Many existing methods of object detection, including edge detection, blob detection, and background subtraction (implemented in libraries such as OpenCV) have proven to be enormously successful when applied to many types of video datasets. However, detecting objects over water presents challenges that are unique and not easily accommodated for by pre-existing algorithms available in popular image processing libraries. In this paper, existing approaches are brie y reviewed, and the challenges encountered in above-water video datasets are highlighted. A recently proposed approach to object detection in radar images - a novel, pixel-intensity statistic based thresholding approach | is then reviewed. In this paper, this approach has been successfully applied to EO/IR datasets as well, extending the implementation to ensure success when applied onto other types of image datasets.
Python State Estimation and Modeling Library, pystemlib, is a library that implements Bayesian State Estimation theory for modeling and tracking target objects. This library was developed to overcome the limitations associated with licensed programming languages as well as imperative and numerical matrix-based programming styles that were used in previously developed libraries. pystemlib incorporates object-oriented, functional, and symbolic programming to develop accurate and easy-to-use tracking filters and models. This library is also capable of mapping state estimation results onto the geographical areas to which they correspond. Future work on this library will include optimizing the algorithms for speed and extending the library to incorporate multi-target tracking, data fusion, and image and video processing.