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

Event camera and depth camera-based visual odometer positioning method and system

A technology of visual odometer and depth camera, which is applied in the field of computer vision, can solve problems such as difficult observation and large measurement deviation, and achieve the effect of high positioning accuracy and high algorithm efficiency

Pending Publication Date: 2022-01-04
SHANGHAI TECH UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a visual odometry positioning method and system based on an event camera and a depth camera to solve the problem of using the visual SLAM and visual odometry in the prior art to locate in high dynamic motion scenes. and the problem of large measurement deviation or difficult observation under complex lighting conditions

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
  • Event camera and depth camera-based visual odometer positioning method and system
  • Event camera and depth camera-based visual odometer positioning method and system
  • Event camera and depth camera-based visual odometer positioning method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] Embodiment 1: A visual odometry positioning method based on an event camera and a depth camera. Such as figure 2 Shown is the flowchart of the visual odometry localization method.

[0096] The methods include:

[0097] Obtain the depth map and event information collected synchronously and in real time by the Azure Kinect camera (depth camera) and Prophesee-Gen3 camera (event camera) that have been calibrated with internal and external parameters; and obtain the data collected by the Pointgrey-GS3 camera (conventional camera) for comparison experiment.

[0098] Accumulate the events triggered in the millisecond-level local time, project the events onto the virtual two-dimensional image along the time dimension, and define the generated virtual two-dimensional image for the event flow called time-surface diagram;

[0099] Projecting the depth map collected by the depth camera synchronized with the event camera at the key frame moment to the event camera plane accordin...

specific Embodiment

[0115] Such as image 3 A schematic structural diagram of a visual odometry positioning system based on an event camera and a depth camera in an embodiment of the present invention is shown.

[0116] The system includes:

[0117] The acquisition module 31 is used to acquire the depth map and events collected synchronously and in real time by the depth camera and the event camera having calibrated internal and external parameters;

[0118] The time surface graph generation module 32 is connected to the acquisition module 31, and is used to accumulate the event flow in the millisecond-level local time, and project each event in the event flow onto the virtual two-dimensional image along the time dimension to generate A time surface diagram of the current moment;

[0119] The key frame local map construction module 33 is connected to the acquisition module 31 and the time surface map generation module 32, and is used to project the depth map collected by the depth camera synchr...

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

Disclosed are an event camera and depth camera-based visual odometer positioning method and system. An event camera and ta depth camera are combined, the event camera is used for replacing a conventional camera in a general RGB-D system, and the time surface graph is generated through the event flow collected by the event camera; and projecting a depth map collected at the time of the key frame to an event camera plane, combining the depth map with the generated time surface map at the time of the key frame to obtain a local map of the nearest key frame, and registering the newly generated time surface map with the local map of the nearest key frame to obtain a new time surface map; obtaining a relative pose and a global pose of the camera relative to the nearest key frame at the current moment; judging whether a new local map of the nearest key frame needs to be constructed or whether the local map of the current nearest key frame continues to be used for registration according to the value of the relative pose; the invention not only has the advantages of high positioning precision, high algorithm efficiency and real-time processing, but also can work normally under challenging illumination conditions.

Description

technical field [0001] The present application relates to the technical field of computer vision, in particular to a visual odometry positioning method and system based on an event camera and a depth camera. Background technique [0002] In recent years, products and technologies such as robots, drones, autonomous driving, and VR / AR have continued to flourish, gradually penetrating into various fields of social life, and having an important impact on economic and social development. The real-time positioning and tracking capabilities based on SLAM technology are the key technologies necessary for the above-mentioned smart mobile devices to perceive and recognize the surrounding environment. Its important academic and application value has always been highly valued by the academic and industrial circles. [0003] Since the concept of SLAM was put forward in the 1980s, it has been introduced to the present. The sensors used in the SLAM system continue to expand. From the earl...

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): G06T7/73G06T7/33G06T3/00
CPCG06T7/74G06T7/337G06T2207/10021G06T2207/10028G06T3/06
Inventor 王一夫康智文左一凡杨家琪
Owner SHANGHAI TECH UNIV