Modification of U-Net neural network in the task of multichannel satellite images segmentation

Khryashchev, Vladimir; Larionov, Roman; Ostrovskaya, Anna; Semenov, Alexander

doi:10.1109/ewdts.2019.8884452

Cited by 14 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, these encoder-decoder-based network structures have been widely used in other directions in remote sensings, such as road segmentation [57], [58], classification [59], [60], and building detection [61], [62]. This U-shaped encoderdecoder structure can perform data enhancement by applying random elastic deformation to the training images, which improves the invariance and stability of the network and gives good results even under the condition of small training samples.…”

Section: B Encoder-decoder Structurementioning

confidence: 99%

MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

Zhang

Hua

2022

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

View full text Add to dashboard Cite

Section: B Encoder-decoder Structurementioning

confidence: 99%

MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

Zhang

Hua

2022

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

View full text Add to dashboard Cite

“…[10,35,42,37,40] There are various U-Net architectures modified in order to suit the dataset for better training processes. [16,34,22] The modified U-Net architecture in MLA-GDCC is designed to segment graphene, a nano-material, from the background. In order for the modified U-Net to accurately detect and classify the objects on the images, multiple features are required.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning-based Automatic Graphene Detection with Color Correction for Optical Microscope Images

Siao¹,

Qi²,

Ding³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graphene serves critical application and research purposes in various fields. However, fabricating highquality and large quantities of graphene is time-consuming and it requires heavy human resource labor costs. In this paper, we propose a Machine Learning-based Automatic Graphene Detection Method with Color Correction (MLA-GDCC), a reliable and autonomous graphene detection from microscopic images. The MLA-GDCC includes a white balance (WB) to correct the color imbalance on the images, a modified U-Net and a support vector machine (SVM) to segment the graphene flakes. Considering the color shifts of the images caused by different cameras, we apply WB correction to correct the imbalance of the color pixels. A modified U-Net model, a convolutional neural network (CNN) architecture for fast and precise image segmentation, is introduced to segment the graphene flakes from the background. In order to improve the pixel-level accuracy, we implement a SVM after the modified U-Net model to separate the monolayer and bilayer graphene flakes. The MLA-GDCC achieves flake-level detection rates of 87.09% for monolayer and 90.41% for bilayer graphene, and the pixel-level accuracy of 99.27% for monolayer and 98.92% for bilayer graphene. MLA-GDCC not only achieves high detection rates of the graphene flakes but also speeds up the latency for the graphene detection process from hours to seconds.

show abstract

“…TPUAR-Net [60], which used a single-input image data by merging four different images among MRI data, improved the performance by using residual U-Net in parallel. Multispectral U-Net [61], modified U-Net [62], and dense multi-path U-Net [63] design multiple encoder structures utilize multiple input image data, and provide features of various input data. In contrast, dual U-Net [64] and W-Net of reinforced U-Net [65] used two decoder structures to improve their output performance, and 3-D MRI image of U-Net [66] also modified the decoder structure.…”

Section: Baseline U-net For Semantic Segmentationmentioning

confidence: 99%

O-Net: Dangerous Goods Detection in Aviation Security Based on U-Net

et al. 2020

View full text Add to dashboard Cite

Aviation security X-ray equipment currently searches objects through primary screening, in which the screener has to re-search a baggage/person to detect the target object from overlapping objects. The advancements of computer vision and deep learning technology can be applied to improve the accuracy of identifying the most dangerous goods, guns and knives, from X-ray images of baggage. Artificial intelligence-based aviation security X-rays can facilitate the high-speed detection of target objects while reducing the overall security search duration and load on the screener. Moreover, the overlapping phenomenon was improved by using raw RGB images from X-rays and simultaneously converting the images into grayscale for input. An O-Net structure was designed through various learning rates and dense/depth-wise experiments as an improvement based on U-Net. Two encoders and two decoders were used to incorporate various types of images in processing and maximize the output performance of the neural network, respectively. In addition, we proposed U-Net segmentation to detect target objects more clearly than the You Only Look Once (YOLO) of Bounding-box (Bbox) type through the concept of a ''confidence score''. Consequently, the comparative analysis of basic segmentation models such as Fully Convolutional Networks (FCN), U-Net, and Segmentation-networks (SegNet) based on the major performance indicators of segmentation-pixel accuracy and mean-intersection over union (m-IoU)-revealed that O-Net improved the average pixel accuracy by 5.8%, 2.26%, and 5.01% and the m-IoU was improved by 43.1%, 9.84%, and 23.31%, respectively. Moreover, the accuracy of O-Net was 6.56% higher than that of U-Net, indicating the superiority of the O-Net architecture.

show abstract

Modification of U-Net neural network in the task of multichannel satellite images segmentation

Cited by 14 publications

References 6 publications

MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

MRSE-Net: Multiscale Residuals and SE-Attention Network for Water Body Segmentation From Satellite Images

Machine Learning-based Automatic Graphene Detection with Color Correction for Optical Microscope Images

O-Net: Dangerous Goods Detection in Aviation Security Based on U-Net

Contact Info

Product

Resources

About