Accession Number:

ADA576440

Title:

Predicting the Probability of Target Detection in Static Infrared and Visual Scenes Using the Fuzzy Logic Approach

Descriptive Note:

Corporate Author:

TACOM RESEARCH DEVELOPMENT AND ENGINEERING CENTER WARREN MI

Personal Author(s):

• Meitzler, Thomas J.
• Singh, Harpreet
• Arefeh, Labib
• Gerhart, Grant R.
• Sohn, Euijung

Report Date:

1997-10-07

Pagination or Media Count:

16.0

Abstract:

The probability of detection PD of targets in static infrared and visually cluttered scenes is computed using the Fuzzy Logic Approach FLA. The FLA is presented as a robust method for the computation and prediction of the PD targets in cluttered scenes. The MamdaniAssilian, and Sugeno Neurofuzzy-based models have been investigated. A large set of infrared IR imagery and a limited set of visual imagery has been used to model the relationships between several input parameters the contrast, camouflage condition,range, aspect, width and experimental PD. The fuzzy and neuro-fuzzy models gave predicted PD values that had 0.98 correlation to the experimental PDs. The results obtained indicate the robustness of the fuzzy-based modeling techniques and the applicability of the FLA to those types of problems having to do with the modeling of human-in-the-loop target detection in any spectral regime.

Descriptors:

• *FUZZY LOGIC
• *TARGET DETECTION
• CLUTTER
• INFRARED IMAGES
• TARGET ACQUISITION
• VISION

Subject Categories:

• Statistics and Probability
• Target Direction, Range and Position Finding

Distribution Statement:

APPROVED FOR PUBLIC RELEASE