scholarly journals Towards On-Board Hyperspectral Satellite Image Segmentation: Understanding Robustness of Deep Learning through Simulating Acquisition Conditions

2021 ◽  
Vol 13 (8) ◽  
pp. 1532
Author(s):  
Jakub Nalepa ◽  
Michal Myller ◽  
Marcin Cwiek ◽  
Lukasz Zak ◽  
Tomasz Lakota ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Hyperspectral Image ◽  
Satellite Image ◽  
Image Data ◽  
Research Area ◽  
Atmospheric Conditions ◽  
Current State ◽  
Noise Contamination ◽  
And Storage

Although hyperspectral images capture very detailed information about the scanned objects, their efficient analysis, transfer, and storage are still important practical challenges due to their large volume. Classifying and segmenting such imagery are the pivotal steps in virtually all applications, hence developing new techniques for these tasks is a vital research area. Here, deep learning has established the current state of the art. However, deploying large-capacity deep models on-board an Earth observation satellite poses additional technological challenges concerned with their memory footprints, energy consumption requirements, and robustness against varying-quality image data, with the last problem being under-researched. In this paper, we tackle this issue, and propose a set of simulation scenarios that reflect a range of atmospheric conditions and noise contamination that may ultimately happen on-board an imaging satellite. We verify their impact on the generalization capabilities of spectral and spectral-spatial convolutional neural networks for hyperspectral image segmentation. Our experimental analysis, coupled with various visualizations, sheds more light on the robustness of the deep models and indicate that specific noise distributions can significantly deteriorate their performance. Additionally, we show that simulating atmospheric conditions is key to obtaining the learners that generalize well over image data acquired in different imaging settings.

scholarly journals ESTIMASI PRODUKSI PADI DENGAN ANALISIS CITRA SATELIT LANDSAT 8 DI KABUPATEN KLUNGKUNG PROVINSI BALI

2018 ◽  
Vol 12 (1) ◽  
pp. 93
Author(s):  
Made Arya Bhaskara Putra ◽  
I Wayan Nuarsa ◽  
I Wayan Sandi Adnyana
Keyword(s):  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Satellite Image ◽  
Image Data ◽  
Research Area ◽  
Rice Production ◽  
Landsat 8 ◽  
Estimation Model ◽  
Accuracy Test ◽  
Accuracy Level

Rice crop is one of the important commodities that must always be available, so estimation of rice production becomes very important to do before harvesting time to know the food availability. The technology that can be used is remote sensing technology using Landsat 8 Satellite. The aims of this study were (1) to obtain the model of estimation of rice production with Landsat 8 image analysis, and (2) to know the accuracy of the model that obtained by Landsat 8. The research area is located in three sub-districts in Klungkung regency. Analysis in this research was conducted by single band analysis and analysis of vegetation index of satellite image of Landsat 8. Estimation model of rice production was developed by finding the relationship between satellite image data and rice production data. The final stage is the accuracy test of the rice production estimation model, with t test and regression analysis. The results showed: (1) estimation of rice production can be calculated between 67 to 77 days after planting; (2) there was a positive correlation between NDVI (Normalized Difference Vegetation Index) vegetation index value with rice yield; (3) the model of rice production estimation is y = 2.0442e1.8787x (x is NDVI value of Landsat 8 and y is rice production); (4) The results of the model accuracy test showed that the obtained model is suitable to predict rice production with accuracy level is 89.29% and standard error of production estimation is + 0.443 ton/ha. Based on research results, it can be concluded that Landsat 8 Satellite image can be used to estimate rice production and the accuracy level is 89.29%. The results are expected to be a reference in estimating rice production in Klungkung Regency.

scholarly journals Biomedical Image Segmentation via Representative Annotation

2019 ◽  
Vol 33 ◽  
pp. 5901-5908 ◽  
Author(s):  
Hao Zheng ◽  
Lin Yang ◽  
Jianxu Chen ◽  
Jun Han ◽  
Yizhe Zhang ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Active Learning ◽  
Iterative Process ◽  
Image Data ◽  
Manual Annotation ◽  
Convolutional Network ◽  
Biomedical Image ◽  
Image Patches ◽  
Representative Image

Deep learning has been applied successfully to many biomedical image segmentation tasks. However, due to the diversity and complexity of biomedical image data, manual annotation for training common deep learning models is very timeconsuming and labor-intensive, especially because normally only biomedical experts can annotate image data well. Human experts are often involved in a long and iterative process of annotation, as in active learning type annotation schemes. In this paper, we propose representative annotation (RA), a new deep learning framework for reducing annotation effort in biomedical image segmentation. RA uses unsupervised networks for feature extraction and selects representative image patches for annotation in the latent space of learned feature descriptors, which implicitly characterizes the underlying data while minimizing redundancy. A fully convolutional network (FCN) is then trained using the annotated selected image patches for image segmentation. Our RA scheme offers three compelling advantages: (1) It leverages the ability of deep neural networks to learn better representations of image data; (2) it performs one-shot selection for manual annotation and frees annotators from the iterative process of common active learning based annotation schemes; (3) it can be deployed to 3D images with simple extensions. We evaluate our RA approach using three datasets (two 2D and one 3D) and show our framework yields competitive segmentation results comparing with state-of-the-art methods.

