tarinmodel12

Sleeping

App Files Files Community

nagasurendra commited on Jun 19

Commit

78f6b92

verified ·

1 Parent(s): 53065c4

Update app.py

Browse files

Files changed (1) hide show

app.py +136 -94

app.py CHANGED Viewed

@@ -165,142 +165,179 @@ def generate_report(
     io_times: List[float]
 ) -> str:
     log_entries.append("Generating report...")
-    report_path = os.path.join(OUTPUT_DIR, f"drone_analysis_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.md")
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
     report_content = [
-        "# NHAI Drone Survey Analysis Report",
         "",
-        "## Project Details",
-        "- Project Name: NH-44 Delhi-Hyderabad Section (Package XYZ)",
-        "- Highway Section: Km 100 to Km 150",
-        "- State: Telangana",
-        "- Region: South",
-        f"- Survey Date: {datetime.now().strftime('%Y-%m-%d')}",
-        "- Drone Service Provider: ABC Drone Services Pvt. Ltd.",
-        "- Technology Service Provider: XYZ AI Analytics Ltd.",
-        f"- Work Order Reference: Data Lake WO-{datetime.now().strftime('%Y-%m-%d')}-XYZ",
-        "- Report Prepared By: Nagasurendra, Data Analyst",
-        f"- Report Date: {datetime.now().strftime('%Y-%m-%d')}",
         "",
-        "## 1. Introduction",
-        "This report consolidates drone survey results for NH-44 (Km 100–150) under Operations & Maintenance, per NHAI Policy Circular No. 18.98/2024, detecting potholes and cracks using YOLOv8 for Monthly Progress Report integration.",
         "",
-        "## 2. Drone Survey Metadata",
-        "- Drone Speed: 5 m/s",
-        "- Drone Height: 60 m",
-        "- Camera Sensor: RGB, 12 MP",
-        "- Recording Type: JPEG, 90° nadir",
-        "- Image Overlap: 85%",
-        "- Flight Pattern: Single lap, ROW centered",
-        "- Geotagging: Enabled",
-        "- Satellite Lock: 12 satellites",
-        "- Terrain Follow Mode: Enabled",
         "",
-        "## 3. Quality Check Results",
-        "- Resolution: 1920x1080",
-        "- Overlap: 85%",
-        "- Camera Angle: 90° nadir",
-        "- Drone Speed: ≤ 5 m/s",
-        "- Geotagging: 100% compliant",
-        "- QC Status: Passed",
         "",
-        "## 4. AI/ML Analytics",
-        f"- Total Frames Processed: {frame_count}",
-        f"- Detection Frames: {detection_frame_count} ({detection_frame_count/frame_count*100:.1f}%)",
-        f"- Total Detections: {metrics['total_detections']}",
-        "  - Breakdown:"
     ]
     for item in metrics.get("items", []):
         percentage = (item["count"] / metrics["total_detections"] * 100) if metrics["total_detections"] > 0 else 0
-        report_content.append(f"    - {item['type']}: {item['count']} ({percentage:.1f}%)")
     report_content.extend([
-        f"- Processing Time: {total_time:.1f} seconds",
-        f"- Average Frame Time: {sum(frame_times)/len(frame_times):.1f} ms" if frame_times else "- Average Frame Time: N/A",
-        f"- Average Resize Time: {sum(resize_times)/len(resize_times):.1f} ms" if resize_times else "- Average Resize Time: N/A",
-        f"- Average Inference Time: {sum(inference_times)/len(inference_times):.1f} ms" if inference_times else "- Average Inference Time: N/A",
-        f"- Average I/O Time: {sum(io_times)/len(io_times):.1f} ms" if io_times else "- Average I/O Time: N/A",
-        f"- Timestamp: {metrics.get('timestamp', 'N/A')}",
-        "- Summary: Potholes and cracks detected in high-traffic areas.",
         "",
-        "## 5. Output File Structure",
-        "- ZIP file contains:",
-        "  - `drone_analysis_report_<timestamp>.md`: This report",
-        "  - `outputs/processed_output.mp4`: Processed video with annotations",
-        "  - `outputs/chart_<timestamp>.png`: Detection trend chart",
-        "  - `outputs/map_<timestamp>.png`: Issue locations map",
-        "  - `captured_frames/detected_<frame>.jpg`: Geotagged images for detected issues",
