Update utilities.py
Browse files- utilities.py +720 -223
utilities.py
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
#!/usr/bin/env python3
|
| 2 |
"""
|
| 3 |
-
utilities.py -
|
| 4 |
-
|
| 5 |
"""
|
| 6 |
|
| 7 |
import os
|
|
@@ -11,271 +11,691 @@
|
|
| 11 |
from PIL import Image, ImageDraw
|
| 12 |
import logging
|
| 13 |
import time
|
|
|
|
|
|
|
| 14 |
|
| 15 |
# Setup logging
|
| 16 |
logging.basicConfig(level=logging.INFO)
|
| 17 |
logger = logging.getLogger(__name__)
|
| 18 |
|
| 19 |
-
# Professional background templates
|
| 20 |
PROFESSIONAL_BACKGROUNDS = {
|
| 21 |
"office_modern": {
|
| 22 |
"name": "Modern Office",
|
| 23 |
"type": "gradient",
|
| 24 |
"colors": ["#f8f9fa", "#e9ecef", "#dee2e6"],
|
| 25 |
"direction": "diagonal",
|
| 26 |
-
"description": "Clean, contemporary office environment"
|
|
|
|
|
|
|
| 27 |
},
|
| 28 |
"studio_blue": {
|
| 29 |
"name": "Professional Blue",
|
| 30 |
"type": "gradient",
|
| 31 |
"colors": ["#1e3c72", "#2a5298", "#3498db"],
|
| 32 |
"direction": "radial",
|
| 33 |
-
"description": "Broadcast-quality blue studio"
|
|
|
|
|
|
|
| 34 |
},
|
| 35 |
"studio_green": {
|
| 36 |
"name": "Broadcast Green",
|
| 37 |
"type": "color",
|
| 38 |
"colors": ["#00b894"],
|
| 39 |
"chroma_key": True,
|
| 40 |
-
"description": "Professional green screen replacement"
|
|
|
|
|
|
|
| 41 |
},
|
| 42 |
"minimalist": {
|
| 43 |
"name": "Minimalist White",
|
| 44 |
"type": "gradient",
|
| 45 |
"colors": ["#ffffff", "#f1f2f6", "#ddd"],
|
| 46 |
"direction": "soft_radial",
|
| 47 |
-
"description": "Clean, minimal background"
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
"warm_gradient": {
|
| 50 |
"name": "Warm Sunset",
|
| 51 |
"type": "gradient",
|
| 52 |
"colors": ["#ff7675", "#fd79a8", "#fdcb6e"],
|
| 53 |
"direction": "diagonal",
|
| 54 |
-
"description": "Warm, inviting atmosphere"
|
|
|
|
|
|
|
| 55 |
},
|
| 56 |
"tech_dark": {
|
| 57 |
"name": "Tech Dark",
|
| 58 |
"type": "gradient",
|
| 59 |
"colors": ["#0c0c0c", "#2d3748", "#4a5568"],
|
| 60 |
"direction": "vertical",
|
| 61 |
-
"description": "Modern tech/gaming setup"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
}
|
| 63 |
}
|
| 64 |
|
| 65 |
-
|
| 66 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
try:
|
| 68 |
-
predictor
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
h, w = image.shape[:2]
|
| 70 |
|
| 71 |
-
#
|
| 72 |
points = np.array([
|
| 73 |
-
[w//2, h//4],
|
| 74 |
-
[w//2, h//2],
|
| 75 |
-
[w//2, 3*h//4],
|
| 76 |
-
[w//
|
| 77 |
-
[
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
else:
|
| 99 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
|
| 101 |
-
#
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
|
| 106 |
-
#
|
| 107 |
-
|
|
|
|
|
|
|
| 108 |
|
| 109 |
-
|
|
|
|
| 110 |
|
| 111 |
-
return
|
| 112 |
|
| 113 |
except Exception as e:
|
| 114 |
-
logger.error(f"
|
| 115 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
h, w = image.shape[:2]
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
|
| 124 |
-
def refine_mask_hq(image, mask, matanyone_processor
|
| 125 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
try:
|
| 127 |
-
# Ensure mask is
|
| 128 |
-
|
| 129 |
-
mask = (mask * 255).astype(np.uint8)
|
| 130 |
|
| 131 |
# Try MatAnyone if available
|
| 132 |
if matanyone_processor is not None:
|
| 133 |
try:
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
if refined_mask.max() <= 1.0:
|
| 140 |
-
refined_mask = (refined_mask * 255).astype(np.uint8)
|
| 141 |
return refined_mask
|
| 142 |
-
|
| 143 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
|
| 145 |
-
#
|
| 146 |
-
|
| 147 |
-
|
|
|
|
| 148 |
|
| 149 |
except Exception as e:
|
| 150 |
-
logger.
|
| 151 |
-
return
|
| 152 |
|
| 153 |
-
def
|
| 154 |
-
"""
|
|
|
|
|
|
|
| 155 |
try:
|
| 156 |
if len(mask.shape) == 3:
|
| 157 |
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
|
| 158 |
|
| 159 |
-
# Ensure
|
| 160 |
if mask.max() <= 1.0:
|
| 161 |
mask = (mask * 255).astype(np.uint8)
|
| 162 |
|
| 163 |
-
#
|
|
|
|
|
|
|
| 164 |
refined_mask = cv2.bilateralFilter(mask, 9, 75, 75)
|
| 165 |
|
| 166 |
-
#
|
| 167 |
-
|
| 168 |
-
refined_mask = cv2.morphologyEx(refined_mask, cv2.MORPH_CLOSE, kernel)
|
| 169 |
-
refined_mask = cv2.morphologyEx(refined_mask, cv2.MORPH_OPEN, kernel)
|
| 170 |
|
| 171 |
-
#
|
| 172 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 173 |
|
| 174 |
-
#
|
| 175 |
-
refined_mask = cv2.GaussianBlur(refined_mask, (3, 3),
|
|
|
|
|
|
|
|
|
|
| 176 |
|
| 177 |
return refined_mask
|
| 178 |
|
| 179 |
except Exception as e:
|
| 180 |
-
logger.warning(f"Enhanced
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 181 |
return mask
|
| 182 |
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 188 |
try:
|
| 189 |
# Resize background to match frame
|
| 190 |
-
background = cv2.resize(background, (frame.shape[1], frame.shape[0]),
|
|
|
|
| 191 |
|
| 192 |
-
#
|
| 193 |
if len(mask.shape) == 3:
|
| 194 |
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
|
| 195 |
|
| 196 |
-
# CRITICAL FIX: Ensure mask is in 0-255 range
|
| 197 |
if mask.dtype != np.uint8:
|
| 198 |
mask = mask.astype(np.uint8)
|
| 199 |
|
| 200 |
if mask.max() <= 1.0:
|
| 201 |
-
logger.
