RSK World - Satellite Images Dataset - Project Files Browser | RSK World

get_real_videos.py index.html process_images.py utils.py config.py

index.html

<!DOCTYPE html>
<html lang="en">
<head>
    <!--
        Satellite Image Dataset Project
        Created by: RSK World
        Website: https://rskworld.in
        Email: help@rskworld.in
        Phone: +91 93305 39277
        Description: High-resolution satellite imagery dataset with land cover classification
    -->
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Satellite Image Dataset - RSK World</title>
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/css/bootstrap.min.css" rel="stylesheet">
    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
    <style>
        :root {
            --primary-color: #0d6efd;
            --info-color: #0dcaf0;
        }
        body {
            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
            min-height: 100vh;
            font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
        }
        .hero-section {
            background: linear-gradient(135deg, rgba(13, 110, 253, 0.9) 0%, rgba(13, 202, 240, 0.9) 100%);
            color: white;
            padding: 80px 0;
            margin-bottom: 50px;
        }
        .project-card {
            background: white;
            border-radius: 15px;
            box-shadow: 0 10px 30px rgba(0,0,0,0.2);
            padding: 30px;
            margin-bottom: 30px;
            transition: transform 0.3s;
        }
        .project-card:hover {
            transform: translateY(-5px);
        }
        .icon-large {
            font-size: 4rem;
            color: var(--info-color);
            margin-bottom: 20px;
        }
        .tech-badge {
            display: inline-block;
            padding: 5px 15px;
            margin: 5px;
            background: #e7f3ff;
            border-radius: 20px;
            color: #0d6efd;
            font-size: 0.9rem;
        }
        .feature-list {
            list-style: none;
            padding: 0;
        }
        .feature-list li {
            padding: 10px 0;
            border-bottom: 1px solid #eee;
        }
        .feature-list li:last-child {
            border-bottom: none;
        }
        .feature-list li i {
            color: var(--info-color);
            margin-right: 10px;
        }
        .difficulty-badge {
            padding: 8px 20px;
            border-radius: 25px;
            font-weight: bold;
        }
        .difficulty-advanced {
            background: #f8d7da;
            color: #721c24;
        }
        .footer {
            background: rgba(0,0,0,0.8);
            color: white;
            padding: 30px 0;
            margin-top: 50px;
        }
    </style>
</head>
<body>
    <!--
        Satellite Image Dataset Project
        Created by: RSK World
        Website: https://rskworld.in
        Email: help@rskworld.in
        Phone: +91 93305 39277
    -->
    <div class="hero-section text-center">
        <div class="container">
            <img src="./satellite-images.png" alt="Satellite Image Dataset - rskworld.in" class="img-fluid mb-4" style="max-width: 600px; border-radius: 15px; box-shadow: 0 10px 30px rgba(0,0,0,0.3);">
            <i class="fas fa-image icon-large"></i>
            <h1 class="display-4 fw-bold mb-3">Satellite Image Dataset</h1>
            <p class="lead">High-resolution satellite imagery with land cover classification, urban planning, and environmental monitoring labels</p>
            <span class="difficulty-badge difficulty-advanced">Advanced</span>
        </div>
    </div>

    <div class="container">
        <div class="row">
            <div class="col-lg-8 mx-auto">
                <div class="project-card">
                    <div class="text-center mb-4">
                        <img src="./satellite-images.png" alt="Satellite Image Dataset - rskworld.in" class="img-fluid rounded" style="max-width: 100%; box-shadow: 0 5px 15px rgba(0,0,0,0.2);">
                    </div>
                    <h2 class="mb-4"><i class="fas fa-info-circle text-info"></i> Project Overview</h2>
                    <p class="lead">This dataset includes high-resolution satellite images with land cover classifications, building detection, and environmental monitoring labels. Perfect for remote sensing, urban planning, agriculture monitoring, and geospatial analysis.</p>
                    
                    <h3 class="mt-4 mb-3"><i class="fas fa-tags text-info"></i> Category</h3>
                    <p><span class="badge bg-primary">Image Data</span></p>

                    <h3 class="mt-4 mb-3"><i class="fas fa-code text-info"></i> Technologies</h3>
                    <div>
                        <span class="tech-badge">PNG</span>
                        <span class="tech-badge">TIFF</span>
                        <span class="tech-badge">GeoTIFF</span>
                        <span class="tech-badge">NumPy</span>
                        <span class="tech-badge">OpenCV</span>
                        <span class="tech-badge">scikit-image</span>
                        <span class="tech-badge">scikit-learn</span>
                        <span class="tech-badge">Matplotlib</span>
                        <span class="tech-badge">Seaborn</span>
                        <span class="tech-badge">Rasterio</span>
                        <span class="tech-badge">PIL/Pillow</span>
                    </div>