-        "  - `flight_logs/flight_log_<frame>.csv`: Flight logs matching image frames",
-        "- Note: Images and logs share frame numbers (e.g., `detected_000001.jpg` corresponds to `flight_log_000001.csv`).",
         "",
-        "## 6. Geotagged Images",
-        f"- Total Images: {len(detected_issues)}",
-        f"- Storage: Data Lake `/project_xyz/images/{datetime.now().strftime('%Y%m%d')}`",
         "",
-        "| Frame | Issue Type | GPS (Lat, Lon) | Timestamp | Confidence | Image Path |",
-        "|-------|------------|----------------|-----------|------------|------------|"
     ])
     for detection in all_detections[:100]:
         report_content.append(
-            f"| {detection['frame']:06d} | {detection['label']} | ({detection['gps'][0]:.6f}, {detection['gps'][1]:.6f}) | {detection['timestamp']} | {detection['conf']:.1f} | captured_frames/{os.path.basename(detection['path'])} |"
         )
     report_content.extend([
         "",
-        "## 7. Flight Logs",
-        f"- Total Logs: {len(detected_issues)}",
-        f"- Storage: Data Lake `/project_xyz/flight_logs/{datetime.now().strftime('%Y%m%d')}`",
         "",
-        "| Frame | Timestamp | Latitude | Longitude | Speed (m/s) | Satellites | Altitude (m) | Log Path |",
-        "|-------|-----------|----------|-----------|-------------|------------|--------------|----------|"
     ])
     for detection in all_detections[:100]:
         log_path = f"flight_logs/flight_log_{detection['frame']:06d}.csv"
         report_content.append(
-            f"| {detection['frame']:06d} | {detection['timestamp']} | {detection['gps'][0]:.6f} | {detection['gps'][1]:.6f} | 5.0 | 12 | 60 | {log_path} |"
         )
     report_content.extend([
         "",
-        "## 8. Processed Video",
-        f"- Path: outputs/processed_output.mp4",
-        f"- Frames: {output_frames}",
-        f"- FPS: {output_fps:.1f}",
-        f"- Duration: {output_duration:.1f} seconds",
         "",
-        "## 9. Visualizations",
-        f"- Detection Trend Chart: outputs/chart_{timestamp}.png",
-        f"- Issue Locations Map: outputs/map_{timestamp}.png",
         "",
-        "## 10. Processing Timestamps",
-        f"- Total Processing Time: {total_time:.1f} seconds",
-        "- Log Entries (Last 10):"
     ])
     for entry in log_entries[-10:]:
-        report_content.append(f"  - {entry}")
     report_content.extend([
         "",
-        "## 11. Stakeholder Validation",
-        "- AE/IE Comments: [Pending]",
-        "- PD/RO Comments: [Pending]",
         "",
-        "## 12. Recommendations",
-        "- Repair potholes in high-traffic areas.",
-        "- Seal cracks to prevent further degradation.",
-        "- Schedule a follow-up survey.",
         "",
-        "## 13. Data Lake References",
-        f"- Images: `/project_xyz/images/{datetime.now().strftime('%Y%m%d')}`",
-        f"- Flight Logs: `/project_xyz/flight_logs/{datetime.now().strftime('%Y%m%d')}`",
-        f"- Video: `/project_xyz/videos/processed_output_{timestamp}.mp4`",
-        f"- DAMS Dashboard: `/project_xyz/dams/{datetime.now().strftime('%Y%m%d')}`",
         "",
-        "## 14. Captured Images",
-        "Below are the embedded images from the captured frames directory showing detected issues:",
         ""
     ])
@@ -310,12 +347,17 @@ def generate_report(
             try:
                 with open(image_path, "rb") as image_file:
                     base64_string = base64.b64encode(image_file.read()).decode('utf-8')
-                report_content.append(f"![{image_name}](data:image/jpeg;base64,{base64_string})")
-                report_content.append(f"**Image: {image_name}**")
                 report_content.append("")
             except Exception as e:
                 log_entries.append(f"Error: Failed to encode image {image_name} to base64: {str(e)}")
     try:
         with open(report_path, 'w') as f:
             f.write("\n".join(report_content))

