Spaces:
Sleeping
Sleeping
File size: 18,869 Bytes
7d1f745 329c034 82ed089 aca5f43 35960dd cdec70d 7a2e724 3d44b76 7ef0fcc 4e43aa1 397b8df 35960dd 4e43aa1 35960dd 4e43aa1 35960dd 7ef0fcc 35960dd 3d44b76 7ef0fcc 329c034 4e43aa1 aca5f43 4e43aa1 3d44b76 35960dd 4e43aa1 35960dd 4e43aa1 35960dd aca5f43 35960dd 3d44b76 329c034 4e43aa1 aca5f43 4e43aa1 397b8df 35960dd 4e43aa1 35960dd 4e43aa1 35960dd aca5f43 35960dd 3d44b76 329c034 4e43aa1 aca5f43 4e43aa1 397b8df 35960dd 4e43aa1 35960dd 4e43aa1 35960dd aca5f43 35960dd 3d44b76 35960dd 40068e9 f97e575 40068e9 d696ec6 40068e9 f97e575 8c7baf3 d696ec6 f97e575 8c7baf3 d696ec6 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 f97e575 8c7baf3 329c034 cdec70d 329c034 40068e9 8c7baf3 329c034 8c7baf3 aca5f43 a202a4e 8c7baf3 35960dd aca5f43 35960dd 329c034 8c7baf3 329c034 8c7baf3 329c034 35960dd aca5f43 329c034 8c7baf3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 |
import gradio as gr
import torch
import cv2
import numpy as np
import time
from ultralytics import YOLO
import spaces
import os
class CrowdDetection:
def __init__(self, model_path="yolov8n.pt"):
self.model_path = model_path
@spaces.GPU
def crowd_detect(self, video_path):
try:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if not os.path.exists(self.model_path):
model = YOLO("yolov8n.pt")
model.save(self.model_path)
else:
model = YOLO(self.model_path)
model.to(device)
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))
output_path = "output_crowd.mp4"
fourcc = cv2.VideoWriter_fourcc(*"mp4v")
out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
if not out.isOpened():
cap.release()
raise ValueError(f"❌ Failed to initialize video writer")
CROWD_THRESHOLD = 10
frame_count = 0
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
frame_count += 1
results = model(frame)
person_count = sum(1 for result in results for cls in result.boxes.cls.cpu().numpy() if int(cls) == 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:
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 > 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 > CROWD_THRESHOLD else (0, 255, 0), 2)
out.write(frame)
cap.release()
out.release()
if frame_count == 0 or not os.path.exists(output_path):
raise ValueError("❌ Processing failed: No frames processed or output not created")
return output_path
except Exception as e:
raise ValueError(f"Error in crowd_detection: {str(e)}")
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:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if not os.path.exists(self.model_path):
model = YOLO("yolov8n.pt")
model.save(self.model_path)
else:
model = YOLO(self.model_path)
model.to(device)
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))
output_path = "output_tracking.mp4"
out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
if not out.isOpened():
cap.release()
raise ValueError(f"❌ Failed to initialize video writer")
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
results = 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 result.boxes.id is not None 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()
if not os.path.exists(output_path):
raise ValueError("❌ Processing failed")
return output_path
except Exception as e:
raise ValueError(f"Error in people_tracking: {str(e)}")
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:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if not os.path.exists(self.model_path):
model = YOLO("yolov8l.pt")
model.save(self.model_path)
else:
model = YOLO(self.model_path)
model.to(device)
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))
output_path = "output_fall.mp4"
out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
if not out.isOpened():
cap.release()
raise ValueError(f"❌ Failed to initialize video writer")
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
results = 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 height > 0 else float('inf')
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()
if not os.path.exists(output_path):
raise ValueError("❌ Processing failed")
return output_path
except Exception as e:
raise ValueError(f"Error in fall_detection: {str(e)}")
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:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if not os.path.exists(self.model_path):
model = YOLO("yolov8n-pose.pt")
model.save(self.model_path)
else:
model = YOLO(self.model_path)
model.to(device)
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))
output_path = "output_fight.mp4"
out = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (width, height))
if not out.isOpened():
cap.release()
raise ValueError(f"❌ Failed to initialize video writer")
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
results = model.track(frame, persist=True)
fight_detected = False
person_count = 0
for result in results:
keypoints = result.keypoints.xy.cpu().numpy() if result.keypoints else []
boxes = result.boxes.xyxy.cpu().numpy() if result.boxes else []
classes = result.boxes.cls.cpu().numpy() if result.boxes else []
for box, kp, cls in zip(boxes, keypoints, classes):
if int(cls) == 0:
person_count += 1
x1, y1, x2, y2 = map(int, box)
if len(kp) > 7 and (kp[5][1] < y1 + (y2 - y1) * 0.3 or kp[7][1] < y1 + (y2 - y1) * 0.3):
fight_detected = True
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255) if fight_detected else (0, 255, 0), 2)
label = "FIGHT DETECTED" if fight_detected else "Person"
cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(0, 0, 255) if fight_detected else (0, 255, 0), 2)
if fight_detected and person_count > 1:
cv2.putText(frame, "FIGHT ALERT!", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)
out.write(frame)
cap.release()
out.release()
if not os.path.exists(output_path):
raise ValueError("❌ Processing failed")
return output_path
except Exception as e:
raise ValueError(f"Error in fight_detection: {str(e)}")
class IntrusionDetection:
def __init__(self, model_path="yolov8n.pt", max_intrusion_time=300, iou_threshold=0.5, conf_threshold=0.5):
self.model_path = model_path
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")
if not os.path.exists(self.model_path):
model = YOLO("yolov8n.pt")
model.save(self.model_path)
else:
model = YOLO(self.model_path)
model.to(device)
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))
output_path = "output_intrusion.mp4"
fourcc = cv2.VideoWriter_fourcc(*"mp4v")
out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
if not out.isOpened():
cap.release()
raise ValueError(f"❌ Failed to initialize video writer")
frame_count = 0
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
frame_count += 1
results = model(frame)
for result in results:
boxes = result.boxes.xyxy.cpu().numpy()
classes = result.boxes.cls.cpu().numpy()
confidences = result.boxes.conf.cpu().numpy()
for box, cls, conf in zip(boxes, classes, confidences):
if int(cls) == 0 and conf > self.conf_threshold: # Person class with confidence filter
x1, y1, x2, y2 = map(int, box)
label = "Intruder"
color = (0, 0, 255)
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()
if frame_count == 0 or not os.path.exists(output_path):
raise ValueError("❌ Processing failed: No frames processed or output not created")
return output_path
except Exception as e:
raise ValueError(f"Error in detect_intrusion: {str(e)}")
import cv2
import numpy as np
from ultralytics import YOLO
from shapely.geometry import Point, Polygon
import time
class LoiteringDetector:
def __init__(self, model_path='loitering_model.pt'):
self.model = YOLO(model_path)
@spaces.GPU
def loitering_detect(self, video_path, area):
# Create polygon zone
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 = Polygon(zone_points)
# Open video
cap = cv2.VideoCapture(video_path)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH) * 0.5)
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT) * 0.5)
fps = int(cap.get(cv2.CAP_PROP_FPS))
# Create video writer
output_path = os.path.join(tempfile.gettempdir(), "loitering_video.mp4")
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
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
# List to store time information for display
time_display = []
if results[0].boxes.id is not None:
boxes = results[0].boxes.xyxy.cpu().numpy().astype(int)
ids = results[0].boxes.id.cpu().numpy().astype(int)
for box, id in zip(boxes, ids):
x1, y1, x2, y2 = box
center = Point((x1 + x2) / 2, (y1 + y2) / 2)
if id not in person_info:
person_info[id] = {'in_zone': False, 'start_time': None, 'duration': 0}
if zone.contains(center):
if not person_info[id]['in_zone']:
person_info[id]['in_zone'] = True
person_info[id]['start_time'] = time.time()
person_info[id]['duration'] = time.time() - person_info[id]['start_time']
if person_info[id]['duration'] > time_threshold:
color = (0, 0, 255) # Red for loitering
else:
color = (0, 255, 0) # Green for in zone
time_display.append(f"ID: {id}, Time: {person_info[id]['duration']:.2f}s")
else:
person_info[id]['in_zone'] = False
person_info[id]['start_time'] = None
person_info[id]['duration'] = 0
color = (255, 0, 0) # Blue for outside zone
cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
cv2.putText(frame, f"ID: {id}", (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
# Draw polygon zone
cv2.polylines(frame, [np.array(zone_points, np.int32)], True, (255, 255, 0), 2)
# Display time information in top left
for i, text in enumerate(time_display):
cv2.putText(frame, text, (10, 30 + i * 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2)
out.write(frame)
cap.release()
out.release()
return output_path
def process_video(feature, video, area=None):
detectors = {
"Crowd Detection": CrowdDetection,
"People Tracking": PeopleTracking,
"Fall Detection": FallDetection,
"Fight Detection": FightDetection,
"Intrusion Detection": IntrusionDetection,
"Loitering Detection": LoiteringDetection
}
try:
detector = detectors[feature]()
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
else:
output_path = getattr(detector, method_name)(video)
return f"{feature} completed successfully", output_path
except Exception as e:
return f"Error: {str(e)}", None
# Gradio Interface with additional input for Loitering Detection
interface = gr.Interface(
fn=process_video,
inputs=[
gr.Dropdown(choices=[
"Crowd Detection", "People Tracking", "Fall Detection",
"Fight Detection", "Intrusion Detection", "Loitering Detection"
], label="Select Feature"),
gr.Video(label="Upload Video"),
gr.Textbox(label="Loitering Area (131 or 145)") # Can be replaced with a drawing tool
],
outputs=[
gr.Textbox(label="Status"),
gr.Video(label="Processed Video")
],
title="YOLOv8 Multitask Video Processing",
description="Select a feature to process your video: Crowd Detection, People Tracking, Fall Detection, or Fight Detection."
)
if __name__ == "__main__":
interface.launch(debug=True)
|