UAV Visual Marker Localization for Low-Power Absolute Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing localization systems for mobile devices, such as UAVs and land vehicles, face challenges in providing accurate and efficient absolute position data in real-time, particularly due to power and weight constraints, robustness issues, and interference from noise and distortion, which affects their ability to control movements effectively.

Innovation Solution

A localization system with onboard sensors and redesigned markers that include a fixed pattern and a variable data area, allowing for efficient detection and processing of markers in a single scan direction, even at various angles, and utilizing a processor to determine absolute positions using marker data from multiple markers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional onboard localization systems are used, then absolute position data can be obtained, but power consumption increases and weight constraints are violated

Engineering Contradiction:
Improveabsolute position data accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent replaces complex onboard localization hardware (accelerometers, gyroscopes, barometers) with a simpler visual marker detection system using image processing algorithms. This substitution dramatically reduces power consumption while maintaining localization accuracy, as the system uses the device's existing camera and processes images through optimized algorithms that track marker positions and calculate device location.

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

Solution Approach 2:

The patent uses visual markers as external references that the device camera captures and processes. Instead of relying on expensive onboard sensors, the system creates a digital copy of the physical environment through marker detection and uses this visual information to determine absolute position, thereby reducing hardware requirements and power consumption.

Inventive Principle:
Principle #26Copying

2Measurement precision

If traditional onboard localization systems are used, then position information can be obtained, but weight of the mobile device increases

Engineering Contradiction:
Improveposition information accuracyVSAvoiddevice weight
Core Design Contradiction:
Measurement precisionVSWeight of moving object

Solution Approach 1:

The patent eliminates heavy onboard localization hardware by substituting it with software-based marker detection and image processing. The system uses the device's existing camera and computational resources to achieve accurate positioning without adding significant weight, making it ideal for mobile devices where weight constraints are critical.

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

Solution Approach 2:

The patent extracts the localization function from the mobile device itself and places it in the external environment through visual markers. By moving the localization reference system from onboard sensors to external markers, the device weight is minimized while maintaining positioning capability.

Inventive Principle:
Principle #2Taking out (Extraction)

3Productivity

If standard marker detection methods are used, then markers can be detected, but detection accuracy decreases due to noise and distortion

Engineering Contradiction:
Improvemarker detection speedVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the marker detection process into distinct stages: preprocessing to remove noise, edge detection to identify marker boundaries, pattern recognition to identify marker types, and coordinate calculation to determine position. This segmentation allows each stage to be optimized independently, maintaining both speed and accuracy even in noisy conditions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies preliminary image preprocessing operations (noise filtering, contrast enhancement, edge detection) before marker detection. This preliminary action prepares the image data to be more robust against noise and distortion, enabling accurate and fast detection even in challenging environments.

Inventive Principle:
Principle #10Preliminary action

4Speed

If fast localization is implemented for real-time control, then responsiveness improves, but robustness to interference and distortion decreases

Engineering Contradiction:
Improvelocalization speedVSAvoidrobustness to interference
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The patent segments the localization process into optimized stages with different computational complexities. The preprocessing and marker identification stages are designed for speed to maintain real-time performance, while the coordinate calculation and verification stages incorporate robustness checks. This segmentation allows the system to achieve both fast response and resistance to interference.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements feedback mechanisms where detected marker positions are continuously verified and adjusted based on expected patterns and previous positions. This feedback loop allows the system to maintain fast localization speeds while correcting for noise and distortion, thereby improving robustness without sacrificing real-time performance.

Inventive Principle:
Principle #23Feedback

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system provides robust and efficient localization, reducing power consumption, improving detection accuracy, and maintaining information integrity, enabling precise control of mobile devices in dynamic environments.

Implementation Method 1

A camera provided on the mobile device captures a plurality of images of the travel space

Methodology Applied
Scientific EffectImage capture: Photography

Data Source

PatentEP3525059B1Visual localization of unmanned aerial vehicles based on marker detection and processing
Publication Date: 2022.06.01 DISNEY ENTERPRISES INC
  • EP3525059B1 patent drawingFigure 1
  • EP3525059B1 patent drawingFigure 2
  • EP3525059B1 patent drawingFigure 3

AI summary

A method for facilitating determination of positions of mobile devices within an operating space containing a number of objects, the method comprising placing at least three markers on exposed surfaces of the objects, wherein each of the markers includes a pattern of linear bars adjacent a data area, wherein the pattern of linear bars is identical on each of the markers and the data area has a pattern that varies between the markers; and operating a mobile device to move about the operating space in response to control signals; the method further comprising the steps, performed at the mobile device of using a single direction scan of an image to locate the markers in the image, wherein at least one of the markers is positioned to be oriented in the image such that the pattern of linear bars is non-orthogonal to the single direction scan; extracting data from the pattern of the data areas; estimating the position of the mobile device based on the extracted data; and generating the control signals based on the estimated position of the mobile device within the operating system.