Super-Resolved Image Tracking for Missile Guidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing tracking technologies, particularly in homing missiles, face inaccuracies due to limitations in image-processing capabilities, which result in reduced accuracy and increased risk of missing the target, and are constrained by size, weight, and computational demands, especially when dealing with high-speed targets.

Innovation Solution

A method and apparatus that utilize super-resolution image processing to enhance tracking accuracy by calculating a super-resolved image from a plurality of images, de-resolving it, and correlating it with a lower quality image to improve target location identification, while being computationally efficient and capable of real-time processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If advanced image-processing equipment is added to improve tracking accuracy, then tracking precision improves, but device weight and cost increase

Engineering Contradiction:
Improvetracking accuracyVSAvoidmissile weight
Core Design Contradiction:
Measurement precisionVSWeight of moving object

Solution Approach 1:

The patent combines multiple low-resolution images into a single super-resolved image through image fusion techniques. By merging information from multiple frames and applying super-resolution algorithms, the system achieves high-tracking precision without requiring heavy advanced image-processing equipment, thus resolving the contradiction between tracking accuracy and device weight

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from spatial resolution enhancement to temporal dimension utilization by processing sequences of images over time. Instead of relying on single high-resolution images requiring powerful hardware, the system uses temporal super-resolution across multiple frames to achieve high tracking accuracy with lighter computational equipment

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

2Measurement precision

If advanced image-processing equipment is added to improve tracking accuracy, then tracking precision improves, but device cost increases

Engineering Contradiction:
Improvetracking accuracyVSAvoidimage-processing equipment cost
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines multiple low-resolution images into a single super-resolved image through image fusion techniques. By merging information from multiple frames and applying super-resolution algorithms, the system achieves high-tracking precision without requiring heavy advanced image-processing equipment, thus resolving the contradiction between tracking accuracy and device weight

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from spatial resolution enhancement to temporal dimension utilization by processing sequences of images over time. Instead of relying on single high-resolution images requiring powerful hardware, the system uses temporal super-resolution across multiple frames to achieve high tracking accuracy with lighter computational equipment

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

3Measurement precision

If computationally demanding image-processing techniques are used to improve tracking accuracy, then measurement precision improves, but processing speed decreases

Engineering Contradiction:
Improvetarget location accuracyVSAvoidimage-processing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent performs preliminary registration and alignment of multiple images before super-resolution processing. By pre-aligning images using feature matching and transformation matrices, the system reduces computational complexity during the actual super-resolution phase, enabling both high target location accuracy and real-time processing speeds required for fast-moving targets

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent segments the image-processing task into distinct stages: image registration, feature extraction, super-resolution computation, and correlation tracking. This segmentation allows optimization of each stage independently, with computationally intensive super-resolution applied only to registered image sequences rather than raw images, thereby maintaining both precision and processing speed

Inventive Principle:
Principle #1Segmentation

4Measurement precision

If more images are processed to improve super-resolution quality, then measurement precision improves, but loss of time increases

Engineering Contradiction:
Improvetarget location accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements periodic processing where super-resolution is applied at specific intervals rather than continuously to every frame. By processing image sequences at optimized intervals and using motion compensation between frames, the system maintains high target location accuracy while reducing overall processing time and enabling real-time tracking of fast-moving targets

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP3028246B1Method and apparatus for tracking an object
Publication Date: 2020.12.16 MBDA UK
  • EP3028246B1 patent drawingFigure 1(a)~3
  • EP3028246B1 patent drawingFigure 4(a)~4(b)
  • EP3028246B1 patent drawingFigure 5(a)

AI summary

In a method of tracking an object, a plurality of images of a target object is obtained. A super-resolved image of the target object is calculated from the plurality of images. A further image of the target object is obtained. The further image is correlated with the super-resolved image, in order to identify the location of the target object in the further image.