Depth Cues for 3D Perception in Non-Visible Spectrum Images

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Non-visible spectrum images, such as those captured by infrared sensors, suffer from poor depth perception of three-dimensional features within the scene.

Innovation Solution

A method and system that captures a non-visible spectrum image and generates depth cues based on three-dimensional data, using virtual light sources, virtual objects, or contour lines to enhance depth perception, which can be applied to the image to create an enhanced depth perception image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If non-visible spectrum sensors are used to capture images, then the ability to detect objects in the scene is improved, but the depth perception of three-dimensional features deteriorates

Engineering Contradiction:
Improveobject detection capabilityVSAvoiddepth perception
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent combines non-visible spectrum image data with visible spectrum image data and depth map data to create an enhanced image that preserves both the detection capabilities of non-visible spectrum sensors and the depth perception capabilities provided by visible spectrum sensors and depth maps

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent uses depth maps and visible spectrum images as intermediary data to bridge the gap between non-visible spectrum image data and depth perception, allowing the system to infer depth information from multiple data sources

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If only two-dimensional image data is used, then the simplicity of image processing is maintained, but the three-dimensional understanding of the scene is lost

Engineering Contradiction:
Improveimage processing simplicityVSAvoidthree-dimensional feature perception
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent transitions from two-dimensional image data to three-dimensional enhanced images by incorporating depth map information and generating depth cues that provide vertical and depth dimension information, enabling three-dimensional understanding while maintaining processing efficiency

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

3Measurement precision

If depth cues are added to non-visible spectrum images, then the depth perception is enhanced, but the authenticity of the original image data is compromised

Engineering Contradiction:
Improvedepth perceptionVSAvoidimage data authenticity
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent merges multiple data sources including non-visible spectrum images, visible spectrum images, and depth maps to create an enhanced image that maintains the authenticity of original data while adding depth perception capabilities through integrated processing

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS12530791B2Methods and systems for enhancing depth perception of a non-visible spectrum image of a scene
Publication Date: 2026.01.20 ELBIT SYSTEMS LTD
  • US12530791B2 patent drawing
  • US12530791B2 patent drawing
  • US12530791B2 patent drawing

AI summary

A method and system for providing depth perception to a two-dimensional (2D) representation of a given three-dimensional (3D) object within a 2D non-visible spectrum image of a scene is provided. The method comprises: capturing the 2D non-visible spectrum image at a capture time, by at least one non-visible spectrum sensor; obtaining 3D data regarding the given 3D object independently of the 2D non-visible spectrum image; generating one or more depth cues based on the 3D data; applying the depth cues on the 2D representation to generate a depth perception image that provides the depth perception to the 2D representation; and displaying the depth perception image.