Segmentation of Vegetation and Flood from Aerial Images Based on Decision Fusion of Neural Networks

Ichim, Loretta; Popescu, Dan

doi:10.3390/rs12152490

Cited by 13 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This classification is usually binary (e.g., Peng et al, 2019;Nemni et al, 2020) but it can also be extended to include permanent water bodies (Sarker et al, 2019) (see the example Fig. 1b), vegetation (Ichim and Popescu, 2020), buildings (Hashemi-Beni and Gebrehiwot, 2021), and more (Muñoz et al, 2021). All the types of floods were well represented for this application but flash floods (Fig.…”

Section: Deep Learning For Flood Inundationmentioning

confidence: 99%

“…Satellite data is the most used input for flood inundation applications (e.g., Sarker et al, 2019;Peng et al, 2019;Nogueira et al, 2017). Other input data sources include unmanned aerial vehicles data (UAV) (e.g., Gebrehiwot et al, 2019;Ichim and Popescu, 2020), hydrographs (e.g., Hou et al, 2021) and DEMs (e.g., Hashemi-Beni and Gebrehiwot, 2021;Muñoz et al, 2021). Inundation maps produced by 3D numerical models are also used as target prediction (Muñoz et al, 2021) remote sensing data that represent a flood event seen from above.…”

Section: Input and Output Datamentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Bentivoglio

Isufi

Jonkman

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. Deep Learning techniques have been increasingly used in flood risk management to overcome the limitations of accurate, yet slow, numerical models, and to improve the results of traditional methods for flood mapping. In this paper, we review 45 recent publications to outline the state-of-the-art of the field, identify knowledge gaps, and propose future research directions. The review focuses on the type of deep learning models used for various flood mapping applications, the flood types considered, the spatial scale of the studied events, and the data used for model development. The results show that models based on convolutional layers are usually more accurate as they leverage inductive biases to better process the spatial characteristics of the flooding events. Traditional models based on fully-connected layers, instead, provide accurate results when coupled with other statistical models. Deep learning models showed increased accuracy when compared to traditional approaches and increased speed when compared to numerical methods. While there exist several applications in flood susceptibility, inundation, and hazard mapping, more work is needed to understand how deep learning can assist real-time flood warning during an emergency, and how it can be employed to estimate flood risk. A major challenge lies in developing deep learning models that can generalize to unseen case studies and sites. Furthermore, all reviewed models and their outputs, are deterministic, with limited considerations for uncertainties in outcomes and probabilistic predictions. The authors argue that these identified gaps can be addressed by exploiting recent fundamental advancements in deep learning or by taking inspiration from developments in other applied areas. Models based on graph neural networks and neural operators can work with arbitrarily structured data and thus should be capable of generalizing across different case studies and could account for complex interactions with the natural and built environment. Neural operators can also speed up numerical models while preserving the underlying physical equations and could thus be used for reliable real-time warning. Similarly, probabilistic models can be built by resorting to Deep Gaussian Processes.

show abstract

Section: Deep Learning For Flood Inundationmentioning

confidence: 99%

Section: Input and Output Datamentioning

confidence: 99%

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Bentivoglio

Isufi

Jonkman

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This classification is usually binary (e.g., Peng et al, 2019;Nemni et al, 2020) but it can also be extended to include permanent water bodies (e.g., Sarker et al, 2019) (see the example Fig. 1a), vegetation (e.g., Ichim and Popescu, 2020), buildings (e.g., Hashemi-Beni and Gebrehiwot, 2021), and more (e.g., Muñoz et al, 2021). All the types of floods were well represented for this application but flash floods (Fig.…”

Section: Deep Learning For Flood Inundationmentioning

confidence: 99%

“…Satellite data is the most used input for flood inundation applications (e.g., Sarker et al, 2019;Peng et al, 2019;Nogueira et al, 2017). Other input data sources include unmanned aerial vehicles data (UAV) (e.g., Gebrehiwot et al, 2019;Ichim and Popescu, 2020), hydrographs (e.g., Hou et al, 2021) and DEMs (e.g., Hashemi-Beni and Gebrehiwot, 2021;Muñoz et al, 2021). Only Dong et al (2021) differ from the other papers by considering sensors in place of flood pictures.…”

