UAV Depth-Thermal Imaging for Warm-Blooded Object Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Unmanned aerial vehicles (UAVs) face challenges in accurately detecting warm-blooded objects during navigation and delivery due to limitations in depth information alone, which can lead to false detection and potential harm to humans or animals.

Innovation Solution

The integration of a multi-camera imaging component that combines depth maps from stereo images with thermal information using infrared cameras, allowing the UAV to differentiate between warm-blooded and non-warm-blooded objects by correlating depth and thermal signatures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If depth information alone is used for object detection, then the device complexity is reduced, but the detection accuracy deteriorates leading to false positives

Engineering Contradiction:
Improveimaging system complexityVSAvoidobject detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent combines depth information from stereo cameras with thermal information from infrared cameras to create a fused representation that integrates multiple sensing modalities. This merging allows the system to maintain relatively simple individual sensor components while achieving high detection accuracy through information fusion, directly resolving the contradiction between device simplicity and detection precision.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent adds a thermal dimension to the traditional depth-based detection by incorporating infrared thermal signatures. This dimensional expansion allows the system to differentiate between warm-blooded and non-warm-blooded objects that may have similar depth profiles, thereby improving detection accuracy without significantly increasing the complexity of the overall imaging architecture.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Ease of operation

If depth information alone is used for object detection, then the system is simpler to operate, but false detection of warm-blooded objects occurs

Engineering Contradiction:
Improvedetection system operationVSAvoidobject detection reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

By merging depth data with thermal signature data, the system creates a more reliable detection mechanism that automatically distinguishes warm-blooded objects. The fusion process maintains ease of operation as the system handles the complex processing internally, while significantly improving reliability through the additional thermal dimension for identification.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The thermal information acts as an intermediary that mediates between the depth data and the final detection decision. This intermediary layer provides additional verification to confirm whether detected objects are warm-blooded, thereby improving reliability without requiring complex operational procedures from the user.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If thermal information is added to depth maps, then the accuracy of warm-blooded object detection is improved, but the device complexity increases

Engineering Contradiction:
Improvewarm-blooded object detection accuracyVSAvoidmulti-camera imaging component complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges depth mapping functionality with thermal imaging by integrating stereo cameras and infrared cameras into a unified imaging component. This merging allows the system to achieve high accuracy in warm-blooded object detection while managing complexity through integrated design and coordinated operation of the camera systems.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The imaging component is designed with multi-functionality, where the same integrated system performs both depth mapping and thermal detection functions. This universal design approach allows a single imaging component to handle multiple detection tasks, improving warm-blooded object detection accuracy without proportionally increasing overall device complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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

This solution enhances the accuracy of object detection, reduces false positives, and ensures safer navigation and delivery by accurately identifying warm-blooded objects, thereby preventing potential interactions.

Implementation Method 1

a first camera at a first position to obtain a first image of a scene using visible light, a second camera at a second position to obtain a second image of the scene using visible light

Methodology Applied
Scientific EffectVisible light imaging: Light

Implementation Method 2

a third camera that may be positioned approximately equidistant between the first camera and the second camera to obtain a third image of the scene using infrared radiation

Methodology Applied
Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentEP3437016B1Combining depth and thermal information for object detection and avoidance
Publication Date: 2021.12.22 AMAZON TECH INC
  • EP3437016B1 patent drawingFigure 1
  • EP3437016B1 patent drawingFigure 2
  • EP3437016B1 patent drawingFigure 3

AI summary

Described is an imaging component for use by an unmanned aerial vehicle ("UAV") for object detection. As described, the imaging component includes one or more cameras that are configured to obtain images of a scene using visible light that are converted into a depth map (e.g., stereo image) and one or more other cameras that are configured to form images, or thermograms, of the scene using infrared radiation ("IR"). The depth information and thermal information are combined to form a representation of the scene based on both depth and thermal information.