Cloud-Free Composite Geospatial Image Generation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cloud cover significantly hampers satellite and aerial imagery by causing data loss and gaps, as approximately 67% of the Earth's surface is typically covered by clouds, making it difficult to monitor changes in large geographical areas over time.

Innovation Solution

A computer-implemented method and system that virtually temporally stacks satellite or aerial images of the same geographic area, using a virtual temporal projection plane to fill occluded areas in more recent images with cloud-free data from older images, ensuring the creation of composite, cloud-free images for current or historical analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If satellite or aerial imagery is used to monitor large geographical areas, then large-scale information can be gathered, but cloud cover causes data loss and gaps

Engineering Contradiction:
Improvegeographical coverage areaVSAvoiddata loss from cloud cover
Core Design Contradiction:
Area of stationary objectVSLoss of information

Solution Approach 1:

The system performs preliminary action by capturing multiple satellite images of the same geographical area at different times before the final composite image is needed. These pre-captured images are stored and processed to create a temporal stack, allowing cloud-obscured areas in one image to be replaced with clear areas from other images taken at different times, thus preventing data loss before the final analysis occurs

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system merges multiple satellite images taken at different times into a single composite image. By combining information from multiple temporal snapshots, the system creates a cloud-free composite that retains the geographical coverage benefits of satellite imagery while eliminating the data loss problem caused by cloud cover in individual images

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If multiple images are processed to compensate for cloud cover, then cloud-free composite images can be generated, but processing complexity increases

Engineering Contradiction:
Improveaccuracy of geospatial dataVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The processing system applies segmentation by dividing the composite image creation process into distinct steps: capturing individual satellite images, creating a temporal stack, identifying cloud-obscured areas, and replacing them with clear areas from other images. This segmented approach manages processing complexity by breaking down the complex task of cloud compensation into manageable, automated stages

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses an intermediary computational process that automatically matches and replaces cloud-obscured pixels with corresponding clear pixels from other temporal images. This intermediary processing layer handles the complexity of comparing multiple images and determining appropriate replacements, shielding the user from the underlying computational complexity while ensuring reliable cloud-free output

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of time

If the most recent image is used as the base image, then the composite image is as up-to-date as possible, but cloud cover in recent images may still cause occlusions

Engineering Contradiction:
Improvetimeliness of image dataVSAvoidcloud occlusion in recent images
Core Design Contradiction:
Loss of timeVSObject-affected harmful factors

Solution Approach 1:

The system performs preliminary action by pre-processing and storing multiple recent images in a temporal stack before composite image generation. When creating the composite, it systematically works through the stack from most recent to oldest, using the most recent clear areas available, thus preserving timeliness while compensating for cloud occlusions through预先 prepared alternative data

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Instead of discarding recent images with cloud cover, the system inverts the traditional approach by using older images to fill gaps in recent images. The composite image is built by inverting the normal temporal flow, allowing data from older images to supplement and complete the most recent image, thereby maintaining both timeliness and completeness

Inventive Principle:
Principle #13The other way round (Inversion)

Data Source

PatentEP3696768B1Method and system for generating composite geospatial images
Publication Date: 2022.07.27 ORDNANCE SURVEY
  • EP3696768B1 patent drawingFigure 1
  • EP3696768B1 patent drawingFigure 2
  • EP3696768B1 patent drawingFigure 3

AI summary

The present invention provides a computer implemented method and system for compensating for cloud cover to allow the build-up of composite, cloud free images of a particular geographic area. The invention takes satellite or aerial image data as an input and temporally stacks the images for a particular geographic area, with the most recent image at the top. The time for the composite image to be produced (may be the present time, or may be a time from the past) is defined as a temporal projection plane. The most recent image prior to this plane is analysed to identify any areas obscured by clouds. Cloud free areas of the most recent image are projected onto the temporal projection plane. For the identified obscured areas, older, cloud free images in the stack are projected onto the temporal projection plane to fill the obscured areas. This forms a cloud free composite image at the defined temporal projection plane.