Update video_processing.py

video_processing.py

@@ -10,7 +10,7 @@ from face_analysis import get_face_embedding, cluster_faces, organize_faces_by_p
 from pose_analysis import pose, calculate_posture_score, draw_pose_landmarks
 from voice_analysis import get_speaker_embeddings, align_voice_embeddings, extract_audio_from_video, diarize_speakers
 from anomaly_detection import anomaly_detection
-from visualization import plot_mse, plot_mse_histogram, plot_mse_heatmap, plot_audio_waveform, plot_stacked_mse_heatmaps
+from visualization import plot_mse, plot_mse_histogram, plot_mse_heatmap, plot_stacked_mse_heatmaps
 from utils import frame_to_timecode
 import pandas as pd
 from facenet_pytorch import MTCNN
@@ -197,9 +197,6 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
             mse_heatmap_posture = plot_mse_heatmap(mse_posture, "Body Posture MSE Heatmap", df)
             mse_heatmap_voice = plot_mse_heatmap(mse_voice, "Voice MSE Heatmap", df)
 
-            # Create audio waveform plot
-            audio_waveform_plot = plot_audio_waveform(audio_path, "Audio Waveform")
-
             stacked_heatmap = plot_stacked_mse_heatmaps(mse_embeddings, mse_posture, mse_voice, df, "Combined MSE Heatmaps")
 
             progress(0.95, "Finishing generating graphs")
@@ -208,7 +205,7 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
             print(f"Error details: {str(e)}")
             import traceback
             traceback.print_exc()
-            return (f"Error in video processing: {str(e)}",) + (None,) * 27
+            return (f"Error in video processing: {str(e)}",) + (None,) * 26
 
         progress(1.0, "Preparing results")
         results = f"Number of persons detected: {num_clusters}\n\n"
@@ -270,7 +267,6 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
             mse_heatmap_embeddings,
             mse_heatmap_posture,
             mse_heatmap_voice,
-            audio_waveform_plot,
             face_samples["most_frequent"],
             anomaly_faces_embeddings,
             anomaly_frames_posture_images,
@@ -281,7 +277,6 @@ def process_video(video_path, anomaly_threshold, desired_fps, progress=None):
         )
 
 
-
 def is_frontal_face(landmarks, threshold=60):
     nose_tip = landmarks[4]
     left_chin = landmarks[234]