English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Supervised object detection methods provide subpar performance when appliedto Foreign Object Debris (FOD) detection because FOD could be arbitrary objectsaccording to the Federal Aviation Administration (FAA) specification. Currentsupervised object detection algorithms require datasets that contain annotatedexamples of every to-be-detected object. While a large and expensive datasetcould be developed to include common FOD examples, it is infeasible to collectall possible FOD examples in the dataset representation because of theopen-ended nature of FOD. Limitations of the dataset could cause FOD detectionsystems driven by those supervised algorithms to miss certain FOD, which canbecome dangerous to airport operations. To this end, this paper presents aself-supervised FOD localization by learning to predict the runway images,which avoids the enumeration of FOD annotation examples. The localizationmethod utilizes the Vision Transformer (ViT) to improve localizationperformance. The experiments show that the method successfully detectsarbitrary FOD in real-world runway situations. The paper also provides anextension to the localization result to perform classification; a feature thatcan be useful to downstream tasks. To train the localization, this paper alsopresents a simple and realistic dataset creation framework that only collectsclean runway images. The training and testing data for this method arecollected at a local airport using unmanned aircraft systems (UAS).Additionally, the developed dataset is provided for public use and furtherstudies.

Foreign Object Debris Detection for Airport Pavement Images based on Self-supervised Localization and Vision Transformer