Visibility improvement of aerial imagery by a locally tuned nonlinear enhancement technique

This paper presents the effectiveness of locally tuned sine nonlinear (LTSN) image enhancement technique on poor contrast and low quality images that exhibit dark shadows and over exposed regions due to the limited dynamic ranges of imaging and display devices. We use a wide area motion imagery data [1] to evaluate the performance of the LTSN method. A quantitative evaluation is performed by estimating the number of Harris corners and Speeded Up Robust Features (SURF) in the enhanced images and compared the performance with other state of the art methods. The evaluation results confirms that the LTSN method can be applied as a preprocessing technique for object detection, tracking and recognition in wide area motion imagery.