Camera Trajectory Guidance for VSLAM Initialization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional methods for initializing Visual Simultaneous Localization and Mapping (VSLAM) in augmented reality systems require unintuitive camera motions, leading to user confusion and suboptimal initialization processes, lacking real-time feedback and guidance for novice users.

Innovation Solution

A method on a user device with a camera and display that determines an optimal camera trajectory for VSLAM initialization based on an initial camera pose and estimated pivot distance, providing real-time feedback and guidance through interactive graphical user interfaces to facilitate intuitive camera motion sequences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional VSLAM initialization methods are used, then accurate 3D target reconstruction is achieved, but user operation becomes complex and unintuitive

Engineering Contradiction:
Improve3D target reconstruction accuracyVSAvoidcamera motion sequence complexity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system provides real-time visual feedback by displaying the current camera pose and the desired trajectory on the display device. This allows users to see their progress and adjust their camera movements accordingly, making the complex initialization process more intuitive and easier to follow while maintaining accurate 3D target reconstruction.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system introduces an intermediary guidance interface that mediates between the user's camera movements and the VSLAM initialization requirements. The graphical user interface acts as a mediator, translating user actions into the specific camera motions needed for accurate initialization without requiring users to understand the underlying complex sequences.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If real-time camera pose estimation is implemented, then trajectory guidance is improved, but computational load increases

Engineering Contradiction:
Improvetrajectory guidance qualityVSAvoidcomputational processing power
Core Design Contradiction:
Ease of operationVSPower

Solution Approach 1:

The system performs partial real-time pose estimation only when needed for guidance updates, rather than continuously processing all camera data. This selective approach provides sufficient trajectory guidance information to users while avoiding the full computational burden of continuous real-time processing, thus balancing ease of operation with power consumption.

Inventive Principle:
Principle #16Partial or excessive action

3Ease of operation

If interactive guidance interface is added, then user experience is enhanced, but system complexity increases

Engineering Contradiction:
Improveinitialization process usabilityVSAvoidsoftware interface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The guidance interface is segmented into distinct functional components: display module for showing camera pose, trajectory calculation module for determining desired path, and feedback module for providing guidance. This segmentation allows each component to be optimized independently and simplifies the overall system architecture while enhancing user experience through coordinated interaction of these modular elements.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP2992507B1Methods for facilitating computer vision application initialization
Publication Date: 2018.07.25 QUALCOMM INC
  • EP2992507B1 patent drawingFigure 1
  • EP2992507B1 patent drawingFigure 2A~2B
  • EP2992507B1 patent drawingFigure 3A~4B

AI summary

Embodiments disclosed pertain to systems, method s and apparatus for the initialization of Computer Vision (CV) applications on user devices (UDs) comprising a camera and a display. In some embodiments, an optimal camera trajectory for initialization of a Computer Vision (CV) application may be determined based on an initial camera pose and an estimated pivot distance. For example, the initial camera pose may be estimated based on a first image captured by the camera. Further, the display may be updated in real-time with an indication of a desired movement direction for the camera. In some embodiments, the indication of desired movement direction may be based, in part, on a current camera pose and the optimal trajectory, where the current camera pose may be estimated based on a current image captured by the camera.