Guided filtering weighted aggregation method and system based on FPGA (Field Programmable Gate Array)

Abstract

The invention provides an FPGA-based guided filtering weighted aggregation method and system, and the method comprises the following steps: S1, carrying out the processing of an image through guided filtering noise reduction, and obtaining a linear regression coefficient of a neighborhood block of a pixel point; and S2, respectively configuring weights for neighborhoods with different pixel points according to the linear regression coefficient, and carrying out weighted aggregation on new weights to generate a denoised image. According to a new weighted aggregation method in the guided filtering process, a halo artifact phenomenon generated in the local smoothing process is solved or relieved by adopting a corrected weight for an edge contour or a flat area in the image, meanwhile, the edge is effectively kept, a good smoothing and noise reduction effect can also be achieved in the area of the edge contour of the image, and the image quality is improved. And the image visual display effect is improved.

Description

technical field [0001] The present invention relates to the field of image processing technology, in particular to an FPGA-based guided filtering weighted aggregation method and system. Background technique [0002] With the popularization and application of video surveillance cameras, especially in the application scenarios of dark night scenes, long-distance observation and personnel temperature measurement, the application of infrared thermal imaging cameras is becoming more and more extensive. The imaging quality of infrared thermal imaging cameras has attracted much attention, but due to The thermal imaging camera’s detector manufacturing process, electronic circuit and other noise causes cause the video image output by thermal imaging to be noisy, while the general traditional filter noise reduction algorithms, such as mean filter, median filter, and Gaussian filter, are not effective in noise reduction. Ideal or blurred image edge outlines. However, bilateral filteri...

AI Technical Summary

Problems solved by technology

Compared with image filtering algorithms such as mean filtering and Gaussian filtering, the guided filtering image algorithm is an edge-preserving filtering algorithm, but as a local filter, guided image filtering has the problem of halo artifacts. Circle artifact outline, seriously affecting the visual effect

[0007] At the same time, when this filtering algorithm calculates the output of each pixel, it needs to go through the process of calculating the linear model parameters multiple times in multiple adjacent neighborhoods centered on the current pixel, and then multiplying, accumulating, summing, averaging, etc., and adjacent The larger the radius of the domain window, the longer the calculation time in the neighborhood, the greater the image output delay, and the more hardware resources are consumed, and it cannot be applied to our display devices in real time

Images