Colorisation of archival aerial imagery using deep learning

2021 ◽  
Author(s):  
Ryusei Ishii ◽  
Patrice Carbonneau ◽  
Hitoshi Miyamoto
Keyword(s):  
Deep Learning ◽  
Urban Expansion ◽  
Research Work ◽  
Fine Tuning ◽  
Aerial Images ◽  
Model Parameters ◽  
Style Transfer ◽  
Freeze Layer ◽  
Rgb Images ◽  
Japanese Rivers

<p>Archival imagery dating back to the mid-twentieth century holds information that pre-dates urban expansion and the worst impacts of climate change.  In this research, we examine deep learning colorisation methods applied to historical aerial images in Japan.  Specifically, we attempt to colorize monochrome images of river basins by applying the method of Neural Style Transfer (NST).    First, we created RGB orthomosaics (1m) for reaches of 3 Japanese rivers, the Kurobe, Ishikari, and Kinu rivers.  From the orthomosaics, we extract 60 thousand image tiles of `100 x100` pixels in order to train the CNN used in NST.  The Image tiles were classified into 6 classes: urban, river, forest, tree, grass, and paddy field.  Second, we use the VGG16 model pre-trained on ImageNet data in a transfer learning approach where we freeze a variable number of layers.  We fine-tuned the training epochs, learning rate, and frozen layers in VGG16 in order to derive the optimal CNN used in NST.  The fine tuning resulted in the F-measure accuracy of 0.961, 0.947, and 0.917 for the freeze layer in 7,11,15, respectively.  Third, we colorize monochrome aerial images by the NST with the retrained model weights.  Here used RGB images for 7 Japanese rivers and the corresponding grayscale versions to evaluate the present NST colorization performance.  The RMSE between the RGB and resultant colorized images showed the best performance with the model parameters of lower content layer (6), shallower freeze layer (7), and larger style/content weighting ratio (1.0 x10⁵).  The NST hyperparameter analysis indicated that the colorized images became rougher when the content layer selected deeper in the VGG model.  This is because the deeper the layer, the more features were extracted from the original image.  It was also confirmed that the Kurobe and Ishikari rivers indicated higher accuracy in colorisation.  It might come from the fact that the training dataset of the fine tuning was extracted from these river images.  Finally, we colorized historical monochrome images of Kurobe river with the best NST parameters, resulting in quality high enough compared with the RGB images.  The result indicated that the fine tuning of the NST model could achieve high performance to proceed further land cover classification in future research work.</p>

scholarly journals IMG2nDSM: Height Estimation from Single Airborne RGB Images with Deep Learning

2021 ◽  
Vol 13 (12) ◽  
pp. 2417
Author(s):  
Savvas Karatsiolis ◽  
Andreas Kamilaris ◽  
Ian Cole
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Aerial Imagery ◽  
Aerial Images ◽  
Surface Model ◽  
Large Area ◽  
Digital Terrain ◽  
Terrain Models ◽  
Architectural Features ◽  
Rgb Images

Estimating the height of buildings and vegetation in single aerial images is a challenging problem. A task-focused Deep Learning (DL) model that combines architectural features from successful DL models (U-NET and Residual Networks) and learns the mapping from a single aerial imagery to a normalized Digital Surface Model (nDSM) was proposed. The model was trained on aerial images whose corresponding DSM and Digital Terrain Models (DTM) were available and was then used to infer the nDSM of images with no elevation information. The model was evaluated with a dataset covering a large area of Manchester, UK, as well as the 2018 IEEE GRSS Data Fusion Contest LiDAR dataset. The results suggest that the proposed DL architecture is suitable for the task and surpasses other state-of-the-art DL approaches by a large margin.

Transfer learning based convolution neural net for authentication and classification of emotions from natural and stimulated speech signals

2021 ◽  
pp. 1-12
Author(s):  
Mukul Kumar ◽  
Nipun Katyal ◽  
Nersisson Ruban ◽  
Elena Lyakso ◽  
A. Mary Mekala ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Transfer Learning ◽  
Research Work ◽  
Oral Communication ◽  
Neural Net ◽  
Emotion Classification ◽  
Style Transfer ◽  
Conventional Machine ◽  
Neural Network Algorithm

Over the years the need for differentiating various emotions from oral communication plays an important role in emotion based studies. There have been different algorithms to classify the kinds of emotion. Although there is no measure of fidelity of the emotion under consideration, which is primarily due to the reason that most of the readily available datasets that are annotated are produced by actors and not generated in real-world scenarios. Therefore, the predicted emotion lacks an important aspect called authenticity, which is whether an emotion is actual or stimulated. In this research work, we have developed a transfer learning and style transfer based hybrid convolutional neural network algorithm to classify the emotion as well as the fidelity of the emotion. The model is trained on features extracted from a dataset that contains stimulated as well as actual utterances. We have compared the developed algorithm with conventional machine learning and deep learning techniques by few metrics like accuracy, Precision, Recall and F1 score. The developed model performs much better than the conventional machine learning and deep learning models. The research aims to dive deeper into human emotion and make a model that understands it like humans do with precision, recall, F1 score values of 0.994, 0.996, 0.995 for speech authenticity and 0.992, 0.989, 0.99 for speech emotion classification respectively.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Mask R-CNN Refitting Strategy for Plant Counting and Sizing in UAV Imagery

