added name and fav animal

SoccerAnalysis/basicSoccerNet/soccerNet.py

@@ -6,30 +6,32 @@
 
 # Paths to files
 PICKLE_FILE_PATH = "video_detections.pkl"  # Path to the saved detections
-SOURCE_VIDEO_PATH = "source_video.mov"      # Path to the source video file
-TARGET_VIDEO_PATH = "video_out.mov"         # Path to the output video file
+SOURCE_VIDEO_PATH = "short_soccer_vid.mp4"      # Path to the source video file
+TARGET_VIDEO_PATH = "video_out.mp4"         # Path to the output video file
 
 # Initialize Roboflow and model
-rf = Roboflow(api_key="")
+rf = Roboflow(api_key="sQSgPz1GyivBdnnWUKtR")
 project = rf.workspace().project("football-players-detection-3zvbc")
 model = project.version(9).model
 
 # Create BYTETracker instance
-byte_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
+#byte_tracker = sv.ByteTrack(track_thresh=0.25, track_buffer=30, match_thresh=0.8, frame_rate=30)
+#byte_tracker = sv.ByteTrack(track_buffer=30, match_thresh=0.8, frame_rate=30)
 
 # Create instance of BoxAnnotator and TraceAnnotator
-box_annotator = sv.BoxAnnotator(thickness=4, text_thickness=4, text_scale=2)
+box_annotator = sv.BoxAnnotator(thickness=4)
+
 trace_annotator = sv.TraceAnnotator(thickness=4, trace_length=50)
 
 # Function to load detections from a pickle file
-def load_detections_from_pickle(pickle_file_path):
-    with open(pickle_file_path, 'rb') as f:
-        detections = pickle.load(f)
-    print(f"Loaded detections from {pickle_file_path}")
-    return detections
+# def load_detections_from_pickle(pickle_file_path):
+#     with open(pickle_file_path, 'rb') as f:
+#         detections = pickle.load(f)
+#     print(f"Loaded detections from {pickle_file_path}")
+#     return detections
 
 # Load detections from pickle file
-all_detections = load_detections_from_pickle(PICKLE_FILE_PATH)
+# all_detections = load_detections_from_pickle(PICKLE_FILE_PATH)
 
 # Open the source video
 cap = cv2.VideoCapture(SOURCE_VIDEO_PATH)
@@ -72,3 +74,7 @@ def load_detections_from_pickle(pickle_file_path):
 cap.release()
 out.release()
 print(f"Processed video saved to {TARGET_VIDEO_PATH}")
+
+"""
+Aarnav, and my favorite animal are dogs
+"""

SoccerAnalysis/basicSoccerNet/updatedSoccerNet.py

@@ -0,0 +1,71 @@
+import numpy as np
+import supervision as sv
+from roboflow import Roboflow
+from inference import get_model
+
+
+SOURCE_VIDEO_PATH = "shortTestVid.mov"
+TARGET_VIDEO_PATH = "video_out.mp4"
+
+rf = Roboflow(api_key="")
+#project = rf.workspace().project("football-players-detection-3zvbc")
+model = get_model(model_id="football-players-detection-3zvbc/9")
+#model = project.version(9).model
+#print("model is 1111", model)
+
+# Create BYTETracker instance
+byte_tracker = sv.ByteTrack(track_activation_threshold=0.25, lost_track_buffer=30, minimum_matching_threshold=0.8, frame_rate=1)
+
+# Create VideoInfo instance
+video_info = sv.VideoInfo.from_video_path(SOURCE_VIDEO_PATH)
+
+# Create frame generator
+generator = sv.get_video_frames_generator(SOURCE_VIDEO_PATH)
+
+# Create instance of BoxAnnotator
+box_annotator = sv.BoxAnnotator(thickness=4)
+
+# Create instance of TraceAnnotator
+trace_annotator = sv.TraceAnnotator(thickness=4, trace_length=50)
+
+# Define callback function to be used in video processing
+def callback(frame: np.ndarray, index: int) -> np.ndarray:
+    # Model prediction on single frame and conversion to supervision Detections
+    print('callback')
+    print("frame is ", frame)
+    print("model is ", model)
+    results = model.infer(frame)
+    detections = sv.Detections.from_inference(results[0].dict(by_alias=True, exclude_none=True))
+
+    # Show detections in real time
+    print(detections)
+
+    # Tracking detections
+    detections = byte_tracker.update_with_detections(detections)
+    print("Updated Detections:", detections)
+
+    # Prepare labels for box annotations
+    labels = [
+        f"{detections.data['class_name'][i]} {detections.confidence[i]:0.2f}"
+        for i in range(len(detections.confidence))
+    ]
+
+    # Annotate frame with traces and boxes
+    annotated_frame = trace_annotator.annotate(
+        scene=frame.copy(),
+        detections=detections
+    )
+    annotated_frame = box_annotator.annotate(
+        scene=annotated_frame,
+        detections=detections,
+    )
+
+    # Return annotated frame
+    return annotated_frame
+
+# Process the whole video
+sv.process_video(
+    source_path=SOURCE_VIDEO_PATH,
+    target_path=TARGET_VIDEO_PATH,
+    callback=callback
+)