File size: 6,425 Bytes
c46c3d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6cc84ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c46c3d9
 
 
 
 
 
 
 
 
 
6cc84ea
c46c3d9
6cc84ea
 
 
 
 
c46c3d9
 
 
 
 
 
 
 
 
 
 
 
 
6cc84ea
c46c3d9
 
6cc84ea
 
 
 
 
 
 
 
c46c3d9
6cc84ea
 
 
 
 
 
c46c3d9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Rendering and summary helpers for street-scene object detection."""

from __future__ import annotations

import csv
from collections import defaultdict
from pathlib import Path
from typing import Iterable

from PIL import Image, ImageDraw, ImageFont


STREET_OBJECT_GROUPS: dict[str, set[str]] = {
    "people": {"person"},
    "active_mobility": {"person", "bicycle"},
    "motor_vehicles": {"car", "motorcycle", "bus", "truck", "train"},
    "all_transport": {
        "bicycle",
        "car",
        "motorcycle",
        "bus",
        "truck",
        "train",
    },
}


def _load_font(size: int) -> ImageFont.ImageFont:
    candidates = (
        "/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf",
        "/usr/share/fonts/truetype/liberation/LiberationSans-Regular.ttf",
        "/System/Library/Fonts/Helvetica.ttc",
    )
    for candidate in candidates:
        try:
            return ImageFont.truetype(candidate, size)
        except (OSError, IOError):
            continue
    return ImageFont.load_default()


def detection_color(class_id: int) -> tuple[int, int, int]:
    """Return a stable, high-contrast color for a COCO class ID."""
    return (
        int((67 * class_id + 37) % 190 + 40),
        int((97 * class_id + 71) % 190 + 40),
        int((43 * class_id + 113) % 190 + 40),
    )


def _boxes_overlap(
    first: tuple[float, float, float, float],
    second: tuple[float, float, float, float],
) -> bool:
    return not (
        first[2] <= second[0]
        or second[2] <= first[0]
        or first[3] <= second[1]
        or second[3] <= first[1]
    )


def _label_box(
    object_box: list[float],
    label_width: float,
    label_height: float,
    image_size: tuple[int, int],
    occupied: list[tuple[float, float, float, float]],
) -> tuple[float, float, float, float]:
    """Place a label near its object while avoiding earlier labels."""
    image_width, image_height = image_size
    center_x = (object_box[0] + object_box[2]) / 2
    x = max(0.0, min(center_x - label_width / 2, image_width - label_width))

    candidates: list[tuple[float, float, float, float]] = []
    for slot in range(7):
        bottom = object_box[1] - 4 - slot * (label_height + 4)
        top = bottom - label_height
        if top >= 0:
            candidates.append((x, top, x + label_width, bottom))
    for slot in range(4):
        top = object_box[3] + 4 + slot * (label_height + 4)
        bottom = top + label_height
        if bottom <= image_height:
            candidates.append((x, top, x + label_width, bottom))

    for candidate in candidates:
        if not any(_boxes_overlap(candidate, used) for used in occupied):
            return candidate
    return candidates[0] if candidates else (x, 0.0, x + label_width, label_height)


def render_detection(
    image: Image.Image,
    detections: Iterable[dict[str, object]],
) -> Image.Image:
    """Draw labeled bounding boxes on a copy of the input image."""
    rendered = image.convert("RGB").copy()
    draw = ImageDraw.Draw(rendered)
    short_side = min(rendered.size)
    line_width = max(2, round(short_side / 320))
    font = _load_font(max(13, min(24, round(short_side / 55))))
    occupied_labels: list[tuple[float, float, float, float]] = []

    ordered_detections = sorted(
        detections,
        key=lambda item: (float(item["x1"]), float(item["y1"])),
    )
    for detection in ordered_detections:
        class_id = int(detection["class_id"])
        color = detection_color(class_id)
        box = [
            float(detection["x1"]),
            float(detection["y1"]),
            float(detection["x2"]),
            float(detection["y2"]),
        ]
        label = (
            f"{detection['class_name']} "
            f"{float(detection['confidence']):.2f}"
        )
        draw.rectangle(box, outline=color, width=line_width)
        text_box = draw.textbbox((0, 0), label, font=font)
        text_height = text_box[3] - text_box[1]
        text_width = text_box[2] - text_box[0]
        background = _label_box(
            box,
            text_width + 8,
            text_height + 8,
            rendered.size,
            occupied_labels,
        )
        occupied_labels.append(background)
        draw.rectangle(background, fill=color)
        draw.text(
            (background[0] + 4, background[1] + 4),
            label,
            fill="white",
            font=font,
        )

    return rendered


def build_detection_summary(
    detections: Iterable[dict[str, object]],
) -> list[list[object]]:
    """Aggregate detection counts and confidence by class."""
    grouped: dict[str, list[float]] = defaultdict(list)
    for detection in detections:
        grouped[str(detection["class_name"])].append(
            float(detection["confidence"])
        )

    rows = [
        [class_name, len(confidences), round(sum(confidences) / len(confidences), 3), round(max(confidences), 3)]
        for class_name, confidences in grouped.items()
    ]
    rows.sort(key=lambda row: (-int(row[1]), str(row[0])))
    return rows


def build_detection_table(
    detections: Iterable[dict[str, object]],
) -> list[list[object]]:
    """Build one exportable row per bounding box."""
    rows: list[list[object]] = []
    for index, detection in enumerate(detections, start=1):
        rows.append(
            [
                index,
                str(detection["class_name"]),
                round(float(detection["confidence"]), 3),
                round(float(detection["x1"]), 1),
                round(float(detection["y1"]), 1),
                round(float(detection["x2"]), 1),
                round(float(detection["y2"]), 1),
            ]
        )
    return rows


def build_street_indicators(
    detections: Iterable[dict[str, object]],
) -> dict[str, int]:
    """Derive transparent street-scene counts from visible COCO objects."""
    class_names = [str(detection["class_name"]) for detection in detections]
    return {
        name: sum(class_name in members for class_name in class_names)
        for name, members in STREET_OBJECT_GROUPS.items()
    }


def write_detection_csv(
    path: Path,
    rows: Iterable[Iterable[object]],
) -> None:
    with path.open("w", newline="", encoding="utf-8") as handle:
        writer = csv.writer(handle)
        writer.writerow(["object_id", "class", "confidence", "x1", "y1", "x2", "y2"])
        writer.writerows(rows)