Thermal fluid image processing method and system, terminal and medium

Abstract

The invention provides a thermal fluid image processing method and system, and the method comprises the steps: firstly extracting the features of a histogram of oriented gradients, then calculating the feature difference of the histogram of oriented gradients, and then carrying out the binarization, segmentation, contour extraction and other operations. The method comprises an algorithm for correcting and updating a dynamic background. Meanwhile, the invention provides a corresponding terminal and a medium. The difference between the target area to be detected and the background area can be increased by extracting the histogram characteristics of the oriented gradients of the target area to be detected and the background area. The invention can be applied to the field of thermal fluid image processing, target identification, edge detection and segmentation are performed on the to-be-detected area and the background area, the nvention has advantages under the conditions that the difference between the to-be-detected target and the background is small and the background changes along with frames, and the invention is low in parameter setting sensitivity and good in universality. The invention can be oriented to different cases, working conditions and optical systems, programs are easy to implement, the processing speed is high, and results are accurate and reliable.

Description

technical field [0001] The present invention relates to the technical field of thermal fluid image processing, in particular to a thermal fluid image processing method, system, terminal and medium based on directional gradient histogram features. Background technique [0002] The experimental data of thermal fluid based on optical diagnostic technology is not only helpful to the mechanism research of thermal fluid, but also has great significance for the establishment and calibration of simulation models. A variety of optical measurement methods have been developed and applied to the research on the relevant properties of thermal fluids, and have been widely used in constant volume incendiary bombs, optical engines, shock tubes and fast presses to measure the macroscopic and microscopic properties of thermal fluids. Including but not limited to Mie scattering, backlight method, shadow method, schlieren method, laser-induced fluorescence, ultraviolet / visible absorption and sc...

AI Technical Summary

Problems solved by technology

However, under high ambient pressure and high ambient density (such as engine-like operating conditions), the temporal and spatial changes in the environmental density gradient will be converted into texture changes in the image, and the texture of the ambient gas will become a complex background noise that changes over time. It makes the image difficult to identify and segment, which greatly increases the difficulty of target recognition, edge detection, image segmentation, and contour extraction. In this case, only subtracting the image to be detected and the background image and selecting the threshold will not be able to obtain the required effect, so it is necessary to develop better image segmentation methods

However, the currently developed processing methods for thermal fluid image segmentation have more or less problems and shortcomings: (1) There are many steps, and the processing process is complicated and not simple enough; (2) In each step, there are artificial The set thresholds, correction factors, etc. are not convenient enough; (3) the processing results are very sensitive to the selection of thresholds and other parameters, and unsatisfactory results will be obtained if there is a slight improper setting; (4) many methods can only deal with the background Relatively clean or a little noisy but not obvious (environmental density 10kg / m 3 In the case of the following), when the intensity difference between the area to be detected and the background area is not obvious, the identified boundary will be blurred; (5) the developed method works well when dealing with a certain case and working condition, but the change An environment, working condition, and optical system will have poor processing effects, and it is necessary to re-determine the threshold and some artificially set parameters, which is not versatile enough; (6) For images with high background noise or background changes with frames, the processing effect Average, poor accuracy

[0004] In summary, the existing thermal fluid image processing methods have problems such as complicated steps, inconvenient, insufficient versatility, and poor accuracy of processing effects. At present, no description or report of similar technology to the present invention has been found, nor has it been collected at home and abroad. similar information

Images