Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

Li, Lianfa

doi:10.3390/rs11182142

Cited by 27 publications

(17 citation statements)

References 71 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More in detail, let l denote an encoding layer and L the corresponding decoding layer of the network. The input and output of the encoding layer l are denoted by X l and Y l , respectively, and by X L and Y L for the corresponding decoding layer L. The residual connection between corresponding layers mitigates the loss of information when backpropagating losses during training [23]. The relationship among the relevant quantities is illustrated in Eq.…”

Section: A Architecturementioning

confidence: 99%

Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Samuel

Cuzzolin

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Anomaly detection in Minimally-Invasive Surgery (MIS) traditionally requires a human expert monitoring the procedure from a console, whereas automated anomaly detection systems in this area typically rely on classical supervised learning. Anomalous surgical events, however, are rare, making it difficult to capture data to train a model in a supervised fashion. In this work we propose an unsupervised approach to anomaly detection for robotic MIS based on deep residual autoencoders. The idea is to make the autoencoder learn the 'normal' distribution of the data and detect abnormal events deviating from this distribution by measuring a reconstruction error. The model is trained and validated upon both the publicly available Cholec80 dataset and a set of videos captured on procedures using artificial anatomies ('phantoms') as part of the Smart Autonomous Robotic Assistant Surgeon (SARAS) project. The system achieves recall and precision equal to 78.4%, 91.5%, respectively, on Cholec80 and of 95.6%, 88.1% on the SARAS phantom dataset. The system was developed and deployed as part of the SARAS platform for real-time anomaly detection with a processing time of 25 ms per frame.

show abstract

Section: A Architecturementioning

confidence: 99%

Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Samuel

Cuzzolin

2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…A further enhancement of the architecture has been proposed through the insertion of residual connections within the architecture's blocks, resulting in what has been called ResUnet [51,64]. These three architectures have been used to classify remote sensing data before with good results [48][49][50][51]64]. We adapted and evaluated these three architectures to describe possible differences when used to detect burnt area changes.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

“…architectures have been used to classify remote sensing data before with good results [48][49][50][51]64]. We adapted and evaluated these three architectures to describe possible differences when used to detect burnt area changes.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Júnior

Carvalho

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Fire is one of the primary sources of damages to natural environments globally. Estimates show that approximately 4 million km2 of land burns yearly. Studies have shown that such estimates often underestimate the real extent of burnt land, which highlights the need to find better, state-of-the-art methods to detect and classify these areas. This study aimed to analyze the use of deep convolutional Autoencoders in the classification of burnt areas, considering different sample patch sizes. A simple Autoencoder and the U-Net and ResUnet architectures were evaluated. We collected Landsat 8 OLI+ data from three scenes in four consecutive dates to detect the changes specifically in the form of burnt land. The data were sampled according to four different sampling strategies to evaluate possible performance changes related to sampling window sizes. The training stage used two scenes, while the validation stage used the remaining scene. The ground truth change mask was created using the Normalized Burn Ratio (NBR) spectral index through a thresholding approach. The classifications were evaluated according to the F1 index, Kappa index, and mean Intersection over Union (mIoU) value. Results have shown that the U-Net and ResUnet architectures offered the best classifications with average F1, Kappa, and mIoU values of approximately 0.96, representing excellent classification results. We have also verified that a sampling window size of 256 by 256 pixels offered the best results.

show abstract

“…Deep learning models for semantic segmentation become increasingly popular in the automatic processing of remote sensing images for building footprint extraction [29][30][31], road extraction [32], land use detection [33], etc. Motivated by good results in many areas, CNNs are becoming researchers' default choice for the segmentation of seismic images and identification of salt deposits.…”

Section: Related Workmentioning

confidence: 99%

Identification of Salt Deposits on Seismic Images Using Deep Learning Method for Semantic Segmentation

Milosavljević

2020

IJGI

View full text Add to dashboard Cite

Several areas of Earth that are rich in oil and natural gas also have huge deposits of salt below the surface. Because of this connection, knowing precise locations of large salt deposits is extremely important to companies involved in oil and gas exploration. To locate salt bodies, professional seismic imaging is needed. These images are analyzed by human experts which leads to very subjective and highly variable renderings. To motivate automation and increase the accuracy of this process, TGS-NOPEC Geophysical Company (TGS) has sponsored a Kaggle competition that was held in the second half of 2018. The competition was very popular, gathering 3221 individuals and teams. Data for the competition included a training set of 4000 seismic image patches and corresponding segmentation masks. The test set contained 18,000 seismic image patches used for evaluation (all images are 101 × 101 pixels). Depth information of the sample location was also provided for every seismic image patch. The method presented in this paper is based on the author’s participation and it relies on training a deep convolutional neural network (CNN) for semantic segmentation. The architecture of the proposed network is inspired by the U-Net model in combination with ResNet and DenseNet architectures. To better comprehend the properties of the proposed architecture, a series of experiments were conducted applying standardized approaches using the same training framework. The results showed that the proposed architecture is comparable and, in most cases, better than these segmentation models.

show abstract

Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images

Cited by 27 publications

References 71 publications

Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Unsupervised Anomaly Detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS) Using a Deep Residual Autoencoder

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Identification of Salt Deposits on Seismic Images Using Deep Learning Method for Semantic Segmentation

Contact Info

Product

Resources

About