CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection

TL;DR

This paper presents an infrastructure-free, CNN-based method for estimating camera pose and localizing scan images on aircraft surfaces, enabling automated visual inspection in outdoor airport environments.

Contribution

It introduces a novel approach using a CNN fine-tuned on synthetic images with domain randomization and aircraft geometry to accurately estimate camera pose without external infrastructure.

Findings

Achieved RMS camera pose errors below 0.24 meters and 2 degrees.

Demonstrated effectiveness on real aircraft in outdoor conditions.

Proposed workflow improves initialisation and scan path planning.

Abstract

General Visual Inspection is a manual inspection process regularly used to detect and localise obvious damage on the exterior of commercial aircraft. There has been increasing demand to perform this process at the boarding gate to minimise the downtime of the aircraft and automating this process is desired to reduce the reliance on human labour. Automating this typically requires estimating a camera's pose with respect to the aircraft for initialisation but most existing localisation methods require infrastructure, which is very challenging in uncontrolled outdoor environments and within the limited turnover time (approximately 2 hours) on an airport tarmac. Additionally, many airlines and airports do not allow contact with the aircraft's surface or using UAVs for inspection between flights, and restrict access to commercial aircraft. Hence, this paper proposes an on-site method that is infrastructure-free and easy to deploy for estimating a pan-tilt-zoom camera's pose and localising scan images. This method initialises using the same pan-tilt-zoom camera used for the inspection task by utilising a Deep Convolutional Neural Network fine-tuned on only synthetic images to predict its own pose. We apply domain randomisation to generate the dataset for fine-tuning the network and modify its loss function by leveraging aircraft geometry to improve accuracy. We also propose a workflow for initialisation, scan path planning, and precise localisation of images captured from a pan-tilt-zoom camera. We evaluate and demonstrate our approach through experiments with real aircraft, achieving root-mean-square camera pose estimation errors of less than 0.24 m and 2 degrees for all real scenes.