Monocular SLAM initialization method, apparatus and device, and storage medium

An initialization method and monocular technology, which are applied in monocular SLAM initialization methods, equipment and storage media, and devices, can solve the problem of low success rate of monocular SLAM initialization, and achieve the effect of low user operation requirements and simple user operations

CN114842162APending Publication Date: 2022-08-02MIGU COMIC CO LTD +2
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2022-08-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a monocular SLAM initialization method, device and equipment and a storage medium, and relates to the technical field of mobile robots, and the method comprises the steps: obtaining a first frame image and a first feature point of the first frame image; inputting the first frame image into a pre-trained generative network model to obtain a first homography matrix; wherein the generative network model is constructed based on a convolutional neural network and a generative adversarial network; performing perspective transformation on the first frame image according to the first homography matrix to obtain a virtual frame image; converting the first feature point to a virtual frame image by using a first homography matrix to obtain a second feature point of the virtual frame image; and obtaining a first map point by using a triangulation algorithm according to the second feature point and the corresponding first feature point. According to the method and the device, the problem of low success rate of monocular SLAM initialization in the prior art is solved, and the effect of monocular SLAM initialization is realized by only needing one video frame image.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of mobile robots, and in particular, to a monocular SLAM initialization method, device, equipment and storage medium. Background technique

[0002] SLAM (Simultaneous Localization and Mapping, real-time positioning and map construction) technology is the key technology to achieve autonomous positioning and navigation of robots; monocular SLAM, full name of monocular vision SLAM system, uses a camera as a sensor to achieve autonomous positioning and navigation of robots The system has the advantages of simple system structure, low cost and easy implementation, and is used in AR (Augmented Reality, augmented reality), AI (Artificial Intelligence, artificial intelligence) and other fields.

[0003] In the current monocular SLAM system, the initialization operation of the monocular SLAM system is generally realized by selecting two key video frame images with large parallax. The problem with this monocu...

Examples

no. 1 example

[0070] refer to figure 1 The first embodiment of the monocular SLAM initialization method of the present invention is proposed. The monocular SLAM initialization method can be applied to a monocular SLAM initialization device, and can be specifically applied to the AR underlying technology of the application in the device.

[0071] Monocular SLAM initialization equipment refers to terminal equipment, network equipment or system equipment that can realize network connection. For example, it can be terminal equipment such as mobile phone, computer, tablet computer, embedded industrial computer, etc., or network equipment such as server and cloud platform It can also be a system device including terminal devices such as computers and mobile phones, and network devices such as edge servers and cloud servers.

[0072] like figure 2 As shown, it is a schematic diagram of the hardware structure of the monocular SLAM initialization device. The monocular SLAM initialization device m...

Embodiment 2

[0103] Based on the same inventive concept, refer to Figure 3 to Figure 5 , on the basis of the first embodiment, a second embodiment of the monocular SLAM initialization method of the present invention is proposed, and the method can also be applied to the monocular SLAM initialization device in the first embodiment.

[0104] Combine below image 3 The schematic flow chart shown is a detailed description of the monocular SLAM initialization method in this embodiment.

[0105] After the step of obtaining the first map point by using the triangulation algorithm according to the second feature point and the corresponding first feature point, the following steps S600-S910 may be performed in sequence to realize the second frame transition after the single-frame initialization operation. , in order to obtain more accurate 3D map points; steps S100-S500 may also be independently executed steps to achieve the purpose of quickly completing the initialization operation.

[0106] Fu...

Embodiment 3

[0185] Based on the same inventive concept, refer to Image 6 , proposes the first embodiment of the monocular SLAM initialization device of the present invention, the monocular SLAM initialization device may be a virtual device, and is applied to a monocular SLAM initialization device.

[0186] Combine below Image 6 The shown schematic diagram of functional modules describes the monocular SLAM initialization device provided in this embodiment in detail, and the device may include:

[0187] a data acquisition module for acquiring a first frame of image and a first feature point of the first frame of image;

[0188] an image processing module, configured to input the first frame image into a pre-trained generative network model to obtain a first homography matrix; wherein, the generative network model is constructed based on a convolutional neural network and a generative confrontation network;

[0189] a perspective transformation module, configured to perform perspective t...