def NMSIndices(self,
bboxes,
scores,
max_output_size,
nms_iou_threshold=0.3,
score_threshold=0.01):
"""Apply NMS to a series of 3d bounding boxes in 7-DOF format.
Args:
bboxes: A [num_boxes, 7] floating point Tensor of bounding boxes in [x, y,
z, dx, dy, dz, phi] format.
scores: A [num_boxes] floating point Tensor containing box
scores.
max_output_size: Maximum number of boxes to predict per input.
nms_iou_threshold: IoU threshold to use when determining whether two boxes
overlap for purposes of suppression.
score_threshold: The score threshold passed to NMS that allows NMS to
quickly ignore irrelevant boxes.
Returns:
The NMS indices and the mask of the padded indices.
"""
bboxes = py_utils.HasShape(bboxes, [-1, 7])
# Extract x, y, w, h, then convert to extrema.
#
# Note that we drop the rotation angle because we don't have an NMS
# operation that takes rotation into account.
bboxes_2d = tf.stack(
[bboxes[:, 0], bboxes[:, 1], bboxes[:, 3], bboxes[:, 4]], axis=-1)
bboxes_extrema = geometry.XYWHToBBoxes(bboxes_2d)
# Compute NMS with padding; we use the padded version so this function can
# be used in a map_fn. This function returns the scalar number of boxes
# for each example.
#
# We use an IoU threshold of 0.3 since our anchor boxes have rotations
# that make the default IoU threshold of 0.5 possibly too high.
nms_index_padded, num_valid = tf.image.non_max_suppression_padded(
bboxes_extrema,
scores,
iou_threshold=nms_iou_threshold,
max_output_size=max_output_size,
score_threshold=score_threshold,
pad_to_max_output_size=True)
# Return the mask of valid indices instead of just a scalar number.
mask = tf.concat(
[tf.ones([num_valid]),
tf.zeros([max_output_size - num_valid])],
axis=0)
nms_index_padded = tf.where(mask > 0, nms_index_padded,
tf.zeros_like(nms_index_padded))
return nms_index_padded, mask
def testXYWHBBoxesCentroid(self):
with self.session():
xywh = np.tile(
np.array([[[10, 20, 8, 6], [0, 0, 0, 0], [-10, -20, 2.4, 3.6]]]),
(3, 2, 1))
bboxes = np.tile(
np.array([[[17, 6, 23, 14], [0, 0, 0, 0], [-21.8, -11.2, -18.2,
-8.8]]]), (3, 2, 1))
centroid = np.tile(np.array([[[10, 20], [0, 0], [-10, -20]]]), (3, 2, 1))
print('shapes = ', xywh.shape, bboxes.shape, centroid.shape)
self.assertAllClose(geometry.XYWHToBBoxes(xywh).eval(), bboxes)
self.assertAllClose(geometry.BBoxesToXYWH(bboxes).eval(), xywh)
self.assertAllClose(geometry.BBoxesCentroid(bboxes).eval(), centroid)
