Publications by authors named "Zide Fan"
Article Synopsis
- The study presents a new scheme for detecting ships in remote sensing images, integrating deep learning for ship body detection and feature-based processing for wake detection.
- By modeling the sea region and analyzing image quality, the method effectively identifies ships even if they are obscured by clouds or outside the image boundaries, resulting in a low rate of false alarms.
- The proposed approach has demonstrated high success rates, detecting over 93.5% of visible ships and more than 70% of targets without visible ship bodies in real datasets, highlighting its practical application in remote sensing.
In the field of remote sensing technology, the semantic segmentation of remote sensing images carries substantial importance. The creation of high-quality models for this task calls for an extensive collection of image data. However, the manual annotation of these images can be both time-consuming and labor-intensive.
View Article and Find Full Text PDF