Update app.py

app.py

@@ -21,7 +21,6 @@ import time
 import matplotlib.pyplot as plt
 from pathlib import Path
 import plotly.express as px
-from google.cloud import videointelligence
 
 # Set page config
 st.set_page_config(
@@ -516,33 +515,6 @@ def process_video_file(video_file, analysis_types):
         "labels": {}
     }
     
-    # Add Video Intelligence API integration for semantic analysis
-    if "Semantic" in analysis_types:
-        # Initialize video intelligence client
-        video_client = videointelligence.VideoIntelligenceServiceClient(credentials=credentials)
-        
-        # Set up features for semantic analysis
-        features = [
-            videointelligence.Feature.LABEL_DETECTION,
-            videointelligence.Feature.SHOT_CHANGE_DETECTION,
-            videointelligence.Feature.ACTION_RECOGNITION
-        ]
-        
-        # Process video for semantic understanding
-        operation = video_client.annotate_video(
-            request={"features": features, "input_content": video_file.read()}
-        )
-        
-        # Get semantic results
-        semantic_results = operation.result()
-        
-        # Store semantic insights for visualization
-        semantic_insights = {
-            "actions": extract_actions(semantic_results),
-            "segments": extract_segments(semantic_results),
-            "scene_labels": extract_labels(semantic_results)
-        }
-    
     try:
         frame_count = 0
         while frame_count < max_frames:  # Limit to 10 seconds
@@ -561,7 +533,7 @@ def process_video_file(video_file, analysis_types):
             cv2.putText(frame, f"Time: {frame_count/fps:.2f}s", 
                       (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
             
-            # Process frames with Vision AI (more frequently for detail)
+            # Process frames with Vision API (more frequently for detail)
             if frame_count % process_every_n_frames == 0:
                 try:
                     # Convert OpenCV frame to PIL Image for Vision API
@@ -725,10 +697,7 @@ def process_video_file(video_file, analysis_types):
         os.unlink(output_path)
         
         # Return both the video and the detection statistics
-        return processed_video_bytes, {
-            "detection_stats": detection_stats,
-            "semantic_insights": semantic_insights if "Semantic" in analysis_types else None
-        }
+        return processed_video_bytes, detection_stats
         
     except Exception as e:
         # Clean up on error
@@ -990,9 +959,7 @@ def main():
             analysis_types.append("Face Detection")
         if st.sidebar.checkbox("Text Recognition"):
             analysis_types.append("Text")
-        if st.sidebar.checkbox("Semantic Analysis", value=True):
-            analysis_types.append("Semantic")
-            
+        
         st.sidebar.markdown("---")
         st.sidebar.warning("⚠️ Video analysis may use a significant amount of API calls. Use responsibly.")
         
@@ -1101,25 +1068,6 @@ def main():
                                         ax.pie(top_labels.values(), labels=top_labels.keys(), autopct='%1.1f%%')
                                         ax.set_title('Distribution of Scene Labels')
                                         st.pyplot(fig)
-                                
-                                # Display semantic analysis results
-                                if "Semantic" in analysis_types and results["semantic_insights"]:
-                                    st.markdown("### 🧠 Semantic Understanding")
-                                    
-                                    # Display scene context
-                                    st.markdown("#### Video Context")
-                                    for label in results["semantic_insights"]["scene_labels"][:10]:
-                                        st.markdown(f"- {label['description']}: {label['confidence']:.1%}")
-                                    
-                                    # Display activities detected
-                                    st.markdown("#### Activities")
-                                    for action in results["semantic_insights"]["actions"]:
-                                        st.markdown(f"- {action['description']} at {action['time_segment']}")
-                                    
-                                    # Visualize relationships and context
-                                    st.markdown("#### Scene Segments")
-                                    fig = create_segment_visualization(results["semantic_insights"]["segments"])
-                                    st.plotly_chart(fig)
                         
                         except Exception as e:
                             st.error(f"Error processing video: {str(e)}")