Synthetic Aircraft Modeling for Visual Docking Guidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing aircraft docking systems rely heavily on human intervention and are inefficient in detecting and guiding various aircraft types, especially in adverse weather conditions, lacking sufficient data sets for accurate guidance and requiring costly manual testing processes.
Innovation Solution
A learning-based guidance system using neural networks processes low-cost image sensors to generate synthetic docking videos for new aircraft models, incorporating 3D modeling and photometric/climatic variations to provide real-time detection and classification, enabling automatic docking guidance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual testing with real aircraft videos is used to test VDGS, then testing accuracy is improved, but time consumption and cost increase significantly
Solution Approach 1:
The patent creates synthetic aircraft videos by rendering 3D aircraft models from top-down perspective images captured during actual docking operations. These synthetic videos serve as copies that preserve the essential visual characteristics needed for VDGS testing without requiring actual aircraft presence, thereby solving the contradiction between testing accuracy and time consumption
Solution Approach 2:
The system performs preliminary capture and processing of top-down perspective images during normal docking operations to build a library of aircraft models. This preliminary action enables subsequent synthetic video generation to be performed quickly without requiring actual aircraft for each test scenario, addressing both accuracy and time efficiency
2Reliability
If comprehensive real aircraft video data is collected for every aircraft model, then system reliability is improved, but operational complexity and cost increase
Solution Approach 1:
The patent creates a universal aircraft modeling system that can generate synthetic videos for any aircraft type using a standardized process. The system extracts essential visual features from top-down images and renders them in a consistent format that works across all aircraft models, eliminating the need for separate data collection processes for each aircraft type while maintaining system reliability
Solution Approach 2:
By creating synthetic copies of aircraft videos from 3D models derived from top-down perspectives, the system achieves comprehensive coverage of all aircraft models without the operational complexity of collecting real videos for each model. The synthetic copies preserve the necessary visual information for reliable VDGS testing
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Automated visual docking guidance in and near a bridge area is described herein. One method for aircraft detection, including capturing camera image data of a new aircraft; generating a segmented aircraft mask; segmenting the image data of the new aircraft into body part segmentation data; classifying the body part segmentation data into a plurality of classes; analyzing each class of body part segmentation data to predict an aircraft type for the new aircraft; determining the aircraft type of the new aircraft based on the prediction analysis; and synthetic video generation of new aircraft for generating aircraft specific docking guidance for the new aircraft based on the determined aircraft type.