Histogram equalization method for infrared image

Abstract

The embodiment of the invention discloses a histogram equalization method for an infrared image. The histogram equalization method for the infrared image comprises the following steps: reading the infrared image; segmenting the infrared image into at least two sub-images; performing histogram equalization processing on each sub-image to obtain at least two histogram equalization sub-images; stitching the histogram equalization sub-images. According to the method provided by the embodiment of the invention, segmentation processing is performed on the infrared image to obtain the multiple sub-images, and moreover, platform histogram equalization enhancement is performed on each sub-image, and then, the sub-images after being subjected to histogram equalization are stitched to be fused into the final histogram equalized infrared image, and thus, when the histogram equalization processing is performed, parallel processing can be performed on the multiple sub-images; then, fusion processing is performed on the image, so that the processing speed of the image is greatly quickened.

Description

[0001] technical field [0002] The invention relates to the technical field of infrared image processing, in particular to a histogram equalization method of an infrared image. [0003] Background technique [0004] Due to the imaging characteristics of the system itself during the imaging process of the infrared imaging system, the resulting image has the characteristics of low signal-to-noise ratio, low contrast, and almost no texture information. Therefore, in order for the human eye to obtain the visual information in the infrared image, a series of processing needs to be performed on the infrared image, including: image non-uniformity correction, blind pixel compensation, image enhancement, etc. [0005] There are many methods of infrared image enhancement, which can be divided into: [0006] (1) Spatial domain processing: directly process the grayscale of infrared images. Common methods include: spatial domain filtering, grayscale linear stretching, histogram equali...

AI Technical Summary

Problems solved by technology

[0008] (3) Transformation domain processing: This method first transforms the infrared image into a specific transformation domain, then performs calculations on the values ​​in the transformation domain, and then obtains the enhanced infrared image through inverse transformation. Commonly used transformation domains include Fourier transform , discrete cosine transform, wavelet transform, etc. This technique is computationally complex and consumes a lot of system resources

[0009] When processing the infrared image enhancement algorithm for the FPGA, due to the need to process a frame of infrared image point by point, the speed of infrared image enhancement is greatly reduced, and the display speed of infrared images is also greatly reduced.

Moreover, for complex multi-target processing, due to the large number of targets, the traditional infrared histogram equalization will cause the stretching range of a single target image to be too narrow and cannot be displayed in detail

Images