|
| 202 |
mask = (mask * 255).astype(np.uint8)
|
| 203 |
|
| 204 |
-
#
|
| 205 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
|
| 207 |
-
|
| 208 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
_, mask_binary = cv2.threshold(mask, threshold, 255, cv2.THRESH_BINARY)
|
| 210 |
|
| 211 |
-
# Clean up mask
|
| 212 |
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
|
| 213 |
-
mask_binary = cv2.morphologyEx(mask_binary, cv2.MORPH_CLOSE, kernel)
|
| 214 |
-
mask_binary = cv2.morphologyEx(mask_binary, cv2.MORPH_OPEN, kernel)
|
| 215 |
|
| 216 |
-
# Create smooth
|
| 217 |
mask_smooth = cv2.GaussianBlur(mask_binary.astype(np.float32), (5, 5), 1.0)
|
| 218 |
-
mask_smooth = mask_smooth / 255.0
|
| 219 |
|
| 220 |
-
#
|
| 221 |
-
mask_smooth = np.power(mask_smooth, 0.8)
|
| 222 |
|
| 223 |
-
#
|
| 224 |
mask_smooth = np.where(mask_smooth > 0.5,
|
| 225 |
-
|
| 226 |
-
|
|
|
|
|
|
|
|
|
|
| 227 |
|
| 228 |
-
# Create 3-channel mask
|
| 229 |
-
|
| 230 |
|
| 231 |
-
# Perform compositing
|
| 232 |
-
frame_float =
|
| 233 |
background_float = background.astype(np.float32)
|
| 234 |
|
| 235 |
-
|
|
|
|
| 236 |
result = np.clip(result, 0, 255).astype(np.uint8)
|
| 237 |
|
| 238 |
-
# Log final statistics
|
| 239 |
-
logger.info(f"Final mask stats - min: {mask_smooth.min():.3f}, max: {mask_smooth.max():.3f}, mean: {mask_smooth.mean():.3f}")
|
| 240 |
-
|
| 241 |
return result
|
| 242 |
|
| 243 |
except Exception as e:
|
| 244 |
-
logger.error(f"
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
-
|
| 255 |
-
|
| 256 |
-
|
| 257 |
-
|
| 258 |
return frame
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 259 |
|
| 260 |
-
def
|
| 261 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 262 |
try:
|
| 263 |
if bg_config["type"] == "color":
|
| 264 |
-
|
| 265 |
-
color_rgb = tuple(int(color_hex[i:i+2], 16) for i in (0, 2, 4))
|
| 266 |
-
color_bgr = color_rgb[::-1]
|
| 267 |
-
background = np.full((height, width, 3), color_bgr, dtype=np.uint8)
|
| 268 |
elif bg_config["type"] == "gradient":
|
| 269 |
-
background =
|
| 270 |
else:
|
|
|
|
| 271 |
background = np.full((height, width, 3), (128, 128, 128), dtype=np.uint8)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
return background
|
|
|
|
| 273 |
except Exception as e:
|
| 274 |
logger.error(f"Background creation error: {e}")
|
| 275 |
return np.full((height, width, 3), (128, 128, 128), dtype=np.uint8)
|
| 276 |
|
| 277 |
-
def
|
| 278 |
-
"""Create
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 279 |
try:
|
| 280 |
colors = bg_config["colors"]
|
| 281 |
direction = bg_config.get("direction", "vertical")
|
|
@@ -290,106 +710,183 @@ def create_gradient_background(bg_config, width, height):
|
|
| 290 |
if not rgb_colors:
|
| 291 |
rgb_colors = [(128, 128, 128)]
|
| 292 |
|
| 293 |
-
#
|
| 294 |
-
pil_img = Image.new('RGB', (width, height))
|
| 295 |
-
draw = ImageDraw.Draw(pil_img)
|
| 296 |
-
|
| 297 |
-
def interpolate_color(colors, progress):
|
| 298 |
-
if len(colors) == 1:
|
| 299 |
-
return colors[0]
|
| 300 |
-
elif len(colors) == 2:
|
| 301 |
-
r = int(colors[0][0] + (colors[1][0] - colors[0][0]) * progress)
|
| 302 |
-
g = int(colors[0][1] + (colors[1][1] - colors[0][1]) * progress)
|
| 303 |
-
b = int(colors[0][2] + (colors[1][2] - colors[0][2]) * progress)
|
| 304 |
-
return (r, g, b)
|
| 305 |
-
else:
|
| 306 |
-
segment = progress * (len(colors) - 1)
|
| 307 |
-
idx = int(segment)
|
| 308 |
-
local_progress = segment - idx
|
| 309 |
-
if idx >= len(colors) - 1:
|
| 310 |
-
return colors[-1]
|
| 311 |
-
c1, c2 = colors[idx], colors[idx + 1]
|
| 312 |
-
r = int(c1[0] + (c2[0] - c1[0]) * local_progress)
|
| 313 |
-
g = int(c1[1] + (c2[1] - c1[1]) * local_progress)
|
| 314 |
-
b = int(c1[2] + (c2[2] - c1[2]) * local_progress)
|
| 315 |
-
return (r, g, b)
|
| 316 |
-
|
| 317 |
-
# Generate gradient based on direction
|
| 318 |
if direction == "vertical":
|
| 319 |
-
|
| 320 |
-
progress = y / height if height > 0 else 0
|
| 321 |
-
color = interpolate_color(rgb_colors, progress)
|
| 322 |
-
draw.line([(0, y), (width, y)], fill=color)
|
| 323 |
elif direction == "horizontal":
|
| 324 |
-
|
| 325 |
-
progress = x / width if width > 0 else 0
|
| 326 |
-
color = interpolate_color(rgb_colors, progress)
|
| 327 |
-
draw.line([(x, 0), (x, height)], fill=color)
|
| 328 |
elif direction == "diagonal":
|
| 329 |
-
|
| 330 |
-
for y in range(height):
|
| 331 |
-
for x in range(width):
|
| 332 |
-
progress = (x + y) / max_distance if max_distance > 0 else 0
|
| 333 |
-
progress = min(1.0, progress)
|
| 334 |
-
color = interpolate_color(rgb_colors, progress)
|
| 335 |
-
pil_img.putpixel((x, y), color)
|
| 336 |
elif direction in ["radial", "soft_radial"]:
|
| 337 |
-
|
| 338 |
-
|
| 339 |
-
|
| 340 |
-
|
| 341 |
-
|
| 342 |
-
progress = distance / max_distance if max_distance > 0 else 0
|
| 343 |
-
progress = min(1.0, progress)
|
| 344 |
-
if direction == "soft_radial":
|
| 345 |
-
progress = progress**0.7
|
| 346 |
-
color = interpolate_color(rgb_colors, progress)
|
| 347 |
-
pil_img.putpixel((x, y), color)
|
| 348 |
-
|
| 349 |
-
# Convert to OpenCV format
|
| 350 |
-
background = cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)
|
| 351 |
-
return background
|
| 352 |
|
| 353 |
except Exception as e:
|
| 354 |
logger.error(f"Gradient creation error: {e}")
|
| 355 |
-
|
| 356 |
-
return background
|
| 357 |
|
| 358 |
-
def
|
| 359 |
-
"""Create
|
| 360 |
-
|
| 361 |
-
color_map = {
|
| 362 |
-
'blue': ['#1e3c72', '#2a5298', '#3498db'],
|
| 363 |
-
'green': ['#27ae60', '#2ecc71', '#58d68d'],
|
| 364 |
-
'red': ['#e74c3c', '#c0392b', '#ff7675'],
|
| 365 |
-
'purple': ['#6c5ce7', '#a29bfe', '#fd79a8'],
|
| 366 |
-
}
|
| 367 |
|
| 368 |
-
|
| 369 |
-
|
| 370 |
-
|
| 371 |
-
|
| 372 |
-
break
|
| 373 |
|
| 374 |
-
|
| 375 |
-
|
| 376 |
-
|
| 377 |
-
|
| 378 |
-
|
| 379 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 380 |
|
| 381 |
-
def
|
| 382 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 383 |
if not video_path or not os.path.exists(video_path):
|
| 384 |
return False, "Video file not found"
|
|
|
|
| 385 |
try:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 386 |
cap = cv2.VideoCapture(video_path)
|
| 387 |
if not cap.isOpened():
|
| 388 |
return False, "Cannot open video file"
