Visual Position Recognition Using Camera and Server Pose Estimation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing global pose estimation methods for mobile devices, such as GPS, WPS, and VL, face challenges in indoor environments, require expensive equipment for mapping, and are prone to false positives and environmental changes.

Innovation Solution

A position recognition method and system that uses visual information processing to recognize a user's position based on a point of interest (POI), involving a camera to generate frame images, transmitting these images to a server for pose estimation, and combining confidence values from different pose estimation methods to determine a final global pose.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If GPS is used for position recognition, then outdoor positioning accuracy is improved, but it cannot be used in indoor environments

Engineering Contradiction:

Improvepositioning accuracyVSAvoidenvironmental adaptability

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system divides the positioning task into two segments: GPS provides initial coarse positioning outdoors, while visual localization takes over for precise indoor positioning. This segmentation allows each method to operate in its optimal environment, resolving the contradiction between outdoor accuracy and indoor usability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The mobile device's camera and image processing system act as an intermediary between GPS and indoor positioning requirements. The camera captures visual features that bridge the gap between satellite-based outdoor positioning and indoor environment navigation, enabling seamless transition between environments.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If WPS is used for position recognition, then indoor positioning is enabled, but it requires sufficient wireless access points

Engineering Contradiction:

Improveindoor positioning capabilityVSAvoidpositioning reliability

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

Instead of relying on wireless signal copies from access points, the system uses visual copies (images) of the physical environment captured by the camera. These visual representations serve as reliable position indicators that do not depend on the density or distribution of wireless infrastructure.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system replaces the wireless signal-based positioning mechanism with a visual image-based mechanism. By substituting radio wave propagation with optical capture and processing, the system achieves positioning reliability that is independent of wireless access point density.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If traditional VL is used for position recognition, then global position estimation is achieved, but expensive equipment like lidar is required for map generation

Engineering Contradiction:

Improveglobal position estimationVSAvoidequipment cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces expensive, complex lidar equipment with a inexpensive camera that is already present in most mobile devices. The camera captures 2D images that are processed to achieve positioning, eliminating the need for costly specialized sensing equipment while maintaining functional capability.

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

Solution Approach 2:

The system extracts positioning information from ordinary 2D images captured by a camera, removing the requirement for specialized 3D sensing equipment. By extracting sufficient geometric and semantic features from simple images, the system achieves global position estimation without lidar or other expensive devices.

Inventive Principle:

Principle #2Taking out (Extraction)

4Ease of operation

If 2D image marker is used for position recognition, then position information can be acquired, but the marker design does not match the real environment and users must photograph the marker from specific angles

Engineering Contradiction:

Improveposition information acquisitionVSAvoidenvironmental integration

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system uses natural POIs in the environment that serve multiple functions: they are inherent environmental features that provide semantic context, visual landmarks for positioning, and do not require special attachment or installation. This universal approach eliminates the need for dedicated 2D markers while maintaining positioning capability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

Instead of attaching artificial markers to the environment, the system inverts the approach by using the environment's existing natural features as positioning targets. Rather than making the environment adapt to markers, the positioning system adapts to the environment's inherent visual characteristics.

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS12254041B2Position recognition method and system based on visual information processing

Publication Date: 2025.03.18 NAVER CORP

AI summary

A position recognition method and a system based on visual information processing are disclosed A position recognition method according to one embodiment including the steps of: generating a frame image through a camera; transmitting, to a server, a first global pose of the camera and the generated frame image; and receiving, from the server, a second global pose of the camera estimated on the basis of a pose of an object included in the transmitted frame image.