okooooooo/supervision
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2006 from roboflow/feature/xyxy_to_mask

Browse Source 
Feature/xyxy to mask
This commit is contained in:
Piotr Skalski authored and GitHub committed 2025-11-05 13:23:13 +01:00
2 parents 171687f3ab 89ee57f519
commit b02ec93b30
5 files changed
+245 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/detection/utils/converters.md
+6
View File
@@ -58,3 +58,9 @@ status: new
</div>
:::supervision.detection.utils.converters.polygon_to_xyxy
<div class="md-typeset">
<h2><a href="#supervision.detection.utils.converters.xyxy_to_mask">xyxy_to_mask</a></h2>
</div>
:::supervision.detection.utils.converters.xyxy_to_mask
pyproject.toml
+1 -1
View File
@@ -2,7 +2,7 @@
name = "supervision"
description = "A set of easy-to-use utils that will come in handy in any Computer Vision project"
license = { text = "MIT" }
version = "0.27.0rc1"
version = "0.27.0rc2"
readme = "README.md"
requires-python = ">=3.9"
authors = [
supervision/__init__.py
+2
View File
@@ -65,6 +65,7 @@ from supervision.detection.utils.converters import (
polygon_to_xyxy,
xcycwh_to_xyxy,
xywh_to_xyxy,
xyxy_to_mask,
xyxy_to_polygons,
xyxy_to_xcycarh,
xyxy_to_xywh,
@@ -249,6 +250,7 @@ __all__ = [
"tint_image",
"xcycwh_to_xyxy",
"xywh_to_xyxy",
"xyxy_to_mask",
"xyxy_to_polygons",
"xyxy_to_xcycarh",
"xyxy_to_xywh",
supervision/detection/utils/converters.py
+64
View File
@@ -229,6 +229,70 @@ def mask_to_xyxy(masks: np.ndarray) -> np.ndarray:
return xyxy
def xyxy_to_mask(boxes: np.ndarray, resolution_wh: tuple[int, int]) -> np.ndarray:
"""
Converts a 2D `np.ndarray` of bounding boxes into a 3D `np.ndarray` of bool masks.
Parameters:
boxes (np.ndarray): A 2D `np.ndarray` of shape `(N, 4)`
containing bounding boxes `(x_min, y_min, x_max, y_max)`
resolution_wh (Tuple[int, int]): A tuple `(width, height)` specifying
the resolution of the output masks
Returns:
np.ndarray: A 3D `np.ndarray` of shape `(N, height, width)`
containing 2D bool masks for each bounding box
Examples:
```python
import numpy as np
import supervision as sv
boxes = np.array([[0, 0, 2, 2]])
sv.xyxy_to_mask(boxes, (5, 5))
# array([
# [[ True, True, True, False, False],
# [ True, True, True, False, False],
# [ True, True, True, False, False],
# [False, False, False, False, False],
# [False, False, False, False, False]]
# ])
boxes = np.array([[0, 0, 1, 1], [3, 3, 4, 4]])
sv.xyxy_to_mask(boxes, (5, 5))
# array([
# [[ True, True, False, False, False],
# [ True, True, False, False, False],
# [False, False, False, False, False],
# [False, False, False, False, False],
# [False, False, False, False, False]],
#
# [[False, False, False, False, False],
# [False, False, False, False, False],
# [False, False, False, False, False],
# [False, False, False, True, True],
# [False, False, False, True, True]]
# ])
```
"""
width, height = resolution_wh
n = boxes.shape[0]
masks = np.zeros((n, height, width), dtype=bool)
for i, (x_min, y_min, x_max, y_max) in enumerate(boxes):
x_min = max(0, int(x_min))
y_min = max(0, int(y_min))
x_max = min(width - 1, int(x_max))
y_max = min(height - 1, int(y_max))
if x_max >= x_min and y_max >= y_min:
masks[i, y_min : y_max + 1, x_min : x_max + 1] = True
return masks
def mask_to_polygons(mask: np.ndarray) -> list[np.ndarray]:
"""
Converts a binary mask to a list of polygons.
test/detection/utils/test_converters.py
+172
View File
@@ -6,6 +6,7 @@ import pytest
from supervision.detection.utils.converters import (
xcycwh_to_xyxy,
xywh_to_xyxy,
xyxy_to_mask,
xyxy_to_xcycarh,
xyxy_to_xywh,
)
@@ -129,3 +130,174 @@ def test_xyxy_to_xcycarh(xyxy: np.ndarray, expected_result: np.ndarray) -> None:
def test_xcycwh_to_xyxy(xcycwh: np.ndarray, expected_result: np.ndarray) -> None:
result = xcycwh_to_xyxy(xcycwh)
np.testing.assert_array_equal(result, expected_result)
@pytest.mark.parametrize(
"boxes,resolution_wh,expected",
[
# 0) Empty input
(
np.array([], dtype=float).reshape(0, 4),
(5, 4),
np.array([], dtype=bool).reshape(0, 4, 5),
),
# 1) Single pixel box
(
np.array([[2, 1, 2, 1]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, False, False],
[False, False, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 2) Horizontal line, inclusive bounds
(
np.array([[1, 2, 3, 2]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, False, False],
[False, False, False, False, False],
[False, True, True, True, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 3) Vertical line, inclusive bounds
(
np.array([[3, 0, 3, 2]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, True, False],
[False, False, False, True, False],
[False, False, False, True, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 4) Proper rectangle fill
(
np.array([[1, 1, 3, 2]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, False, False],
[False, True, True, True, False],
[False, True, True, True, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 5) Negative coordinates clipped to [0, 0]
(
np.array([[-2, -1, 1, 1]], dtype=float),
(5, 4),
np.array(
[
[
[True, True, False, False, False],
[True, True, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 6) Overflow coordinates clipped to width-1 and height-1
(
np.array([[3, 2, 10, 10]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, True, True],
[False, False, False, True, True],
]
],
dtype=bool,
),
),
# 7) Invalid box where max < min after ints, mask stays empty
(
np.array([[3, 2, 1, 4]], dtype=float),
(5, 4),
np.array(
[
[
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 8) Fractional coordinates are floored by int conversion
# (0.2,0.2)-(2.8,1.9) -> (0,0)-(2,1)
(
np.array([[0.2, 0.2, 2.8, 1.9]], dtype=float),
(5, 4),
np.array(
[
[
[True, True, True, False, False],
[True, True, True, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
]
],
dtype=bool,
),
),
# 9) Multiple boxes, separate masks
(
np.array([[0, 0, 1, 0], [2, 1, 4, 3]], dtype=float),
(5, 4),
np.array(
[
# Box 0: row 0, cols 0..1
[
[True, True, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
[False, False, False, False, False],
],
# Box 1: rows 1..3, cols 2..4
[
[False, False, False, False, False],
[False, False, True, True, True],
[False, False, True, True, True],
[False, False, True, True, True],
],
],
dtype=bool,
),
),
],
)
def test_xyxy_to_mask(boxes: np.ndarray, resolution_wh, expected: np.ndarray) -> None:
result = xyxy_to_mask(boxes, resolution_wh)
assert result.dtype == np.bool_
assert result.shape == expected.shape
np.testing.assert_array_equal(result, expected)