scholarly journals Pansformers: Transformer-Based Self-Attention Network for Pansharpening

2021 ◽  
Author(s):  
Nithin G R ◽  
Nitish Kumar M ◽  
Venkateswaran Narasimhan ◽  
Rajanikanth Kakani ◽  
Ujjwal Gupta ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Performance Metrics ◽  
Satellite Image ◽  
Image Data ◽  
Landsat 8 ◽  
Learning Models ◽  
Attention Network ◽  
Panchromatic Image ◽  
Recent Success

Pansharpening is the task of creating a High-Resolution Multi-Spectral Image (HRMS) by extracting and infusing pixel details from the High-Resolution Panchromatic Image into the Low-Resolution Multi-Spectral (LRMS). With the boom in the amount of satellite image data, researchers have replaced traditional approaches with deep learning models. However, existing deep learning models are not built to capture intricate pixel-level relationships. Motivated by the recent success of self-attention mechanisms in computer vision tasks, we propose Pansformers, a transformer-based self-attention architecture, that computes band-wise attention. A further improvement is proposed in the attention network by introducing a Multi-Patch Attention mechanism, which operates on non-overlapping, local patches of the image. Our model is successful in infusing relevant local details from the Panchromatic image while preserving the spectral integrity of the MS image. We show that our Pansformer model significantly improves the performance metrics and the output image quality on imagery from two satellite distributions IKONOS and LANDSAT-8.

scholarly journals Drone Image Segmentation Using Machine and Deep Learning for Mapping Raised Bog Vegetation Communities

2020 ◽  
Vol 12 (16) ◽  
pp. 2602 ◽  
Author(s):  
Saheba Bhatnagar ◽  
Laurence Gill ◽  
Bidisha Ghosh
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Computation Time ◽  
Semantic Segmentation ◽  
Training Dataset ◽  
Atmospheric Conditions ◽  
Raised Bog ◽  
Vegetation Communities ◽  
Lower Accuracy ◽  
Cost Efficient

The application of drones has recently revolutionised the mapping of wetlands due to their high spatial resolution and the flexibility in capturing images. In this study, the drone imagery was used to map key vegetation communities in an Irish wetland, Clara Bog, for the spring season. The mapping, carried out through image segmentation or semantic segmentation, was performed using machine learning (ML) and deep learning (DL) algorithms. With the aim of identifying the most appropriate, cost-efficient, and accurate segmentation method, multiple ML classifiers and DL models were compared. Random forest (RF) was identified as the best pixel-based ML classifier, which provided good accuracy (≈85%) when used in conjunction graph cut algorithm for image segmentation. Amongst the DL networks, a convolutional neural network (CNN) architecture in a transfer learning framework was utilised. A combination of ResNet50 and SegNet architecture gave the best semantic segmentation results (≈90%). The high accuracy of DL networks was accompanied with significantly larger labelled training dataset, computation time and hardware requirements compared to ML classifiers with slightly lower accuracy. For specific applications such as wetland mapping where networks are required to be trained for each different site, topography, season, and other atmospheric conditions, ML classifiers proved to be a more pragmatic choice.

scholarly journals Pansformers: Transformer-Based Self-Attention Network for Pansharpening

2021 ◽  
Author(s):  
Nithin G R ◽  
Nitish Kumar M ◽  
Venkateswaran Narasimhan ◽  
Rajanikanth Kakani ◽  
Ujjwal Gupta ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Performance Metrics ◽  
Satellite Image ◽  
Image Data ◽  
Landsat 8 ◽  
Learning Models ◽  
Attention Network ◽  
Panchromatic Image ◽  
Recent Success

Pansharpening is the task of creating a High-Resolution Multi-Spectral Image (HRMS) by extracting and infusing pixel details from the High-Resolution Panchromatic Image into the Low-Resolution Multi-Spectral (LRMS). With the boom in the amount of satellite image data, researchers have replaced traditional approaches with deep learning models. However, existing deep learning models are not built to capture intricate pixel-level relationships. Motivated by the recent success of self-attention mechanisms in computer vision tasks, we propose Pansformers, a transformer-based self-attention architecture, that computes band-wise attention. A further improvement is proposed in the attention network by introducing a Multi-Patch Attention mechanism, which operates on non-overlapping, local patches of the image. Our model is successful in infusing relevant local details from the Panchromatic image while preserving the spectral integrity of the MS image. We show that our Pansformer model significantly improves the performance metrics and the output image quality on imagery from two satellite distributions IKONOS and LANDSAT-8.

