Crop bounding boxes
[___] = bboxcrop(___,
specifies options using one or more name-value arguments in addition to any combination of
arguments from previous syntaxes. For example,
the positive overlap threshold to
Center Crop Image and Corresponding Bounding Boxes
Read an image.
I = imread('peppers.png');
Define bounding boxes and labels.
bboxA = [ 410 230 100 90 186 78 80 60 ]
bboxA = 2×4 410 230 100 90 186 78 80 60
labelsA = [ "garlic" "onion" ];
Create a center cropping window.
targetSize = [256 256]; win = centerCropWindow2d(size(I),targetSize);
Center crop the image.
[r,c] = deal(win.YLimits(1):win.YLimits(2),win.XLimits(1):win.XLimits(2)); J = I(r,c,:);
Center crop boxes and labels. Boxes outside the cropping window are removed.
[bboxB,indices] = bboxcrop(bboxA,win); labelsB = labelsA(indices);
Display the results.
figure I = insertObjectAnnotation(I,'Rectangle',bboxA,labelsA); J = insertObjectAnnotation(J,'Rectangle',bboxB,labelsB); imshowpair(I,J,'montage')
bboxA — Bounding boxes
M-by-4 matrix | M-by-5 matrix | M-by-9 matrix
Bounding boxes, specified as an M-by-4, M-by-5, or M-by-9 nonsparse numeric matrix. M is the number of bounding boxes. Each row of the matrix defines a bounding box as either an axis-aligned rectangle, a rotated rectangle, or a cuboid. This table describes the format for each bounding box.
Defined in spatial coordinates as an M-by-4 numeric matrix with rows of the form [x y w h], where:
Defined in spatial coordinates as an M-by-5 numeric matrix with rows of the form [xctr yctr xlen ylen yaw], where:
Defined in spatial coordinates as an M-by-9 numeric matrix with rows of the form [xctr yctr zctr xlen ylen zlen xrot yrot zrot], where:
The figure shows how these values determine the position of a cuboid.
window — Cropping window
four-element vector (default) |
images.spatialref.Rectangle | six-element vector |
images.spatialref.Cuboid | numeric | image
Cropping window, specified as a four-element vector, a six-element vector, or a
Cuboid object. The
output bounding box positions are relative to the location of the cropping
When you specify
bboxA as a cuboid, the cropping window must be
a six-element vector in the format
Specify optional pairs of arguments as
the argument name and
Value is the corresponding value.
Name-value arguments must appear after other arguments, but the order of the
pairs does not matter.
Before R2021a, use commas to separate each name and value, and enclose
Name in quotes.
OverlapThreshold=1, sets the positive overlap threshold to
OverlapThreshold — Overlap threshold
1 (default) | positive scalar less than or equal to
If the computed overlap value is greater than the value of the
threshold property, then the boxes are clipped to the bounding
rectangle border. Otherwise, the boxes are discarded. Lowering the threshold can
result in parts of the object getting discarded.
bboxB — Cropped bounding boxes
M2-by-N matrix | nonsparse numeric
Cropped bounding boxes, returned as an M2-by-N
matrix of M2 bounding boxes. The number of bounding boxes returned is
less than the number of bounding boxes in the input. Each row, M2, of
the matrix defines one bounding box of the same type as the input
bboxA. The output bounding box positions are relative to the
location of the cropping window.
indices — Indices
vector of integers
Indices, returned as a vector of integers. The indices indicate which bounding boxes
in the input,
bboxA, are within the cropping window.
Version HistoryIntroduced in R2019b
R2022a: Bounding Box Coordinates: Data augmentation for object detection using spatial coordinates
Behavior changed in R2022a