File size: 8,310 Bytes
7d1f745
329c034
 
 
 
 
82ed089
93fb51e
 
329c034
cdec70d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
329c034
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cdec70d
329c034
 
 
 
 
 
 
 
 
 
 
 
 
cdec70d
329c034
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
import gradio as gr
import torch
import cv2
import numpy as np
import time
from ultralytics import YOLO
import spaces

@spaces.GPU

class CrowdDetection:
    def __init__(self, model_path="yolov8n.pt", crowd_threshold=10):
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        print(f"🔍 Using device: {self.device}")
        self.model = YOLO(model_path).to(self.device)
        self.crowd_threshold = crowd_threshold

    def detect_crowd(self, video_path):
        cap = cv2.VideoCapture(video_path)
        if not cap.isOpened():
            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))
        print(f"🎥 Video details - FPS: {fps}, Width: {width}, Height: {height}")

        output_path = "output_crowd.mp4"
        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
        out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))

        frame_count = 0

        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break
            
            frame_count += 1
            results = self.model(frame)
            person_count = 0

            for result in results:
                boxes = result.boxes.xyxy.cpu().numpy()
                classes = result.boxes.cls.cpu().numpy()

                for box, cls in zip(boxes, classes):
                    if int(cls) == 0:  # Class ID 0 = "person"
                        person_count += 1
                        x1, y1, x2, y2 = map(int, box)
                        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
                        cv2.putText(frame, "Person", (x1, y1 - 10),
                                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)

            alert_text = "Crowd Alert!" if person_count > self.crowd_threshold else f"People: {person_count}"
            cv2.putText(frame, alert_text, (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1,
                        (0, 0, 255) if person_count > self.crowd_threshold else (0, 255, 0), 2)
            out.write(frame)

        cap.release()
        out.release()

        if frame_count == 0:
            raise ValueError("❌ No frames were processed!")

        if not os.path.exists(output_path):
            raise FileNotFoundError(f"❌ Output video not found: {output_path}")

        print(f"✅ Processed video saved at: {output_path}")
        return output_path

class PeopleTracking:
    def __init__(self, yolo_model_path="yolov8n.pt"):
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self.model = YOLO(yolo_model_path).to(self.device)
    
    def track_people(self, video_path):
        cap = cv2.VideoCapture(video_path)
        output_path = "output_tracking.mp4"
        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
        out = cv2.VideoWriter(output_path, fourcc, int(cap.get(cv2.CAP_PROP_FPS)),
                              (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))))
        
        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break
            
            results = self.model.track(frame, persist=True)
            for result in results:
                boxes = result.boxes.xyxy.cpu().numpy()
                classes = result.boxes.cls.cpu().numpy()
                ids = result.boxes.id.cpu().numpy() if hasattr(result.boxes, "id") else np.arange(len(boxes))
                
                for box, cls, obj_id in zip(boxes, classes, ids):
                    if int(cls) == 0:
                        x1, y1, x2, y2 = map(int, box)
                        cv2.rectangle(frame, (x1, y1), (x2, y2), (255, 0, 0), 2)
                        cv2.putText(frame, f"ID {int(obj_id)}", (x1, y1 - 10),
                                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)
            
            out.write(frame)
        
        cap.release()
        out.release()
        return output_path

# Define Fall Detection
class FallDetection:
    def __init__(self, yolo_model_path="yolov8l.pt"):
        self.model = YOLO(yolo_model_path)
    
    def detect_fall(self, video_path):
        cap = cv2.VideoCapture(video_path)
        output_path = "output_fall.mp4"
        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
        out = cv2.VideoWriter(output_path, fourcc, int(cap.get(cv2.CAP_PROP_FPS)),
                              (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))))
        
        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break
            
            results = self.model(frame)
            for result in results:
                boxes = result.boxes.xyxy.cpu().numpy()
                classes = result.boxes.cls.cpu().numpy()
                
                for box, cls in zip(boxes, classes):
                    if int(cls) == 0:
                        x1, y1, x2, y2 = map(int, box)
                        width = x2 - x1
                        height = y2 - y1
                        aspect_ratio = width / height
                        
                        if aspect_ratio > 0.55:
                            color = (0, 0, 255)
                            label = "FALL DETECTED"
                        else:
                            color = (0, 255, 0)
                            label = "Standing"
                        
                        cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
                        cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
            
            out.write(frame)
        
        cap.release()
        out.release()
        return output_path

# Define Fight Detection
class FightDetection:
    def __init__(self, yolo_model_path="yolov8n-pose.pt"):
        self.model = YOLO(yolo_model_path).to(torch.device("cuda" if torch.cuda.is_available() else "cpu"))
    
    def detect_fight(self, video_path):
        cap = cv2.VideoCapture(video_path)
        output_path = "output_fight.mp4"
        fourcc = cv2.VideoWriter_fourcc(*"mp4v")
        out = cv2.VideoWriter(output_path, fourcc, int(cap.get(cv2.CAP_PROP_FPS)),
                              (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))))
        
        while cap.isOpened():
            ret, frame = cap.read()
            if not ret:
                break
            
            results = self.model.track(frame, persist=True)
            for result in results:
                keypoints = result.keypoints.xy.cpu().numpy() if result.keypoints else []
                classes = result.boxes.cls.cpu().numpy() if result.boxes else []
                
                for kp, cls in zip(keypoints, classes):
                    if int(cls) == 0:
                        x1, y1 = int(kp[0][0]), int(kp[0][1])
                        x2, y2 = int(kp[-1][0]), int(kp[-1][1])
                        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
                        cv2.putText(frame, "FIGHT DETECTED", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
            
            out.write(frame)
        
        cap.release()
        out.release()
        return output_path

# Function to process video based on selected feature
def process_video(feature, video):
    detectors = {
        "Crowd Detection": CrowdDetection,
        "People Tracking": PeopleTracking,
        "Fall Detection": FallDetection,
        "Fight Detection": FightDetection
    }
    
    detector = detectors[feature]()
    method_name = f"detect_{feature.lower().replace(' ', '_')}"
    return getattr(detector, method_name)(video)

# Gradio Interface
interface = gr.Interface(
    fn=process_video,
    inputs=[
        gr.Dropdown(choices=["Crowd Detection", "People Tracking", "Fall Detection", "Fight Detection"], label="Select Feature"),
        gr.Video(label="Upload Video")
    ],
    outputs=gr.Video(label="Processed Video"),
    title="YOLOv8 Multitask Video Processing"
)

if __name__ == "__main__":
    interface.launch()