INFRARED IMAGE ENHANCEMENT ALGORITHM BASED ON NONLINEAR TRANSFORMATION AND MULTI-SCALE DETAIL ENHANCEMENT

In a completely dark or enclosed imaging environment, the infrared image collected in the tank has problems such as low resolution, poor contrast, and noise. Aimed at the characteristics of the infrared image in the tank, an infrared image enhancement algorithm based on nonlinear transformation and multi-scale detail enhancement is proposed. The brightness of the infrared image was improved by adaptive nonlinear transformation, and the image was decomposed into base and detail layers through multi-scale filtering. The base layer and the detail layer were processed by different methods and merged into a detail image to achieve the effect of enhancing image detail information and contrast. The brightness map and the detail map were processed by linear fusion to obtain a high-quality image. Experimental results show that the algorithm not only improves the brightness of the image, but also enhances the image contrast, highlights the texture details, significantly improves the sense of hierarchy, and has better visual effects.