Back to Search Start Over

Feature-Enhanced CenterNet for Small Object Detection in Remote Sensing Images.

Authors :
Shi, Tianjun
Gong, Jinnan
Hu, Jianming
Zhi, Xiyang
Zhang, Wei
Zhang, Yin
Zhang, Pengfei
Bao, Guangzheng
Source :
Remote Sensing. Nov2022, Vol. 14 Issue 21, p5488. 16p.
Publication Year :
2022

Abstract

Compared with anchor-based detectors, anchor-free detectors have the advantage of flexibility and a lower calculation complexity. However, in complex remote sensing scenes, the limited geometric size, weak features of objects, and widely distributed environmental elements similar to the characteristics of objects make small object detection a challenging task. To solve these issues, we propose an anchor-free detector named FE-CenterNet, which can accurately detect small objects such as vehicles in complicated remote sensing scenes. First, we designed a feature enhancement module (FEM) composed of a feature aggregation structure (FAS) and an attention generation structure (AGS). This module contributes to suppressing the interference of false alarms in the scene by mining multiscale contextual information and combining a coordinate attention mechanism, thus improving the perception of small objects. Meanwhile, to meet the high positioning accuracy requirements of small objects, we proposed a new loss function without extra calculation and time cost during the inference process. Finally, to verify the algorithm performance and provide a foundation for subsequent research, we established a dim and small vehicle dataset (DSVD) containing various objects and complex scenes. The experiment results demonstrate that the proposed method performs better than mainstream object detectors. Specifically, the average precision (AP) metric of our method is 7.2% higher than that of the original CenterNet with only a decrease of 1.3 FPS. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
20724292
Volume :
14
Issue :
21
Database :
Academic Search Index
Journal :
Remote Sensing
Publication Type :
Academic Journal
Accession number :
160219806
Full Text :
https://doi.org/10.3390/rs14215488