Multi-Class Segmentation of Urban Floods from Multispectral Imagery Using Deep Learning

Potnis, Abhishek V.; Shinde, Rajat C.; Durbha, Surya S.; Kurte, Kuldeep

doi:10.1109/igarss.2019.8900250

Cited by 9 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A major focus is on damage assessment after natural hazards like earthquakes [291][292][293], tsunamis [294,295], their combination [296] or wildfires [297]. In four studies flooded areas were derived, two by spaceborne sensors on a larger scale [298,299] and two by UAVs for fast response mapping on a local scale [300,301]. Also, on a local scale with UAVs, slope failures were investigated by Ghorbanzadeh et al [302].…”

Section: Natural Hazardsmentioning

confidence: 99%

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

2020

View full text Add to dashboard Cite

In Earth observation (EO), large-scale land-surface dynamics are traditionally analyzed by investigating aggregated classes. The increase in data with a very high spatial resolution enables investigations on a fine-grained feature level which can help us to better understand the dynamics of land surfaces by taking object dynamics into account. To extract fine-grained features and objects, the most popular deep-learning model for image analysis is commonly used: the convolutional neural network (CNN). In this review, we provide a comprehensive overview of the impact of deep learning on EO applications by reviewing 429 studies on image segmentation and object detection with CNNs. We extensively examine the spatial distribution of study sites, employed sensors, used datasets and CNN architectures, and give a thorough overview of applications in EO which used CNNs. Our main finding is that CNNs are in an advanced transition phase from computer vision to EO. Upon this, we argue that in the near future, investigations which analyze object dynamics with CNNs will have a significant impact on EO research. With a focus on EO applications in this Part II, we complete the methodological review provided in Part I.

show abstract

Section: Natural Hazardsmentioning

confidence: 99%

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

2020

View full text Add to dashboard Cite

show abstract

“…proposed an approach to obtain waterlogging depth from video images using CNN. Hong et al, 2004;Hayatbini et al, 2019;Pan et al, 2019;Potnis et al, 2019;Jain et al, 2020;Jiang et al, 2020 Knowledge-based approaches Kurte et al (2017) used a semantics-driven framework to enable spatial relationships based semantic queries to detect flooded regions from satellite imagery and further extended the framework (Kurte et al, 2019) to accommodate temporal dimension that enabled spatio-temporal queries over flooded regions. In a similar approach, Potnis et al (2018) developed a flood scene ontology (FSO) which formally defines complex classes such as Accessible Residential Buildings, to classify flooded regions in urban area from satellite imagery.…”

Section: Xu Et Al 2019amentioning

confidence: 99%

Toward Urban Water Security: Broadening the Use of Machine Learning Methods for Mitigating Urban Water Hazards

Allen‐Dumas

Kurte

et al. 2021

Front. Water

Self Cite

View full text Add to dashboard Cite

Due to the complex interactions of human activity and the hydrological cycle, achieving urban water security requires comprehensive planning processes that address urban water hazards using a holistic approach. However, the effective implementation of such an approach requires the collection and curation of large amounts of disparate data, and reliable methods for modeling processes that may be co-evolutionary yet traditionally represented in non-integrable ways. In recent decades, many hydrological studies have utilized advanced machine learning and information technologies to approximate and predict physical processes, yet none have synthesized these methods into a comprehensive urban water security plan. In this paper, we review ways in which advanced machine learning techniques have been applied to specific aspects of the hydrological cycle and discuss their potential applications for addressing challenges in mitigating multiple water hazards over urban areas. We also describe a vision that integrates these machine learning applications into a comprehensive watershed-to-community planning workflow for smart-cities management of urban water resources.

show abstract

“…Recent research in computer vision has combined high spatial resolution satellite images with machine learning to estimate disaster damage at a pixel or incident level (Potnis et al, 2019;Bai et al, 2020;Weber and Kané, 2020;Gupta and Shah, 2021;Wu et al, 2021). These approaches use the XBD dataset created by Gupta et al (2019), the largest disaster damage dataset worldwide, providing pre-and post-disaster images with pixel-level damage labels.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed classification models were trained with a large number of damage labels specific to their input image data. With methodological advances in machine learning techniques, semantic segmentation models built on detailed pixel-level ground-truth data have also emerged (Potnis et al, 2019;Bai et al, 2020;Weber and Kané, 2020;Gupta and Shah, 2021;Wu et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Disaster assessment using computer vision and satellite imagery: Applications in detecting water-related building damages

Kim

Won²,

Lee³

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

The increasing frequency and severity of water-related disasters such as floods, tornadoes, hurricanes, and tsunamis in low- and middle-income countries exemplify the uneven effects of global climate change. The vulnerability of high-risk societies to natural disasters has continued to increase. To develop an effective and efficient adaptation strategy, local damage assessments must be timely, exhaustive, and accurate. We propose a novel deep-learning-based solution that uses pairs of pre- and post-disaster satellite images to identify water-related disaster-affected regions. The model extracts features of pre- and post-disaster images and uses the feature difference with them to predict damage in the pair. We demonstrate that the model can successfully identify local destruction using less granular and less complex ground-truth data than those used by previous segmentation models. When tested with various water-related disasters, our detection model reported an accuracy of 85.9% in spotting areas with damaged buildings. It also achieved a reliable performance of 80.3% in out-of-domain settings. Our deep learning-based damage assessment model can help direct resources to areas most vulnerable to climate disasters, reducing their impacts while promoting adaptive capacities for climate-resilient development in the most vulnerable regions.

show abstract

Multi-Class Segmentation of Urban Floods from Multispectral Imagery Using Deep Learning

Cited by 9 publications

References 4 publications

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

Object Detection and Image Segmentation with Deep Learning on Earth Observation Data: A Review—Part II: Applications

Toward Urban Water Security: Broadening the Use of Machine Learning Methods for Mitigating Urban Water Hazards

Disaster assessment using computer vision and satellite imagery: Applications in detecting water-related building damages

Contact Info

Product

Resources

About