Quantitative analysis of the improvement in high zoom maritime tracking due to real-time image enhancement

This work aims to evaluate the improvement in the performance of tracking small maritime targets due to real-time enhancement of the video streams from high zoom cameras on pan-tilt pedestal. Due to atmospheric conditions these images can frequently have poor contrast, or exposure of the target if it is far and thus small in the camera’s field of view. A 300mm focal length lens and machine vision camera were mounted on a pan-tilt unit and used to observe the False Bay near Simon’s Town, South Africa. A ground truth data-set was created by performing a least squares geo-alignment of the camera system and placing a differential global position system receiver on a target boat, thus allowing the boat’s position in the camera’s field of view to be determined. Common tracking techniques including level-sets, Kalman filters and particle filters were implemented to run on the central processing unit of the tracking computer. Image enhancement techniques including multi-scale tone mapping, interpolated local histogram equalisation and several sharpening techniques were implemented on the graphics processing unit. This allowed the 1.3 mega-pixel 20 frames per second video stream to be processed in real-time. A quantified measurement of each tracking algorithm’s robustness in the presence of sea-glint, low contrast visibility and sea clutter- such as white caps is performed on the raw recorded video data. These results are then compared to those obtained using data enhanced with the algorithms described