J-DDL: Surface Damage Detection and Localization System for Fighter Aircraft

2025-06-12

AI Summary

To address the low efficiency, poor consistency, and limited coverage of manual inspection for surface damage on fighter aircraft—particularly over complex curved surfaces—this paper proposes a laser-vision fusion intelligent damage detection and 3D localization system. Methodologically, we design a lightweight YOLO-based detection network incorporating the Fasternet backbone, an efficient multi-scale attention (EMA) neck, and the Inner-CIOU loss function; further, we establish a cross-modal mapping mechanism between 2D images and 3D point clouds to achieve sub-millimeter spatial localization. Key contributions include: (1) the first publicly available aircraft-specific surface damage dataset; (2) significant improvements in detecting small targets and low-contrast defects (mAP increased by 8.2%) with 3D localization error <1.5 mm; and (3) automated, high-coverage 3D visualization of full-aircraft surface damage, boosting inspection efficiency by over threefold.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Ensuring the safety and extended operational life of fighter aircraft necessitates frequent and exhaustive inspections. While surface defect detection is feasible for human inspectors, manual methods face critical limitations in scalability, efficiency, and consistency due to the vast surface area, structural complexity, and operational demands of aircraft maintenance. We propose a smart surface damage detection and localization system for fighter aircraft, termed J-DDL. J-DDL integrates 2D images and 3D point clouds of the entire aircraft surface, captured using a combined system of laser scanners and cameras, to achieve precise damage detection and localization. Central to our system is a novel damage detection network built on the YOLO architecture, specifically optimized for identifying surface defects in 2D aircraft images. Key innovations include lightweight Fasternet blocks for efficient feature extraction, an optimized neck architecture incorporating Efficient Multiscale Attention (EMA) modules for superior feature aggregation, and the introduction of a novel loss function, Inner-CIOU, to enhance detection accuracy. After detecting damage in 2D images, the system maps the identified anomalies onto corresponding 3D point clouds, enabling accurate 3D localization of defects across the aircraft surface. Our J-DDL not only streamlines the inspection process but also ensures more comprehensive and detailed coverage of large and complex aircraft exteriors. To facilitate further advancements in this domain, we have developed the first publicly available dataset specifically focused on aircraft damage. Experimental evaluations validate the effectiveness of our framework, underscoring its potential to significantly advance automated aircraft inspection technologies.

Problem

• Detects and localizes surface damage on fighter aircraft
• Overcomes manual inspection scalability and efficiency limitations
• Integrates 2D images and 3D point clouds for precise defect mapping

Innovation

• Integrates 2D images and 3D point clouds
• Uses YOLO-based network with Fasternet blocks
• Maps 2D damage to 3D point clouds