Infrared thermal image processing method and device

Abstract

The invention discloses an infrared thermal image processing method and device. The method comprises the following steps: obtaining a basic layer image and a detail layer image according to an original image by utilizing a guide filtering algorithm; performing histogram projection compression on the basic layer image; performing halo artifact removal and gain mask enhancement on the detail layer image; fusing the processed basic layer image and the detail layer image; carrying out second-time guide filtering on the fused image; and finally, obtaining an output infrared image with de-noising and detail enhancement. The algorithm provided by the invention is good in real-time performance, can be transplanted into an FPGA (Field Programmable Gate Array) to be realized, can be used as infraredthermal image preprocessing of robot vision navigation, and has wide application value.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an infrared thermal image processing method and device. Background technique [0002] Infrared thermal imaging technology is a technology that converts infrared radiation wave images into visible images. It uses the difference in thermal radiation on the surface of an object due to factors such as temperature and materials to generate image details, so infrared thermal imaging is a passive imaging technology. Its outstanding advantages are: not affected by visible light such as sunlight, strong penetration ability to obstacles such as smoke, almost able to work around the clock, good concealment, strong ability to identify camouflage, and good portability. [0003] It has a wide range of applications in the military field. In recent years, with the improvement of infrared sensor performance and the decline in price, and the demand for infrared thermal imaging technology...

AI Technical Summary

Problems solved by technology

[0004] However, compared with visible light images, infrared images still have defects that cannot be ignored, including: (1) no color and shadow, because it is a grayscale image with low resolution and no stereoscopic effect; (2) low contrast, Affected by factors such as long infrared wavelength and atmospheric attenuation during transmission; (3) The clarity is much lower than that of visible light, which is limited by software and hardware such as technology and device materials; (4) The signal-to-noise ratio is low, which is affected by its own system and external environment various noise effects

These defects not only affect human eye observation, but also largely limit subsequent engineering applications, such as: feature extraction, detection analysis, identification and tracking, etc.

Images