Update app.py

app.py

@@ -75,7 +75,10 @@ def on_button_click(video, threshold, fps):
         face_samples_most_frequent: results[13],
         heatmap_video: results[14],
         combined_mse_plot: results[15],
-        correlation_heatmap_plot: results[16]
+        correlation_heatmap_plot: results[16],
+        video_display_facial: video,
+        video_display_body: video,
+        video_display_voice: video
     }
 
 with gr.Blocks() as iface:
@@ -86,8 +89,7 @@ with gr.Blocks() as iface:
     It extracts faces, postures, and voice from video frames, and analyzes them to identify anomalies using time series analysis and a variational autoencoder (VAE) approach.
     """)
 
-    with gr.Row():
-        video_input = gr.Video()
+    video_input = gr.Video(label="Input Video", visible=True)
 
     anomaly_threshold = gr.Slider(minimum=1, maximum=5, step=0.1, value=3, label="Anomaly Detection Threshold (Standard deviation)")
     fps_slider = gr.Slider(minimum=5, maximum=20, step=1, value=10, label="Frames Per Second (FPS)")
@@ -174,8 +176,7 @@ with gr.Blocks() as iface:
                 ### High-Speed Cameras
                 
                 Effective capture of micro-expressions generally requires frame rates above 100 fps. High-speed video systems designed for micro-expression detection often operate at 118 fps or higher, with some systems reaching up to 200 fps.
-                caution.
-                
+            
                 ## Limitations
                 
                 - **Evaluation Challenges**: Since this is an unsupervised method, there is no labeled data to compare against. This makes it difficult to quantitatively evaluate the accuracy or effectiveness of the anomaly detection.
@@ -190,12 +191,13 @@ with gr.Blocks() as iface:
                 
                 ## Conclusion
                 This tool offers solutions for detecting emotional, posture, and vocal anomalies in video-based facial expressions, body language, and speech, beneficial for both forensic analysis and HUMINT operations. However, users should be aware of its limitations and the challenges inherent in unsupervised anomaly detection methodologies. By leveraging advanced computer vision techniques and the power of autoencoders, it provides crucial insights into human behavior in a timely manner, but results should be interpreted with caution and, where possible, supplemented with additional context and expert analysis.
-
+                h caution.
                 """)
 
         with gr.TabItem("Results", id="results_tab", visible=False) as results_tab:
             with gr.Tabs():
                 with gr.TabItem("Facial Features"):
+                    video_display_facial = gr.Video(label="Input Video")
                     results_text = gr.TextArea(label="Faces Breakdown", lines=5)
                     mse_features_plot = gr.Plot(label="MSE: Facial Features")
                     mse_features_hist = gr.Plot(label="MSE Distribution: Facial Features")
@@ -204,12 +206,14 @@ with gr.Blocks() as iface:
                     face_samples_most_frequent = gr.Gallery(label="Most Frequent Person Samples", columns=10, rows=2, height="auto")
 
                 with gr.TabItem("Body Posture"):
+                    video_display_body = gr.Video(label="Input Video")
                     mse_posture_plot = gr.Plot(label="MSE: Body Posture")
                     mse_posture_hist = gr.Plot(label="MSE Distribution: Body Posture")
                     mse_posture_heatmap = gr.Plot(label="MSE Heatmap: Body Posture")
                     anomaly_frames_posture = gr.Gallery(label="Anomaly Frames (Body Posture)", columns=6, rows=2, height="auto")
 
                 with gr.TabItem("Voice"):
+                    video_display_voice = gr.Video(label="Input Video")
                     mse_voice_plot = gr.Plot(label="MSE: Voice")
                     mse_voice_hist = gr.Plot(label="MSE Distribution: Voice")
                     mse_voice_heatmap = gr.Plot(label="MSE Heatmap: Voice")
@@ -229,7 +233,7 @@ with gr.Blocks() as iface:
             mse_features_heatmap, mse_posture_heatmap, mse_voice_heatmap,
             anomaly_frames_features, anomaly_frames_posture,
             face_samples_most_frequent, heatmap_video, combined_mse_plot,
-            correlation_heatmap_plot
+            correlation_heatmap_plot, video_display_facial, video_display_body, video_display_voice
         ]
     )