|
|
|
|
| 389 |
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
| 390 |
-
|
| 391 |
-
|
|
|
|
|
|
|
| 392 |
cap.release()
|
| 393 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 394 |
except Exception as e:
|
| 395 |
return False, f"Error validating video: {str(e)}"
|
|
|
|
| 1 |
#!/usr/bin/env python3
|
| 2 |
"""
|
| 3 |
+
Enhanced utilities.py - Core computer vision functions with improved error handling
|
| 4 |
+
Fixed transparency issues, added fallback strategies, and enhanced memory management
|
| 5 |
"""
|
| 6 |
|
| 7 |
import os
|
|
|
|
| 11 |
from PIL import Image, ImageDraw
|
| 12 |
import logging
|
| 13 |
import time
|
| 14 |
+
from typing import Optional, Dict, Any, Tuple
|
| 15 |
+
from pathlib import Path
|
| 16 |
|
| 17 |
# Setup logging
|
| 18 |
logging.basicConfig(level=logging.INFO)
|
| 19 |
logger = logging.getLogger(__name__)
|
| 20 |
|
| 21 |
+
# Professional background templates with enhanced configurations
|
| 22 |
PROFESSIONAL_BACKGROUNDS = {
|
| 23 |
"office_modern": {
|
| 24 |
"name": "Modern Office",
|
| 25 |
"type": "gradient",
|
| 26 |
"colors": ["#f8f9fa", "#e9ecef", "#dee2e6"],
|
| 27 |
"direction": "diagonal",
|
| 28 |
+
"description": "Clean, contemporary office environment",
|
| 29 |
+
"brightness": 0.95,
|
| 30 |
+
"contrast": 1.1
|
| 31 |
},
|
| 32 |
"studio_blue": {
|
| 33 |
"name": "Professional Blue",
|
| 34 |
"type": "gradient",
|
| 35 |
"colors": ["#1e3c72", "#2a5298", "#3498db"],
|
| 36 |
"direction": "radial",
|
| 37 |
+
"description": "Broadcast-quality blue studio",
|
| 38 |
+
"brightness": 0.9,
|
| 39 |
+
"contrast": 1.2
|
| 40 |
},
|
| 41 |
"studio_green": {
|
| 42 |
"name": "Broadcast Green",
|
| 43 |
"type": "color",
|
| 44 |
"colors": ["#00b894"],
|
| 45 |
"chroma_key": True,
|
| 46 |
+
"description": "Professional green screen replacement",
|
| 47 |
+
"brightness": 1.0,
|
| 48 |
+
"contrast": 1.0
|
| 49 |
},
|
| 50 |
"minimalist": {
|
| 51 |
"name": "Minimalist White",
|
| 52 |
"type": "gradient",
|
| 53 |
"colors": ["#ffffff", "#f1f2f6", "#ddd"],
|
| 54 |
"direction": "soft_radial",
|
| 55 |
+
"description": "Clean, minimal background",
|
| 56 |
+
"brightness": 0.98,
|
| 57 |
+
"contrast": 0.9
|
| 58 |
},
|
| 59 |
"warm_gradient": {
|
| 60 |
"name": "Warm Sunset",
|
| 61 |
"type": "gradient",
|
| 62 |
"colors": ["#ff7675", "#fd79a8", "#fdcb6e"],
|
| 63 |
"direction": "diagonal",
|
| 64 |
+
"description": "Warm, inviting atmosphere",
|
| 65 |
+
"brightness": 0.85,
|
| 66 |
+
"contrast": 1.15
|
| 67 |
},
|
| 68 |
"tech_dark": {
|
| 69 |
"name": "Tech Dark",
|
| 70 |
"type": "gradient",
|
| 71 |
"colors": ["#0c0c0c", "#2d3748", "#4a5568"],
|
| 72 |
"direction": "vertical",
|
| 73 |
+
"description": "Modern tech/gaming setup",
|
| 74 |
+
"brightness": 0.7,
|
| 75 |
+
"contrast": 1.3
|
| 76 |
+
},
|
| 77 |
+
"corporate_blue": {
|
| 78 |
+
"name": "Corporate Blue",
|
| 79 |
+
"type": "gradient",
|
| 80 |
+
"colors": ["#667eea", "#764ba2", "#f093fb"],
|
| 81 |
+
"direction": "diagonal",
|
| 82 |
+
"description": "Professional corporate background",
|
| 83 |
+
"brightness": 0.88,
|
| 84 |
+
"contrast": 1.1
|
| 85 |
+
},
|
| 86 |
+
"nature_blur": {
|
| 87 |
+
"name": "Soft Nature",
|
| 88 |
+
"type": "gradient",
|
| 89 |
+
"colors": ["#a8edea", "#fed6e3", "#d299c2"],
|
| 90 |
+
"direction": "radial",
|
| 91 |
+
"description": "Soft blurred nature effect",
|
| 92 |
+
"brightness": 0.92,
|
| 93 |
+
"contrast": 0.95
|
| 94 |
}
|
| 95 |
}
|
| 96 |
|
| 97 |
+
class SegmentationError(Exception):
|
| 98 |
+
"""Custom exception for segmentation failures"""
|
| 99 |
+
pass
|
| 100 |
+
|
| 101 |
+
class MaskRefinementError(Exception):
|
| 102 |
+
"""Custom exception for mask refinement failures"""
|
| 103 |
+
pass
|
| 104 |
+
|
| 105 |
+
class BackgroundReplacementError(Exception):
|
| 106 |
+
"""Custom exception for background replacement failures"""
|
| 107 |
+
pass
|
| 108 |
+
|
| 109 |
+
def segment_person_hq(image: np.ndarray, predictor: Any, fallback_enabled: bool = True) -> np.ndarray:
|
| 110 |
+
"""
|
| 111 |
+
High-quality person segmentation with enhanced error handling and fallback strategies
|
| 112 |
+
|
| 113 |
+
Args:
|
| 114 |
+
image: Input image (H, W, 3)
|
| 115 |
+
predictor: SAM2 predictor instance
|
| 116 |
+
fallback_enabled: Whether to use fallback segmentation if AI fails
|
| 117 |
+
|
| 118 |
+
Returns:
|
| 119 |
+
Binary mask (H, W) with values 0-255
|
| 120 |
+
|
| 121 |
+
Raises:
|
| 122 |
+
SegmentationError: If segmentation fails and fallback is disabled
|
| 123 |
+
"""
|
| 124 |
+
if image is None or image.size == 0:
|
| 125 |
+
raise SegmentationError("Invalid input image")
|
| 126 |
+
|
| 127 |
try:
|
| 128 |
+
# Validate predictor
|
| 129 |
+
if predictor is None:
|
| 130 |
+
if fallback_enabled:
|
| 131 |
+
logger.warning("SAM2 predictor not available, using fallback")
|
| 132 |
+
return _fallback_segmentation(image)
|
| 133 |
+
else:
|
| 134 |
+
raise SegmentationError("SAM2 predictor not available")
|
| 135 |
+
|
| 136 |
+
# Set image for prediction
|
| 137 |
+
try:
|
| 138 |
+
predictor.set_image(image)
|
| 139 |
+
except Exception as e:
|
| 140 |
+
logger.error(f"Failed to set image in predictor: {e}")
|
| 141 |
+
if fallback_enabled:
|
| 142 |
+
return _fallback_segmentation(image)
|
| 143 |
+
else:
|
| 144 |
+
raise SegmentationError(f"Predictor setup failed: {e}")
|
| 145 |
+
|
| 146 |
h, w = image.shape[:2]
|
| 147 |
|
| 148 |
+
# Enhanced strategic point placement for better person detection
|
| 149 |
points = np.array([
|
| 150 |
+
[w//2, h//4], # Head center
|
| 151 |
+
[w//2, h//2], # Torso center
|
| 152 |
+
[w//2, 3*h//4], # Lower body
|
| 153 |
+
[w//3, h//2], # Left side
|
| 154 |
+
[2*w//3, h//2], # Right side
|
| 155 |
+
[w//2, h//6], # Upper head
|
| 156 |
+
[w//4, 2*h//3], # Left leg area
|
| 157 |
+
[3*w//4, 2*h//3], # Right leg area
|
| 158 |
+
], dtype=np.float32)
|
| 159 |
+
|
| 160 |
+
labels = np.ones(len(points), dtype=np.int32)
|
| 161 |
+
|
| 162 |
+
# Perform prediction with error handling
|
| 163 |
+
try:
|
| 164 |
+
with torch.no_grad():
|
| 165 |
+
masks, scores, _ = predictor.predict(
|
| 166 |
+
point_coords=points,
|
| 167 |
+
point_labels=labels,
|
| 168 |
+
multimask_output=True
|
| 169 |
+
)
|
| 170 |
+
except Exception as e:
