Efficient image correspondence measurements in airborne applications using inertial navigation sensors

This paper presents a computationally efficient method for the measurement of a dense image correspondence vector field using supplementary data from an inertial navigation sensor. The application is suited to airborne imaging systems (such as on a UAV) where size, weight, and power restrictions limit the amount of onboard processing available. The limited processing will typically exclude the use of traditional, but expensive, optical flow algorithms such as Lucas-Kanade. Alternately, the measurements from an inertial navigation sensor lead to a closed-form solution to the correspondence field. Airborne platforms are also well suited to this application because they already possess inertial navigation sensors and global positioning systems (GPS) as part of their existing avionics package. We derive the closed form solution for the image correspondence vector field based on the inertial navigation sensor data. We then show experimentally that the inertial sensor solution outperforms traditional optical flow methods both in processing speed and accuracy.