APLIKASI DATA CITRA SATELIT LANDSAT UNTUK PEMANTAUAN DINAMIKA PESISIR MUARA DAS BARITO DAN SEKITARNYA

2016 ◽  
Vol 2 (3) ◽  
pp. 13
Author(s):  
Abdur Rahman
Keyword(s):  
Coastal Area ◽  
Satellite Image ◽  
River Estuary ◽  
Image Data ◽  
Research Area ◽  
Multi Temporal ◽  
Satellite Image Data

Telah terjadi terjadi kerusakan habitat lingkungan mangrove, abrasi dan akresi yang menyebabkan semakin tingginya muka air  di sepanjang DAS Sungai Barito (DAS Martapura, DAS Alalak dan DAS Kuin), sebab erjadinya proses abrasi dan akresi  yang terjadi di sepanjang garis pantai, terutama DAS Martapura, DAS Alalak dan DAS Kuin.Klasifikasi pemanfaatan lahan dan konversinya serta perubahan pesisir berupa akresi dan abrasi di sepanjang pantai area penelitian di analisis dengan memanfaatkan informasi dari data citra satelit Landsat multi temporal yang di peroleh pada tanggal 29 Juni tahun 1985, dan 03 September 2006.Dominasi pemanfaatan lahan berupa HPH, pertambangan dan pemukiman dengan konversi lahan pada hutan untuk pemanfaatan lain memberikan dampak erosi yang cukup besar dengan ditunjukannya wilayah pesisir yang mengalami peningkatan akresi terutama pada bagian muara sungai (delta). Tren perubahan yang terlihat pada kawasan pesisir di area penelitian selama 21 tahun adalah abrasi sebesar 294,55 m2 di daerah Muara S. Martapura, 75,53 m2 di sekitar muara S. Alalak. Dan perubahan Abrasi sebesar 177,42 m2 , dan akresi sebesar 610,86 m2 di sekitar Muara S. Barito/Kuin).Have happened happened damage of environmental habitat of mangrove, and abrasi of akresi causing its excelsior of face irrigate alongside DAS River of Barito (DAS Martapura, DAS Alalak and of DAS Kuin), because the happening of process of abrasi and of akresi that happened alongside coastline, especially DAS Martapura, DAS Alalak and  DAS Kuin. Classification exploiting of farm and its conversion and also change of coastal area in the form of and akresi of abrasialongside research area coast in analysis by exploiting information of satellite image data of Landsat temporal multi which in obtaining on 29 June year 1985, and 03 September 2006.Domination exploiting of farm in the form of HPH, settlement and mining with farm conversion at forest for other exploiting give big enough erosion impact with  regional and natural coastal area that make-up of akresi especially  part of river estuary    (delta).  Seen Change Tren at coastal area in research area during 21 year was abrasi equal to 294,55 m2 in Estuary area S. Martapura, 75,53 m2 around estuary S. Alalak. And change of Abrasi equal to 177,42 m2 , and akresi equal to 610,86 m2 around Estuary S. Barito / kuin).           

scholarly journals A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1751
Author(s):  
Xiang Hu ◽  
Wenjing Yang ◽  
Hao Wen ◽  
Yu Liu ◽  
Yuanxi Peng
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Image Classification ◽  
Language Processing ◽  
Hyperspectral Image ◽  
Metric Learning ◽  
Image Data ◽  
Activation Function ◽  
Classification Performance ◽  
Hyperspectral Image Classification

Hyperspectral image (HSI) classification is the subject of intense research in remote sensing. The tremendous success of deep learning in computer vision has recently sparked the interest in applying deep learning in hyperspectral image classification. However, most deep learning methods for hyperspectral image classification are based on convolutional neural networks (CNN). Those methods require heavy GPU memory resources and run time. Recently, another deep learning model, the transformer, has been applied for image recognition, and the study result demonstrates the great potential of the transformer network for computer vision tasks. In this paper, we propose a model for hyperspectral image classification based on the transformer, which is widely used in natural language processing. Besides, we believe we are the first to combine the metric learning and the transformer model in hyperspectral image classification. Moreover, to improve the model classification performance when the available training samples are limited, we use the 1-D convolution and Mish activation function. The experimental results on three widely used hyperspectral image data sets demonstrate the proposed model’s advantages in accuracy, GPU memory cost, and running time.

scholarly journals A pilot exploratory study of the potentials of deep learning methods in cancer image segmentation and classification

2020 ◽  
Author(s):  
Eric Yi ◽  
Yanling Liu
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Transfer Learning ◽  
Exploratory Study ◽  
Resource Constraints ◽  
Image Data ◽  
Tumor Classification ◽  
Cancer Tissue ◽  
Learning Methods

