Sensor fusion potential exploitation - Innovative architectures and illustrative applications

被引:298
作者
Dasarathy, BV
机构
[1] Dynetics, Inc., Huntsville, AL
关键词
D O I
10.1109/5.554206
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Sensor fusion models have been characterized in the literature in a number of distinctly different ways: in terms of information levels at which the fusion is accomplished; the objectives of the fusion process, the application domain; the types of sensors employed, the sensor suite configuration and so on. The characterization most commonly encountered in the rapidly growing sensor fusion literature based on level of detail in the information is that of the now well known triplet: data level, feature level, and decision level. We consider here a generalized input-output (I/O) descriptor pair based characterization of the sensor fusion process that can be looked upon as a natural out growth of the trilevel characterization. The fusion system design philosophy expounded here is that an exhaustive exploitation of the sensor fusion potential should explore fusion under all of the different I/O-based fusion modes conceivable under such such a characterization. Fusion system architectures designed to permit such exploitation offer the requisitc flexibility for developing the most effective fusion system designs for a given application. A second facet of this exploitation is aimed at exploring the new concept of self-improving multisensor fusion system architectures, wherein the central (fusion system) and local (individual sensor subsystems) decision makers mutually enhance the other's performance by providing reinforced learning. A third facet is that of investigating fusion system architectures for environments wherein the different local decision makers may only be capable of narrower decisions that span only a subset of decision choices. The paper discusses these flexible fusion system architectures along with related issues and illustrates them with examples of their application to real-world scenarios.
引用
收藏
页码:24 / 38
页数:15
相关论文
共 20 条
[1]   LEARNING WITH A PROBABILISTIC TEACHER [J].
AGRAWALA, AK .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1970, 16 (04) :373-+
[2]  
Clark JJ, 1990, Data fusion for sensory information processing systems
[3]  
Dasarathy B.V., 1994, DECISION FUSION
[4]   SEQUENTIAL LEARNING EMPLOYING UNFAMILIAR TEACHER HYPOTHESIS (SLEUTH) WITH CONCURRENT ESTIMATION OF BOTH PARAMETERS AND TEACHER CHARACTERISTICS [J].
DASARATHY, BV ;
LAKSHMINARASIMHAN, AL .
INTERNATIONAL JOURNAL OF COMPUTER & INFORMATION SCIENCES, 1976, 5 (01) :1-7
[5]   Adaptive fusion processor paradigms for fusion of information acquired at different levels of detail [J].
Dasarathy, BV .
OPTICAL ENGINEERING, 1996, 35 (03) :634-649
[6]   Fusion strategies for enhancing decision reliability in multisensor environments [J].
Dasarathy, BV .
OPTICAL ENGINEERING, 1996, 35 (03) :603-616
[7]   LEARNING UNDER A VEDIC TEACHER [J].
DASARATHY, BV ;
LAKSHMINARASIMHAN, AL .
INTERNATIONAL JOURNAL OF COMPUTER & INFORMATION SCIENCES, 1979, 8 (01) :75-88
[8]   Fusion strategies for deployment of binary-decision sensors in multi-choice decision environments [J].
Dasarathy, BV .
SIGNAL PROCESSING, SENSOR FUSION, AND TARGET RECOGNITION V, 1996, 2755 :206-217
[9]   Fuzzy evidential reasoning based decision fusion [J].
Dasarathy, BV .
APPLICATIONS OF FUZZY LOGIC TECHNOLOGY III, 1996, 2761 :29-40
[10]  
DASARATHY BV, 1992, 11TH IAPR INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, PROCEEDINGS, VOL II, P500, DOI 10.1109/ICPR.1992.201827