Aircraft Landing Zone Detection Using AI and Dual-Camera Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for controlling aircraft flight movements for landing or dropping loads lack efficient and safe control mechanisms that account for varying ground conditions, particularly in identifying free landing or dropping areas without obstacles.

Innovation Solution

The method employs multiple camera devices on the aircraft to capture image data, using both AI-based and non-AI image analyses to determine overlapping safe landing or drop areas, with position coordinates compared to target sites to ensure clearance or release characteristics are transmitted for safe aircraft control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If only AI-based image analysis is used to determine landing areas, then the accuracy of obstacle detection is improved, but the computational time and processing complexity increase

Engineering Contradiction:
Improvelanding area detection accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The image analysis task is segmented into two independent parts: AI-based analysis for high-accuracy obstacle detection and non-AI analysis for rapid processing. Both analyses operate in parallel on the same image data, and their results are combined to determine the final landing area, thus balancing accuracy and speed requirements

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes the processing parameters by applying different analysis methods (AI and non-AI) with different computational characteristics to the same input data. This allows the system to leverage the strengths of both approaches: high accuracy from AI and fast processing from non-AI methods

Inventive Principle:
Principle #35Parameter changes

2Reliability

If multiple camera devices are used to capture image data from different angles, then the reliability of landing area identification is improved, but the device complexity increases

Engineering Contradiction:
Improvelanding area identification reliabilityVSAvoidcamera system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Multiple camera devices capturing images from different angles are merged into a unified analysis framework. The images from all cameras are processed simultaneously through both AI and non-AI analysis pipelines, and the results are integrated to produce a single reliable landing area identification, thus managing complexity while maintaining reliability

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If both AI-based and non-AI image analyses are performed and their results are compared, then the safety of landing area selection is improved, but the processing complexity increases

Engineering Contradiction:
Improvelanding area selection safetyVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system implements feedback by comparing results from both AI and non-AI analyses. When the results agree, confidence in the landing area selection increases. When they differ, the system can request additional analysis or select the more conservative option, thus improving safety through systematic verification

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

Both AI and non-AI analyses are performed in advance before the final landing decision is made. This preliminary dual analysis ensures that all potential obstacles are identified before commitment to a landing site, improving safety through thorough pre-checking

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4102332B1Method for controlling a flight movement of an aircraft for landing or discarding a load and an aircraft
Publication Date: 2025.01.01 SPLEENLAB GMBH
  • EP4102332B1 patent drawingFigure 1
  • EP4102332B1 patent drawingFigure 2

AI summary

The invention relates to a method for controlling the flight movement of an aircraft for landing, comprising the following steps: acquiring first image data by means of a first camera device (1.1) arranged and configured on an aircraft to capture a ground area, wherein the first image data displays a first sequence of first camera images; acquiring second image data by means of a second camera device (1.2) arranged and configured on the aircraft to capture the ground area, wherein the second image data displays a second sequence of second camera images; and processing the first and second image data by means of an evaluation device (2). The processing of the first and second image data comprises: performing a first artificial intelligence-based image analysis on the first image data, wherein at least one first ground area is determined within the captured ground area;Performing a second image analysis, free of artificial intelligence, on the second image data, whereby at least a second ground area is determined within the captured ground area; determining position coordinates for a free ground area encompassed by the first and second ground areas, if a comparison shows that the first and second ground areas overlap at least in the free ground area; receiving position coordinates for a target location in the monitored ground area from a control device (3) of the aircraft; determining release parameters if a comparison of the position coordinates for the free ground area and the position coordinates for the target location shows a match;and transmission of release data indicating the availability of the destination to the aircraft's control unit (3). The aircraft's flight movement can then be controlled by the control unit (3) to drop a payload and/or land the aircraft at the destination. Furthermore, an aircraft is created.