Quantified evaluation method of image mosaic algorithms

Abstract

The invention belongs to the field of computer vision and relates to a quantified evaluation method of image mosaic algorithms. The method comprises the following steps: carrying out mosaic on mosaic sequence images by adopting different mosaic algorithms to be evaluated so as to obtain mosaic composite images; carrying out overall statistics on the mosaic composite images and computing a global evaluation index; selecting corresponding mosaic sequence images as reference images in allusion to local mosaic composite images so as to carry out reference image quality evaluation and compute a local evaluation index; and constructing image mosaic evaluation index system levels by adopting a multi-index comprehensive evaluation method, determining the weighting coefficients of the indexes according to the mosaic requirement and purpose, normalizing the evaluation indexes and carrying out weighted aggregation step by step to finally obtain a comprehensive evaluation result. Through the quantified evaluation method of the image mosaic algorithms, the difficulties existing in the current mosaic evaluation algorithms are overcome; and the evaluation result fits the subjective judgment results of people and has objectivity, consistency and stability. The quantified evaluation method of the image mosaic algorithms can also be used for the quantified comprehensive evaluation of the algorithms such as image fusion and the like.

Description

technical field [0001] The invention includes technologies such as image splicing, image quality evaluation, etc., belongs to the field of computer vision, and relates to a quantitative evaluation method for an image splicing algorithm. Background technique [0002] With the development of the electronic information industry and technological progress, equipment that can acquire and record video information is becoming more and more popular. However, compared with the field of view of the human eye, the field of view of ordinary cameras is much smaller. How to effectively use computer technology to expand The range of the field of view of the camera to capture images and videos has attracted extensive attention from researchers. Image mosaic technology can solve the problem that large pictures cannot be produced due to the limitation of the viewing angle and size of imaging instruments such as cameras. The so-called image stitching is a technology that constructs a seamless...

AI Technical Summary

Problems solved by technology

The existing evaluation method is to compare the spliced ​​image with it on the basis of defining the panoramic reference image, but it is difficult to obtain the panoramic reference image; Sequence source images, then splicing and comparing algorithms

They all require a lot of human intervention and complicated calculations

Images