Three-dimensional map distributed construction method and device and electronic equipment

By dividing the image set according to image information and time during the 3D map construction process and performing fusion processing, the problem of inaccurate 3D map model construction caused by inaccurate image classification is solved, achieving higher image classification accuracy and 3D map construction precision.

CN116843842BActive Publication Date: 2026-11-06BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210283916.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-21
Publication Date
2026-11-06
Estimated Expiration
2042-03-21

AI Technical Summary

Technical Problem

In existing technologies, when data collectors repeatedly collect images of the same area at different times, images in similar locations cannot be classified into the same type, resulting in low accuracy of image classification, which in turn affects the accuracy of 3D map model construction.

Method used

By acquiring image information and acquisition time from multiple images, the images are divided into M first image sets based on location information and global image features. These sets are then fused according to the acquisition time to obtain N second image sets, and finally a 3D map model is constructed.

Benefits of technology

This improves the accuracy and robustness of image classification, thereby enhancing the accuracy of 3D map construction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116843842B_ABST
    Figure CN116843842B_ABST
Patent Text Reader

Abstract

The present disclosure provides a three-dimensional map distributed construction method, device and electronic equipment, the method comprising: acquiring a plurality of images of a three-dimensional model for constructing a map; determining image information of the plurality of images and acquisition time of the plurality of images; dividing the plurality of images into M first image sets according to the image information, the similarity between each image in the first image set being greater than or equal to a first threshold, M being a positive integer; performing fusion processing on the M first image sets according to the acquisition time of the plurality of images to obtain N second image sets, N being a positive integer less than or equal to M; and constructing a three-dimensional model of a map according to the second image sets.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Face image clustering method, system, product and medium

    CN110516586A

  • Map construction method and device and positioning method and device

    CN110866953A