Loading...
Please wait, while we are loading the content...
Similar Documents
Semantic-Edge-Supervised Single-Stage Detector for Oriented Object Detection in Remote Sensing Imagery
| Content Provider | MDPI |
|---|---|
| Author | Cao, Dujuan Zhu, Changming Hu, Xinxin Zhou, Rigui |
| Copyright Year | 2022 |
| Description | In recent years, significant progress has been made in arbitrary-oriented object detection. Different from natural images, object detection in aerial images remains its problems and challenges. Current feature enhancement strategies in this field mainly focus on enhancing the local critical response of the target while ignoring the target’s contextual information, which is indispensable for detecting remote sensing targets in complex backgrounds. In this paper, we innovatively combine semantic edge detection with arbitrary-oriented object detection and propose a feature enhancement network base on a semantic edge supervision module (SES) that realizes an attention-like mechanism in three dimensions of space, channel, and pyramid level. It helps the network pay attention to the edge features of targets at multiple scales to obtain more regression clues. Furthermore, to solve the problem of dense objects with different directions in remote sensing images, we propose a rotation-invariant spatial pooling pyramid (RISPP) to extract the features of objects from multiple orientations. Based on the two feature enhancement modules, we named the network S |
| Starting Page | 3637 |
| e-ISSN | 20724292 |
| DOI | 10.3390/rs14153637 |
| Journal | Remote Sensing |
| Issue Number | 15 |
| Volume Number | 14 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-07-29 |
| Access Restriction | Open |
| Subject Keyword | Remote Sensing Imaging Science Aerial Images Oriented Object Detection Feature Enhancement Convolutional Neural Network |
| Content Type | Text |
| Resource Type | Article |
