Target coordinate deduplication method and system, electronic equipment and readable storage medium

Abstract

The invention provides a target coordinate deduplication method and system, electronic equipment and a readable storage medium, and relates to the technical field of data processing. The method comprises the steps: acquiring target coordinates, types and the number of all targets in a specific area range; dividing the specific area range into a plurality of area sub-arrays; performing set division on all the target coordinates according to the regional sub-arrays, wherein all the target coordinates in the same regional sub-array form a set; grouping all the target coordinates in the same set in pairs to construct an adjacent matrix; judging whether the measurement between the two target coordinates in the adjacent matrix is smaller than a threshold value or not; if the metric is smaller than the threshold value, judging whether the types of two targets corresponding to the two target coordinates are the same or not; if the types of the two targets are the same, judging that the coordinates of the two targets correspond to the same target; and removing the repeated target coordinates. According to the technical scheme, the target coordinates which are repeatedly recognized can be effectively removed, and the accuracy of a recognition result is improved.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method, system, electronic equipment and readable storage medium for deduplication of target coordinates. Background technique [0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects in various patterns. It is a practical application of deep learning algorithms. In real life / production, many fields need to apply image recognition technology to identify targets. For example, in the inspection process of photovoltaic power plants, it is necessary to use image recognition technology to identify defects and further determine the coordinates of defects for easy maintenance; in the process of face recognition, it is necessary to use image recognition technology to identify facial feature points and their coordinates, and then Check whether it belongs to the same user as the avatar stored...

AI Technical Summary

Problems solved by technology

[0003] The inventors found that in the process of image recognition, in order to prevent omissions, in the process of image acquisition, it is usually necessary to have a certain overlap in the range of two adjacent image acquisitions, but this will lead to an increase in the number of acquired images, and in the image The number of targets that need to be identified also increases, which affects the accuracy of the identification results

Images