|
| 171 |
+
logger.error(f"SAM2 prediction failed: {e}")
|
| 172 |
+
if fallback_enabled:
|
| 173 |
+
return _fallback_segmentation(image)
|
| 174 |
+
else:
|
| 175 |
+
raise SegmentationError(f"Prediction failed: {e}")
|
| 176 |
+
|
| 177 |
+
# Validate prediction results
|
| 178 |
+
if masks is None or len(masks) == 0:
|
| 179 |
+
logger.warning("SAM2 returned no masks")
|
| 180 |
+
if fallback_enabled:
|
| 181 |
+
return _fallback_segmentation(image)
|
| 182 |
+
else:
|
| 183 |
+
raise SegmentationError("No masks generated")
|
| 184 |
+
|
| 185 |
+
if scores is None or len(scores) == 0:
|
| 186 |
+
logger.warning("SAM2 returned no scores")
|
| 187 |
+
best_mask = masks[0]
|
| 188 |
+
else:
|
| 189 |
+
# Select best mask based on score
|
| 190 |
+
best_idx = np.argmax(scores)
|
| 191 |
+
best_mask = masks[best_idx]
|
| 192 |
+
logger.debug(f"Selected mask {best_idx} with score {scores[best_idx]:.3f}")
|
| 193 |
+
|
| 194 |
+
# Process mask to ensure correct format
|
| 195 |
+
mask = _process_mask(best_mask)
|
| 196 |
+
|
| 197 |
+
# Validate mask quality
|
| 198 |
+
if not _validate_mask_quality(mask, image.shape[:2]):
|
| 199 |
+
logger.warning("Mask quality validation failed")
|
| 200 |
+
if fallback_enabled:
|
| 201 |
+
return _fallback_segmentation(image)
|
| 202 |
+
else:
|
| 203 |
+
raise SegmentationError("Poor mask quality")
|
| 204 |
+
|
| 205 |
+
logger.debug(f"Segmentation successful - mask range: {mask.min()}-{mask.max()}")
|
| 206 |
+
return mask
|
| 207 |
+
|
| 208 |
+
except SegmentationError:
|
| 209 |
+
raise
|
| 210 |
+
except Exception as e:
|
| 211 |
+
logger.error(f"Unexpected segmentation error: {e}")
|
| 212 |
+
if fallback_enabled:
|
| 213 |
+
return _fallback_segmentation(image)
|
| 214 |
else:
|
| 215 |
+
raise SegmentationError(f"Unexpected error: {e}")
|
| 216 |
+
|
| 217 |
+
def _process_mask(mask: np.ndarray) -> np.ndarray:
|
| 218 |
+
"""Process raw mask to ensure correct format and range"""
|
| 219 |
+
try:
|
| 220 |
+
# Handle different input formats
|
| 221 |
+
if len(mask.shape) > 2:
|
| 222 |
+
mask = mask.squeeze()
|
| 223 |
+
|
| 224 |
+
if len(mask.shape) > 2:
|
| 225 |
+
mask = mask[:, :, 0] if mask.shape[2] > 0 else mask.sum(axis=2)
|
| 226 |
|
| 227 |
+
# Ensure proper data type and range
|
| 228 |
+
if mask.dtype == bool:
|
| 229 |
+
mask = mask.astype(np.uint8) * 255
|
| 230 |
+
elif mask.dtype == np.float32 or mask.dtype == np.float64:
|
| 231 |
+
if mask.max() <= 1.0:
|
| 232 |
+
mask = (mask * 255).astype(np.uint8)
|
| 233 |
+
else:
|
| 234 |
+
mask = np.clip(mask, 0, 255).astype(np.uint8)
|
| 235 |
+
else:
|
| 236 |
+
mask = mask.astype(np.uint8)
|
| 237 |
|
| 238 |
+
# Post-process for cleaner edges
|
| 239 |
+
kernel = np.ones((3, 3), np.uint8)
|
| 240 |
+
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)
|
| 241 |
+
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
|
| 242 |
|
| 243 |
+
# Ensure binary threshold
|
| 244 |
+
_, mask = cv2.threshold(mask, 127, 255, cv2.THRESH_BINARY)
|
| 245 |
|
| 246 |
+
return mask
|
| 247 |
|
| 248 |
except Exception as e:
|
| 249 |
+
logger.error(f"Mask processing failed: {e}")
|
| 250 |
+
# Return a basic fallback mask
|
| 251 |
+
h, w = mask.shape[:2] if len(mask.shape) >= 2 else (256, 256)
|
| 252 |
+
fallback = np.zeros((h, w), dtype=np.uint8)
|
| 253 |
+
fallback[h//4:3*h//4, w//4:3*w//4] = 255
|
| 254 |
+
return fallback
|
| 255 |
+
|
| 256 |
+
def _validate_mask_quality(mask: np.ndarray, image_shape: Tuple[int, int]) -> bool:
|
| 257 |
+
"""Validate that the mask meets quality criteria"""
|
| 258 |
+
try:
|
| 259 |
+
h, w = image_shape
|
| 260 |
+
mask_area = np.sum(mask > 127)
|
| 261 |
+
total_area = h * w
|
| 262 |
+
|
| 263 |
+
# Check if mask area is reasonable (5% to 80% of image)
|
| 264 |
+
area_ratio = mask_area / total_area
|
| 265 |
+
if area_ratio < 0.05 or area_ratio > 0.8:
|
| 266 |
+
logger.warning(f"Suspicious mask area ratio: {area_ratio:.3f}")
|
| 267 |
+
return False
|
| 268 |
+
|
| 269 |
+
# Check if mask is not just a blob in corner
|
| 270 |
+
mask_binary = mask > 127
|
| 271 |
+
mask_center_y, mask_center_x = np.where(mask_binary)
|
| 272 |
+
|
| 273 |
+
if len(mask_center_y) == 0:
|
| 274 |
+
logger.warning("Empty mask")
|
| 275 |
+
return False
|
| 276 |
+
|
| 277 |
+
center_y = np.mean(mask_center_y)
|
| 278 |
+
center_x = np.mean(mask_center_x)
|
| 279 |
+
|
| 280 |
+
# Person should be roughly centered
|
| 281 |
+
if center_y < h * 0.2 or center_y > h * 0.9:
|
| 282 |
+
logger.warning(f"Mask center too far from expected person location: y={center_y/h:.2f}")
|
| 283 |
+
return False
|
| 284 |
+
|
| 285 |
+
return True
|
| 286 |
+
|
| 287 |
+
except Exception as e:
|
| 288 |
+
logger.warning(f"Mask validation error: {e}")
|
| 289 |
+
return True # Default to accepting mask if validation fails
|
| 290 |
+
|
| 291 |
+
def _fallback_segmentation(image: np.ndarray) -> np.ndarray:
|
| 292 |
+
"""Fallback segmentation when AI models fail"""
|
| 293 |
+
try:
|
| 294 |
+
logger.info("Using fallback segmentation strategy")
|
| 295 |
h, w = image.shape[:2]
|
| 296 |
+
|
| 297 |
+
# Try background subtraction approach
|
| 298 |
+
try:
|
| 299 |
+
# Simple background subtraction
|
| 300 |
+
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
| 301 |
+
|
| 302 |
+
# Assume background is around the edges
|
| 303 |
+
edge_pixels = np.concatenate([
|
| 304 |
+
gray[0, :], gray[-1, :], gray[:, 0], gray[:, -1]
|
| 305 |
+
])
|
| 306 |
+
bg_color = np.median(edge_pixels)
|
| 307 |
+
|
| 308 |
+
# Create mask based on difference from background
|
| 309 |
+
diff = np.abs(gray.astype(float) - bg_color)
|
| 310 |
+
mask = (diff > 30).astype(np.uint8) * 255
|
| 311 |
+
|
| 312 |
+
# Morphological operations to clean up
|
| 313 |
+
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (7, 7))
|
| 314 |
+
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)
|
| 315 |
+
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
|
| 316 |
+
|
| 317 |
+
# If mask looks reasonable, use it
|
| 318 |
+
if _validate_mask_quality(mask, image.shape[:2]):
|
| 319 |
+
logger.info("Background subtraction fallback successful")
|
| 320 |
+
return mask
|
| 321 |
+
|
| 322 |
+
except Exception as e:
|
| 323 |
+
logger.warning(f"Background subtraction fallback failed: {e}")
