Despite recent advances, customized multispectral cameras can be challenging or costly to deploy in some use cases. Complexities span electronic synchronization, multi-camera calibration, parallax and spatial coregistration, and data acquisition from multiple cameras, all of which can hamper their ease of use. This paper discusses a generalized procedure for multispectral sensing using a pixelated polarization camera and Solc stages to create multivariate optical filters. We then describe some preliminary experimental results of a fabricated filtered camera system. Finally, classification of the imagery is achieved using either shallow or deep neural networks. We also discuss the potential of using a color red, green, and blue microgrid polarization camera to detect upwards of 12 spectral channels using readily available standard off-the-shelf components.
|