File size: 10,687 Bytes
e1c010e | 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 | """
Visualization Module — Annotates images with detection results
and action plan overlays using OpenCV.
Provides two visualization modes:
1. **Detection overlay** — All detected objects with labels + confidence.
2. **Action overlay** — Source/destination bounding boxes, arrow, and steps.
"""
import logging
from typing import Any
import cv2
import numpy as np
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Color palette (BGR for OpenCV)
# ---------------------------------------------------------------------------
COLOR_GREEN = (0, 200, 0)
COLOR_RED = (0, 0, 220)
COLOR_YELLOW = (0, 220, 220)
COLOR_CYAN = (220, 200, 0)
COLOR_WHITE = (255, 255, 255)
COLOR_BLACK = (0, 0, 0)
COLOR_ORANGE = (0, 140, 255)
COLOR_BLUE = (255, 100, 0)
# Distinct palette for detection overlay
_DETECTION_COLORS = [
COLOR_GREEN,
COLOR_CYAN,
COLOR_YELLOW,
COLOR_ORANGE,
COLOR_BLUE,
COLOR_RED,
(200, 0, 200), # magenta
(100, 200, 100), # light green
]
class ActionVisualizer:
"""
Draws visual annotations on images for detection results and action plans.
"""
# ------------------------------------------------------------------
# Detection Overlay
# ------------------------------------------------------------------
def draw_detections(
self,
image: np.ndarray,
detections: list[dict[str, Any]],
) -> np.ndarray:
"""
Draw all detected objects on the image with labels and confidence.
Args:
image: Input image (H, W, C) as NumPy array.
detections: List of detection dicts from the vision module.
Returns:
Annotated copy of the image.
"""
if image is None or not isinstance(image, np.ndarray):
logger.error("Invalid image for detection visualization.")
return image if image is not None else np.zeros((400, 600, 3), dtype=np.uint8)
annotated = image.copy()
if not detections:
logger.info("No detections to visualize.")
self._put_centered_text(annotated, "No objects detected")
return annotated
for idx, det in enumerate(detections):
color = _DETECTION_COLORS[idx % len(_DETECTION_COLORS)]
bbox = det.get("bbox", [])
label = det.get("label", "unknown")
confidence = det.get("confidence", 0.0)
if len(bbox) != 4:
continue
x1, y1, x2, y2 = [int(c) for c in bbox]
# Draw bounding box
cv2.rectangle(annotated, (x1, y1), (x2, y2), color, 2)
# Label with confidence
text = f"{label} ({confidence:.2f})"
text_size = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.6, 2)[0]
# Background rectangle for text
cv2.rectangle(
annotated,
(x1, y1 - text_size[1] - 10),
(x1 + text_size[0] + 6, y1),
color,
-1,
)
cv2.putText(
annotated,
text,
(x1 + 3, y1 - 5),
cv2.FONT_HERSHEY_SIMPLEX,
0.6,
COLOR_WHITE,
2,
)
logger.info("Detection overlay drawn with %d objects.", len(detections))
return annotated
# ------------------------------------------------------------------
# Action Overlay
# ------------------------------------------------------------------
def visualize(
self,
image: np.ndarray,
action_plan: dict[str, Any],
) -> np.ndarray:
"""
Draw the action plan overlay: source/destination boxes, arrow,
and step labels.
Args:
image: Input image.
action_plan: Dict from the ActionPlanner containing
``source_bbox``, ``dest_bbox``, ``steps``, etc.
Returns:
Annotated copy of the image.
"""
if image is None or not isinstance(image, np.ndarray):
logger.error("Invalid image for action visualization.")
return image if image is not None else np.zeros((400, 600, 3), dtype=np.uint8)
annotated = image.copy()
source_bbox = action_plan.get("source_bbox")
dest_bbox = action_plan.get("dest_bbox")
steps = action_plan.get("steps", [])
status = action_plan.get("status", "unknown")
# Draw source bounding box (green)
if source_bbox and len(source_bbox) == 4:
self._draw_highlighted_box(
annotated, source_bbox, COLOR_GREEN, "SOURCE"
)
# Draw destination bounding box (red)
if dest_bbox and len(dest_bbox) == 4:
self._draw_highlighted_box(
annotated, dest_bbox, COLOR_RED, "DESTINATION"
)
# Draw arrow from source to destination
if source_bbox and dest_bbox:
self._draw_action_arrow(annotated, source_bbox, dest_bbox)
# Draw step annotations
self._draw_steps_overlay(annotated, steps, status)
logger.info("Action visualization drawn (status=%s).", status)
return annotated
# ------------------------------------------------------------------
# Drawing helpers
# ------------------------------------------------------------------
@staticmethod
def _draw_highlighted_box(
image: np.ndarray,
bbox: list[int],
color: tuple,
label: str,
) -> None:
"""Draw a highlighted bounding box with a corner-style frame."""
