Target Tracking based on Kernelized Correlation Filter Using MWIR and SWIR Sensors

When tracking small UAVs and drone targets in cloud clutter environments, MWIR sensors are often unable to track continuously. To overcome this problem, the SWIR sensor is mounted on same gimbal. Target uses information fusion or selectively applies from each sensor. In case, parallax correction using target distance used. However, it difficult apply existing method because laser rangefinder's beam divergence angle small, making measure distance. We propose a which needs not of sensors. method, images captured simultaneously error for gimbal driving chosen by effectiveness measure. order prove performance was demonstrated real sky background image