Title :
Computer Tracking of Moving Point Targets in Space
Author_Institution :
Aeronutronic Division, Ford Aerospace and Communications Corporation, Newport Beach, CA 92663; The Aerospace Corporation, P.O. Box 92957, Los Angeles, CA 90009.
Abstract :
An adaptive algorithm based on the maximum likelihood ratio is described in this correspondence. The algorithm detects low-intensity targets and tracks their paths. The charged-coupled device (CCD) mosaic sensor collects photons from the targets and the sky background. The algorithm computes the noise statistics, simulates the target pattern, correlates the received data with the target patterns, compares with the corresponding threshold, and prints out the positions and paths of the targets when present.
Keywords :
Graphics; Histograms; Image edge detection; Image processing; Image segmentation; Pattern recognition; Relaxation methods; Robustness; Smoothing methods; Target tracking; Computer tracking; moving objects; pattern recognition; statistical inference;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.1981.4767153