Thermal Image Warm-Target Detection Outline Formation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques face challenges in effectively depicting warm targets in complex environments, especially when imaging conditions are poor or when competing scene contents interfere with the target, making simultaneous depiction difficult or impossible.

Innovation Solution

An image processing system that receives thermal images from sensors, applies filters using moving windows to generate outlines, and uses continuous, monotonic color maps with independent controls to enhance target depiction, while also considering image quality metrics and fusion of images from different sensors to improve visibility.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If thermal imaging is used to detect warm targets in complex environments, then target detection capability is improved, but image quality and target visibility deteriorate due to poor imaging conditions and competing scene contents

Engineering Contradiction:
Improvetarget detection capabilityVSAvoidimage quality
Core Design Contradiction:
Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The patent segments the thermal image processing into multiple independent stages: initial filtering to generate target candidates, quality metric evaluation to assess each candidate region, and selective enhancement processing. This segmentation allows the system to focus computational resources on potential targets rather than processing the entire image uniformly, thereby maintaining detection capability while improving image quality for target regions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality enhancement to specific regions of the thermal image where warm targets are detected. By using quality metrics to identify target regions and applying enhancement processing only to those regions, the system improves local image quality and target visibility without degrading the overall image or wasting resources on non-target areas.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If filters are applied to generate target outlines, then target visibility is improved, but processing complexity increases

Engineering Contradiction:
Improvetarget visibilityVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies filtering operations to generate target outlines and quality metrics before the final enhancement stage. This preliminary action prepares the image data by identifying potential targets and their boundaries, which simplifies subsequent enhancement processing by focusing computations only on regions of interest rather than the entire image.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent extracts target outlines and quality metric information from the thermal image through filtering operations. By separating the target detection and outlining functions from the main enhancement process, the system can generate clear target boundaries while keeping the overall processing architecture modular and manageable.

Inventive Principle:
Principle #2Taking out (Extraction)

3Measurement precision

If image enhancement processing is applied to improve target depiction, then target visibility is improved, but competing scene contents may interfere and make simultaneous depiction difficult

Engineering Contradiction:
Improvetarget depiction qualityVSAvoidscene content interference
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent applies enhancement processing locally to regions identified as containing warm targets, rather than enhancing the entire image. By using quality metrics to mask non-target regions, the system improves target depiction quality while preserving the natural appearance of competing scene contents, avoiding the interference that would result from uniform enhancement.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent introduces quality metrics as an intermediary between the thermal image and the enhancement process. These metrics act as a mediator that identifies target regions and controls where enhancement is applied, allowing the system to improve target depiction while maintaining the integrity of other scene contents that should not be enhanced.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3703002B1Thermal image warm-target detection and outline formation
Publication Date: 2023.05.31 GOODRICH CORP
  • EP3703002B1 patent drawingFigure 1A
  • EP3703002B1 patent drawingFigure 1B
  • EP3703002B1 patent drawingFigure 2

AI summary

An image processing system is provided. The image processing system includes a memory configured to store instructions and a processor disposed in communication with the memory. The processor, upon execution of the instructions is configured to receive an input image output by an imaging sensor, wherein the image sensor is sensitive to thermal emissions. The processor, upon execution of the instructions, is further configured to determine a continuous and monotonic color map for each of at least two color channels of a color scheme system, apply at least one filter to the input image by sliding a moving window through the entire input image and applying the filter to content of the input image at each location of the moving window to generate an outline of a warm target based on the content of the input image, and output a result of the applied at least one filter mapped in accordance with the color maps to a displayable image product.