Enhancement of Thermal Imagery Using a Low-Cost High-Resolution Visual Spectrum Camera for Scene Understanding

Smith, R., Anderson, D., Bethel, C. L., & Archibald, C. (2017). Enhancement of Thermal Imagery Using a Low-Cost High-Resolution Visual Spectrum Camera for Scene Understanding. Proceedings of SPIE Defense + Commercial Sensing Expo in the Infrared Technology and Applications XLIII Track. Anaheim, CA: SPIE.

Abstract

Thermal cameras are used in numerous computer vision applications such as human detection and scene understanding. However, the cost of high quality and high resolution thermal sensors is often a limiting factor. Conversely, high resolution visual spectrum cameras are readily available and generally inexpensive. Herein, we explore the creation of higher quality upsampled thermal imagery using a high resolution visual spectrum camera and Markov random field theory. This paper also presents a discussion of the tradeoffs and effects of the upsampling, both quantitatively and qualitatively. Our results demonstrate the successful use of this approach for human detection and accurate propagation of thermal measurements within the image for more general tasks like scene understanding. Tradeoff analyses of the cost to performance as the resolution of the thermal camera decreases are provided.