Accurate Instance Segmentation for Remote Sensing Images via Adaptive and Dynamic Feature Learning
Open Access
- 25 November 2021
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 13 (23) , 4774
Abstract
Instance segmentation for high-resolution remote sensing images (HRSIs) is a fundamental yet challenging task in earth observation, which aims at achieving instance-level location and pixel-level classification for instances of interest on the earth’s surface. The main difficulties come from the huge scale variation, arbitrary instance shapes, and numerous densely packed small objects in HRSIs. In this paper, we design an end-to-end multi-category instance segmentation network for HRSIs, where three new modules based on adaptive and dynamic feature learning are proposed to address the above issues. The cross-scale adaptive fusion (CSAF) module introduces a novel multi-scale feature fusion mechanism to enhance the capability of the model to detect and segment objects with noticeable size variation. To predict precise masks for the complex boundaries of remote sensing instances, we embed a context attention upsampling (CAU) kernel instead of deconvolution in the segmentation branch to aggregate contextual information for refined upsampling. Furthermore, we extend the general fixed positive and negative sample judgment threshold strategy into a dynamic sample selection (DSS) module to select more suitable positive and negative samples flexibly for densely packed instances. These three modules enable a better feature learning of the instance segmentation network. Extensive experiments are conducted on the iSAID and NWU VHR-10 instance segmentation datasets to validate the proposed method. Attributing to the three proposed modules, we have achieved 1.9% and 2.9% segmentation performance improvements on these two datasets compared with the baseline method and achieved the state-of-the-art performance.Keywords
Funding Information
- National Natural Science Foundation of China (61906025, 62176035)
- Chongqing Research Program of Basic Research and Frontier Technology (cstc2020jcyj-msxmX0835, cstc2021jcyj-bsh0155)
- Science and Technology Research Program of Chongqing Municipal Education Commission (KJZD-K202100606)
- Science and Technology Research Program of Chongqing Municipal Education Commission under Grant (KJQN201900607, KJQN202000647, KJQN202100646)
- China Postdoctoral Science Foundation (2021MD703940)
This publication has 51 references indexed in Scilit:
- Learning to Refine Object Segments2016
- Higher Order Conditional Random Fields in Deep Neural Networks2016
- Instance-Sensitive Fully Convolutional Networks2016
- Semisupervised Sparse Manifold Discriminative Analysis for Feature Extraction of Hyperspectral ImagesIEEE Transactions on Geoscience and Remote Sensing, 2016
- A survey on object detection in optical remote sensing imagesISPRS Journal of Photogrammetry and Remote Sensing, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Fast R-CNN2015
- Multi-class geospatial object detection and geographic image classification based on collection of part detectorsISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Multiscale Combinatorial Grouping2014
- CPMC: Automatic Object Segmentation Using Constrained Parametric Min-CutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011