Image Enhancement-Based Detection with Small Infrared Targets

Today, target detection has an indispensable application in various fields. Infrared small-target detection, as a branch of can improve the perception capability autonomous systems, and it good prospects infrared alarm, automatic driving other There are many well-established algorithms that perform well detection. Nevertheless, current cannot achieve expected effect complex environments, such background clutter, noise inundation or very small targets. We have designed image enhancement-based algorithm to solve both problems through detail enhancement expansion. This method first enhances mutation information, edge information then improves contrast between adjacent pixels make more prominent. The robustness with clutter noise-flooded scenes. Moreover, bicubic interpolation is used on input image, expanded upsampling, which effectiveness for tiny From results qualitative quantitative experiments, proposed this paper outperforms existing work evaluation indicators.