Moving Object Detection for Airport Scene Using Patterns of Motion and Appearance
- 1 November 2021
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 18 (11), 852-859
- https://doi.org/10.2514/1.i010902
Abstract
This paper presents a novel method for localization and recognition of moving objects in a real airport surface scene. Different from the traditional applications, moving object detection (MOD) in the airport surface is more challenging because the background is an open outdoor environment, which means that the target objects are usually low in resolution and the MOD task is vulnerable to many undesired changes, such as cloud movement and illumination variations. To address these issues, this paper proposes a unified and effective deep-learning-based MOD architecture, which combines both appearance and motion cues. Specifically, a novel moving region proposal generation module is first designed, which can effectively locate the regions of moving object based on the motion information. Meanwhile, a novel cascade multilayer feature fusion module with transposed convolution is applied to produce both enriched-semantics and fine-resolution convolutional feature maps for category recognition. Finally, a large-scale dataset acquired by the daily surveillance videos of a real airport surface is manually constructed. Results show that the proposed methods outperform state-of-the-art solutions in extracting moving objects from airport surface scenes.Keywords
Funding Information
- National Natural Science Foundation of China (Grant No. U1933134)
- Si-Chuan Science and Technology Program (No. 2020YFG0134)
- Si-Chuan University Grant (No. 2020SCUNG205)
This publication has 24 references indexed in Scilit:
- Fast Edge Detection Using Structured ForestsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Evaluation of the effectiveness of Gaussian filtering in distinguishing punctate synaptic signals from background noise during image analysisJournal of Neuroscience Methods, 2014
- A survey of video datasets for human action and activity recognitionComputer Vision and Image Understanding, 2013
- A background subtraction algorithm for detecting and tracking vehiclesExpert Systems with Applications, 2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Efficient adaptive density estimation per image pixel for the task of background subtractionPattern Recognition Letters, 2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Two-Frame Motion Estimation Based on Polynomial ExpansionLecture Notes in Computer Science, 2003
- A survey on industrial vision systems, applications and toolsImage and Vision Computing, 2002
- An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow DetectionPublished by Springer Science and Business Media LLC ,2002