When the target is several miles away from the ultra-wide field of view (UWFV) infrared warning system, it will be a
point target in the infrared image, so there is no the target information of distance, geometry and texture without which it
is hard to assess the threat of target accurately. It is very important for the air defense command and decision making to
have a correct threat assessment of the aerial target, and at present there are few reports about the aerial target threat
assessment of the UWFV infrared warning system. The characteristic of the UWFV infrared image is analyzed. A laser
range finder is used to measure the initial distance of each target which will be sent back to the infrared warning system.
Together with the target information of initial distance, gray value, course angle and angular altitude, considering the
nonlinear characteristic of aerial target threat assessment, the threat assessment method based on RBF neural network is
presented for its good self-adaptive and self study ability to solve nonlinear complex problems. After simulation
experiment, it is found that this method is available and effective.