     io_times: List[float]
 ) -> str:
     log_entries.append("Generating report...")
+    report_path = os.path.join(OUTPUT_DIR, f"drone_analysis_report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.html")
     timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
     report_content = [
+        "<!DOCTYPE html>",
+        "<html lang='en'>",
+        "<head>",
+        "<meta charset='UTF-8'>",
+        "<title>NHAI Drone Survey Analysis Report</title>",
+        "<style>",
+        "body { font-family: Arial, sans-serif; margin: 40px; }",
+        "h1, h2, h3 { color: #333; }",
+        "ul { margin-left: 20px; }",
+        "table { border-collapse: collapse; width: 100%; margin: 10px 0; }",
+        "th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }",
+        "th { background-color: #f2f2f2; }",
+        "img { max-width: 600px; height: auto; margin: 10px 0; }",
+        "p.caption { font-weight: bold; margin: 5px 0; }",
+        "</style>",
+        "</head>",
+        "<body>",
+        "<h1>NHAI Drone Survey Analysis Report</h1>",
         "",
+        "<h2>Project Details</h2>",
+        "<ul>",
+        "<li><strong>Project Name:</strong> NH-44 Delhi-Hyderabad Section (Package XYZ)</li>",
+        "<li><strong>Highway Section:</strong> Km 100 to Km 150</li>",
+        "<li><strong>State:</strong> Telangana</li>",
+        "<li><strong>Region:</strong> South</li>",
+        f"<li><strong>Survey Date:</strong> {datetime.now().strftime('%Y-%m-%d')}</li>",
+        "<li><strong>Drone Service Provider:</strong> ABC Drone Services Pvt. Ltd.</li>",
+        "<li><strong>Technology Service Provider:</strong> XYZ AI Analytics Ltd.</li>",
+        f"<li><strong>Work Order Reference:</strong> Data Lake WO-{datetime.now().strftime('%Y-%m-%d')}-XYZ</li>",
+        "<li><strong>Report Prepared By:</strong> Nagasurendra, Data Analyst</li>",
+        f"<li><strong>Report Date:</strong> {datetime.now().strftime('%Y-%m-%d')}</li>",
+        "</ul>",
         "",
+        "<h2>1. Introduction</h2>",
+        "<p>This report consolidates drone survey results for NH-44 (Km 100–150) under Operations & Maintenance, per NHAI Policy Circular No. 18.98/2024, detecting potholes and cracks using YOLOv8 for Monthly Progress Report integration.</p>",
         "",
+        "<h2>2. Drone Survey Metadata</h2>",
+        "<ul>",
+        "<li><strong>Drone Speed:</strong> 5 m/s</li>",
+        "<li><strong>Drone Height:</strong> 60 m</li>",
+        "<li><strong>Camera Sensor:</strong> RGB, 12 MP</li>",
+        "<li><strong>Recording Type:</strong> JPEG, 90° nadir</li>",
+        "<li><strong>Image Overlap:</strong> 85%</li>",
+        "<li><strong>Flight Pattern:</strong> Single lap, ROW centered</li>",
+        "<li><strong>Geotagging:</strong> Enabled</li>",
+        "<li><strong>Satellite Lock:</strong> 12 satellites</li>",
+        "<li><strong>Terrain Follow Mode:</strong> Enabled</li>",
+        "</ul>",
         "",
+        "<h2>3. Quality Check Results</h2>",
+        "<ul>",
+        "<li><strong>Resolution:</strong> 1920x1080</li>",
+        "<li><strong>Overlap:</strong> 85%</li>",
+        "<li><strong>Camera Angle:</strong> 90° nadir</li>",
+        "<li><strong>Drone Speed:</strong> ≤ 5 m/s</li>",
+        "<li><strong>Geotagging:</strong> 100% compliant</li>",
+        "<li><strong>QC Status:</strong> Passed</li>",
+        "</ul>",
         "",
+        "<h2>4. AI/ML Analytics</h2>",
+        f"<p><strong>Total Frames Processed:</strong> {frame_count}</p>",
