bboxcrop

Crop bounding boxes

collapse all in page

Syntax

bboxB = bboxcrop(bboxA,window)
[bboxB,indices] = bboxcrop(bboxA,window)
[___] = bboxcrop(___,'OverlapThreshold',threshold)

Description

example

bboxB = bboxcrop(bboxA,window) crops bounding boxes from a set of input bounding boxes, bboxA, located in the cropping area, window.

[bboxB,indices] = bboxcrop(bboxA,window) additionally returns a vector of indices that indicate which bounding boxes in bboxA are within the cropping window, window.

[___] = bboxcrop(___,'OverlapThreshold',threshold) additionally sets an overlap threshold.

Examples

collapse all

Open Live Script

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')

Input Arguments

collapse all

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 rotate rectangle, or a cuboid. This table describes the format for each bounding box.

Bounding BoxRowDescription
Axis-aligned rectangle[xmin, ymin, width, height]This type of bounding box is defined in pixel coordinates as an M-by-4 matrix representing M bounding boxes
Rotated rectangle[xcenter, ycenter, width, height, yaw]This type of bounding box is defined in spatial coordinates as an M-by-5 matrix representing M bounding boxes. The xcenter and ycenter coordinates represent the center of the bounding box. The width and height elements represent the length of the box along the x and y axes, respectively. The yaw represents the rotation angle in degrees. The amount of rotation about the center of the bounding box is measured in the clockwise direction.
Cuboid[xcenter, ycenter, zcenter, width, height, depth, rx, ry, rz]Defined in spatial coordinates as an M-by-9 matrix representing M bounding boxes. The xcenter, ycenter, and ycenter coordinates represent the center of the bounding box. The width and height elements represent the length of the box along the x and y axes, respectively. The rx,ry, and rz rotation angles are in degrees about the cuboid center. The rotation is positive in the clockwise direction, with respect to the positive direction of the axis.

Rotation matrices are computed assuming ZYX order Euler angles [rx, ry, rz].

Crop window, specified as a four-element vector or an images.spatialref.Cuboid object.

When you specify bboxA as a rectangular input, the cropping window must be a four-element vector in the format [x,y,width,height].

When you specify bboxA as a cuboid, the cropping window must be an images.spatialref.Cuboid object.

Overlap threshold, specified positive scalar less than or equal to 1. The amount of overlap between transformed boxes and the area defined by the output view is defined as:

area(bbox intersect bounding rectangle) / area(bbox)

  • bounding rectangle — Defined by the input spatial reference object, ref.

  • bbox — Result of transforming boxes in bboxA.

If the computed overlap value is greater than the value of the threshold property, then the transformed 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.

Output Arguments

collapse all

Warped 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.

Indices, returned as a vector of integers. The indices indicate which bounding boxes in the input, bboxA, are within the cropping window.

See Also

| |

Introduced in R2019b

Computer Vision Toolbox Documentation
Support