                    <h3 class="mt-4 mb-3"><i class="fas fa-star text-info"></i> Core Features</h3>
                    <ul class="feature-list">
                        <li><i class="fas fa-check-circle"></i> High-resolution images</li>
                        <li><i class="fas fa-check-circle"></i> Land cover labels</li>
                        <li><i class="fas fa-check-circle"></i> Building detection</li>
                        <li><i class="fas fa-check-circle"></i> Multiple regions</li>
                        <li><i class="fas fa-check-circle"></i> Geospatial metadata</li>
                    </ul>

                    <h3 class="mt-4 mb-3"><i class="fas fa-rocket text-info"></i> Advanced Features (NEW!)</h3>
                    <ul class="feature-list">
                        <li><i class="fas fa-check-circle"></i> <strong>Advanced Image Processing:</strong> Edge detection, segmentation, feature extraction (HOG, LBP, GLCM)</li>
                        <li><i class="fas fa-check-circle"></i> <strong>Machine Learning Integration:</strong> Classification, object detection, change detection, NDVI extraction</li>
                        <li><i class="fas fa-check-circle"></i> <strong>Real Image Downloading:</strong> Multiple sources (Planetary Computer, USGS, Copernicus)</li>
                        <li><i class="fas fa-check-circle"></i> <strong>Advanced Visualization:</strong> 3D plots, statistical analysis, interactive dashboards</li>
                        <li><i class="fas fa-check-circle"></i> <strong>Batch Processing:</strong> Parallel processing, data augmentation, export utilities</li>
                        <li><i class="fas fa-check-circle"></i> <strong>Image Enhancement:</strong> CLAHE, histogram equalization, noise reduction</li>
                    </ul>

                    <h3 class="mt-4 mb-3"><i class="fas fa-download text-info"></i> Download</h3>
                    <p>Download the complete dataset:</p>
                    <a href="./satellite-images.zip" class="btn btn-primary btn-lg">
                        <i class="fas fa-download"></i> Download Dataset
                    </a>

                    <h3 class="mt-4 mb-3"><i class="fas fa-book text-info"></i> Documentation</h3>
                    <p>Complete documentation is available below. All information is embedded in this page for easy access.</p>
                </div>

                <div class="project-card">
                    <h2 class="mb-4"><i class="fas fa-cog text-info"></i> Quick Start</h2>
                    <h4>Installation</h4>
                    <pre class="bg-light p-3 rounded"><code>pip install -r requirements.txt

# For real image downloading (optional)
pip install pystac-client planetary-computer</code></pre>
                    
                    <h4 class="mt-3">Basic Usage</h4>
                    <pre class="bg-light p-3 rounded"><code>import numpy as np
import cv2
from pathlib import Path

# Load satellite image
image_path = Path('data/images/sample_001.png')
image = cv2.imread(str(image_path))
print(f"Image shape: {image.shape}")</code></pre>

                    <h4 class="mt-3">Advanced Features Example</h4>
                    <pre class="bg-light p-3 rounded"><code>from advanced_processing import AdvancedImageProcessor
from ml_integration import SatelliteMLProcessor
from enhanced_real_image_downloader import EnhancedRealImageDownloader

# Advanced processing
processor = AdvancedImageProcessor()
edges = processor.detect_edges(image, method='canny')
features = processor.extract_all_features(image)

# ML integration
ml = SatelliteMLProcessor()
buildings = ml.detect_buildings_simple(image)
ndvi = ml.extract_ndvi(image)

# Download real images
downloader = EnhancedRealImageDownloader()
files = downloader.download_sample_real_images(num_images=10)</code></pre>

                    <h4 class="mt-3">Run Complete Demo</h4>
                    <pre class="bg-light p-3 rounded"><code>python advanced_example.py</code></pre>
                </div>

                <div class="project-card">
                    <h2 class="mb-4"><i class="fas fa-tools text-info"></i> Advanced Modules</h2>
                    
                    <div class="mb-3">
                        <h5><i class="fas fa-image text-info"></i> advanced_processing.py</h5>
                        <p>Edge detection, segmentation, feature extraction (HOG, LBP, GLCM), image enhancement, noise reduction</p>
                    </div>

                    <div class="mb-3">
                        <h5><i class="fas fa-brain text-info"></i> ml_integration.py</h5>
                        <p>Machine learning features: classification, building detection, change detection, NDVI extraction, training utilities</p>
                    </div>

