Skip to content

Commit

Permalink
Remote sensing
Browse files Browse the repository at this point in the history
  • Loading branch information
@arunp77
arunp77 committed Nov 20, 2023
1 parent d11221d commit f1ee01b
Showing 1 changed file with 7 additions and 65 deletions.
72 changes: 7 additions & 65 deletions Satellite-data.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -178,49 +178,7 @@ <h2>Various aspects of Satellite data collection </h2>
The algorithm is then trained using a training set which includes images from different geographical locations with similar characteristics. </li>
</ol>

<h4>Image enhancement process</h4>
<ol>
<li><strong>Data Preparation:</strong>
<ul>
<li>Acquire the satellite imagery and corresponding labels. The labels indicate the types of land cover (e.g., forest, water, urban, etc.) present in the images.</li>
<li>Reshape the images to have a consistent size and channel ordering. This can be achieved by using Python libraries like NumPy or OpenCV.</li>
<li>Normalize the pixel values of the images to ensure consistent scale. This can be achieved by dividing the pixel values by 255.</li>
<li>Split the data into training, validation, and testing sets.</li>
</ul>
</li>
<li><strong>Feature Extraction: </strong>
<ul>
<li>Convert the satellite images from their RGB color space to another color space, such as HSV or YCrCb. This can help capture additional information about the land cover
present in the images.</li>
<li>Apply a transformation, such as wavelet transformation, to the satellite images. This can help enhance the quality of the images by reducing noise and preserving the
original features of the images.</li>
</ul>
</li>
<li><strong>Model Training:</strong>
<ul>
<li>Select a suitable machine learning model, such as a convolutional neural network (CNN), for the classification task.</li>
<li>Train the model on the training set, using the extracted features as inputs and the corresponding labels as targets.</li>
<li>Evaluate the performance of the model on the validation set, using appropriate metrics like accuracy, precision, recall, and F1-score.</li>
</ul>
</li>
<li><strong>Model Optimization:</strong>
<ul>
<li>If the model's performance on the validation set is not satisfactory, try to improve the model's architecture or adjust its hyperparameters.</li>
<li>Continue training and evaluating the model until its performance is satisfactory. </li>
</ul>
</li>
<li><strong>Model Deployment:</strong>
<ul>
<li>Once the model has been trained and optimized, deploy it to a production environment.</li>
<li>Use the deployed model to enhance satellite imagery by classifying the types of land cover present in the images.</li>
</ul>
</li>
</ol>
<p>By following these steps, you can successfully enhance satellite imagery using machine learning techniques. This can have a
significant impact on various applications, such as land use planning, natural resource management, and disaster response.</p>




<h3>Satellite data collection levels</h3>

<p>Within remote sensing and its applications, there are a series of levels that are used to define the amount of processing that has been performed to provide a given dataset.
Expand Down Expand Up @@ -248,33 +206,17 @@ <h3>Satellite data collection levels</h3>
<img src="assets/img/remote-sensing/Level-0-4-stages.png" alt="" style="max-width: 90%; max-height: 90%;">
<figcaption style="text-align: center;">Level-0 to Level-1 remote sensing data transformation. (<strong>Image credit: © </strong><a href="https://arunp77.github.io/Arun-Kumar-Pandey/" target="_blank"> Arun Kumar Pandey</a>)</figcaption>
</figure>

<h3>Data Processing</h3>
<p>Processing of satellite data typically involves these steps:</p>

<ul>
<li><strong>Data Reception:</strong> Raw data is received from the satellite by ground stations or satellite receivers.</li>
<li><strong>Preprocessing:</strong> This step involves initial data quality checks, formatting, and metadata extraction.</li>
<li><strong>Calibration:</strong> Radiometric and geometric corrections are applied to make the data consistent and accurate.</li>
<li><strong>Georeferencing:</strong> The data is geolocated to specific geographic coordinates using satellite orbit and attitude information.</li>
<li><strong>Atmospheric Correction:</strong> Corrections are made to account for the effects of the atmosphere on the data, especially for optical and infrared sensors.</li>
<li><strong>Data Fusion:</strong> In some cases, data from multiple sensors or satellites are combined to create composite datasets.</li>
<li><strong>Validation:</strong> The processed data is compared with ground-based measurements or models to ensure its accuracy.</li>
<li><strong>Data Distribution:</strong> Processed data products are made available to researchers and the public through various data centers and platforms.</li>
</ul>

<figure style="text-align: center;">
<img src="assets/img/remote-sensing/Level-0-4.png" alt="" style="max-width: 90%; max-height: 90%;">
<figcaption style="text-align: center;"><strong>Image credit:</strong><a href="https://link.springer.com/referenceworkentry/10.1007/978-0-387-36699-9_36">Processing Levels,
Ron Weaver </a></figcaption>
</figure>

</section>

<section id="Data-Transformation-required">
<h3 id="Data-Transformation-required">Data Transformation required<a class="anchor-link" href="#Data-Transformation-required">&#182;</a></h3><p>Level 0 (L0) data represents
<h3 id="Data-Transformation-required">Data Processing<a class="anchor-link" href="#Data-Transformation-required">&#182;</a></h3><p>Level 0 (L0) data represents
the raw, unprocessed data directly received from a satellite's sensors. Transforming Level 0 data into Level 1 (L1) involves several essential steps to convert the raw
sensor measurements into physically meaningful units. Here's a step-by-step process for this transformation:</p>
<figure style="text-align: center;">
<img src="assets/img/remote-sensing/Level-0-4.png" alt="" style="max-width: 90%; max-height: 90%;">
<figcaption style="text-align: center;"><strong>Image credit:</strong><a href="https://link.springer.com/referenceworkentry/10.1007/978-0-387-36699-9_36">Processing Levels,
Ron Weaver </a></figcaption>
</figure>
<p><strong>Step 1: Data Reception</strong></p>
<ul>
<li>The satellite collects raw data from its sensors while orbiting Earth.</li>
Expand Down

0 comments on commit f1ee01b

Please sign in to comment.