Abstract Background Tumor classification and feature quantification from H&E histology images are critical tasks for cancer diagnosis, cancer research, and treatment. However, both tasks involve tedious and time-consuming manual examination of histology images. We explored the usage of deep learning methods in segmentation and classification of histology images of cancer tissue for their potential in computer-aided tumor diagnosis and other clinical and research applications. Specifically, we evaluated performance of selected deep learning methods in stroma and glandular objects segmentation in tumor image data and tumor images classification. We automated these tasks to help facilitate downstream tumor image analysis, reduce the labor load of pathologists, and provide them with a second opinion on their analysis. Methods We modified a patch-based U-Net model and trained it to perform stroma detection and segmentation in cancer tissue. Then the semantic segmentation capabilities of the U-Net model were compared with that of a DeepLabV3+ model. We explored the possible use of transfer learning to train a patch-based model to classify cancer tissue images as carcinoma and sarcoma and to further classify them as carcinoma subtypes. Results In spite of the limited dataset available for the pilot study, we found that the DeepLabV3+ model performed biomedical image segmentation more effectively than U-Net when k-fold cross-validation was utilized, but U-Net still showed promise as an effective and efficient model when we used a customized validation approach. We believe that the DeepLabV3+ model can perform segmentation with even more accuracy if computation resource constraints are removed or if more data is used to augment the result. In terms of tumor classification, our selected models also consistently achieve test accuracies above 80%, with a model trained using transfer learning with VGG-16 network as the feature extractors, or convolutional base performing best. For multi-class tumor subtype classification, we also observed promising test accuracies from our models, and a customized post-processing method provided even higher prediction accuracy on test set images and this method can be further investigated. Conclusions This pilot exploratory study provided strong evidence for the powerful potentials of deep learning models for segmentation and classification of tumor image data.

scholarly journals Analysis of the influence hybrid mass coordinate on WRF-ARW models to the turbulence simulation of Batik airlines aviation (case study October 24, 2017)

2021 ◽  
Vol 893 (1) ◽  
pp. 012032
Author(s):  
N A A Halimy ◽  
N J Trilaksono
Keyword(s):  
Energy Dissipation ◽  
Dissipation Rate ◽  
Richardson Number ◽  
Satellite Image ◽  
Image Data ◽  
Energy Dissipation Rate ◽  
Atmospheric Conditions ◽  
Turbulence Simulation ◽  
Satellite Image Data

Abstract The influence of hybrid sigma coordinate is better to represent turbulence in America than basic sigma coordinate. Therefore, it is necessary to search the effect of these coordinates on turbulence simulations in Indonesia due to the analysis of different atmospheric conditions from America. In this research, two experiments are performed using two different vertical coordinates with a case study flight turbulence from Batik Airlines on October 24, 2017. The two different vertical coordinates are the hybrid sigma coordinate and basic sigma coordinate. The data used are NCEP-FNL, Himawari-8 satellite image data, and sounding data. Based on the result of this research, simulation using hybrid sigma coordinate shows isentropic lines that have the potential turbulence during and after turbulence event. Richardson number value about 0.1 – 0.2 and intensity of the energy dissipation rate is 0.06 m 2/3s-1. According to the Richardson number value and intensity of the energy dissipation rate, the hybrid sigma coordinate simulation shows turbulence potential more significant than the basic sigma coordinate.

scholarly journals Minimización de los efectos atmosféricos en el índice espectral de la vegetación IVIS

2018 ◽  
Vol 36 (1) ◽  
pp. 31
Author(s):  
Fernando Paz Pellat
Keyword(s):  
Time Series ◽  
Vegetation Index ◽  
Satellite Image ◽  
Vegetation Indices ◽  
Atmospheric Correction ◽  
Image Data ◽  
Atmospheric Effects ◽  
Atmospheric Conditions ◽  
Atmospheric Effect ◽  
Remote Sensors

It is essential to minimize atmospheric effects on spectral information of remote sensors from space platforms to avoid under estimation of biophysical variables associated with satellite image data. In this paper, a generic algorithm was developed, based on sound theoretical arguments, to analyze time series ISVI spectral vegetation index (vegetation index based on iso-soil curves), thus avoiding the problems associated with the classic design of vegetation indices, where the spectral signal saturates quickly. The results, when applying the algorithm in pixel time series of AVHRR satellite images, showed that reduction and standardization of atmospheric effects in the ISVI was achieved. Using ISVI maximum values in time series (temporal window), a reasonable approximation to atmospheric conditions with minimum or standardized effects was obtained. In conclusion, although the scheme developed failed to eliminate the atmospheric effect on ISVI entirely, it was reduced to a minimum. The algorithm developed was simple enough for operational use, with regard to atmospheric correction methods using radiative model inversions.

Sign in / Sign up

Export Citation Format

Share Document