Image generating method, electronic device, and computer-readable storage medium

Abstract

The embodiments of the present application relate to the technical field of image processing, and disclose an image generation method, electronic equipment, and a computer-readable storage medium. The above image generation method includes: judging whether the obtained curve meets the preset line offset curve judgment standard; if the curve meets the preset line offset curve judgment standard, then generating a mapping relationship according to the curve; according to the obtained The original image and the mapping relationship are used to generate a target image corresponding to the original image, wherein there is a row offset represented by the curve between the target image and the original image. The image generation method provided by the embodiment of the present application can simply and quickly obtain a large number of images with line offsets and the line offset curves of the images, effectively reducing the training cost of the model and enriching the training samples of the model at the same time.

Description

technical field [0001] The embodiments of the present application relate to the technical field of image processing, and in particular, to an image generation method, electronic equipment, and a computer-readable storage medium. Background technique [0002] The most dynamic technology branch in the field of machine vision is depth perception technology, and stereo vision technology is an important part of depth perception technology, whether it is active or passive stereo vision research, or traditional algorithms, machine learning and even depth perception technology. The research on the depth restoration algorithm of learning requires the use of a large amount of image data, and the amount of image data is directly related to the training scale of various deep learning models. [0003] In addition to direct collection, image data acquisition methods also include data augmentation and data simulation generation. Image augmentation methods include rotating, zooming, mirrori...

AI Technical Summary

Problems solved by technology

[0004] However, if you want to obtain the line offset data of the image, you need to know the real working conditions of the camera structure and the real influence of temperature on the camera structure, but the real working conditions of the camera structure and the real influence of temperature on the camera structure are very small. Difficult to measure, so the line offset curve of the line image is difficult to obtain, the cost of obtaining training samples is too high, and the richness of the training samples of the model is insufficient, which is not conducive to the training of the model

Images