|
| 324 |
+
|
| 325 |
+
# Simple geometric fallback
|
| 326 |
+
mask = np.zeros((h, w), dtype=np.uint8)
|
| 327 |
+
|
| 328 |
+
# Create an elliptical mask in center assuming person location
|
| 329 |
+
center_x, center_y = w // 2, h // 2
|
| 330 |
+
radius_x, radius_y = w // 3, h // 2.5
|
| 331 |
+
|
| 332 |
+
y, x = np.ogrid[:h, :w]
|
| 333 |
+
mask_ellipse = ((x - center_x) / radius_x) ** 2 + ((y - center_y) / radius_y) ** 2 <= 1
|
| 334 |
+
mask[mask_ellipse] = 255
|
| 335 |
+
|
| 336 |
+
logger.info("Using geometric fallback mask")
|
| 337 |
+
return mask
|
| 338 |
+
|
| 339 |
+
except Exception as e:
|
| 340 |
+
logger.error(f"All fallback strategies failed: {e}")
|
| 341 |
+
# Last resort: simple center rectangle
|
| 342 |
+
h, w = image.shape[:2]
|
| 343 |
+
mask = np.zeros((h, w), dtype=np.uint8)
|
| 344 |
+
mask[h//6:5*h//6, w//4:3*w//4] = 255
|
| 345 |
+
return mask
|
| 346 |
|
| 347 |
+
def refine_mask_hq(image: np.ndarray, mask: np.ndarray, matanyone_processor: Any,
|
| 348 |
+
fallback_enabled: bool = True) -> np.ndarray:
|
| 349 |
+
"""
|
| 350 |
+
Enhanced mask refinement with MatAnyone and robust fallbacks
|
| 351 |
+
|
| 352 |
+
Args:
|
| 353 |
+
image: Input image (H, W, 3)
|
| 354 |
+
mask: Input mask (H, W) with values 0-255
|
| 355 |
+
matanyone_processor: MatAnyone processor instance
|
| 356 |
+
fallback_enabled: Whether to use fallback refinement if MatAnyone fails
|
| 357 |
+
|
| 358 |
+
Returns:
|
| 359 |
+
Refined mask (H, W) with values 0-255
|
| 360 |
+
|
| 361 |
+
Raises:
|
| 362 |
+
MaskRefinementError: If refinement fails and fallback is disabled
|
| 363 |
+
"""
|
| 364 |
+
if image is None or mask is None:
|
| 365 |
+
raise MaskRefinementError("Invalid input image or mask")
|
| 366 |
+
|
| 367 |
try:
|
| 368 |
+
# Ensure mask is in correct format
|
| 369 |
+
mask = _process_mask(mask)
|
|
|
|
| 370 |
|
| 371 |
# Try MatAnyone if available
|
| 372 |
if matanyone_processor is not None:
|
| 373 |
try:
|
| 374 |
+
logger.debug("Attempting MatAnyone refinement")
|
| 375 |
+
refined_mask = _matanyone_refine(image, mask, matanyone_processor)
|
| 376 |
+
|
| 377 |
+
if refined_mask is not None and _validate_mask_quality(refined_mask, image.shape[:2]):
|
| 378 |
+
logger.debug("MatAnyone refinement successful")
|
|
|
|
|
|
|
| 379 |
return refined_mask
|
| 380 |
+
else:
|
| 381 |
+
logger.warning("MatAnyone produced poor quality mask")
|
| 382 |
+
|
| 383 |
+
except Exception as e:
|
| 384 |
+
logger.warning(f"MatAnyone refinement failed: {e}")
|
| 385 |
+
|
| 386 |
+
# Fallback to enhanced OpenCV refinement
|
| 387 |
+
if fallback_enabled:
|
| 388 |
+
logger.debug("Using enhanced OpenCV refinement")
|
| 389 |
+
return enhance_mask_opencv_advanced(image, mask)
|
| 390 |
+
else:
|
| 391 |
+
raise MaskRefinementError("MatAnyone failed and fallback disabled")
|
| 392 |
+
|
| 393 |
+
except MaskRefinementError:
|
| 394 |
+
raise
|
| 395 |
+
except Exception as e:
|
| 396 |
+
logger.error(f"Unexpected mask refinement error: {e}")
|
| 397 |
+
if fallback_enabled:
|
| 398 |
+
return enhance_mask_opencv_advanced(image, mask)
|
| 399 |
+
else:
|
| 400 |
+
raise MaskRefinementError(f"Unexpected error: {e}")
|
| 401 |
+
|
| 402 |
+
def _matanyone_refine(image: np.ndarray, mask: np.ndarray, processor: Any) -> Optional[np.ndarray]:
|
| 403 |
+
"""Attempt MatAnyone mask refinement"""
|
| 404 |
+
try:
|
| 405 |
+
# Different possible MatAnyone interfaces
|
| 406 |
+
if hasattr(processor, 'infer'):
|
| 407 |
+
refined_mask = processor.infer(image, mask)
|
| 408 |
+
elif hasattr(processor, 'process'):
|
| 409 |
+
refined_mask = processor.process(image, mask)
|
| 410 |
+
elif callable(processor):
|
| 411 |
+
refined_mask = processor(image, mask)
|
| 412 |
+
else:
|
| 413 |
+
logger.warning("Unknown MatAnyone interface")
|
| 414 |
+
return None
|
| 415 |
+
|
| 416 |
+
if refined_mask is None:
|
| 417 |
+
return None
|
| 418 |
|
| 419 |
+
# Process the refined mask
|
| 420 |
+
refined_mask = _process_mask(refined_mask)
|
| 421 |
+
|
| 422 |
+
return refined_mask
|
| 423 |
|
| 424 |
except Exception as e:
|
| 425 |
+
logger.warning(f"MatAnyone processing error: {e}")
|
| 426 |
+
return None
|
| 427 |
|
| 428 |
+
def enhance_mask_opencv_advanced(image: np.ndarray, mask: np.ndarray) -> np.ndarray:
|
| 429 |
+
"""
|
| 430 |
+
Advanced OpenCV-based mask enhancement with multiple techniques
|
| 431 |
+
"""
|
| 432 |
try:
|
| 433 |
if len(mask.shape) == 3:
|
| 434 |
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
|
| 435 |
|
| 436 |
+
# Ensure proper range
|
| 437 |
if mask.max() <= 1.0:
|
| 438 |
mask = (mask * 255).astype(np.uint8)
|
| 439 |
|
| 440 |
+
# Multi-stage refinement
|
| 441 |
+
|
| 442 |
+
# 1. Bilateral filtering for edge preservation
|
| 443 |
refined_mask = cv2.bilateralFilter(mask, 9, 75, 75)
|
| 444 |
|
| 445 |
+
# 2. Edge-aware smoothing using guided filter approximation
|
| 446 |
+
refined_mask = _guided_filter_approx(image, refined_mask, radius=8, eps=0.2)
|
|
|
|
|
|
|
| 447 |
|
| 448 |
+
# 3. Morphological operations for structure
|
| 449 |
+
kernel_close = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
|
| 450 |
+
refined_mask = cv2.morphologyEx(refined_mask, cv2.MORPH_CLOSE, kernel_close)
|
| 451 |
+
|
| 452 |
+
kernel_open = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
|
| 453 |
+
refined_mask = cv2.morphologyEx(refined_mask, cv2.MORPH_OPEN, kernel_open)
|
| 454 |
|
| 455 |
+
# 4. Final smoothing
|
| 456 |
+
refined_mask = cv2.GaussianBlur(refined_mask, (3, 3), 0.8)
|
| 457 |
+
|
| 458 |
+
# 5. Ensure binary output
|
| 459 |
+
_, refined_mask = cv2.threshold(refined_mask, 127, 255, cv2.THRESH_BINARY)
|
| 460 |
|
| 461 |
return refined_mask
|
| 462 |
|
| 463 |
except Exception as e:
|
| 464 |
+
logger.warning(f"Enhanced OpenCV refinement failed: {e}")
|
| 465 |
+
# Simple fallback
|
| 466 |
+
return cv2.GaussianBlur(mask, (5, 5), 1.0)
|
| 467 |
+
|
| 468 |
+
def _guided_filter_approx(guide: np.ndarray, mask: np.ndarray, radius: int = 8, eps: float = 0.2) -> np.ndarray:
|
| 469 |
+
"""Approximation of guided filter for edge-aware smoothing"""
|
| 470 |
+
try:
|
| 471 |
+
guide_gray = cv2.cvtColor(guide, cv2.COLOR_BGR2GRAY) if len(guide.shape) == 3 else guide
|
| 472 |
+
guide_gray = guide_gray.astype(np.float32) / 255.0