2020 ◽  
Vol 12 (18) ◽  
pp. 3015 ◽  
Author(s):  
Mélissande Machefer ◽  
François Lemarchand ◽  
Virginie Bonnefond ◽  
Alasdair Hitchins ◽  
Panagiotis Sidiropoulos
Keyword(s):  
Deep Learning ◽  
Fine Tuning ◽  
Aerial Images ◽  
Individual Plant ◽  
Low Density ◽  
Tracking Accuracy ◽  
Potato Plants ◽  
The Individual ◽  
Segmentation Task ◽  
Vision Algorithm

This work introduces a method that combines remote sensing and deep learning into a framework that is tailored for accurate, reliable and efficient counting and sizing of plants in aerial images. The investigated task focuses on two low-density crops, potato and lettuce. This double objective of counting and sizing is achieved through the detection and segmentation of individual plants by fine-tuning an existing deep learning architecture called Mask R-CNN. This paper includes a thorough discussion on the optimal parametrisation to adapt the Mask R-CNN architecture to this novel task. As we examine the correlation of the Mask R-CNN performance to the annotation volume and granularity (coarse or refined) of remotely sensed images of plants, we conclude that transfer learning can be effectively used to reduce the required amount of labelled data. Indeed, a previously trained Mask R-CNN on a low-density crop can improve performances after training on new crops. Once trained for a given crop, the Mask R-CNN solution is shown to outperform a manually-tuned computer vision algorithm. Model performances are assessed using intuitive metrics such as Mean Average Precision (mAP) from Intersection over Union (IoU) of the masks for individual plant segmentation and Multiple Object Tracking Accuracy (MOTA) for detection. The presented model reaches an mAP of 0.418 for potato plants and 0.660 for lettuces for the individual plant segmentation task. In detection, we obtain a MOTA of 0.781 for potato plants and 0.918 for lettuces.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Automatic Generation of Aerial Orthoimages Using Sentinel-2 Satellite Imagery with a Context-Based Deep Learning Approach

2021 ◽  
Vol 11 (3) ◽  
pp. 1089
Author(s):  
Suhong Yoo ◽  
Jisang Lee ◽  
Junsu Bae ◽  
Hyoseon Jang ◽  
Hong-Gyoo Sohn
Keyword(s):  
Deep Learning ◽  
Satellite Imagery ◽  
Mean Squared Error ◽  
Similarity Index ◽  
Super Resolution ◽  
Structural Similarity ◽  
Automatic Generation ◽  
Fine Tuning ◽  
Aerial Images ◽  
Sentinel 2

Aerial images are an outstanding option for observing terrain with their high-resolution (HR) capability. The high operational cost of aerial images makes it difficult to acquire periodic observation of the region of interest. Satellite imagery is an alternative for the problem, but low-resolution is an obstacle. In this study, we proposed a context-based approach to simulate the 10 m resolution of Sentinel-2 imagery to produce 2.5 and 5.0 m prediction images using the aerial orthoimage acquired over the same period. The proposed model was compared with an enhanced deep super-resolution network (EDSR), which has excellent performance among the existing super-resolution (SR) deep learning algorithms, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and root-mean-squared error (RMSE). Our context-based ResU-Net outperformed the EDSR in all three metrics. The inclusion of the 60 m resolution of Sentinel-2 imagery performs better through fine-tuning. When 60 m images were included, RMSE decreased, and PSNR and SSIM increased. The result also validated that the denser the neural network, the higher the quality. Moreover, the accuracy is much higher when both denser feature dimensions and the 60 m images were used.

scholarly journals Fine-tuning deep learning model parameters for improved super-resolution of dynamic MRI with prior-knowledge

2021 ◽  
pp. 102196
Author(s):  
Chompunuch Sarasaen ◽  
Soumick Chatterjee ◽  
Mario Breitkopf ◽  
Georg Rose ◽  
Andreas Nürnberger ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prior Knowledge ◽  
Super Resolution ◽  
Dynamic Mri ◽  
Learning Model ◽  
Fine Tuning ◽  
Model Parameters ◽  
Deep Learning Model

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals In search of the best nuclear data file for proton induced reactions: Varying both models and their parameters

2020 ◽  
Vol 239 ◽  
pp. 13005
Author(s):  
E. Alhassan ◽  
D. Rochman ◽  
A. Vasiliev ◽  
R.M. Bergmann ◽  
M. Wohlmuther ◽  
...  
Keyword(s):  
Experimental Data ◽  
Cross Sections ◽  
Goodness Of Fit ◽  
Research Work ◽  
Nuclear Data ◽  
Fine Tuning ◽  
Model Parameters ◽  
Large Set ◽  
Model Calculations ◽  
Proton Induced Reactions

A lot of research work has been carried out in fine tuning model parameters to reproduce experimental data for neutron induced reactions. This however is not the case for proton induced reactions where large deviations still exist between model calculations and experiments for some cross sections. In this work, we present a method for searching both the model and model parameter space in order to identify the ’best’ nuclear reaction models with their parameter sets that reproduces carefully selected experimental data. Three sets of experimental data from EXFOR are used in this work: (1) cross sections of the target nucleus (2) cross sections of the residual nuclei and (3) angular distributions. Selected models and their parameters were varied simultaneously to produce a large set of random nuclear data files. The goodness of fit between our adjustments and experimental data was achieved by computing a global reduced chi square which took into consideration the above listed experimental data. The method has been applied for the adjustment of proton induced reactions on 59Co between 1 to 100 MeV. The adjusted files obtained are compared with available experimental data and evaluations from other nuclear data libraries.

Sign in / Sign up

Export Citation Format

Share Document