Multi-Label Remote Sensing Scene Classification Using Multi-Bag Integration

Abstract

For remote sensing (RS) scene classification, most of the existing techniques annotate a scene image with merely a single semantic label. However, with the recent advance of remote sensing technology, more abundant information is contained in high-resolution scenes, making a scene image having multiple semantic meanings (i.e., multilabels). Since multi-label RS scene image annotation is a domain full of challenges due to the ambiguities between complicated scene contents and labels, it motivates us to present a novel algorithm which is based on multi-bag integration. First, to describe the semantic content of RS scene image, we propose to partition a scene image into image patches, defined by a regular grid, and extract the heterogeneous features within each. Second, two kinds of image instance bag, namely segmented instance bag (SIB) and layered instance bag (LIB), are designed to represent the scene image. Third, a Mahalanobis distance-based K-Medoids approach is applied to cluster SIB and LIB, respectively, to convert the multi-instance into single-instance, and then the obtained two single-instances are concatenated to generate more powerful scene-aware representation. At last, a multi-class classification technique is used to make predictions on the class labels. Experiments are performed on real remote sensing images and the results show that the proposed method is valid and can achieve superior performance to a number of stateof-the-art approaches.

Aerial scene understanding in the wild: Multi-scene recognition via prototype-based memory networks

“…In recent years, many efforts ( Zhu et al, 2017 ), e.g., developing novel network architectures ( Murray et al, 2019 , Cheng et al, 2020 , Bi et al, 2020 , Niazmardi et al, 2017 , Lin et al, 2020 , Zhu et al, 2018 ) and pipelines ( Byju et al, 2000 , Xu et al, 2020 , Wang et al, 2019 , Zhu et al, 2019 ), publishing large-scale datasets ( Xia et al, 2017 , Jin et al, 2018 ), introducing multi-modal and multi-temporal data ( Hu et al, 2020 , Tuia et al, 2016 , Ru et al, 2020 , Li et al, 2020a ), have been deployed to address this task, and most of them treat it as a single-label classification problem. A common assumption shared by these researches is that an aerial image belongs to only one scene category, while in real-world scenarios, it is more often that there exist various scenes in a single image (cf.…”

Global Context-Based Multilevel Feature Fusion Networks for Multilabel Remote Sensing Image Scene Classification

“…ITH the development of remote sensing (RS) technology, the resolution of remote sensing images has been increasing continuously, and so far high-resolution (HR) or very high-resolution (VHR) RS images have been used in various applications, such as urban cartography [1], land use determination [2]- [3], and terrain surface analysis [4]. However, X. Wang and L. Duan are with the College of Computer and Information, Hohai University, Nanjing 211100, China (e-mail: wang_xin@hhu.edu.cn ).…”

“…A diversity of algorithms have been proposed for multi-label classification. Earlier studies mainly rely on different hand-crafted features equipped with various classifiers for classification [2], [4]- [7]. For example, Tan et al [4] proposed a low rank representation based algorithm for RS image MLC.…”

“…Zhou et al [5] introduced a multi-instance multi-label learning framework for scene understanding. Wang et al [2] designed a multi-bag integration approach to annotate RS scene images. Wu et al [7] integrated channel features extraction, feature learning, image pyramid matching, etc., into a unified framework, called ORSIm detector, for RS object detection.…”

Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks

“…In recent years, many efforts [19], e.g., developing novel network architectures [20,21,22,23,24,25] and pipelines [26,27,28,29], publishing large-scale datasets [30,31], introducing multi-modal and multi-temporal data [32,33,34,35], have been deployed to address this task, and most of them treat it as a single-label classification problem. A common assumption shared by these researches is that an aerial image belongs to only one scene category, while in real-world scenarios, it is more often that there exist various scenes in a single image (cf.…”