Unlock instant, AI-driven research and patent intelligence for your innovation.

Map fusion method and device based on multiple frames of images

A map fusion, multi-frame image technology, applied in the field of virtual reality, can solve problems such as incorrect matching, affecting the map fusion results, etc., to reduce interference, improve fusion accuracy, and improve accuracy.

Pending Publication Date: 2022-07-19
HISENSE VISUAL TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when the same or similar objects exist in different environments, the same feature points may be extracted during the loop closure detection process. In this way, when matching the current key frames of different SLAM terminals based on the extracted feature points, it will cause wrong matching. , thus affecting the fusion result of the map

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Map fusion method and device based on multiple frames of images
  • Map fusion method and device based on multiple frames of images
  • Map fusion method and device based on multiple frames of images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the objectives, implementations and advantages of the present application clearer, the exemplary embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the exemplary embodiments of the present application. Obviously, the exemplary embodiments described It is only a part of the embodiments of the present application, but not all of the embodiments.

[0034] Based on the exemplary embodiments described in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the appended claims of this application. Furthermore, although the disclosures in this application have been presented in terms of illustrative example or instances, it should be understood that various aspects of this disclosure may also constitute a complete embodiment in isolation.

[0035] In the process of map fusion, mul...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of VR, and provides a map fusion method and device based on multiple frames of images, when the similarity of two key frames in a first initial map and a second initial map is greater than a similarity threshold, the positions of the key frames are marked in the first initial map and the second initial map respectively, and the key frames are fused according to a preset key frame interval. The key frames are obtained again from the two initial maps, when the similarity between the two key frames obtained again is larger than a similarity threshold value, positions are marked in the first initial map and the second initial map, in this way, the two initial maps respectively obtain a position vector, and when the two position vectors are consistent, it is determined that the common-view area is detected. Map fusion can be performed. The loopback detection is carried out through the two position vectors, compared with a method based on a single-frame key frame, wrong matching caused by local similar areas contained in different scenes can be reduced, the accuracy and robustness of loopback detection are improved, and then the accuracy of map fusion is improved.

Description

technical field [0001] The present application relates to the field of virtual reality (Virtual Reality, VR) technology, and in particular, to a method and device for map fusion based on multi-frame images. Background technique [0002] With the continuous development of Simultaneous Localization and Mapping (SLAM) technology, SLAM technology has gradually been widely used in the fields of unmanned logistics vehicles, unmanned vehicles, and drones from the field of robotics. SLAM technology builds a map of the environment around the robot in real time based on sensor data without any prior knowledge, and at the same time infers its own position based on this map. [0003] Loopback detection determines whether to perform map fusion at this location by detecting whether multiple SLAM terminals have reached the same location. At present, in most loop closure detection methods, when the similarity between current key frames of different SLAM terminals is greater than a set simi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T17/05G06T5/50G06V10/74G06K9/62
CPCG06T17/05G06T5/50G06T2207/20221G06F18/22
Inventor 张子浩鲁翔
Owner HISENSE VISUAL TECH CO LTD