Object Probability Maps for Neural Network Change Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated change detection methods in remote sensing data face challenges such as high false positives, sensitivity to noise, and misclassification, especially when comparing images from different sources or over longer time series, limiting their effectiveness in accurately identifying changes in objects of interest.

Innovation Solution

A hybrid change-detection method using dedicated object detectors to generate object probability maps, which are then processed by a neural network to reduce noise and improve specificity, allowing for reliable comparison and interpretation of changes across dissimilar remote sensing data sets, including those from different sensors and time instances.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated change detection methods are used to process remote sensing data, then productivity increases, but false positive rate increases and measurement precision deteriorates

Engineering Contradiction:
Improveautomated processing capabilityVSAvoidchange detection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces an object probability map as an intermediary representation between the input remote sensing images and the change detection output. This intermediate step allows the system to first identify and segment objects with high confidence before performing change detection, thereby maintaining automated processing while improving accuracy by filtering out false positives through probabilistic object validation

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the remote sensing data into discrete objects with associated probability maps, rather than processing pixel-level data directly. This segmentation approach allows the system to focus computational resources on identified objects, improving both productivity through efficient processing and measurement precision through object-level change analysis

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If dedicated object detectors with probability maps are used, then measurement precision improves, but device complexity increases

Engineering Contradiction:
Improveobject detection accuracyVSAvoidsystem architecture complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs a universal object detector architecture that can handle multiple object types and remote sensing data sources through a single probabilistic framework. The same object detection and probability mapping mechanism works across different scenarios, reducing the need for multiple specialized components and thereby limiting the increase in device complexity while maintaining high measurement precision

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

Data Source

PatentEP3997616B1Object-based change detection using a neural network
Publication Date: 2023.09.06 NEO NETHERLANDS GEOMATICS & EARTH OBSERVATION BV
  • EP3997616B1 patent drawingFigure 1
  • EP3997616B1 patent drawingFigure 2
  • EP3997616B1 patent drawingFigure 3

AI summary

A method is described for determining a change in an object or class of objects in image data, wherein the method comprises: receiving a first image data set of a geographical region associated with a first time instance and receiving a second image data set of the geographical region associated with a second time instance; determining a first object probability map on the basis of the first image data set and a second object probability map on the basis of the second image data set, a pixel in the first and second object probability maps having a pixel value, the pixel value representing a probability that the pixel is associated with the object or class of objects; providing the first object probability map and the second object probability map to an input of a neural network, preferably a recurrent neural network, the neural network being trained to determine a probability of a change in the object or class of objects, based on the pixel values in the first object probability map and in the second object probability map; receiving an output probability map from an output of the neural network, a pixel in the output probability map having a pixel value, the pixel value representing a probability of a change in the object or class of objects; and, determining a change in the object or class of objects in the geographical region, based on the output probability map.