Target image content aggregation method, apparatus and device, and readable storage medium

Abstract

The invention discloses a target image content aggregation method, apparatus and device, and a readable storage medium, and relates to the field of machine learning. The method comprises the followingsteps: acquiring a first image frame and a second image frame in an image set; performing image content identification on the first image frame and the second image frame to obtain a first area and asecond area; for a first region feature point corresponding to the first region, performing epipolar line search in the second image frame to obtain a corresponding epipolar line; and aggregating thetarget image content according to the second region feature points and the epipolar lines. And for the first region feature points corresponding to the first region, determining the corresponding epipolar lines in the second image frame in an epipolar line search mode, and filtering the matching condition of the first region feature points and the second region feature points in combination withthe matching relationship between the second region feature points and the epipolar lines, thereby improving the aggregation efficiency of the target image content, and improving the user experience.And the aggregation accuracy of the target image content is improved.

Description

technical field [0001] The embodiments of the present application relate to the field of machine learning, and in particular to a method, device, device, and readable storage medium for aggregating target image content. Background technique [0002] With the rapid development of artificial intelligence (AI), more and more tasks can be automatically completed by computer equipment. Schematically, in the development process of the map application program, it is necessary to collect the information of the electronic eye set on the road, such as: location information, function information, etc., wherein the collection process of the electronic eye information is usually collected by the information collection vehicle through the camera owned. [0003] In the images collected by the information collection vehicle, it is necessary to aggregate the associated content in them. For example, if the electronic eye A has appeared in both image 1 and image 2, then the electronic eye A i...

AI Technical Summary

Problems solved by technology

[0004] However, when the above method is aggregated, the matching process is affected by the illumination changes between different image frames, as well as by the changes in shooting angles, resulting in low aggregation accuracy of associated content.

Images