Update app.py

app.py

@@ -4,8 +4,8 @@ import cv2
 import numpy as np
 import time
 from ultralytics import YOLO
-import spaces
 import os
+import spaces
 
 class CrowdDetection:
     def __init__(self, model_path="yolov8n.pt"):
@@ -27,8 +27,8 @@ class CrowdDetection:
                 raise ValueError(f"❌ Failed to open video: {video_path}")
 
             fps = int(cap.get(cv2.CAP_PROP_FPS))
-            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
 
             output_path = "output_crowd.mp4"
             fourcc = cv2.VideoWriter_fourcc(*"mp4v")
@@ -44,6 +44,7 @@ class CrowdDetection:
                 ret, frame = cap.read()
                 if not ret:
                     break
+                frame = cv2.resize(frame, (width, height))
                 frame_count += 1
 
                 results = model(frame)
@@ -74,7 +75,7 @@ class CrowdDetection:
 class PeopleTracking:
     def __init__(self, yolo_model_path="yolov8n.pt"):
         self.model_path = yolo_model_path
-
+    
     @spaces.GPU
     def people_tracking(self, video_path):
         try:
@@ -91,8 +92,8 @@ class PeopleTracking:
                 raise ValueError(f"❌ Failed to open video: {video_path}")
 
             fps = int(cap.get(cv2.CAP_PROP_FPS))
-            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
             output_path = "output_tracking.mp4"
             out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
             if not out.isOpened():
@@ -104,6 +105,7 @@ class PeopleTracking:
                 if not ret:
                     break
 
+                frame = cv2.resize(frame, (width, height))
                 results = model.track(frame, persist=True)
                 for result in results:
                     boxes = result.boxes.xyxy.cpu().numpy()
@@ -129,7 +131,7 @@ class PeopleTracking:
 class FallDetection:
     def __init__(self, yolo_model_path="yolov8l.pt"):
         self.model_path = yolo_model_path
-
+    
     @spaces.GPU
     def fall_detect(self, video_path):
         try:
@@ -146,8 +148,8 @@ class FallDetection:
                 raise ValueError(f"❌ Failed to open video: {video_path}")
 
             fps = int(cap.get(cv2.CAP_PROP_FPS))
-            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
             output_path = "output_fall.mp4"
             out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
             if not out.isOpened():
@@ -158,7 +160,7 @@ class FallDetection:
                 ret, frame = cap.read()
                 if not ret:
                     break
-
+                frame = cv2.resize(frame, (width, height))
                 results = model(frame)
                 for result in results:
                     boxes = result.boxes.xyxy.cpu().numpy()
@@ -194,7 +196,7 @@ class FallDetection:
 class FightDetection:
     def __init__(self, yolo_model_path="yolov8n-pose.pt"):
         self.model_path = yolo_model_path
-
+    
     @spaces.GPU
     def fight_detect(self, video_path):
         try:
@@ -211,8 +213,8 @@ class FightDetection:
                 raise ValueError(f"❌ Failed to open video: {video_path}")
 
             fps = int(cap.get(cv2.CAP_PROP_FPS))
-            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
             output_path = "output_fight.mp4"
             out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
             if not out.isOpened():
@@ -223,7 +225,8 @@ class FightDetection:
                 ret, frame = cap.read()
                 if not ret:
                     break
-
+                
+                frame = cv2.resize(frame, (width, height))
                 results = model.track(frame, persist=True)
                 fight_detected = False
                 person_count = 0
@@ -262,8 +265,8 @@ class IntrusionDetection:
         self.max_intrusion_time = max_intrusion_time
         self.iou_threshold = iou_threshold
         self.conf_threshold = conf_threshold
+    
     @spaces.GPU
-
     def intrusion_detect(self, video_path):
         try:
             device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -279,8 +282,8 @@ class IntrusionDetection:
                 raise ValueError(f"❌ Failed to open video: {video_path}")
 
             fps = int(cap.get(cv2.CAP_PROP_FPS))
-            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
+            height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
 
             output_path = "output_intrusion.mp4"
             fourcc = cv2.VideoWriter_fourcc(*"mp4v")
@@ -296,6 +299,7 @@ class IntrusionDetection:
                 if not ret:
                     break
                 frame_count += 1
+                frame = cv2.resize(frame, (width, height))
 
                 results = model(frame)
                 for result in results:
@@ -326,21 +330,75 @@ import numpy as np
 from ultralytics import YOLO
 from shapely.geometry import Point, Polygon
 import time
+import tempfile
+import moviepy.editor as mpy
+
+class FireAndSmokeDetection:
+    def __init__(self, model_path='fire_model.pt'):
+        self.model_path = model_path
+    
+    @spaces.GPU
+    def fire_and_smoke_detect(self, video_path):
+        model = YOLO(self.model_path, task="detect")
+        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        model.to(device)
 
