Image processing method and device

Abstract

The invention relates to the field of digital image processing, and especially relates to an image processing method and device. The image processing method comprises obtaining the number of images tobe processed and the size of each image to be processed, and computing an image segmentation parameter according to the number of the images to be processed and the current operation resource; wherein the current operation resource represents ways of parallel computation supported by the system at present; segmenting each image to be processed according to the image segmentation parameter and thesize of each image to be processed, and obtaining each segmented image; computing image features of all the segmented images in parallel at the same time according to a preset image processing algorithm, and splicing each image to be processed according to the image features of all the segmented image to obtain a spliced image. In this way, the image to be processed is segmented, furthermore allthe segmented images are processed in parallel at the same time, image splicing is achieved, the processing performance of a parallel device can be achieved furthest, and the processing speed and efficiency are increased.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to an image processing method and device. Background technique [0002] Panoramic image stitching technology is used in application scenarios such as video surveillance and panoramic video. Due to the limitations of the shooting angle and viewing angle of the shooting terminal equipment, a single image can only capture a partial scene. It is necessary to use digital image processing technology to stitch multiple images shot from different angles to generate a panoramic image of the shooting environment. In image stitching, it is usually necessary to process thousands or tens of thousands of images, especially in some applications that require high real-time performance such as real-time monitoring of UAVs and panoramic video live broadcasts, it is necessary to stitch many captured images in real time Processing, which puts forward higher requirements on the processing speed ...

AI Technical Summary

Problems solved by technology

[0007] However, due to its many calculation steps, the algorithm is greatly affected by the calculation performance of the system, and there is still a problem of limited calculation speed.

[0008] It can be seen that in the prior art, the image stitching processing speed and processing efficiency are relatively low, which cannot well meet the real-time requirements of the system.

Images