                    <div class="mb-3">
                        <h5><i class="fas fa-download text-info"></i> enhanced_real_image_downloader.py</h5>
                        <p>Download real satellite images from Planetary Computer, USGS EarthExplorer, and Copernicus Hub</p>
                    </div>

                    <div class="mb-3">
                        <h5><i class="fas fa-chart-line text-info"></i> advanced_visualization.py</h5>
                        <p>3D plots, statistical analysis, comparison views, time series visualization, interactive dashboards</p>
                    </div>

                    <div class="mb-3">
                        <h5><i class="fas fa-layer-group text-info"></i> batch_processing.py</h5>
                        <p>Parallel batch processing, data augmentation (flip, rotate, brightness, contrast, noise), export utilities</p>
                    </div>
                </div>

                <div class="project-card">
                    <h2 class="mb-4"><i class="fas fa-book text-info"></i> Complete Documentation</h2>
                    
                    <div class="mb-4">
                        <h4><i class="fas fa-info-circle text-info"></i> Project Overview</h4>
                        <p>This satellite image dataset project provides comprehensive tools for working with satellite imagery, including:</p>
                        <ul>
                            <li><strong>Data Loading:</strong> Load images, labels, metadata, and building detections</li>
                            <li><strong>Image Processing:</strong> Basic and advanced image processing capabilities</li>
                            <li><strong>Machine Learning:</strong> Classification, detection, and feature extraction</li>
                            <li><strong>Visualization:</strong> Statistical analysis, 3D plots, and interactive dashboards</li>
                            <li><strong>Real Data:</strong> Download real satellite images from multiple sources</li>
                        </ul>
                    </div>

                    <div class="mb-4">
                        <h4><i class="fas fa-rocket text-info"></i> Advanced Features Details</h4>
                        <div class="row">
                            <div class="col-md-6 mb-3">
                                <h6><i class="fas fa-image"></i> Advanced Processing</h6>
                                <ul class="small">
                                    <li>Edge Detection (Canny, Sobel, Laplacian)</li>
                                    <li>Image Segmentation (Watershed, SLIC)</li>
                                    <li>Feature Extraction (HOG, LBP, GLCM)</li>
                                    <li>Image Enhancement (CLAHE, Histogram EQ)</li>
                                    <li>Noise Reduction (Bilateral, NLM)</li>
                                </ul>
                            </div>
                            <div class="col-md-6 mb-3">
                                <h6><i class="fas fa-brain"></i> ML Integration</h6>
                                <ul class="small">
                                    <li>Land Cover Classification</li>
                                    <li>Building Detection</li>
                                    <li>Change Detection</li>
                                    <li>NDVI Extraction</li>
                                    <li>Training Dataset Creation</li>
                                </ul>
                            </div>
                            <div class="col-md-6 mb-3">
                                <h6><i class="fas fa-download"></i> Real Image Download</h6>
                                <ul class="small">
                                    <li>Planetary Computer (No credentials)</li>
                                    <li>USGS EarthExplorer (Landsat)</li>
                                    <li>Copernicus Hub (Sentinel-2)</li>
                                    <li>Multiple locations worldwide</li>
                                    <li>Automatic metadata extraction</li>
                                </ul>
                            </div>
                            <div class="col-md-6 mb-3">
                                <h6><i class="fas fa-chart-line"></i> Visualization</h6>
                                <ul class="small">
                                    <li>3D Surface Plots</li>
                                    <li>Statistical Analysis</li>
                                    <li>Comparison Views</li>
                                    <li>Time Series Visualization</li>
                                    <li>Interactive Dashboards</li>
                                </ul>
                            </div>
                        </div>
                    </div>

                    <div class="mb-4">
                        <h4><i class="fas fa-exclamation-triangle text-warning"></i> Installation & Troubleshooting</h4>
                        <div class="alert alert-info">
                            <strong>Required Packages:</strong><br>
                            <code>pip install numpy opencv-python matplotlib scikit-image scikit-learn scipy seaborn tqdm rasterio pillow</code>
                        </div>
                        <div class="alert alert-secondary">
                            <strong>Optional (for real images):</strong><br>
                            <code>pip install pystac-client planetary-computer</code>
                        </div>
                        <p><strong>Check Installation:</strong> Run <code>python check_errors.py</code> to verify all packages are installed correctly.</p>
                    </div>

                    <div class="mb-4">
                        <h4><i class="fas fa-file-download text-info"></i> Download Real Images</h4>
                        <p>To download real satellite images:</p>
                        <pre class="bg-light p-3 rounded"><code>from enhanced_real_image_downloader import EnhancedRealImageDownloader

downloader = EnhancedRealImageDownloader()
files = downloader.download_sample_real_images(num_images=10)</code></pre>
                        <p class="small">Note: Requires internet connection and optional packages (pystac-client, planetary-computer)</p>
                    </div>