x1, y1, x2, y2 = [int(c) for c in bbox]
thickness = 3
# Semi-transparent overlay
overlay = image.copy()
cv2.rectangle(overlay, (x1, y1), (x2, y2), color, -1)
cv2.addWeighted(overlay, 0.15, image, 0.85, 0, image)
# Solid border
cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)
# Corner accents (L-shaped)
corner_len = min(30, (x2 - x1) // 4, (y2 - y1) // 4)
ct = thickness + 1
# Top-left
cv2.line(image, (x1, y1), (x1 + corner_len, y1), color, ct)
cv2.line(image, (x1, y1), (x1, y1 + corner_len), color, ct)
# Top-right
cv2.line(image, (x2, y1), (x2 - corner_len, y1), color, ct)
cv2.line(image, (x2, y1), (x2, y1 + corner_len), color, ct)
# Bottom-left
cv2.line(image, (x1, y2), (x1 + corner_len, y2), color, ct)
cv2.line(image, (x1, y2), (x1, y2 - corner_len), color, ct)
# Bottom-right
cv2.line(image, (x2, y2), (x2 - corner_len, y2), color, ct)
cv2.line(image, (x2, y2), (x2, y2 - corner_len), color, ct)
# Label above box
text_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)[0]
cv2.rectangle(
image,
(x1, y1 - text_size[1] - 14),
(x1 + text_size[0] + 10, y1 - 2),
color,
-1,
)
cv2.putText(
image,
label,
(x1 + 5, y1 - 7),
cv2.FONT_HERSHEY_SIMPLEX,
0.7,
COLOR_WHITE,
2,
)
@staticmethod
def _draw_action_arrow(
image: np.ndarray,
source_bbox: list[int],
dest_bbox: list[int],
) -> None:
"""Draw a curved arrow from the source centre to the destination centre."""
sx = (source_bbox[0] + source_bbox[2]) // 2
sy = (source_bbox[1] + source_bbox[3]) // 2
dx = (dest_bbox[0] + dest_bbox[2]) // 2
dy = (dest_bbox[1] + dest_bbox[3]) // 2
# Draw a dashed path then a solid arrowhead
mid_x = (sx + dx) // 2
mid_y = min(sy, dy) - 40 # curve above
# Bezier-approximated curve via polyline
pts: list[tuple[int, int]] = []
for t_i in range(21):
t = t_i / 20.0
px = int((1 - t) ** 2 * sx + 2 * (1 - t) * t * mid_x + t ** 2 * dx)
py = int((1 - t) ** 2 * sy + 2 * (1 - t) * t * mid_y + t ** 2 * dy)
pts.append((px, py))
for i in range(len(pts) - 1):
# Dashed effect: draw every other segment
if i % 2 == 0:
cv2.line(image, pts[i], pts[i + 1], COLOR_ORANGE, 3)
# Arrowhead at destination
cv2.arrowedLine(
image, pts[-3], (dx, dy), COLOR_ORANGE, 3, tipLength=0.3
)
# "ACTION" label at midpoint
cv2.putText(
image,
"ACTION",
(mid_x - 30, mid_y - 10),
cv2.FONT_HERSHEY_SIMPLEX,
0.6,
COLOR_ORANGE,
2,
)
@staticmethod
def _draw_steps_overlay(
image: np.ndarray,
steps: list[str],
status: str,
) -> None:
"""Draw the steps list as a semi-transparent panel at the bottom."""
if not steps:
return
h, w = image.shape[:2]
line_height = 28
panel_height = len(steps) * line_height + 20
panel_top = h - panel_height
# Semi-transparent dark panel
overlay = image.copy()
cv2.rectangle(overlay, (0, panel_top), (w, h), COLOR_BLACK, -1)
cv2.addWeighted(overlay, 0.7, image, 0.3, 0, image)
# Status badge
status_color = (
COLOR_GREEN
if status == "success"
else COLOR_YELLOW if status == "partial" else COLOR_RED
)
cv2.putText(
image,
f"Status: {status.upper()}",
(10, panel_top + 20),
cv2.FONT_HERSHEY_SIMPLEX,
0.5,
status_color,
2,
)
# Steps text
for i, step in enumerate(steps):
y = panel_top + 20 + (i + 1) * line_height
# Truncate long steps
display_step = step if len(step) < 80 else step[:77] + "..."
cv2.putText(
image,
display_step,
(10, y),
cv2.FONT_HERSHEY_SIMPLEX,
0.5,
COLOR_WHITE,
1,
)
@staticmethod
def _put_centered_text(
image: np.ndarray,
text: str,
color: tuple = COLOR_WHITE,
) -> None:
"""Put centred text on the image."""
h, w = image.shape[:2]
text_size = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 1.0, 2)[0]
x = (w - text_size[0]) // 2
y = (h + text_size[1]) // 2
cv2.putText(image, text, (x, y), cv2.FONT_HERSHEY_SIMPLEX, 1.0, color, 2)
|