cleanedup automation

app.py

@@ -4,7 +4,7 @@ import os
 import json
 import numpy as np
 
-folderPath = "videos/rte-archive-football"
+baseFolderPath = "videos"
 output_file = "embeddings.json"
 
 embeddings = []
@@ -23,11 +23,14 @@ backends = [
 ]
 
 def main():
-    image_paths = setup()
-    run(image_paths)
+    video_folders = setup()
+    for folder_info in video_folders:
+        foldername, video_path, image_paths = folder_info
+        print(1)
+        run(image_paths, foldername, video_path)
     saveToJson()
 
-def processImage(image, idx):
+def processImage(image, idx, foldername, video_path):
     try:
 
         anaylse_obj = DeepFace.analyze(
@@ -46,31 +49,50 @@ def processImage(image, idx):
         normalised_emotions = normalised_emotions.tolist()
 
         entry = {
-            "index": idx,
-            "filename": os.path.basename(image),  # Extract the filename from the path
+            "folder": foldername,
+            "frame": image,  # Extract the filename from the path
+            "video": video_path,
             "vector": normalised_emotions
         }
         
         # Add the entry to the JSON data list
         embeddings.append(entry)
     except:
+        pass
         print("Could not locate face in image. Skipping.")
 
-def run(image_paths):
-    for idx, image in enumerate(image_paths):
-        processImage(image, idx)
 
 def setup():
-    # List of all images in the specified folder
-    image_files = glob.glob(os.path.join(folderPath, '*'))
+    video_folders = []
+
+    subfolders = [f.path for f in os.scandir(baseFolderPath) if f.is_dir()]
+
+    for subfolder in subfolders:
+        frames_folder_path = os.path.join(subfolder, "frames")
+        
+        # Find the video file in the subfolder
+        video_files = [f for f in os.listdir(subfolder) if f.endswith(('.mp4', '.avi', '.mov'))]
+        if video_files:
+            video_path = os.path.join(subfolder, video_files[0])
+
+        # List of all image files in the frames folder
+        image_files = glob.glob(os.path.join(frames_folder_path, '*'))
 
-    # Optional: Filter by specific image extensions (e.g., .jpg, .png)
+        # Filter by specific image extensions (e.g., .jpg, .png)
         image_paths = [img for img in image_files if img.endswith(('.jpg', '.jpeg', '.png', '.bmp', '.tiff', '.gif'))]
 
-    # Sort the image paths by filename
-    image_paths.sort(key=lambda x: os.path.basename(x))
+        # Sort the image paths by filename (assuming the filenames are numerically ordered)
+        image_paths.sort(key=lambda x: int(os.path.splitext(os.path.basename(x))[0]))
 
-    return image_paths
+        # Add the information to the list
+        video_folders.append((os.path.basename(subfolder), video_path, image_paths))
+
+    return video_folders
+        
+
+def run(image_paths, foldername, video_path):
+    for idx, image in enumerate(image_paths):
+        processImage(image, idx, foldername, video_path)
 
 def l2_normalize(vector):
     norm = np.linalg.norm(vector)

process_video.py

@@ -1,6 +1,26 @@
 import os
 import subprocess
 import re
+import shutil
+
+def convert_video(video_path, output_path):
+    print(f"Converting video, {video_path}")
+
+    # Codec that works with openframeworks!
+    
+    command = [
+        "ffmpeg", 
+        "-i", video_path,                  # Input file
+        "-c:v", "libx264",                 # Video codec
+        "-profile:v", "high",              # Video profile
+        "-c:a", "copy",                    # Copy audio without re-encoding
+        output_path                       # Output file
+    ]
+
+    results = subprocess.run(command, stderr=subprocess.PIPE, text=True)
+    output = results.stderr
+
+    print(f"Video converted {output}")
 
 def get_frame_rate(video_path):
     """
@@ -34,7 +54,7 @@ def extract_frames_from_video(video_path, output_folder):
         '-i', video_path,                 # Input file
         '-vf', 'fps=1',                   # Extract 1 frame per second
         '-vsync', 'vfr',                  # Variable frame rate
-        os.path.join(output_folder, 'frame_%04d.png')  # Output pattern
+        os.path.join(output_folder, 'frame_%09d.png')  # Output pattern
     ]
 
     subprocess.run(command, check=True)
@@ -49,7 +69,7 @@ def rename_frames(output_folder, frame_rate):
         original_frame_number = int(i * frame_rate)
         
         # Create the new filename with the original frame number
-        new_filename = f"frame_{original_frame_number:05d}.png"
+        new_filename = f"{original_frame_number:09d}.png"
         os.rename(
             os.path.join(output_folder, filename),
             os.path.join(output_folder, new_filename)
@@ -61,17 +81,32 @@ def process_videos_in_folder(folder_path):
     """
     for filename in os.listdir(folder_path):
         if filename.lower().endswith(('.mp4', '.avi', '.mov', '.mkv', '.flv')):
+
             video_path = os.path.join(folder_path, filename)
+
             output_folder = os.path.join(folder_path, os.path.splitext(filename)[0])  # Create a folder for each video
 
+            # New location for .mp4
+            video_copy_location = os.path.join(output_folder, filename)
+
+            # Create frames folder
+            frames_folder = os.path.join(output_folder, "frames")
+            
+            if not os.path.exists(output_folder):
+                os.mkdir(output_folder)
+
+            if not os.path.exists(frames_folder):
+                os.mkdir(frames_folder)
+
             print(f'Processing video: {video_path}')
             
             try:
-                frame_rate = get_frame_rate(video_path)
+                convert_video(video_path, video_copy_location)
+                frame_rate = get_frame_rate(video_copy_location)
                 print(f'Original frame rate: {frame_rate} fps')
-                extract_frames_from_video(video_path, output_folder)
-                rename_frames(output_folder, frame_rate)
-                print(f'Frames saved and renamed to: {output_folder}')
+                extract_frames_from_video(video_copy_location, frames_folder)
+                rename_frames(frames_folder, frame_rate)
+                print(f'Frames saved and renamed to: {frames_folder}')
             except ValueError as e:
                 print(f'Error processing video {video_path}: {e}')