+        f"<p><strong>Detection Frames:</strong> {detection_frame_count} ({detection_frame_count/frame_count*100:.1f}%)</p>",
+        f"<p><strong>Total Detections:</strong> {metrics['total_detections']}</p>",
+        "<p><strong>Breakdown:</strong></p>",
+        "<ul>"
     ]
     for item in metrics.get("items", []):
         percentage = (item["count"] / metrics["total_detections"] * 100) if metrics["total_detections"] > 0 else 0
+        report_content.append(f"<li>{item['type']}: {item['count']} ({percentage:.1f}%)</li>")
     report_content.extend([
+        "</ul>",
+        f"<p><strong>Processing Time:</strong> {total_time:.1f} seconds</p>",
+        f"<p><strong>Average Frame Time:</strong> {sum(frame_times)/len(frame_times):.1f} ms</p>" if frame_times else "<p><strong>Average Frame Time:</strong> N/A</p>",
+        f"<p><strong>Average Resize Time:</strong> {sum(resize_times)/len(resize_times):.1f} ms</p>" if resize_times else "<p><strong>Average Resize Time:</strong> N/A</p>",
+        f"<p><strong>Average Inference Time:</strong> {sum(inference_times)/len(inference_times):.1f} ms</p>" if inference_times else "<p><strong>Average Inference Time:</strong> N/A</p>",
+        f"<p><strong>Average I/O Time:</strong> {sum(io_times)/len(io_times):.1f} ms</p>" if io_times else "<p><strong>Average I/O Time:</strong> N/A</p>",
+        f"<p><strong>Timestamp:</strong> {metrics.get('timestamp', 'N/A')}</p>",
+        "<p><strong>Summary:</strong> Potholes and cracks detected in high-traffic areas.</p>",
         "",
+        "<h2>5. Output File Structure</h2>",
+        "<p>ZIP file contains:</p>",
+        "<ul>",
+        f"<li><code>drone_analysis_report_{timestamp}.html</code>: This report</li>",
+        "<li><code>outputs/processed_output.mp4</code>: Processed video with annotations</li>",
+        f"<li><code>outputs/chart_{timestamp}.png</code>: Detection trend chart</li>",
+        f"<li><code>outputs/map_{timestamp}.png</code>: Issue locations map</li>",
+        "<li><code>captured_frames/detected_&lt;frame&gt;.jpg</code>: Geotagged images for detected issues</li>",
+        "<li><code>flight_logs/flight_log_&lt;frame&gt;.csv</code>: Flight logs matching image frames</li>",
+        "</ul>",
+        "<p><strong>Note:</strong> Images and logs share frame numbers (e.g., <code>detected_000001.jpg</code> corresponds to <code>flight_log_000001.csv</code>).</p>",
         "",
+        "<h2>6. Geotagged Images</h2>",
+        f"<p><strong>Total Images:</strong> {len(detected_issues)}</p>",
+        f"<p><strong>Storage:</strong> Data Lake <code>/project_xyz/images/{datetime.now().strftime('%Y%m%d')}</code></p>",
         "",
+        "<table>",
+        "<tr><th>Frame</th><th>Issue Type</th><th>GPS (Lat, Lon)</th><th>Timestamp</th><th>Confidence</th><th>Image Path</th></tr>"
     ])
     for detection in all_detections[:100]:
         report_content.append(
+            f"<tr><td>{detection['frame']:06d}</td><td>{detection['label']}</td><td>({detection['gps'][0]:.6f}, {detection['gps'][1]:.6f})</td><td>{detection['timestamp']}</td><td>{detection['conf']:.1f}</td><td>captured_frames/{os.path.basename(detection['path'])}</td></tr>"
         )
     report_content.extend([
+        "</table>",
         "",
+        "<h2>7. Flight Logs</h2>",
+        f"<p><strong>Total Logs:</strong> {len(detected_issues)}</p>",
+        f"<p><strong>Storage:</strong> Data Lake <code>/project_xyz/flight_logs/{datetime.now().strftime('%Y%m%d')}</code></p>",
