Infrared and Visible Airborne Targets Image Fusion with Applications to Sense and Avoid

Abstract Machine vision has revealed great potential in recent years for Sense and Avoid (SAA) ability of Unmanned Aerial Vehicle (UAV). However, the target perception capability of machine vision largely depends on illumination, which restricts UAV to move safely in dark environment. Since images acquired by infrared and visible sensors are complementary in most cases, enhancing image qualities in dark environments by fusion of infrared and visible images is a promising solution. By considering the difficulties of image fusion for airborne targets, a Convolutional Sparse Representation (CSR) based infrared and visible airborne targets image fusion algorithm is proposed in this paper for enhancing SAA capability of UAV in dark environments, which contains three parts: image decomposition, image transformation and image reconstruction. A series of registered infrared and visible images containing airborne targets are selected to evaluate the algorithm proposed in this paper. Simulation results demonstrate the algorithm proposed in this paper effectively increases image qualities in dark environments. In the aspects of fusion metrics, the algorithm proposed in this paper can achieve favorable performance against other image fusion algorithms.