A hierarchical structure approach to MultiSensor Information Fusion
- Tennessee Univ., Tullahoma, TN (United States). Space Inst.
- Accurate Automation Corp., Chattanooga, TN (United States)
A major problem with image-based MultiSensor Information Fusion (MSIF) is establishing the level of processing at which information should be fused. Current methodologies, whether based on fusion at the pixel, segment/feature, or symbolic levels, are each inadequate for robust MSIF. Pixel-level fusion has problems with coregistration of the images or data. Attempts to fuse information using the features of segmented images or data relies an a presumed similarity between the segmentation characteristics of each image or data stream. Symbolic-level fusion requires too much advance processing to be useful, as we have seen in automatic target recognition tasks. Image-based MSIF systems need to operate in real-time, must perform fusion using a variety of sensor types, and should be effective across a wide range of operating conditions or deployment environments. We address this problem through developing a new representation level which facilitates matching and information fusion. The Hierarchical Scene Structure (HSS) representation, created using a multilayer, cooperative/competitive neural network, meets this need. The MSS is intermediate between a pixel-based representation and a scene interpretation representation, and represents the perceptual organization of an image. Fused HSSs will incorporate information from multiple sensors. Their knowledge-rich structure aids top-down scene interpretation via both model matching and knowledge-based,region interpretation.
- Research Organization:
- Tennessee Univ., Tullahoma, TN (United States). Space Inst.; Accurate Automation Corp., Chattanooga, TN (United States)
- Sponsoring Organization:
- USDOE; National Science Foundation (NSF); USDOE, Washington, DC (United States); National Science Foundation, Washington, DC (United States)
- DOE Contract Number:
- FG07-88ER12824
- OSTI ID:
- 6855099
- Report Number(s):
- CONF-8903223-1; ON: DE93002956; CNN: EET8901748
- Resource Relation:
- Conference: 2. sensor fusion conference, Orlando, FL (United States), 28-29 Mar 1989
- Country of Publication:
- United States
- Language:
- English
Similar Records
A hierarachical data structure representation for fusing multisensor information
A hierarachical data structure representation for fusing multisensor information