-class LoiteringDetector:
+        cap = cv2.VideoCapture(video_path)
+
+        fps = cap.get(cv2.CAP_PROP_FPS)
+        if not fps or fps == 0:
+            fps = 30
+        fps = int(fps)
+
+        frames = []
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+            frames.append(frame)
+        cap.release()
+
+        if not frames:
+            return None
+
+        processed_frames = []
+        total_frames = len(frames)
+
+        # Process frames one by one (with progress feedback)
+        for i, frame in enumerate(frames):
+            result = model(frame)
+            processed_frame = result[0].plot()
+            processed_frames.append(processed_frame)
+
+        # Convert frames from BGR (OpenCV) to RGB (MoviePy expects RGB)
+        processed_frames_rgb = [cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) for frame in processed_frames]
+
+        # Use MoviePy to assemble the video file using H.264 encoding
+        output_video_path = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4").name
+        clip = mpy.ImageSequenceClip(processed_frames_rgb, fps=fps)
+        clip.write_videofile(output_video_path, codec='libx264', audio=False, verbose=False, logger=None)
+
+        return output_video_path
+
+
+class LoiteringDetection:
     def __init__(self, model_path='loitering_model.pt'):
-        self.model = YOLO(model_path)
+        self.model_path = model_path
     
     @spaces.GPU
     def loitering_detect(self, video_path, area):
         # Create polygon zone
+        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+        model = YOLO(self.model_path)
+        model.to(device)
+        person_info = {}
         time_threshold = 7
         detection_threshold = 0.6
         zone_points = None
         if area == '131':
             zone_points = [(842//1.5, 514//1.7), (686//1.5, 290//1.7), (775//1.5, 279//1.7), (961//1.5, 488//1.7)]
         elif area == '145':
-            zone_points = [(153, 850), (139, 535), (239, 497), (291, 857)]
+            zone_points = [(153//1.8, 850//1.7), (139//1.8, 535//1.7), (239//1.8, 497//1.7), (291//1.8, 857//1.7)]
         zone = Polygon(zone_points)
 
         # Open video
@@ -361,7 +419,7 @@ class LoiteringDetector:
 
             frame = cv2.resize(frame, (width, height))
             # Perform object detection and tracking
-            results = self.model.track(frame, persist=True, classes=[0], conf=detection_threshold)  # 0 is the class ID for person
+            results = model.track(frame, persist=True, classes=[0], conf=detection_threshold)  # 0 is the class ID for person
 
             # List to store time information for display
             time_display = []
@@ -421,7 +479,8 @@ def process_video(feature, video, area=None):
         "Fall Detection": FallDetection,
         "Fight Detection": FightDetection,
         "Intrusion Detection": IntrusionDetection,
-        "Loitering Detection": LoiteringDetection
+        "Loitering Detection": LoiteringDetection,
+        "Fire And Smoke Detection": FireAndSmokeDetection
     }
     
     try:
@@ -429,7 +488,7 @@ def process_video(feature, video, area=None):
         method_name = feature.lower().replace(" ", "_").replace("detection", "detect")  # Ensures correct method name
         
         if feature == "Loitering Detection":
-            output_path = detector.detect_loitering(video, area)  # Pass area if required
+            output_path = detector.loitering_detect(video, area)  # Pass area if required
         else:
             output_path = getattr(detector, method_name)(video)
         
@@ -443,10 +502,11 @@ interface = gr.Interface(
     inputs=[
         gr.Dropdown(choices=[
             "Crowd Detection", "People Tracking", "Fall Detection", 
-            "Fight Detection", "Intrusion Detection", "Loitering Detection"
+            "Fight Detection", "Intrusion Detection", "Loitering Detection",
+            "Fire And Smoke Detection"
         ], label="Select Feature"),
         gr.Video(label="Upload Video"),
-        gr.Textbox(label="Loitering Area (131 or 145)")  # Can be replaced with a drawing tool
+        gr.Textbox(label="Loitering Area (131 or 145)")
     ],
     outputs=[
         gr.Textbox(label="Status"),
@@ -457,4 +517,4 @@ interface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    interface.launch(debug=True)
+    interface.launch(debug=True)