Small Object Detection in Remote Sensing Images Based on Redundant Feature Removal and Progressive Regression

被引：7

作者：

Yang, Yang ^{[1
]}

Zang, Bingjie ^{[1
]}

Song, Chunying ^{[1
]}

Li, Beichen ^{[1
]}

Lang, Yue ^{[2
]}

Zhang, Wenyuan ^{[3
]}

Huo, Peng ^{[4
]}

机构：

[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin 300072, Peoples R China

[2] Hebei Univ Technol, Sch Elect & Informat Engn, Tianjin 300401, Peoples R China

[3] China Univ Min & Technol, Sch Environm & Spatial Informat, Xuzhou 221116, Peoples R China

[4] Longyuan Beijing Renewable Energy Engn Technol Co, High Voltage Syst Dept, Beijing 100034, Peoples R China

来源：

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2024年 / 62卷

基金：

中国国家自然科学基金;

关键词：

Feature extraction; Object detection; Semantics; Location awareness; Remote sensing; Interference; Detectors; Feature filter; progressive regression; remote sensing images (RSIs); small object detection;

D O I：

10.1109/TGRS.2024.3417960

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Small object detection in large-scale remote sensing images (RSIs) is crucial for military and civil applications, but it remains challenging. Since small objects occupy few pixels, their features are easily interfered with by complex backgrounds and large objects. In addition, they are susceptible to localization offsets, which are prone to false or missed detections as there are few predicted bounding boxes matching the ground truth. To overcome these issues, this article proposes a filter progressive small object detection (FPSOD) model that is based on the progressive mechanism. With the proposed attention-based soft-threshold filtering module, FPSOD significantly filters out redundant information in high-level feature maps thus enhancing the semantic features of small objects. Furthermore, a progressive regression loss (PR-Loss) function is proposed to facilitate the precise localization, which mitigates predicted bounding box drift by limiting the fluctuated range of the gradients. The experimental results show that the proposed model substantially improves the precision and recall of small objects, effectively reduces missed detections, and improves detection performance.

引用

页数：14