|
| 473 |
+
mask_float = mask.astype(np.float32) / 255.0
|
| 474 |
+
|
| 475 |
+
# Box filter approximation
|
| 476 |
+
kernel_size = 2 * radius + 1
|
| 477 |
+
|
| 478 |
+
# Mean filters
|
| 479 |
+
mean_guide = cv2.boxFilter(guide_gray, -1, (kernel_size, kernel_size))
|
| 480 |
+
mean_mask = cv2.boxFilter(mask_float, -1, (kernel_size, kernel_size))
|
| 481 |
+
corr_guide_mask = cv2.boxFilter(guide_gray * mask_float, -1, (kernel_size, kernel_size))
|
| 482 |
+
|
| 483 |
+
# Covariance
|
| 484 |
+
cov_guide_mask = corr_guide_mask - mean_guide * mean_mask
|
| 485 |
+
mean_guide_sq = cv2.boxFilter(guide_gray * guide_gray, -1, (kernel_size, kernel_size))
|
| 486 |
+
var_guide = mean_guide_sq - mean_guide * mean_guide
|
| 487 |
+
|
| 488 |
+
# Coefficients
|
| 489 |
+
a = cov_guide_mask / (var_guide + eps)
|
| 490 |
+
b = mean_mask - a * mean_guide
|
| 491 |
+
|
| 492 |
+
# Apply coefficients
|
| 493 |
+
mean_a = cv2.boxFilter(a, -1, (kernel_size, kernel_size))
|
| 494 |
+
mean_b = cv2.boxFilter(b, -1, (kernel_size, kernel_size))
|
| 495 |
+
|
| 496 |
+
output = mean_a * guide_gray + mean_b
|
| 497 |
+
output = np.clip(output * 255, 0, 255).astype(np.uint8)
|
| 498 |
+
|
| 499 |
+
return output
|
| 500 |
+
|
| 501 |
+
except Exception as e:
|
| 502 |
+
logger.warning(f"Guided filter approximation failed: {e}")
|
| 503 |
return mask
|
| 504 |
|
| 505 |
+
def replace_background_hq(frame: np.ndarray, mask: np.ndarray, background: np.ndarray,
|
| 506 |
+
fallback_enabled: bool = True) -> np.ndarray:
|
| 507 |
+
"""
|
| 508 |
+
Enhanced background replacement with comprehensive error handling and quality improvements
|
| 509 |
+
|
| 510 |
+
Args:
|
| 511 |
+
frame: Input frame (H, W, 3)
|
| 512 |
+
mask: Binary mask (H, W) with values 0-255
|
| 513 |
+
background: Background image (H, W, 3)
|
| 514 |
+
fallback_enabled: Whether to use fallback if main method fails
|
| 515 |
+
|
| 516 |
+
Returns:
|
| 517 |
+
Composited frame (H, W, 3)
|
| 518 |
+
|
| 519 |
+
Raises:
|
| 520 |
+
BackgroundReplacementError: If replacement fails and fallback is disabled
|
| 521 |
+
"""
|
| 522 |
+
if frame is None or mask is None or background is None:
|
| 523 |
+
raise BackgroundReplacementError("Invalid input frame, mask, or background")
|
| 524 |
+
|
| 525 |
try:
|
| 526 |
# Resize background to match frame
|
| 527 |
+
background = cv2.resize(background, (frame.shape[1], frame.shape[0]),
|
| 528 |
+
interpolation=cv2.INTER_LANCZOS4)
|
| 529 |
|
| 530 |
+
# Process mask
|
| 531 |
if len(mask.shape) == 3:
|
| 532 |
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
|
| 533 |
|
|
|
|
| 534 |
if mask.dtype != np.uint8:
|
| 535 |
mask = mask.astype(np.uint8)
|
| 536 |
|
| 537 |
if mask.max() <= 1.0:
|
| 538 |
+
logger.debug("Converting normalized mask to 0-255 range")
|
| 539 |
mask = (mask * 255).astype(np.uint8)
|
| 540 |
|
| 541 |
+
# Enhanced compositing with multiple techniques
|
| 542 |
+
try:
|
| 543 |
+
result = _advanced_compositing(frame, mask, background)
|
| 544 |
+
logger.debug("Advanced compositing successful")
|
| 545 |
+
return result
|
| 546 |
+
|
| 547 |
+
except Exception as e:
|
| 548 |
+
logger.warning(f"Advanced compositing failed: {e}")
|
| 549 |
+
if fallback_enabled:
|
| 550 |
+
return _simple_compositing(frame, mask, background)
|
| 551 |
+
else:
|
| 552 |
+
raise BackgroundReplacementError(f"Advanced compositing failed: {e}")
|
| 553 |
|
| 554 |
+
except BackgroundReplacementError:
|
| 555 |
+
raise
|
| 556 |
+
except Exception as e:
|
| 557 |
+
logger.error(f"Unexpected background replacement error: {e}")
|
| 558 |
+
if fallback_enabled:
|
| 559 |
+
return _simple_compositing(frame, mask, background)
|
| 560 |
+
else:
|
| 561 |
+
raise BackgroundReplacementError(f"Unexpected error: {e}")
|
| 562 |
+
|
| 563 |
+
def _advanced_compositing(frame: np.ndarray, mask: np.ndarray, background: np.ndarray) -> np.ndarray:
|
| 564 |
+
"""Advanced compositing with edge feathering and color correction"""
|
| 565 |
+
try:
|
| 566 |
+
# Create high-quality alpha mask
|
| 567 |
+
threshold = 100 # Lower threshold for better person extraction
|
| 568 |
_, mask_binary = cv2.threshold(mask, threshold, 255, cv2.THRESH_BINARY)
|
| 569 |
|
| 570 |
+
# Clean up mask
|
| 571 |
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5))
|
| 572 |
+
mask_binary = cv2.morphologyEx(mask_binary, cv2.MORPH_CLOSE, kernel)
|
| 573 |
+
mask_binary = cv2.morphologyEx(mask_binary, cv2.MORPH_OPEN, kernel)
|
| 574 |
|
| 575 |
+
# Create smooth alpha channel with edge feathering
|
| 576 |
mask_smooth = cv2.GaussianBlur(mask_binary.astype(np.float32), (5, 5), 1.0)
|
| 577 |
+
mask_smooth = mask_smooth / 255.0
|
| 578 |
|
| 579 |
+
# Apply gamma correction for better blending
|
| 580 |
+
mask_smooth = np.power(mask_smooth, 0.8)
|
| 581 |
|
| 582 |
+
# Enhance edges - boost values near 1.0, reduce values near 0.0
|
| 583 |
mask_smooth = np.where(mask_smooth > 0.5,
|
| 584 |
+
np.minimum(mask_smooth * 1.1, 1.0),
|
| 585 |
+
mask_smooth * 0.9)
|
| 586 |
+
|
| 587 |
+
# Color matching between foreground and background
|
| 588 |
+
frame_adjusted = _color_match_edges(frame, background, mask_smooth)
|
| 589 |
|
| 590 |
+
# Create 3-channel alpha mask
|
| 591 |
+
alpha_3ch = np.stack([mask_smooth] * 3, axis=2)
|
| 592 |
|
| 593 |
+
# Perform high-quality compositing
|
| 594 |
+
frame_float = frame_adjusted.astype(np.float32)
|
| 595 |
background_float = background.astype(np.float32)
|
| 596 |
|
| 597 |
+
# Alpha blending with gamma correction
|
| 598 |
+
result = frame_float * alpha_3ch + background_float * (1 - alpha_3ch)
|
| 599 |
result = np.clip(result, 0, 255).astype(np.uint8)
|
| 600 |
|
|
|
|
|
|
|
|
|
|
| 601 |
return result
|
| 602 |
|
| 603 |
except Exception as e:
|
| 604 |
+
logger.error(f"Advanced compositing error: {e}")
|
| 605 |
+
raise
|
| 606 |
+
|
| 607 |
+
def _color_match_edges(frame: np.ndarray, background: np.ndarray, alpha: np.ndarray) -> np.ndarray:
|
| 608 |
+
"""Subtle color matching at edges to reduce halos"""
|
| 609 |
+
try:
|
| 610 |
+
# Find edge regions (transition areas)
|
| 611 |
+
edge_mask = cv2.Sobel(alpha, cv2.CV_64F, 1, 1, ksize=3)
|
| 612 |
+
edge_mask = np.abs(edge_mask)
|
| 613 |
+
edge_mask = (edge_mask > 0.1).astype(np.float32)
|
| 614 |
