Real-Time Algorithms And Systems For Fused True Color Night Vision Imagery.

The proposal addresses the need for better multi-camera night vision fusion (e.g., low-light-level visible or SWIR with thermal infrared) through the development of systems that produce true-color output in real-time. Fusion algorithms demonstrated in Phase I will be made fully functional in Phase II, and prototype systems will be developed to work out practical issues and more quickly transition the technology into the field. Two different modalities have been developed to obtain the color information. One mode uses a knowledge based material identification algorithm adapted specifically for night vision imagery, and the other uses color values obtained from a true-color night vision camera. In addition to color values, in both cases, the images from the multiple cameras must be fused together in an optimal manner to provide brightness detail that improves scene understanding and object identification. The approach builds on previous OKSI work in true-color night vision, multispectral image processing, infrared scene rendering, and multi-camera fusion. It moves beyond the current state of the art by using innovative algorithms that enable efficient and invariant scene rendering in an actual embedded device.