Hybrid Feature Aligned Network for Salient Object Detection in Optical Remote Sensing Imagery

Qi Wang, Yanfeng Liu, Zhitong Xiong, Yuan Yuan

Research output: Contribution to journalArticlepeer-review

131 Scopus citations

Abstract

Recently, salient object detection in optical remote sensing images (RSI-SOD) has attracted great attention. Benefiting from the success of deep learning and the inspiration of natural SOD task, RSI-SOD has achieved fast progress over the past two years. However, existing methods usually suffer from the intrinsic problems of optical RSIs: 1) cluttered background; 2) scale variation of salient objects; 3) complicated edges and irregular topology. To remedy these problems, we propose a hybrid feature aligned network (HFANet) jointly modeling boundary learning to detect salient objects effectively. Specifically, we design a hybrid encoder by unifying two components to capture global context for mitigating the disturbance of complex background. Then, to detect multiscale salient objects effectively, we propose a Gated Fold-ASPP (GF-ASPP) to extract abundant context in the deep semantic features. Furthermore, an adjacent feature aligned module (AFAM) is presented for integrating adjacent features with unparameterized alignment strategy. Finally, we propose a novel interactive guidance loss (IGLoss) to combine saliency and edge detection, which can adaptively perform mutual supervision of the two subtasks to facilitate detection of salient objects with blurred edges and irregular topology. Adequate experimental results on three optical RSI-SOD datasets reveal that the presented approach exceeds 18 state-of-the-art ones. All codes and detection results are available at https://github.com/lyf0801/HFANet.

Original languageEnglish
Article number5624915
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume60
DOIs
StatePublished - 2022

Keywords

  • Feature alignment
  • jointing boundary learning
  • multiscale context modeling
  • optical remote sensing image (RSI)
  • salient object detection (SOD)

Fingerprint

Dive into the research topics of 'Hybrid Feature Aligned Network for Salient Object Detection in Optical Remote Sensing Imagery'. Together they form a unique fingerprint.

Cite this