         "",
+        "<table>",
+        "<tr><th>Frame</th><th>Timestamp</th><th>Latitude</th><th>Longitude</th><th>Speed (m/s)</th><th>Satellites</th><th>Altitude (m)</th><th>Log Path</th></tr>"
     ])
     for detection in all_detections[:100]:
         log_path = f"flight_logs/flight_log_{detection['frame']:06d}.csv"
         report_content.append(
+            f"<tr><td>{detection['frame']:06d}</td><td>{detection['timestamp']}</td><td>{detection['gps'][0]:.6f}</td><td>{detection['gps'][1]:.6f}</td><td>5.0</td><td>12</td><td>60</td><td>{log_path}</td></tr>"
         )
     report_content.extend([
+        "</table>",
         "",
+        "<h2>8. Processed Video</h2>",
+        f"<p><strong>Path:</strong> outputs/processed_output.mp4</p>",
+        f"<p><strong>Frames:</strong> {output_frames}</p>",
+        f"<p><strong>FPS:</strong> {output_fps:.1f}</p>",
+        f"<p><strong>Duration:</strong> {output_duration:.1f} seconds</p>",
         "",
+        "<h2>9. Visualizations</h2>",
+        f"<p><strong>Detection Trend Chart:</strong> outputs/chart_{timestamp}.png</p>",
+        f"<p><strong>Issue Locations Map:</strong> outputs/map_{timestamp}.png</p>",
         "",
+        "<h2>10. Processing Timestamps</h2>",
+        f"<p><strong>Total Processing Time:</strong> {total_time:.1f} seconds</p>",
+        "<p><strong>Log Entries (Last 10):</strong></p>",
+        "<ul>"
     ])
     for entry in log_entries[-10:]:
+        report_content.append(f"<li>{entry}</li>")
     report_content.extend([
+        "</ul>",
         "",
+        "<h2>11. Stakeholder Validation</h2>",
+        "<ul>",
+        "<li><strong>AE/IE Comments:</strong> [Pending]</li>",
+        "<li><strong>PD/RO Comments:</strong> [Pending]</li>",
+        "</ul>",
         "",
+        "<h2>12. Recommendations</h2>",
+        "<ul>",
+        "<li>Repair potholes in high-traffic areas.</li>",
+        "<li>Seal cracks to prevent further degradation.</li>",
+        "<li>Schedule a follow-up survey.</li>",
+        "</ul>",
         "",
+        "<h2>13. Data Lake References</h2>",
+        "<ul>",
+        f"<li><strong>Images:</strong> <code>/project_xyz/images/{datetime.now().strftime('%Y%m%d')}</code></li>",
+        f"<li><strong>Flight Logs:</strong> <code>/project_xyz/flight_logs/{datetime.now().strftime('%Y%m%d')}</code></li>",
+        f"<li><strong>Video:</strong> <code>/project_xyz/videos/processed_output_{timestamp}.mp4</code></li>",
+        f"<li><strong>DAMS Dashboard:</strong> <code>/project_xyz/dams/{datetime.now().strftime('%Y%m%d')}</code></li>",
+        "</ul>",
         "",
+        "<h2>14. Captured Images</h2>",
+        "<p>Below are the embedded images from the captured frames directory showing detected issues:</p>",
         ""
     ])
             try:
                 with open(image_path, "rb") as image_file:
                     base64_string = base64.b64encode(image_file.read()).decode('utf-8')
+                report_content.append(f"<img src='data:image/jpeg;base64,{base64_string}' alt='{image_name}'>")
+                report_content.append(f"<p class='caption'>Image: {image_name}</p>")
                 report_content.append("")
             except Exception as e:
                 log_entries.append(f"Error: Failed to encode image {image_name} to base64: {str(e)}")
+    report_content.extend([
+        "</body>",
+        "</html>"
+    ])
     try:
         with open(report_path, 'w') as f:
             f.write("\n".join(report_content))