+
|
| 615 |
+
# Calculate color difference in edge regions
|
| 616 |
+
edge_areas = edge_mask > 0
|
| 617 |
+
if not np.any(edge_areas):
|
| 618 |
return frame
|
| 619 |
+
|
| 620 |
+
# Subtle color adjustment
|
| 621 |
+
frame_adjusted = frame.copy().astype(np.float32)
|
| 622 |
+
background_float = background.astype(np.float32)
|
| 623 |
+
|
| 624 |
+
# Apply very subtle color shift towards background in edge areas
|
| 625 |
+
adjustment_strength = 0.1
|
| 626 |
+
for c in range(3):
|
| 627 |
+
frame_adjusted[:, :, c] = np.where(
|
| 628 |
+
edge_areas,
|
| 629 |
+
frame_adjusted[:, :, c] * (1 - adjustment_strength) +
|
| 630 |
+
background_float[:, :, c] * adjustment_strength,
|
| 631 |
+
frame_adjusted[:, :, c]
|
| 632 |
+
)
|
| 633 |
+
|
| 634 |
+
return np.clip(frame_adjusted, 0, 255).astype(np.uint8)
|
| 635 |
+
|
| 636 |
+
except Exception as e:
|
| 637 |
+
logger.warning(f"Color matching failed: {e}")
|
| 638 |
+
return frame
|
| 639 |
|
| 640 |
+
def _simple_compositing(frame: np.ndarray, mask: np.ndarray, background: np.ndarray) -> np.ndarray:
|
| 641 |
+
"""Simple fallback compositing method"""
|
| 642 |
+
try:
|
| 643 |
+
logger.info("Using simple compositing fallback")
|
| 644 |
+
|
| 645 |
+
# Resize background
|
| 646 |
+
background = cv2.resize(background, (frame.shape[1], frame.shape[0]))
|
| 647 |
+
|
| 648 |
+
# Process mask
|
| 649 |
+
if len(mask.shape) == 3:
|
| 650 |
+
mask = cv2.cvtColor(mask, cv2.COLOR_BGR2GRAY)
|
| 651 |
+
if mask.max() <= 1.0:
|
| 652 |
+
mask = (mask * 255).astype(np.uint8)
|
| 653 |
+
|
| 654 |
+
# Simple binary threshold
|
| 655 |
+
_, mask_binary = cv2.threshold(mask, 127, 255, cv2.THRESH_BINARY)
|
| 656 |
+
|
| 657 |
+
# Create alpha mask
|
| 658 |
+
mask_norm = mask_binary.astype(np.float32) / 255.0
|
| 659 |
+
mask_3ch = np.stack([mask_norm] * 3, axis=2)
|
| 660 |
+
|
| 661 |
+
# Simple alpha blending
|
| 662 |
+
result = frame * mask_3ch + background * (1 - mask_3ch)
|
| 663 |
+
return result.astype(np.uint8)
|
| 664 |
+
|
| 665 |
+
except Exception as e:
|
| 666 |
+
logger.error(f"Simple compositing failed: {e}")
|
| 667 |
+
# Last resort: return original frame
|
| 668 |
+
return frame
|
| 669 |
+
|
| 670 |
+
def create_professional_background(bg_config: Dict[str, Any], width: int, height: int) -> np.ndarray:
|
| 671 |
+
"""Enhanced professional background creation with quality improvements"""
|
| 672 |
try:
|
| 673 |
if bg_config["type"] == "color":
|
| 674 |
+
background = _create_solid_background(bg_config, width, height)
|
|
|
|
|
|
|
|
|
|
| 675 |
elif bg_config["type"] == "gradient":
|
| 676 |
+
background = _create_gradient_background_enhanced(bg_config, width, height)
|
| 677 |
else:
|
| 678 |
+
# Fallback to neutral gray
|
| 679 |
background = np.full((height, width, 3), (128, 128, 128), dtype=np.uint8)
|
| 680 |
+
|
| 681 |
+
# Apply brightness and contrast adjustments
|
| 682 |
+
background = _apply_background_adjustments(background, bg_config)
|
| 683 |
+
|
| 684 |
return background
|
| 685 |
+
|
| 686 |
except Exception as e:
|
| 687 |
logger.error(f"Background creation error: {e}")
|
| 688 |
return np.full((height, width, 3), (128, 128, 128), dtype=np.uint8)
|
| 689 |
|
| 690 |
+
def _create_solid_background(bg_config: Dict[str, Any], width: int, height: int) -> np.ndarray:
|
| 691 |
+
"""Create solid color background"""
|
| 692 |
+
color_hex = bg_config["colors"][0].lstrip('#')
|
| 693 |
+
color_rgb = tuple(int(color_hex[i:i+2], 16) for i in (0, 2, 4))
|
| 694 |
+
color_bgr = color_rgb[::-1]
|
| 695 |
+
return np.full((height, width, 3), color_bgr, dtype=np.uint8)
|
| 696 |
+
|
| 697 |
+
def _create_gradient_background_enhanced(bg_config: Dict[str, Any], width: int, height: int) -> np.ndarray:
|
| 698 |
+
"""Create enhanced gradient background with better quality"""
|
| 699 |
try:
|
| 700 |
colors = bg_config["colors"]
|
| 701 |
direction = bg_config.get("direction", "vertical")
|
|
|
|
| 710 |
if not rgb_colors:
|
| 711 |
rgb_colors = [(128, 128, 128)]
|
| 712 |
|
| 713 |
+
# Use NumPy for better performance on large images
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 714 |
if direction == "vertical":
|
| 715 |
+
background = _create_vertical_gradient(rgb_colors, width, height)
|
|
|
|
|
|
|
|
|
|
| 716 |
elif direction == "horizontal":
|
| 717 |
+
background = _create_horizontal_gradient(rgb_colors, width, height)
|
|
|
|
|
|
|
|
|
|
| 718 |
elif direction == "diagonal":
|
| 719 |
+
background = _create_diagonal_gradient(rgb_colors, width, height)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 720 |
elif direction in ["radial", "soft_radial"]:
|
| 721 |
+
background = _create_radial_gradient(rgb_colors, width, height, direction == "soft_radial")
|
| 722 |
+
else:
|
| 723 |
+
background = _create_vertical_gradient(rgb_colors, width, height)
|
| 724 |
+
|
| 725 |
+
return cv2.cvtColor(background, cv2.COLOR_RGB2BGR)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 726 |
|
| 727 |
except Exception as e:
|
| 728 |
logger.error(f"Gradient creation error: {e}")
|
| 729 |
+
return np.full((height, width, 3), (128, 128, 128), dtype=np.uint8)
|
|
|
|
| 730 |
|
| 731 |
+
def _create_vertical_gradient(colors: list, width: int, height: int) -> np.ndarray:
|
| 732 |
+
"""Create vertical gradient using NumPy for performance"""
|
| 733 |
+
gradient = np.zeros((height, width, 3), dtype=np.uint8)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 734 |
|
| 735 |
+
for y in range(height):
|
| 736 |
+
progress = y / height if height > 0 else 0
|
| 737 |
+
color = _interpolate_color(colors, progress)
|
| 738 |
+
gradient[y, :] = color
|
|
|
|
| 739 |
|
| 740 |
+
return gradient
|
| 741 |
+
|
| 742 |
+
def _create_horizontal_gradient(colors: list, width: int, height: int) -> np.ndarray:
|
| 743 |
+
"""Create horizontal gradient using NumPy for performance"""
|
| 744 |
+
gradient = np.zeros((height, width, 3), dtype=np.uint8)
|
| 745 |
+
|
| 746 |
+
for x in range(width):
|
| 747 |
+
progress = x / width if width > 0 else 0
|
| 748 |
+
color = _interpolate_color(colors, progress)
|
| 749 |
+
gradient[:, x] = color
|
| 750 |
+
|
| 751 |
+
return gradient
|
| 752 |
+
|
| 753 |
+
def _create_diagonal_gradient(colors: list, width: int, height: int) -> np.ndarray:
|
| 754 |
+
