Visual information determination method and device, equipment and storage medium

A technology for visual information and determination methods, applied in the field of image processing, can solve the problems of difficulty in feature point extraction, reduction of feature point constraint relations, and reduction in the number and quality of extracted feature points

Pending Publication Date: 2021-04-09
BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, in a white wall environment with a single texture, due to the difficulty of feature point extraction, the quantity and quality of the extracted feature points will be significantly reduced, so t

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
  • Visual information determination method and device, equipment and storage medium
  • Visual information determination method and device, equipment and storage medium
  • Visual information determination method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] figure 1 It is a flow chart of a method for determining visual information provided by Embodiment 1 of the present invention. This embodiment is applicable to camera pose optimization and map reconstruction based on image frame sequences, especially for unmanned aerial vehicles, robots, automatic Scenarios for determining visual information in driving technology or augmented reality. The method can be executed by a visual information determination device, which can be implemented by software and / or hardware, and integrated into devices that need to perform map reconstruction, such as drones, robots, glasses, and the like. The method specifically includes the following steps:

[0030] S110. Acquire a sequence of image frames captured by the camera, and perform feature point extraction on each image frame in the sequence of image frames, and determine a set of feature points in each image frame.

[0031] Wherein, the sequence of image frames may be a sequence composed o...

Embodiment 2

[0051] image 3 It is a flow chart of a method for determining visual information provided by Embodiment 2 of the present invention. On the basis of the above embodiments, this embodiment "according to collinear constraints and observation constraints, the camera position at each shooting moment The pose and the 3D world coordinates of each feature point are optimized, and the target camera pose and the target 3D world coordinates of each feature point are determined at each shooting moment" and optimized. The explanations of terms that are the same as or corresponding to those in the foregoing embodiments are not repeated here.

[0052] see image 3 The method for determining visual information provided in this embodiment specifically includes the following steps:

[0053] S210. Acquire a sequence of image frames captured by the camera, and perform feature point extraction on each image frame in the sequence of image frames, and determine a set of feature points in each ima...

Embodiment 3

[0080] Figure 4 It is a schematic structural diagram of a visual information determination device provided by Embodiment 3 of the present invention. This embodiment is applicable to camera pose optimization and map reconstruction based on image frame sequences. The device includes: a feature point extraction module 310, a feature point A point collinear set determination module 320 and a visual information determination module 330 .

[0081] Wherein, the feature point extraction module 310 is used to obtain the image frame sequence taken by the camera, and perform feature point extraction for each image frame in the image frame sequence, and determine the feature point set in each image frame; the feature point collinear set The determining module 320 is configured to perform collinear detection on each feature point in each feature point set, and determine each feature point collinear set composed of feature points on the same straight line, wherein each feature point collin...

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 embodiment of the invention discloses a visual information determination method and device, equipment and a storage medium. The method comprises the steps: obtaining an image frame sequence photographed by a camera, carrying out the feature point extraction of each image frame in the image frame sequence, and determining a feature point set in each image frame; carrying out collinear detection on all the feature points in each feature point set, and determining collinear sets of all the feature points composed of the feature points located on the same straight line, wherein each feature point collinear set comprises at least three feature points; determining a target camera pose at each shooting moment and a target three-dimensional world coordinate of each feature point according to the collinear set of each feature point, the camera internal reference information and the pixel coordinate of each feature point in the feature point set. Through the technical scheme of the embodiment of the invention, the precision and robustness of visual information determination can be improved.

Description

technical field [0001] Embodiments of the present invention relate to image processing technologies, and in particular, to a method, device, device, and storage medium for determining visual information. Background technique [0002] In the field of computer vision research, image frame sequences are usually used to estimate the camera pose. SLAM (Simultaneous localization and mapping, real-time positioning and mapping) is a commonly used technology. It tracks the pose of the camera, constructs the 3D trajectory of the camera, and maps the environment in which the camera is located. SLAM has a wide range of application scenarios, such as robot navigation, automatic driving, augmented reality, etc. [0003] At present, the SLAM system based on the feature point method is often used to estimate the camera pose and reconstruct the environment map where the camera is located. For example, feature points are first extracted from image frames, and then the constraint relationshi...

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
IPC IPC(8): G06T7/73G06K9/00
CPCG06T7/73G06V20/46
Inventor 张鹏许腾康轶非李雨倩
Owner BEIJING JINGDONG QIANSHITECHNOLOGY CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap