AFTD: a foreground target detection dataset for airport scenario
Keywords: airport surface.+video surveillance.+object detection.+movable target
TL;DR: This paper mainly introduces the dataset AFTD for airport surveillance scenarios, and presents relevant experiments and discusses relevant challenges.
Abstract: The detection of foreground targets on airport surface is the foundation of airport surveillance applications. However, effective algorithms and specialized benchmarks are still lacking in this area. Based on this fact, we propose an Airport Foreground Target Detection dataset (AFTD), which contains the three most important foreground targets moving on the airport surface: aircraft, vehicle, and person. Through self collection and collection of web images, we have obtained a total of over 200000 images and filtered out 10050 images based on diversity principles to form the AFTD dataset, which includes a total of 26968 aircraft instances, 24759 vehicle instances, and 5064 person instances. AFTD includes a variety of changes of these targets, such as super multi-scale, multi-level occlusion and viewangle changes, etc. In addition, we further illustrate the challenges posed by AFTD to existing algorithms through statistical analysis and detailed experiments, and discuss how to solve these challenges in the airport surveillance scenario.The AFTD dataset can be downloaded from http://www.agvs-caac.com/aftd/aftd.html.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10783
Loading