Title :
A systems approach to data fusion
Author :
Kerrow, Phillip John M ; Volk, Sandra Joy
Author_Institution :
Dept. of Comput. Sci., Wollongong Univ., NSW, Australia
Abstract :
Data fusion is the process of combining signals from several sensors into a single world view. A four-level software architecture provides a generalised framework for designing data fusion systems. Important issues in data fusion are feature extraction, closure criteria, paradigm shifts between levels, error correction and knowledge engineering. Each of these is discussed in the context of a data fusion system for ultrasonic mapping with a mobile robot
Keywords :
distance measurement; feature extraction; mobile robots; sensor fusion; software engineering; ultrasonic transducers; closure criteria; data fusion; error correction; feature extraction; four-level software architecture; knowledge engineering; mobile robot; paradigm shifts; systems approach; ultrasonic mapping; Acoustic sensors; Computer architecture; Computer science; Mobile robots; Robot kinematics; Robot sensing systems; Sensor fusion; Sensor systems; Signal processing; Software architecture;
Conference_Titel :
Data Fusion Symposium, 1996. ADFS '96., First Australian
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-3601-1
DOI :
10.1109/ADFS.1996.581109