                    <div class="alert alert-success">
                        <h5><i class="fas fa-lightbulb"></i> Quick Tips</h5>
                        <ul class="mb-0">
                            <li>Run <code>python advanced_example.py</code> to see all features in action</li>
                            <li>Check <code>data/images/</code> for sample images</li>
                            <li>Use <code>python check_errors.py</code> to diagnose issues</li>
                            <li>All modules include detailed docstrings and examples</li>
                        </ul>
                    </div>
                </div>

                <div class="project-card">
                    <h2 class="mb-4"><i class="fas fa-check-circle text-info"></i> Error Checking</h2>
                    <p>Run the error checker to verify your installation:</p>
                    <pre class="bg-light p-3 rounded"><code>python check_errors.py</code></pre>
                    <p class="mt-2">This will check for missing packages, syntax errors, and import issues.</p>
                </div>
            </div>
        </div>
    </div>

    <footer class="footer text-center">
        <div class="container">
            <p class="mb-2">
                <strong>Satellite Image Dataset</strong> - Created by <a href="https://rskworld.in" class="text-info">RSK World</a>
            </p>
            <p class="mb-0">
                <i class="fas fa-envelope"></i> <a href="mailto:help@rskworld.in" class="text-info">help@rskworld.in</a> | 
                <i class="fas fa-phone"></i> <a href="tel:+919330539277" class="text-info">+91 93305 39277</a>
            </p>
            <p class="mt-2 mb-0">
                <small>&copy; 2024 RSK World. All rights reserved.</small>
            </p>
        </div>
    </footer>

    <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0/dist/js/bootstrap.bundle.min.js"></script>
</body>
</html>

359 lines•18.5 KB

markup

process_images.py

Raw Download

#!/usr/bin/env python3
"""
Satellite Image Dataset - Image Processing Script
Created by: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277

This script provides utilities for processing satellite images including:
- Loading and preprocessing images
- Extracting geospatial metadata
- Processing land cover labels
- Building detection utilities
"""

import cv2
import numpy as np
from pathlib import Path
import json
from typing import Dict, List, Tuple, Optional
import rasterio
from rasterio.plot import show
import matplotlib.pyplot as plt


class SatelliteImageProcessor:
    """
    Main class for processing satellite images.
    Created by: RSK World (https://rskworld.in)
    """
    
    def __init__(self, data_dir: str = "data"):
        """
        Initialize the processor with data directory.
        
        Args:
            data_dir: Path to the data directory
        """
        self.data_dir = Path(data_dir)
        self.images_dir = self.data_dir / "images"
        self.labels_dir = self.data_dir / "labels"
        self.metadata_dir = self.data_dir / "metadata"
        
    def load_image(self, image_path: str, format: str = "png") -> np.ndarray:
        """
        Load a satellite image from file.
        
        Args:
            image_path: Path to the image file
            format: Image format (png, tiff, geotiff)
            
        Returns:
            Image as numpy array
        """
        path = Path(image_path)
        
        if format.lower() == "geotiff" or path.suffix.lower() == ".tif":
            return self._load_geotiff(str(path))
        else:
            image = cv2.imread(str(path))
            if image is None:
                raise ValueError(f"Could not load image from {path}")
            return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    
    def _load_geotiff(self, path: str) -> Tuple[np.ndarray, Dict]:
        """
        Load GeoTIFF file with metadata.
        
        Args:
            path: Path to GeoTIFF file
            
        Returns:
            Tuple of (image array, metadata dictionary)
        """
        with rasterio.open(path) as src:
            image = src.read()
            metadata = {
                'crs': str(src.crs),
                'transform': src.transform,
                'bounds': src.bounds,
                'width': src.width,
                'height': src.height,
                'count': src.count
            }
            # Convert to RGB if multi-band
            if image.shape[0] == 1:
                image = image[0]
            elif image.shape[0] >= 3:
                image = np.transpose(image[:3], (1, 2, 0))
            
        return image, metadata
    
    def load_labels(self, label_path: str) -> Dict:
        """
        Load land cover classification labels.
        
        Args:
            label_path: Path to label JSON file
            
        Returns:
            Dictionary containing label data
        """
        with open(label_path, 'r') as f:
            return json.load(f)
    
    def preprocess_image(self, image: np.ndarray, 
                        target_size: Optional[Tuple[int, int]] = None,
                        normalize: bool = True) -> np.ndarray:
        """
        Preprocess satellite image.
        
