ia

app.py

@@ -88,7 +88,7 @@ def process_video(input_video, player_stats=True, ball_stats=True):
     speed_and_distance_estimator.draw_speed_and_distance(output_video_frames, tracks)
 
     # Save output video
-    output_path = 'output_videos/output_video.mp4'
+    output_path = 'output_videos/output_video.avi'
     save_video(output_video_frames, output_path)
 
     return output_path
@@ -97,13 +97,14 @@ def process_video(input_video, player_stats=True, ball_stats=True):
 title="Football Match Analytics with YOLO and OpenCV"
 description="""
     This tool processes football game videos to detect players and referees, track the ball, assign players to teams using color pixel clustering, and compute ball possession. 
+    
     It also estimates camera movement with Optical Flow, applies perspective transformation for scene depth, and calculates real-time speed and total distance traveled by each player and the ball.
 
     The YOLO model was fine-tuned with https://universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc
 
     Original Reference: https://www.youtube.com/watch?v=neBZ6huolkg
     
-    **Note**: the space is running on CPU, so inferencing new video may take a long time (avg speed in test: 1.5min processing per 1 sec of video)"""
+    **Note**: the space is running on CPU, so inferencing new video may take a bit of time. (Avg time during test: 1min processing per 5 second of video)"""
 
 examples = [["input_videos/121364_0_small.mp4", True, True]]