SAR-based landslide classification pretraining leads to better segmentation

• URL: http://arxiv.org/abs/2211.09927v1
• Date: Thu, 17 Nov 2022 22:57:18 GMT
• Title: SAR-based landslide classification pretraining leads to better segmentation
• Authors: Vanessa B\"ohm, Wei Ji Leong, Ragini Bal Mahesh, Ioannis Prapas, Edoardo Nemni, Freddie Kalaitzis, Siddha Ganju, Raul Ramos-Pollan
• Abstract summary: Rapid assessment after a natural disaster is key for prioritizing emergency resources. Deep learning algorithms can be applied to SAR data, but training them requires large labeled datasets. Here, we study how deep learning algorithms for landslide segmentation on SAR products can benefit from pretraining.
• Score: 0.8208704543835964
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rapid assessment after a natural disaster is key for prioritizing emergency resources. In the case of landslides, rapid assessment involves determining the extent of the area affected and measuring the size and location of individual landslides. Synthetic Aperture Radar (SAR) is an active remote sensing technique that is unaffected by weather conditions. Deep Learning algorithms can be applied to SAR data, but training them requires large labeled datasets. In the case of landslides, these datasets are laborious to produce for segmentation, and often they are not available for the specific region in which the event occurred. Here, we study how deep learning algorithms for landslide segmentation on SAR products can benefit from pretraining on a simpler task and from data from different regions. The method we explore consists of two training stages. First, we learn the task of identifying whether a SAR image contains any landslides or not. Then, we learn to segment in a sparsely labeled scenario where half of the data do not contain landslides. We test whether the inclusion of feature embeddings derived from stage-1 helps with landslide detection in stage-2. We find that it leads to minor improvements in the Area Under the Precision-Recall Curve, but also to a significantly lower false positive rate in areas without landslides and an improved estimate of the average number of landslide pixels in a chip. A more accurate pixel count allows to identify the most affected areas with higher confidence. This could be valuable in rapid response scenarios where prioritization of resources at a global scale is important. We make our code publicly available at https://github.com/VMBoehm/SAR-landslide-detection-pretraining.

Related papers

• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Deep Homography Estimation for Visual Place Recognition [49.235432979736395]
  We propose a transformer-based deep homography estimation (DHE) network. It takes the dense feature map extracted by a backbone network as input and fits homography for fast and learnable geometric verification. Experiments on benchmark datasets show that our method can outperform several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-25T13:22:17Z)
• Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It [2.1665407462280446]
  State-of-the-art methods are trained predominantly using nuScenes and Argoverse 2 datasets. Over $80$% of nuScenes and $40$% of Argoverse 2 validation and test samples are less than $5$ m from a training sample. We propose geographically disjoint data splits to reveal the true performance in unseen environments.
  arXiv  Detail & Related papers  (2023-12-11T14:43:23Z)
• Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization [56.95046107046027]
  We propose to leverage Neural Radiance Fields (NeRF) to generate training samples for scene coordinate regression. Despite NeRF's efficiency in rendering, many of the rendered data are polluted by artifacts or only contain minimal information gain.
  arXiv  Detail & Related papers  (2023-10-10T20:11:13Z)
• SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data [55.609946936979036]
  We propose a novel spatial event ranking approach named SpatialRank. We show that SpatialRank can effectively identify the top riskiest locations of crimes and traffic accidents.
  arXiv  Detail & Related papers  (2023-09-30T06:20:21Z)
• DeepStay: Stay Region Extraction from Location Trajectories using Weak Supervision [4.243592852049962]
  Mobile devices enable constant tracking of the user's position and location trajectories can be used to infer personal points of interest (POIs) A common way to extract POIs is to first identify regions where a user spends a significant amount of time, known as stay regions (SRs) Common approaches to SR extraction are evaluated either solely unsupervised or on a small-scale private dataset. We propose a weakly and self-supervised transformer-based model called DeepStay, which is trained on location trajectories to predict stay regions.
  arXiv  Detail & Related papers  (2023-06-05T11:16:47Z)
• Deep learning based landslide density estimation on SAR data for rapid response [0.8208704543835964]
  This work aims to produce landslide density estimates using Synthetic Aperture Radar (SAR) satellite imageries to prioritise emergency resources. We use the United States Geological Survey (USGS) Landslide Inventory data annotated by experts after Hurricane Mar'ia in Puerto Rico. Our method obtains 0.814 AUC in predicting the correct density estimation class at the chip level.
  arXiv  Detail & Related papers  (2022-11-18T16:50:02Z)
• Deep Learning for Rapid Landslide Detection using Synthetic Aperture Radar (SAR) Datacubes [0.8208704543835964]
  We provide pre-processed, machine-learning ready SAR datacubes for four globally located landslide events. We study the feasibility of SAR-based landslide detection with supervised deep learning (DL) DL models can be used to detect landslides from SAR data, achieving an Area under the Precision-Recall curve exceeding 0.7.
  arXiv  Detail & Related papers  (2022-11-05T10:31:57Z)
• Relict landslide detection using Deep-Learning architectures for image segmentation in rainforest areas: A new framework [0.5735035463793008]
  A new CNN framework is proposed for semi-automatic detection of relict landslides. A total of 42 combinations of CNNs are tested. Predictions of the proposed framework were more accurate and correctly detected more landslides.
  arXiv  Detail & Related papers  (2022-08-04T14:46:02Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Residual Moment Loss for Medical Image Segmentation [56.72261489147506]
  Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects. Most existing methods encode the location information in an implicit way, for the network to learn. We propose a novel loss function, namely residual moment (RM) loss, to explicitly embed the location information of segmentation targets.
  arXiv  Detail & Related papers  (2021-06-27T09:31:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.