        Args:
            image: Input image array
            target_size: Target size (width, height) for resizing
            normalize: Whether to normalize pixel values to [0, 1]
            
        Returns:
            Preprocessed image
        """
        processed = image.copy()
        
        if target_size:
            processed = cv2.resize(processed, target_size, 
                                 interpolation=cv2.INTER_LINEAR)
        
        if normalize:
            processed = processed.astype(np.float32) / 255.0
        
        return processed
    
    def extract_features(self, image: np.ndarray) -> Dict:
        """
        Extract basic features from satellite image.
        
        Args:
            image: Input image array
            
        Returns:
            Dictionary of extracted features
        """
        features = {
            'shape': image.shape,
            'dtype': str(image.dtype),
            'min': float(np.min(image)),
            'max': float(np.max(image)),
            'mean': float(np.mean(image)),
            'std': float(np.std(image))
        }
        
        if len(image.shape) == 3:
            features['channels'] = image.shape[2]
            for i in range(image.shape[2]):
                features[f'channel_{i}_mean'] = float(np.mean(image[:, :, i]))
        
        return features
    
    def visualize_image(self, image: np.ndarray, 
                       labels: Optional[Dict] = None,
                       save_path: Optional[str] = None):
        """
        Visualize satellite image with optional labels overlay.
        
        Args:
            image: Image array to visualize
            labels: Optional label data for overlay
            save_path: Optional path to save the visualization
        """
        fig, ax = plt.subplots(1, 1, figsize=(12, 12))
        ax.imshow(image)
        ax.axis('off')
        ax.set_title('Satellite Image', fontsize=16, fontweight='bold')
        
        if labels:
            # Overlay land cover regions if available
            if 'regions' in labels:
                for region in labels['regions']:
                    if 'polygon' in region:
                        polygon = np.array(region['polygon'])
                        ax.plot(polygon[:, 0], polygon[:, 1], 
                               'r-', linewidth=2, alpha=0.7)
        
        plt.tight_layout()
        
        if save_path:
            plt.savefig(save_path, dpi=150, bbox_inches='tight')
        else:
            plt.show()
        
        plt.close()


def main():
    """
    Example usage of the SatelliteImageProcessor.
    Created by: RSK World (https://rskworld.in)
    """
    processor = SatelliteImageProcessor()
    
    # Example: Process a sample image
    print("Satellite Image Dataset - Processing Example")
    print("Created by: RSK World (https://rskworld.in)")
    print("-" * 50)
    
    # Check if sample data exists
    sample_image = processor.images_dir / "sample_001.png"
    if sample_image.exists():
        # Load image
        image = processor.load_image(str(sample_image))
        print(f"Loaded image: {image.shape}")
        
        # Extract features
        features = processor.extract_features(image)
        print(f"Features: {features}")
        
        # Preprocess
        processed = processor.preprocess_image(image, normalize=True)
        print(f"Processed image shape: {processed.shape}")
        
        # Visualize
        processor.visualize_image(image)
    else:
        print("Sample image not found. Please add images to data/images/ directory.")


if __name__ == "__main__":
    main()

228 lines•7 KB

python

config.py

Raw Download

#!/usr/bin/env python3
"""
Satellite Image Dataset - Configuration
Created by: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277

Configuration settings for the satellite image dataset.
"""

# Dataset paths
DATA_DIR = "data"
IMAGES_DIR = "data/images"
LABELS_DIR = "data/labels"
METADATA_DIR = "data/metadata"
BUILDING_DETECTION_DIR = "data/building_detection"
SAMPLES_DIR = "data/samples"
OUTPUT_DIR = "visualizations"

# Image processing settings
DEFAULT_IMAGE_SIZE = (512, 512)
NORMALIZE_IMAGES = True
SUPPORTED_FORMATS = ['.png', '.tiff', '.tif', '.jpg', '.jpeg', '.geotiff']

# Land cover classes
LAND_COVER_CLASSES = [
    "water",
    "forest",
    "urban",
    "agriculture",
    "barren",
    "grassland",
    "wetland",
    "snow"
]

# Visualization settings
VISUALIZATION_DPI = 150
FIGURE_SIZE = (12, 12)

# Project metadata
PROJECT_NAME = "Satellite Image Dataset"
PROJECT_VERSION = "1.0.0"
AUTHOR = "RSK World"
AUTHOR_WEBSITE = "https://rskworld.in"
AUTHOR_EMAIL = "help@rskworld.in"
AUTHOR_PHONE = "+91 93305 39277"

50 lines•1.1 KB

python

Theme Settings

Color Scheme

Display Options

Font Size

Theme Settings

Color Scheme

Display Options

Font Size

🚀 Support RSK World