Custom Detector Code Bug?

Software Python
1

Good day,

The following method can be found in the Custom Detector:

def xywh2abcd(xywh, im_shape):
    output = np.zeros((4, 2))

    # Center / Width / Height -> BBox corners coordinates
    x_min = (xywh[0] - 0.5*xywh[2]) * im_shape[1]
    x_max = (xywh[0] + 0.5*xywh[2]) * im_shape[1]
    y_min = (xywh[1] - 0.5*xywh[3]) * im_shape[0]
    y_max = (xywh[1] + 0.5*xywh[3]) * im_shape[0]

    # A ------ B
    # | Object |
    # D ------ C

    output[0][0] = x_min
    output[0][1] = y_min

    output[1][0] = x_max
    output[1][1] = y_min

    output[2][0] = x_min
    output[2][1] = y_max

    output[3][0] = x_max
    output[3][1] = y_max
    return output

In my opinion, C and D were mixed up there. At least if you look at the sketches for the definition of A, B, C and D.

2

Hi,
Good catch ! Definitions of point C and D are mixed up there. Documentation also specify a clockwise rotation. It should not have any impact on the sample, due to how the camera ingests the bounding box, but it might change in the future, so thank you for notifying us. We will include the change in the next patch.
Stereolabs Support