Visual image intelligent acquisition method and platform

Abstract

The invention relates to the technical field of image acquisition, in particular to a visual image intelligent acquisition method and platform. The method comprises the steps of collecting a target image, obtaining the light ratio degree of the target image, and judging whether a collected scene is a large-light-ratio scene; when the collection scene is a large-light-ratio scene, obtaining the accumulation degree of pixel values according to the number of the pixel values in the dark area of the gray histogram of the target image, screening accumulated pixel points to form a plurality of connected domains, and obtaining segmented images; obtaining change pixels in the connected domains, and obtaining a first level submerging degree of the segmented image according to the quantitative proportion of the change pixels in each connected domain in all stacked pixel points; similarly, obtaining a second level submerging degree corresponding to a bright region of the gray histogram of the target image; further obtaining the overflow degree; and adjusting parameters of the acquisition equipment according to the overflow degree and the latitude to obtain an acquired image. According to the method of the invention, the parameters of the acquisition equipment can be adaptively adjusted, and the acquired image with ideal quality is obtained.

Description

technical field [0001] The invention relates to the technical field of image acquisition, in particular to a method and platform for intelligent acquisition of visual images. Background technique [0002] In the process of image acquisition, there is often a certain difference between the captured image and the scene seen by the human eye. This is because the tolerance of the human eye is much higher than that of digital equipment. For the human eye, details in bright and dark areas can be seen clearly. However, for cameras with limited latitude, only certain trade-offs can be made, so that there are certain differences between the captured image and the scene observed by human eyes. [0003] At the same time, in a high light ratio environment, it is easy to make the imaging of the scene exceed the latitude of the camera. The bright area becomes white due to overexposure, and the dark area becomes black due to underexposure, and the details corresponding to the bright and da...

AI Technical Summary

Problems solved by technology

[0002] In the process of image acquisition, there is often a certain difference between the captured image and the scene seen by the human eye. This is because the tolerance of the human eye is much higher than that of digital equipment. For the human eye, details in bright and dark areas can be seen clearly. However, for cameras with limited latitude, only certain trade-offs can be made, so that there is a certain difference between the captured image and the scene observed by human eyes

[0003] At the same time, in a high light ratio environment, it is easy to make the imaging of the scene exceed the latitude of the camera. The bright area becomes white due to overexposure, and the dark area becomes black due to underexposure, and the details corresponding to the bright and dark areas are lost. The image carries missing information, and the image quality is poor. If the image is collected according to the general method, a suitable image cannot be collected

Images