IR image databases generation under target intrinsic thermal variability constraints
This work addresses the need for large, realistic infrared image databases for objective ATR assessment in military or surveillance domains, but it appears incremental as it builds on existing methods for image generation and thermal variability modeling.
The paper tackles the problem of generating infrared image databases for automatic target recognition assessment by proposing methods to superimpose targets and occultants on backgrounds under image quality constraints and to generate target signatures with intrinsic thermal variability using 3D models and real infrared textures, resulting in realistic images for quantitative performance evaluations.
This paper deals with the problem of infrared image database generation for ATR assessment purposes. Huge databases are required to have quantitative and objective performance evaluations. We propose a method which superimpose targets and occultants on background under image quality metrics constraints to generate realistic images. We also propose a method to generate target signatures with intrinsic thermal variability based on 3D models plated with real infrared textures.