Biological eagle eye-based method for change detection in water scenes. (February 2022)

• Record Type: Journal Article
• Authors: Li, Xuan; Duan, Haibin; Li, Jingchun; Deng, Yimin; Wang, Fei-Yue
• Is Part Of: Pattern recognition. Volume 122(2022)
• Publication Date: 2022-02
• Subjects: Change detection -- Eagle eye -- Synthetic boat sequence -- Synthetic dataset -- Unmanned aerial vehicle; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108203
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: In this work, a novel biologic computational method based on structure and properties in eagle eyes as proposed for change detection. Besides, we present a cloning method to simulate water scenes and collect a new synthetic dataset (called "Synthetic Boat Sequence") for UAV vision research. The synthetic dataset is available at: https://github.com/lx7555/Synthetic-Boat-Sequence, which may has large potential to benefit the change detection community in the future. Furthermore, we utilize synthetic datasets and corresponding real datasets to conduct change detection experiments. The experimental results demonstrate that the bionic vision model has a good performance in water scenes. Abstract: Change detection (CD) is an important vision task for autonomous landing of unmanned aerial vehicles (UAV) on water. High-density photoreceptors and lateral inhibition mechanisms have inspired a novel biologic computational method based on structure and properties in eagle eyes as proposed for change detection. We call this method "STabCD, " which ensures spatiotemporal distribution consistency to achieve foreground acquisition, noise reduction, and background adaptability. Therefore, our proposed model responds strongly to object information and suppresses noise and wave textures. Then, we present a cloning method to simulate water scenes and collect a new synthetic dataset (called "Synthetic Boat Sequence") for UAV vision research. Besides, we utilize synthetic datasets and corresponding real datasets to conduct change detection experiments. The experimental results indicate that: 1) the STabCD model achieves the best results in real or synthetic water landing scenes; and 2) change detection models for UAV can be quantitatively analyzed and tested under challenging synthetic scenarios.