File size: 4,238 Bytes
543832d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Pure image-processing helpers for the street-scene Space."""

from __future__ import annotations

import csv
from pathlib import Path
from typing import Iterable

import numpy as np
from PIL import Image, ImageOps


MAX_OUTPUT_SIDE = 2048

# Official Cityscapes train-ID palette.
CITYSCAPES_PALETTE: dict[str, tuple[int, int, int]] = {
    "road": (128, 64, 128),
    "sidewalk": (244, 35, 232),
    "building": (70, 70, 70),
    "wall": (102, 102, 156),
    "fence": (190, 153, 153),
    "pole": (153, 153, 153),
    "traffic light": (250, 170, 30),
    "traffic sign": (220, 220, 0),
    "vegetation": (107, 142, 35),
    "terrain": (152, 251, 152),
    "sky": (70, 130, 180),
    "person": (220, 20, 60),
    "rider": (255, 0, 0),
    "car": (0, 0, 142),
    "truck": (0, 0, 70),
    "bus": (0, 60, 100),
    "train": (0, 80, 100),
    "motorcycle": (0, 0, 230),
    "bicycle": (119, 11, 32),
}


def _normalise_label(label: str) -> str:
    return label.lower().replace("_", " ").strip()


def _fallback_color(class_id: int) -> tuple[int, int, int]:
    """Return a deterministic, visually distinct color for an unknown class."""
    return (
        int((37 * class_id + 71) % 205 + 25),
        int((67 * class_id + 29) % 205 + 25),
        int((97 * class_id + 11) % 205 + 25),
    )


def class_color(class_id: int, label: str) -> tuple[int, int, int]:
    return CITYSCAPES_PALETTE.get(_normalise_label(label), _fallback_color(class_id))


def resize_for_output(image: Image.Image, max_side: int = MAX_OUTPUT_SIDE) -> Image.Image:
    """Bound output resolution so large phone photos do not exhaust Space memory."""
    image = ImageOps.exif_transpose(image).convert("RGB")
    width, height = image.size
    longest = max(width, height)
    if longest <= max_side:
        return image

    scale = max_side / longest
    size = (max(1, round(width * scale)), max(1, round(height * scale)))
    resampling = getattr(Image, "Resampling", Image)
    return image.resize(size, resampling.LANCZOS)


def render_segmentation(
    image: Image.Image,
    class_map: np.ndarray,
    id2label: dict[int, str],
    opacity: float,
) -> tuple[Image.Image, Image.Image]:
    """Create a Cityscapes-color mask and an overlay with white boundaries."""
    height, width = class_map.shape
    color_array = np.zeros((height, width, 3), dtype=np.uint8)

    for class_id in np.unique(class_map):
        label = id2label.get(int(class_id), f"class_{int(class_id)}")
        color_array[class_map == class_id] = class_color(int(class_id), label)

    base_array = np.asarray(image, dtype=np.float32)
    overlay_array = (
        base_array * (1.0 - opacity) + color_array.astype(np.float32) * opacity
    ).astype(np.uint8)

    boundaries = np.zeros((height, width), dtype=bool)
    boundaries[1:, :] |= class_map[1:, :] != class_map[:-1, :]
    boundaries[:, 1:] |= class_map[:, 1:] != class_map[:, :-1]
    overlay_array[boundaries] = (255, 255, 255)

    return Image.fromarray(overlay_array), Image.fromarray(color_array)


def build_class_table(
    class_map: np.ndarray,
    id2label: dict[int, str],
    min_share_percent: float,
) -> list[list[object]]:
    """Summarise class coverage in descending order."""
    class_ids, counts = np.unique(class_map, return_counts=True)
    total_pixels = int(class_map.size)
    rows: list[list[object]] = []

    for class_id, count in zip(class_ids, counts):
        share = 100.0 * int(count) / total_pixels
        if share < min_share_percent:
            continue
        label = id2label.get(int(class_id), f"class_{int(class_id)}")
        color = class_color(int(class_id), label)
        rows.append(
            [
                int(class_id),
                label,
                int(count),
                round(share, 2),
                "#{:02X}{:02X}{:02X}".format(*color),
            ]
        )

    rows.sort(key=lambda row: float(row[3]), reverse=True)
    return rows


def write_class_csv(path: Path, rows: Iterable[Iterable[object]]) -> None:
    with path.open("w", newline="", encoding="utf-8") as handle:
        writer = csv.writer(handle)
        writer.writerow(["class_id", "class_name", "pixels", "share_percent", "color"])
        writer.writerows(rows)