cutting sensor signals in pursuance of re...
详细信息
The potential application of neural networks in manufacturing scenarios is increasingly becoming feasible. Typical of such a manufacturing scenario is the integration of metal cutting sensor signals in pursuance of reliable Tool Condition Monitoring (TCM) system. Successful application of this method of sensor integration could save downtime and costs, that would otherwise not have been realized through traditional tool changing philosophies. Unfortunately, the neural network algorithms used have been complicated, requiring detailed sensor signal pre-processing. Partly as a consequence, developed systems have found very limited applications to-date. In this paper, the authors present a simple sensorfusion method via the neural networks approach to the TCM problem. Turning tests were conducted from which the static cutting force, dynamic cutting force and the vibration signature were recorded. The obtained data was used to investigate the classification capability of simple Multi-layer Perceptron (MLP) neural network architectures to the detection of tool wear. Obtained results showed classification accuracy of well over 90% was attainable.
In an era of reduced defense budgets, there is increased pressure to reuse any available technology or capability to the extent possible. For data fusionapplications, this requirement can lead to situations where the...
详细信息
ISBN:
(纸本)0819424838
In an era of reduced defense budgets, there is increased pressure to reuse any available technology or capability to the extent possible. For data fusionapplications, this requirement can lead to situations where the output of disparate individual algorithms would like to be fused;ideally, this would be done in the most quantitative way possible. This paper reviews, integrates, and comments on various prior works in both the data fusion, remote sensing, and character recognition communities which are helpful to the data fusion algorithm/process designer dealing, in particular, with target identification and classification problems. It is shown that generalized voting and rank-based methods may be useful in these cases;the issue of source reliability is also addressed and methods for incorporating assigned reliabilities are described.
Commercially available Digital Signal Processors (DSPs) can be used to host state-of-the-art air acoustic adaptive beamforming algorithms in low power, low cost, real-time sensor systems. These systems are suitable fo...
详细信息
ISBN:
(纸本)081942496X
Commercially available Digital Signal Processors (DSPs) can be used to host state-of-the-art air acoustic adaptive beamforming algorithms in low power, low cost, real-time sensor systems. These systems are suitable for use as both unattended ground sensors and in platform-mounted applications. This:paper describes a compact state-of-the-art, real-time adaptive beamforming approach and sensor hardware. Recent day/night field test results for detection range, multiple target tracking, and classification are presented for various vehicles. The data focuses on long range target detection as well as tracking and classification performance in multiple target environments composed of closely spaced or clustered targets. Target location (x-y position) performance using real-time netted sensors (sensorfusion) is also presented.
The U.S. Army Research Laboratory (ARL) is developing an acoustic target classifier using a backpropagation neural network (BPNN) algorithm. Various techniques for extracting features have been evaluated to improve th...
详细信息
ISBN:
(纸本)081942496X
The U.S. Army Research Laboratory (ARL) is developing an acoustic target classifier using a backpropagation neural network (BPNN) algorithm. Various techniques for extracting features have been evaluated to improve the confidence level and probability of correct identification. Some techniques used in the past include simple power spectral estimates (PSEs), split-window peak-picking, harmonic line association (HLA), principal component analysis (PCA), wavelet packet analysis,(1,2,3,4) and others. In addition, improved results have been obtained when data are combined from other sensors co-located with the acoustic sensor. A three-axis seismic sensor has been configured as part of an acoustic sensor array that ARL uses on typical field experiments, with data collected and sampled simultaneously. The PSE, HLA, and shape statistic feature data are extracted from a group of vehicles and then split into testing and training files. The training file typically consists of 75 percent of the data set, and the performance of the trained neural network is evaluated with the remaining test data. Cross-validation is performed with vehicle data collected at different times of day and under various conditions. Results of the neural network from a few of the feature extraction algorithms under evaluation and from the fusion of the acoustic and seismic sensor data are presented.
The information processing tasks associated with real-time applications (e.g., automatic target recognition, intelligent robotics, information fusion) have very diverse computational requirements that result in differ...
详细信息
The information processing tasks associated with real-time applications (e.g., automatic target recognition, intelligent robotics, information fusion) have very diverse computational requirements that result in different needs for different computing system capabilities. Heterogeneous parallel computing provides a variety of architectural capabilities, orchestrated to perform an application whose tasks have such diverse execution requirements. A key issue that must be addressed in embedding real-time applications on heterogeneous parallel computing architectures is the design of a high-level operating system for selecting algorithms, matching subtasks to processors, and scheduling subtask execution. Essentially, high-level descriptions of an application would be `intelligently executed' by such an operating system. This paper presents on-going research in the development of an Intelligent Operating System, specifically describing the mechanism for the selection of algorithms that functionally satisfy the processing needs of ATR subtasks. The methodology presented here can also be used for other application domains and classes of hardware platforms whose characteristics are similar to those of the applications and platform considered here.
This paper presents an approach to image fusion for concealed weapon detection (CWD) applications. In this work, we use image fusion to combine complementary image information from different sensors to obtain a single...
详细信息
ISBN:
(纸本)0819423440
This paper presents an approach to image fusion for concealed weapon detection (CWD) applications. In this work, we use image fusion to combine complementary image information from different sensors to obtain a single composite image with more detailed and complete information content. As a result of this processing, the new images are more useful for human perception and automatic computer analysis, tasks such as feature extraction and object recognition. In the fusion process, the images are first decomposed based on wavelet transform. Then at each lower resolution the images are fused by using several feature selection algorithms. The final composite image is obtained by taking the inverse wavelet transform of the fused wavelet coefficients. This technique has been applied to real data obtained from IR sensors. Special emphasis is placed on situations when weapons may not be completely visible from the sensors. fusion results thadt demonstrate the utility of our approach are presented.
暂无评论