We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Aircraft type recognition in 3D-view optical image with contour segmentation.
- Authors
Liang, Zhixiang; Li, Yanshan; Yu, Rui; Zhang, Kaihao
- Abstract
Aircraft type recognition has been researched deeply for plenty years on remote sensing and radar signal processing fields because of military needs. However, with the rapid development of UAV visualization technology in recent years, the advanced optical sensors on high-altitude drones are able to capture high-definition aircraft images of various aircraft flight postures, which brings aircraft type recognition into a brand-new research field. Different from remote sensing images, images with aircrafts in flight have larger intra-class difference caused by flight posture variation, which is 3D-view and more challenging for aircraft type recognition. Facing the new challenges, we propose a aircraft type recognition framework in 3D-view optical images. The framework consists of two stages: a coarse stage for aircraft contour segmentation and a fine stage for aircraft contour template matching. At the coarse stage, we propose a instance segmentation network CP-Deepsnake with a novel loss function CP loss which improves the accuracy of extracted aircraft contours by supervising the global distribution of contour points during contour deformation. At the fine stage, we utilize contour template matching to realize aircraft type recognition in 3D-view images. Based on IDSC contour feature descriptor, we propose a fast contour template matching approach with a new matching evaluation criterion and establish an aircraft contour template database for aircraft contour template matching. To train and test our aircraft type recognition framework, we build two datasets with 3D-view aircraft images of 10 aircraft types. Experiments show that our method achieves considerable recognition accuracy on the aircraft type testing dataset. Besides, we evaluate the proposed CP-Deepsnake network on two challenging instance segmentation public datasets SBD and KINS, where it compares favorably against state-of-the-art methods, which means our CP-Deepsnake network can be extended to more instance segmentation sences like road pedestrian detection and vehicle detection.
- Subjects
OPTICAL sensors; IMAGE segmentation; REMOTE sensing by radar; OPTICAL images; RADAR signal processing; AIRPLANE testing; DRONE aircraft
- Publication
Multimedia Tools & Applications, 2024, Vol 83, Issue 18, p54495
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-023-17542-9