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

Object detection and tracking method, head-mounted display device and storage medium

A medium and object technology, applied in the acquisition of 3D object measurement, character and pattern recognition, image data processing, etc.

Pending Publication Date: 2019-07-23
SEIKO EPSON CORP
View PDF22 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, existing techniques such as JP-A-2013-50947 only use cameras to estimate pose
However, the camera has a latency that increases with the movement or speed of the user's head

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
  • Object detection and tracking method, head-mounted display device and storage medium
  • Object detection and tracking method, head-mounted display device and storage medium
  • Object detection and tracking method, head-mounted display device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 approach

[0050] A-1. Configuration of information processing device

[0051] A-2. Template creation (training)

[0052] A-2-1. Selection of 2D model points

[0053] A-2-2. Determination of 3D model points and creation of templates

[0054] A-2-3. In-Plane Rotation Optimization for Training

[0055] A-2-4. Super template

[0056] A-3. Configuration of Head Mounted Display (HMD)

[0057] A-4. Execution of Estimation of Target Object Pose

[0058] A-4-1. Edge detection

[0059] A-4-2. Template selection

[0060] A-4-3. 2D model point correspondence

[0061] A-4-4. Attitude optimization

[0062] A-4-5. Sub-pixel correspondence

no. 3 approach

[0065] D.Modification

[0066] D-1. Modification 1

[0067] E. Tracking objects in 3D using a fusion of inertial motion sensors (IMUs) and camera sensors

[0068] E-1. Introduction

[0069] E-2-1. Overview

[0070] E-2-1-1. System

[0071] E-2-1-2. Overview of Sensor Fusion Methods

[0072] E-2-2. Tracker Fusion IMU

[0073] E-2-2-1. The method of fusing IMU and 3D object tracker

[0074] E-2-2-2. Initialize IMU fusion

[0075] E-2-2-2-1. Detecting stationary motion

[0076] E-2-2-3. IMU attitude prediction

[0077] E-2-2-4. IMU divergence determination

[0078] E-2-2-5. IMU object tracker

[0079] E-2-2-5-1. Detect stationary motion

[0080] E-2-2-5-2. Use the IMU to predict the pose to predict the feature point position / use the predicted feature position to predict the KLT match

[0081] E-2-2-5-3. Pose Estimation Using KLT Matching Results and IMU Predicted Pose

[0082] E-2-2-5-4. Pose Refinement by Edge Alignment and IMU Predicted Pose

[0083] E-2-2-5-5. ...

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 discloses an object detection and tracking method, a head-mounted display device and a storage medium. The method may include the following steps: acquiring, from a camera, an image frame; acquiring, from an inertial sensor, a sensor data sequence; tracking a first pose of an object in a real scene based at least on the image frame; deriving a sensor pose of an inertial sensor basedon the sensor data sequence; determining whether the first pose is lost; retrieving from one or more memories, or generating from a 3D model stored in one or more memories, a training template corresponding to a view that is based on the sensor pose obtained on or after the first pose is lost; and deriving a second pose of the object using the training template.

Description

technical field [0001] Embodiments of the present invention relate to techniques of an information processing device that processes information about a three-dimensional model of a target object using a camera and a motion sensor (eg, an inertial sensor). Background technique [0002] A method of estimating the pose of an object imaged by a camera is disclosed in JP-A-2013-50947, which discloses a technique in which a binary mask of an input image including an image of an object is created from A binary mask extracts monomers that are points in the inner and outer contours of an object, and connects sets of monomers to each other to form a mesh represented as a double matrix, allowing the pose of the object to be estimated. [0003] However, existing techniques such as JP-A-2013-50947 only use cameras to estimate pose. However, the camera has a latency that increases with the movement or speed of the user's head. [0004] Furthermore, accurate and fast object detection is ...

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): G06T7/73G06T7/13
CPCG06T7/73G06T7/13G06T7/75G06T2207/30164G02B27/017G02B2027/0138G06V20/653G06V20/20G06V2201/12G06T17/05H04N13/332G06F30/00G06T17/00G06F3/04815G06V20/64
Inventor 杨杨I·莫拉维奇
Owner SEIKO EPSON CORP