Camera-Rendered Object Positioning for Reliable Tunnel Navigation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle and robot positioning systems face inaccuracies due to unreliable environment information from sensors, leading to reduced positioning reliability, especially in severe conditions like tunnels.

Innovation Solution

An object positioning method that utilizes environment images captured by a camera, determines candidate position information based on a virtual camera parameter, and renders a corresponding image using a three-dimensional model to accurately determine the target object's position, allowing for flexible and broader application scope.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If sensor-based positioning methods are used, then positioning can be implemented in various environments, but positioning reliability deteriorates due to inaccurate environment information

Engineering Contradiction:
Improvepositioning environment coverageVSAvoidpositioning reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent creates a virtual copy of the real environment through a three-dimensional model, and generates a rendered image that replicates what the camera should capture from the target object's position. This virtual copy allows positioning without relying on potentially inaccurate sensor data, as the rendered image serves as a reliable reference for comparison.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces a rendered image as an intermediary between the camera's actual capture and the positioning determination. Instead of directly using sensor data for positioning, the system generates a synthetic rendered image based on candidate positions and compares it with the actual camera image, using the rendered image as a mediator to achieve more reliable positioning.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If traditional sensor-based positioning is used, then positioning can be performed, but positioning accuracy deteriorates in severe conditions like tunnels

Engineering Contradiction:
Improvepositioning accuracyVSAvoidenvironmental interference
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

By creating a virtual three-dimensional model and rendering the expected camera view from candidate positions, the system establishes a reliable reference that is independent of environmental conditions. This virtual copy remains accurate even in severe conditions like tunnels where sensor-based positioning fails.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical sensor-based detection system with a computational rendering and comparison system. Instead of relying on physical sensors to detect environment information, the system uses virtual rendering to synthesize expected views and compares them with actual camera images, eliminating the harmful effects of environmental interference on sensor performance.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If camera-based rendering method is used, then positioning reliability improves, but system complexity increases due to three-dimensional model requirements

Engineering Contradiction:
Improvepositioning reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by pre-building a three-dimensional model of the environment before positioning is needed. This model is prepared in advance and stored, so during actual positioning operations, the system only needs to perform rendering and comparison operations based on candidate positions, reducing real-time computational complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The positioning process is segmented into distinct steps: obtaining camera image, determining candidate positions, generating rendered images for each candidate, comparing rendered images with actual image, and determining final position. This segmentation allows each step to be optimized independently and facilitates parallel processing of multiple candidate positions.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4310780B1Object positioning method, electronic apparatus, and computer-readable storage medium
Publication Date: 2025.11.05 SHANGHAI LICHI SEMICON LTD
  • EP4310780B1 patent drawingFigure 1~2
  • EP4310780B1 patent drawingFigure 3
  • EP4310780B1 patent drawingFigure 4

AI summary

An object positioning method includes obtaining an environment image collected by a target object through a camera of the target object and a camera parameter of collecting the environment image, determining candidate position information of the target object and a virtual camera parameter, rendering, based on a predetermined three-dimensional model, the candidate position information, and the virtual camera parameter, to generate a rendered image corresponding to the candidate position information, and determining position information of the target object based on the environment image, the rendered image, and the candidate position information. The virtual camera parameter and the camera parameter of the environmental image have a first correspondence. The three-dimensional model and a real space have a second correspondence.