Cross-domain landslide mapping from large-scale remote sensing images using prototype-guided domain-aware progressive representation learning

Zhang, Xiaokang; Yu, Weikang; Pun, Man-On; Shi, Wenzhong

doi:10.1016/j.isprsjprs.2023.01.018

Cited by 44 publications

(13 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive experiments were conducted on GVLM-CD [43], CLCD [44] and SYSU-CD [45] to verify the practical performance of the proposed MSFGNet. In this section, the above datasets are briefly introduced.…”

Section: B Data Descriptionmentioning

confidence: 99%

“…1) GVLM-CD: GVLM-CD [43] is the first large-scale open source VHR landslide mapping dataset, and it includes 17 pairs of bi-temporal very high resolution images at a resolution of 0.59 meters obtained through the Google Earth service. These images were cropped to a size of 256 × 256 without any overlap, resulting in a total of 7327 pairs.…”

Section: B Data Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images

Huang,

Yuan,

Lam

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Change Detection of remote sensing images is an essential method for observing changes on the Earth's surface. Deep learning can efficiently process remote sensing images. However, shallow features in remote sensing data from different time are inherently inconsistent. During the feature extraction stage, these shallow features are mapped onto different dimensional feature maps, giving rise to noise information. Existing algorithms are ineffective in dealing with noise effectively. This can lead to detection results being influenced by shallow features noise information, resulting in fake detections. To address this issue, Feature Filtering Fusing Network (F3Net) is proposed in this article. In F3Net, Feature Filtering and Aggregation Module (FFA) is designed to integrate bi-temporal remote sensing features, which initially filters out noise information from different temporal domains. Additionally, the Channel Feature Difference Fusion Module (CFDF) is introduced to fuse high-dimensional features. Within CFDF, Channel Information Filtering Convolution (CIFConv) is utilized to filter out noise information from high-dimensional feature channels across multiple receptive fields. In order to verify the performance of F3Net, comparative experiments were conducted on multiple public datasets with other state-of-the-art models, and F3Net achieved the best performance. The code of F3Net can be achieved from https://github.com/juncyan/f3net.git.

show abstract

Section: B Data Descriptionmentioning

confidence: 99%

Section: B Data Descriptionmentioning

confidence: 99%

F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images

Huang,

Yuan,

Lam

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, the limited image resolution (10 m) may result in overlooking small-scale landslides [12]. Zhang et al created a VHR landslide identification dataset using pre-and post-disaster imagery from Google Earth, covering 17 different cities around the world [35]. Meenal et al generated a 3 m resolution landslide dataset based on PlanetScope imagery [14], sampling landslide instances from 10 different geographic regions worldwide, including South Asia, Southeast Asia, East Asia, South America, and Central America.…”

Section: Related Workmentioning

confidence: 99%

“…Finally, to explore the generalization of the model trained on the DMLD, we tested two landslide areas selected from the GVLM dataset using seven advanced deep learning models [35]. Further, the results were analyzed and evaluated to validate the adaptability potential of the DMLD dataset in other mountain environments.…”

Section: Loss Functions Formulas Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

The Diverse Mountainous Landslide Dataset (DMLD): A High-Resolution Remote Sensing Landslide Dataset in Diverse Mountainous Regions

Chen,

Zeng,

Zhu

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The frequent occurrence of landslides poses a serious threat to people’s lives and property. In order to evaluate disaster hazards based on remote sensing images via machine learning means, it is essential to establish an image database with manually labeled boundaries of landslides. However, the existing datasets do not cover diverse types of mountainous landslides. To address this issue, we propose a high-resolution (1 m) diverse mountainous landslide remote sensing dataset (DMLD), including 990 landslide instances across different terrain in southwestern China. To evaluate the performance of the DMLD, seven state-of-the-art deep learning models with different loss functions were implemented on it. The experiment results demonstrate not only that all of these deep learning methods with different characteristics can adapt well to the DMLD, but also that the DMLD has potential adaptability to other geographical regions.

show abstract

Analysis of the impact of terrain factors and data fusion methods on uncertainty in intelligent landslide detection

Zhang,

Lv,

Yang

et al. 2024

Landslides

View full text Add to dashboard Cite

Cross-domain landslide mapping from large-scale remote sensing images using prototype-guided domain-aware progressive representation learning

Cited by 44 publications

References 52 publications

F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images

F3Net: Feature Filtering Fusing Network for Change Detection of Remote Sensing Images

The Diverse Mountainous Landslide Dataset (DMLD): A High-Resolution Remote Sensing Landslide Dataset in Diverse Mountainous Regions

Analysis of the impact of terrain factors and data fusion methods on uncertainty in intelligent landslide detection

Contact Info

Product

Resources

About