"""Create diagonal gradient using vectorized operations"""
|
| 755 |
+
y_coords, x_coords = np.mgrid[0:height, 0:width]
|
| 756 |
+
max_distance = width + height
|
| 757 |
+
progress = (x_coords + y_coords) / max_distance
|
| 758 |
+
progress = np.clip(progress, 0, 1)
|
| 759 |
+
|
| 760 |
+
# Vectorized color interpolation
|
| 761 |
+
gradient = np.zeros((height, width, 3), dtype=np.uint8)
|
| 762 |
+
for c in range(3):
|
| 763 |
+
gradient[:, :, c] = _vectorized_color_interpolation(colors, progress, c)
|
| 764 |
+
|
| 765 |
+
return gradient
|
| 766 |
+
|
| 767 |
+
def _create_radial_gradient(colors: list, width: int, height: int, soft: bool = False) -> np.ndarray:
|
| 768 |
+
"""Create radial gradient using vectorized operations"""
|
| 769 |
+
center_x, center_y = width // 2, height // 2
|
| 770 |
+
max_distance = np.sqrt(center_x**2 + center_y**2)
|
| 771 |
+
|
| 772 |
+
y_coords, x_coords = np.mgrid[0:height, 0:width]
|
| 773 |
+
distances = np.sqrt((x_coords - center_x)**2 + (y_coords - center_y)**2)
|
| 774 |
+
progress = distances / max_distance
|
| 775 |
+
progress = np.clip(progress, 0, 1)
|
| 776 |
+
|
| 777 |
+
if soft:
|
| 778 |
+
progress = np.power(progress, 0.7)
|
| 779 |
+
|
| 780 |
+
# Vectorized color interpolation
|
| 781 |
+
gradient = np.zeros((height, width, 3), dtype=np.uint8)
|
| 782 |
+
for c in range(3):
|
| 783 |
+
gradient[:, :, c] = _vectorized_color_interpolation(colors, progress, c)
|
| 784 |
+
|
| 785 |
+
return gradient
|
| 786 |
|
| 787 |
+
def _vectorized_color_interpolation(colors: list, progress: np.ndarray, channel: int) -> np.ndarray:
|
| 788 |
+
"""Vectorized color interpolation for performance"""
|
| 789 |
+
if len(colors) == 1:
|
| 790 |
+
return np.full_like(progress, colors[0][channel], dtype=np.uint8)
|
| 791 |
+
|
| 792 |
+
num_segments = len(colors) - 1
|
| 793 |
+
segment_progress = progress * num_segments
|
| 794 |
+
segment_indices = np.floor(segment_progress).astype(int)
|
| 795 |
+
segment_indices = np.clip(segment_indices, 0, num_segments - 1)
|
| 796 |
+
local_progress = segment_progress - segment_indices
|
| 797 |
+
|
| 798 |
+
# Get start and end colors for each pixel
|
| 799 |
+
start_colors = np.array([colors[i][channel] for i in range(len(colors))])
|
| 800 |
+
end_colors = np.array([colors[min(i + 1, len(colors) - 1)][channel] for i in range(len(colors))])
|
| 801 |
+
|
| 802 |
+
start_vals = start_colors[segment_indices]
|
| 803 |
+
end_vals = end_colors[segment_indices]
|
| 804 |
+
|
| 805 |
+
result = start_vals + (end_vals - start_vals) * local_progress
|
| 806 |
+
return np.clip(result, 0, 255).astype(np.uint8)
|
| 807 |
+
|
| 808 |
+
def _interpolate_color(colors: list, progress: float) -> tuple:
|
| 809 |
+
"""Interpolate between multiple colors"""
|
| 810 |
+
if len(colors) == 1:
|
| 811 |
+
return colors[0]
|
| 812 |
+
elif len(colors) == 2:
|
| 813 |
+
r = int(colors[0][0] + (colors[1][0] - colors[0][0]) * progress)
|
| 814 |
+
g = int(colors[0][1] + (colors[1][1] - colors[0][1]) * progress)
|
| 815 |
+
b = int(colors[0][2] + (colors[1][2] - colors[0][2]) * progress)
|
| 816 |
+
return (r, g, b)
|
| 817 |
+
else:
|
| 818 |
+
segment = progress * (len(colors) - 1)
|
| 819 |
+
idx = int(segment)
|
| 820 |
+
local_progress = segment - idx
|
| 821 |
+
if idx >= len(colors) - 1:
|
| 822 |
+
return colors[-1]
|
| 823 |
+
c1, c2 = colors[idx], colors[idx + 1]
|
| 824 |
+
r = int(c1[0] + (c2[0] - c1[0]) * local_progress)
|
| 825 |
+
g = int(c1[1] + (c2[1] - c1[1]) * local_progress)
|
| 826 |
+
b = int(c1[2] + (c2[2] - c1[2]) * local_progress)
|
| 827 |
+
return (r, g, b)
|
| 828 |
+
|
| 829 |
+
def _apply_background_adjustments(background: np.ndarray, bg_config: Dict[str, Any]) -> np.ndarray:
|
| 830 |
+
"""Apply brightness and contrast adjustments to background"""
|
| 831 |
+
try:
|
| 832 |
+
brightness = bg_config.get("brightness", 1.0)
|
| 833 |
+
contrast = bg_config.get("contrast", 1.0)
|
| 834 |
+
|
| 835 |
+
if brightness != 1.0 or contrast != 1.0:
|
| 836 |
+
background = background.astype(np.float32)
|
| 837 |
+
background = background * contrast * brightness
|
| 838 |
+
background = np.clip(background, 0, 255).astype(np.uint8)
|
| 839 |
+
|
| 840 |
+
return background
|
| 841 |
+
|
| 842 |
+
except Exception as e:
|
| 843 |
+
logger.warning(f"Background adjustment failed: {e}")
|
| 844 |
+
return background
|
| 845 |
+
|
| 846 |
+
def validate_video_file(video_path: str) -> Tuple[bool, str]:
|
| 847 |
+
"""Enhanced video file validation with detailed checks"""
|
| 848 |
if not video_path or not os.path.exists(video_path):
|
| 849 |
return False, "Video file not found"
|
| 850 |
+
|
| 851 |
try:
|
| 852 |
+
# Check file size
|
| 853 |
+
file_size = os.path.getsize(video_path)
|
| 854 |
+
if file_size == 0:
|
| 855 |
+
return False, "Video file is empty"
|
| 856 |
+
|
| 857 |
+
if file_size > 2 * 1024 * 1024 * 1024: # 2GB limit
|
| 858 |
+
return False, "Video file too large (>2GB)"
|
| 859 |
+
|
| 860 |
+
# Check with OpenCV
|
| 861 |
cap = cv2.VideoCapture(video_path)
|
| 862 |
if not cap.isOpened():
|
| 863 |
return False, "Cannot open video file"
|
| 864 |
+
|
| 865 |
frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
| 866 |
+
fps = cap.get(cv2.CAP_PROP_FPS)
|
| 867 |
+
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
| 868 |
+
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
| 869 |
+
|
| 870 |
cap.release()
|
| 871 |
+
|
| 872 |
+
# Validation checks
|
| 873 |
+
if frame_count == 0:
|
| 874 |
+
return False, "Video appears to be empty (0 frames)"
|
| 875 |
+
|
| 876 |
+
if fps <= 0 or fps > 120:
|
| 877 |
+
return False, f"Invalid frame rate: {fps}"
|
| 878 |
+
|
| 879 |
+
if width <= 0 or height <= 0:
|
| 880 |
+
return False, f"Invalid resolution: {width}x{height}"
|
| 881 |
+
|
| 882 |
+
if width > 4096 or height > 4096:
|
| 883 |
+
return False, f"Resolution too high: {width}x{height} (max 4096x4096)"
|
| 884 |
+
|
| 885 |
+
duration = frame_count / fps
|
| 886 |
+
if duration > 300: # 5 minutes
|
| 887 |
+
return False, f"Video too long: {duration:.1f}s (max 300s)"
|
| 888 |
+
|
| 889 |
+
return True, f"Valid video: {width}x{height}, {fps:.1f}fps, {duration:.1f}s"
|
| 890 |
+
|
| 891 |
except Exception as e:
|
| 892 |
return False, f"Error validating video: {str(e)}"
|