Update app.py

app.py

@@ -1,6 +1,4 @@
-##############
-
-#Maximize CPU usage
+# Maximize CPU usage
 import multiprocessing
 import cv2
 
@@ -178,7 +176,7 @@ def draw_angled_line(image, line_params, color=(0, 255, 0), thickness=2):
     _, _, start_point, end_point = line_params
     cv2.line(image, start_point, end_point, color, thickness)
 
-def process_video(confidence_threshold=0.5, selected_classes=None, stream_url=None):
+def process_video(confidence_threshold=0.5, selected_classes=None, stream_url=None, resolution_scale=1.0):
     """
     Processes the IP camera stream to count objects of the selected classes crossing the line.
     """
@@ -213,8 +211,14 @@ def process_video(confidence_threshold=0.5, selected_classes=None, stream_url=No
             errors.append("Error: Could not read frame from the stream.")
             break
 
+        # Resize the frame for processing
+        height, width = frame.shape[:2]
+        new_width = int(width * resolution_scale)
+        new_height = int(height * resolution_scale)
+        resized_frame = cv2.resize(frame, (new_width, new_height))
+
         # Perform object tracking with confidence threshold
-        results = model.track(frame, persist=True, conf=confidence_threshold)
+        results = model.track(resized_frame, persist=True, conf=confidence_threshold)
 
         if results[0].boxes.id is not None:
             track_ids = results[0].boxes.id.int().cpu().tolist()
@@ -224,6 +228,8 @@ def process_video(confidence_threshold=0.5, selected_classes=None, stream_url=No
 
             for box, cls, t_id, conf in zip(boxes, clss, track_ids, confs):
                 if conf >= confidence_threshold and model.names[cls] in selected_classes:
+                    # Scale the bounding box back to the original resolution
+                    box = box * (width / new_width)
                     # Check if the object crosses the line
                     if is_object_crossing_line(box, line_params) and t_id not in crossed_objects:
                         crossed_objects[t_id] = True
@@ -232,8 +238,8 @@ def process_video(confidence_threshold=0.5, selected_classes=None, stream_url=No
                         if len(crossed_objects) > max_tracked_objects:
                             crossed_objects.clear()
 
-        # Visualize the results with bounding boxes, masks, and IDs
-        annotated_frame = results[0].plot()
+        # Visualize the results with bounding boxes, masks, and IDs on the original frame
+        annotated_frame = results[0].plot(img=frame)
 
         # Draw the angled line on the frame
         draw_angled_line(annotated_frame, line_params, color=(0, 255, 0), thickness=2)
@@ -264,11 +270,7 @@ with gr.Blocks() as demo:
     gr.Markdown("<h1>Real-time monitoring, object tracking, and line-crossing detection for CCTV camera streams.</h1></center>")
     gr.Markdown("## https://github.com/SanshruthR/CCTV_SENTRY_YOLO11")
     
-   
-   
     # Step 1: Enter the IP Camera Stream URL
-    # gr.Markdown("### Step 0: Enter the IP Camera Stream URL")
-    # stream_url = gr.Textbox(label="Enter IP Camera Stream URL", value="https://s103.ipcamlive.com/streams/67n4ojknye7lkxpmf/stream.m3u8", visible=False)
     stream_url = gr.Textbox(label="Enter IP Camera Stream URL", value="https://s104.ipcamlive.com/streams/68idokwtondsqpmkr/stream.m3u8", visible=False)
 
     # Step 1: Extract the first frame from the stream
@@ -280,15 +282,9 @@ with gr.Blocks() as demo:
         # Image component for displaying the first frame
         image = gr.Image(value=first_frame, label="First Frame of Stream", type="pil")
 
-      
         line_info = gr.Textbox(label="Line Coordinates", value="Line Coordinates:\nStart: None, End: None")
         image.select(update_line, inputs=image, outputs=[image, line_info])
 
-        # Reset the line (optional)
-        # gr.Markdown("### Step 4: Reset the Line (Optional)")
-        # reset_button = gr.Button("Reset Line")
-        # reset_button.click(reset_line, inputs=None, outputs=[image, line_info])
-
         # Step 2: Select classes to detect
         gr.Markdown("### Step 2: Select Classes to Detect")
         model = YOLO(model="yolo11n.pt")  # Load the model to get class names
@@ -299,7 +295,11 @@ with gr.Blocks() as demo:
         gr.Markdown("### Step 3: Adjust Confidence Threshold (Optional)")
         confidence_threshold = gr.Slider(minimum=0.0, maximum=1.0, value=0.2, label="Confidence Threshold")
 
-        #process the stream
+        # Step 4: Adjust resolution scale
+        gr.Markdown("### Step 4: Adjust Resolution Scale (Optional)")
+        resolution_scale = gr.Slider(minimum=0.1, maximum=1.0, value=1.0, label="Resolution Scale")
+
+        # Process the stream
         process_button = gr.Button("Process Stream")
 
         # Output image for real-time frame rendering
@@ -309,7 +309,7 @@ with gr.Blocks() as demo:
         error_box = gr.Textbox(label="Errors/Warnings", interactive=False)
 
         # Event listener for processing the video
-        process_button.click(process_video, inputs=[confidence_threshold, selected_classes, stream_url], outputs=[output_image, error_box])
+        process_button.click(process_video, inputs=[confidence_threshold, selected_classes, stream_url, resolution_scale], outputs=[output_image, error_box])
 
 # Launch the interface
-demo.launch(debug=True)
+demo.launch(debug=True)