一种AUV自主定位辅助的节能型多图像拼接方法

By using AUV autonomous positioning assistance, overlapping areas in underwater images are screened and estimated, and the optimal stitching path is planned. This solves the problems of slow underwater image stitching speed and insufficient accuracy, improves stitching efficiency, and saves energy.

CN116188263BActive Publication Date: 2026-07-17HOHAI UNIV

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HOHAI UNIV
Filing Date
2023-01-13
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Feature matching in underwater image stitching takes too long, the stitching speed is slow, the stitching accuracy is insufficient, and the efficiency of stitching multiple images continuously is low, making it difficult to meet the needs of AUV underwater operations.

Method used

With the assistance of autonomous positioning by AUV, the system acquires its own motion information to construct a coordinate set, filters and estimates overlapping areas of images, finds the most suitable reference image, plans the optimal stitching order, and optimizes the navigation path to improve stitching speed and accuracy while reducing energy consumption.

Benefits of technology

It achieves ordered integrity in multi-image stitching, improves algorithm speed and accuracy, reduces AUV energy consumption, adapts to environmental changes, and conforms to the concept of environmental protection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116188263B_ABST
    Figure CN116188263B_ABST
Patent Text Reader

Abstract

本发明公开了一种AUV自主定位辅助的节能型多图像拼接方法,构建拍摄图像各时刻AUV的位置信息;去除信息冗余的图像,并对剩余图像进行重合区域估计,寻找基准图像方便拼接;根据重合区域和基准图像,规划最优图像拼接次序,达到水下多图像连续拼接的目的;同时,依靠拼接过程中对拼接次序的选择,对AUV航行路线进行优化,以延长AUV在水下作业的时间。本发明缩小了特征匹配的范围,提升了算法运行的速度;基于重合区域大小对拼接次序进行规划,解决了待拼接图像数量较多时的拼接顺序问题,提供了可靠的水下多图像拼接方法,同时保证了图像拼接的效率和精度;基于拼接次序优化了水下机器人的航行路线,有效节约了水下作业所需能源,延长AUV的工作时间。
Need to check novelty before this filing date? Find Prior Art