Towards optimal foreign object debris detection in an airport environment

Noroozi, Mohammad; Shah, Ankit

doi:10.1016/j.eswa.2022.118829

Cited by 25 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FOD refers to any foreign objects, debris, or substances that have the potential to cause damage to the aircraft. These can include metal components [34], crushed stones, paper products, animals, plants, and more. Among them, metal components are ingested by the engine, and it is very easy to cause accidents.…”

Section: Experimental Dataset Creation and Analysismentioning

confidence: 99%

“…Based on the distribution of foreign objects in actual airport runway scenes and the technical characteristics of deep learning for sample requirements, an Infrared-Visible Foreign Object Debris Dataset (IVFOD) was FOD refers to any foreign objects, debris, or substances that have the potential to cause damage to the aircraft. These can include metal components [34], crushed stones, paper products, animals, plants, and more. Among them, metal components are ingested by the engine, and it is very easy to cause accidents.…”

Section: Experimental Dataset Creation and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Small-Scale Foreign Object Debris Detection Using Deep Learning and Dual Light Modes

Mo,

Wang,

Hong

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The intrusion of foreign objects on airport runways during aircraft takeoff and landing poses a significant safety threat to air transportation. Small-scale Foreign Object Debris (FOD) cannot be ruled out on time by traditional manual inspection, and there is also a potential risk of secondary foreign body intrusion. A deep-learning-based intelligent detection method is proposed to solve the problem of low accuracy and low efficiency of small-scale FOD detection. Firstly, a dual light camera system is utilized for the collection of FOD data. It generates a dual light FOD dataset containing both infrared and visible light images. Subsequently, a multi-attention mechanism and a bidirectional feature pyramid are integrated into the baseline network YOLOv5. This integration prioritizes the extraction of foreign object features and boosts the network’s ability to distinguish FOD from complex backgrounds. Additionally, it enhances the fusion of higher-level features to improve the representation of multi-scale objects. To ensure fast and accurate localization and recognition of targets, the Complete-IoU (CIoU) loss function is used to optimize the bounding boxes’ positions. The experimental results indicate that the proposed model achieves a detection speed of 36.3 frame/s, satisfying real-time detection requirements. The model also attains an average accuracy of 91.1%, which is 7.4% higher than the baseline network. Consequently, this paper verifies the effectiveness and practical utility of our algorithm for the detection of small-scale FOD targets.

show abstract

Section: Experimental Dataset Creation and Analysismentioning

confidence: 99%

Section: Experimental Dataset Creation and Analysismentioning

confidence: 99%

Small-Scale Foreign Object Debris Detection Using Deep Learning and Dual Light Modes

Mo,

Wang,

Hong

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Monitoring obstacles on runways Monitoring vegetation growth and construction activity Amit et al [24] 2022 Wang et al [25] 2020 Noroozi et al [26] 2023 Congress et al [27] 2022 Papadopoulos et al [28] 2021…”

Section: Obstruction Monitoringmentioning

confidence: 99%

“…Noroozi and Shah (2023) crafted a framework that capitalized on the YOLO object detector models, with the YOLOV4 model excelling in speed and accuracy [26]. Papadopoulos and Gonzalez (2021) offered a model to pinpoint foreign object debris (FOD) on runways.…”

Section: Obstruction Monitoringmentioning

confidence: 99%

Monitoring Nodal Transportation Assets with Uncrewed Aerial Vehicles: A Comprehensive Review

Askarzadeh,

Bridgelall,

Tolliver

2024

Drones

View full text Add to dashboard Cite

Using Uncrewed Aerial Vehicles (UAVs) to monitor the condition of nodal transportation assets—airports, seaports, heliports, vertiports, and cargo terminals—presents a transformative approach to traditional inspection methods. The focus on nodal assets rather than linear assets like roads, railways, bridges, and waterways fills a gap in addressing the dynamic challenges specific to transportation hubs. This study reviews scholarly literature on applying UAV-based remote sensing (URS) techniques to assess the condition of various transportation hubs, which are critical junctures in global logistics networks. Utilizing a systematic literature review framework, this study reviewed 486 publications from 2015 to 2023 to extract insights from the evolving discourse on URS applications. The findings suggest that these emerging methods resulted in substantial enhancements in time saving, cost efficiency, safety, and reliability. Specifically, this study presents evidence on how URS approaches can overcome the constraints of conventional inspection methods by enabling rapid, high-precision mapping and surveillance in complex and constrained environments. The findings highlight the role of UAVs in enhancing operational workflows and decision making in transportation planning and maintenance. By bridging the gap between traditional practices and innovative technology, this research offers significant implications for stakeholders in the field, advocating for a shift towards more dynamic, cost-effective, and precise asset management strategies.

show abstract

“…Later these FOD video were split into frames and using You Only Look Once algorithm efficiency detection was done. In [8], YOLOv4 which is one of the YOLO model, is used with transfer learning and obtained fast results for FOD detection. In [9], the authors present a spatial transformer network (STN), region recommendation network (RPN) and convolutional neural network (CNN)-based method for detecting FOD.…”

Section: Introductionmentioning

confidence: 99%

Examining The Effect of Different Networks on Foreign Object Debris Detection

Kaya

2023

Bitlis Eren Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Foreign Object Debris (FOD) at airports poses a risk to aircraft and passenger safety. FOD can seriously harm aircraft engines and injure personnel. Accurate and careful FOD detection is of great importance for a safe flight. According to the FAA's report, FOD types are aircraft fasteners such as nut, safety; aircraft parts such as fuel blast, landing gear parts, rubber parts; construction materials such as wooden pieces, stones; plastic materials, natural plant and animal parts. For this purpose, in this study, the effect of different networks and optimizer on object detection and accuracy analysis were examined by using a data set of possible materials at the airport. AlexNet, Resnet18 and Squeezenet networks were used. Application is applied two stages. The first one, 3000 data were divided into two parts, 70% to 30%, training and test data, and the results were obtained. The second one, 3000 data were used for training, except for the training data, 440 data were used for validation. Also, for each application, both SGDM and ADAM optimizer are used. The best result is obtained from ADAM optimizer with Resnet18, accuracy rate is %99,56.

show abstract

Towards optimal foreign object debris detection in an airport environment

Cited by 25 publications

References 22 publications

Small-Scale Foreign Object Debris Detection Using Deep Learning and Dual Light Modes

Small-Scale Foreign Object Debris Detection Using Deep Learning and Dual Light Modes

Monitoring Nodal Transportation Assets with Uncrewed Aerial Vehicles: A Comprehensive Review

Examining The Effect of Different Networks on Foreign Object Debris Detection

Contact Info

Product

Resources

About