Section: Input and Output Datamentioning

confidence: 99%

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Bentivoglio

Isufi

Jonkman

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Deep Learning techniques have been increasingly used in flood management to overcome the limitations of accurate, yet slow, numerical models, and to improve the results of traditional methods for flood mapping. In this paper, we review 58 recent publications to outline the state-of-the-art of the field, identify knowledge gaps, and propose future research directions. The review focuses on the type of deep learning models used for various flood mapping applications, the flood types considered, the spatial scale of the studied events, and the data used for model development. The results show that models based on convolutional layers are usually more accurate as they leverage inductive biases to better process the spatial characteristics of the flooding events. Models based on fully-connected layers, instead, provide accurate results when coupled with other statistical models. Deep learning models showed increased accuracy when compared to traditional approaches and increased speed when compared to numerical methods. While there exist several applications in flood susceptibility, inundation, and hazard mapping, more work is needed to understand how deep learning can assist real-time flood warning during an emergency, and how it can be employed to estimate flood risk. A major challenge lies in developing deep learning models that can generalize to unseen case studies. Furthermore, all reviewed models and their outputs, are deterministic, with limited considerations for uncertainties in outcomes and probabilistic predictions. The authors argue that these identified gaps can be addressed by exploiting recent fundamental advancements in deep learning or by taking inspiration from developments in other applied areas. Models based on graph neural networks and neural operators can work with arbitrarily structured data and thus should be capable of generalizing across different case studies and could account for complex interactions with the natural and built environment. Physics-based deep learning can be used to preserve the underlying physical equations resulting in more reliable speed-up alternatives for numerical models. Similarly, probabilistic models can be built by resorting to Deep Gaussian Processes or Bayesian neural networks.

show abstract

“…Experiments show that no statistical difference between PB and OB classifications was found. While PB classification is widely used in optical satellite imagery segmentation [11,12], OB classification has more advantages in detection [13,14]. For instance, an object-based classification method using NDVI (normalized difference vegetation index) values was proposed to implement broadleaf deciduous forests (BDF) classification mapping [15], and this method has achieved acceptable accuracy (79%) in multi-resolution SAR (Synthetic Aperture Radar) image segmentation.…”

Section: Introductionmentioning

confidence: 99%

DEANet: Dual Encoder with Attention Network for Semantic Segmentation of Remote Sensing Imagery

Wei

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Remote sensing has now been widely used in various fields, and the research on the automatic land-cover segmentation methods of remote sensing imagery is significant to the development of remote sensing technology. Deep learning methods, which are developing rapidly in the field of semantic segmentation, have been widely applied to remote sensing imagery segmentation. In this work, a novel deep learning network—Dual Encoder with Attention Network (DEANet) is proposed. In this network, a dual-branch encoder structure, whose first branch is used to generate a rough guidance feature map as area attention to help re-encode feature maps in the next branch, is proposed to improve the encoding ability of the network, and an improved pyramid partial decoder (PPD) based on the parallel partial decoder is put forward to make fuller use of the features form the encoder along with the receptive filed block (RFB). In addition, an edge attention module using the transfer learning method is introduced to explicitly advance the segmentation performance in edge areas. Except for structure, a loss function composed with the weighted Cross Entropy (CE) loss and weighted Union subtract Intersection (UsI) loss is designed for training, where UsI loss represents a new region-based aware loss which replaces the IoU loss to adapt to multi-classification tasks. Furthermore, a detailed training strategy for the network is introduced as well. Extensive experiments on three public datasets verify the effectiveness of each proposed module in our framework and demonstrate that our method achieves more excellent performance over some state-of-the-art methods.

show abstract

Segmentation of Vegetation and Flood from Aerial Images Based on Decision Fusion of Neural Networks

Cited by 13 publications

References 43 publications

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

Deep Learning Methods for Flood Mapping: A Review of Existing Applications and Future Research Directions

DEANet: Dual Encoder with Attention Network for Semantic Segmentation of Remote Sensing Imagery

Contact Info

Product

Resources

About