cuboid
Last updated
Last updated
A 3D bounding box is a cuboid in 3D Euclidean space. It is defined by position, rotation, and size. Position and size are defined as 3-vectors, while rotation can be expressed in two alternative forms, using 4-vector quaternion notation or 3-vector Euler notation (to be applied in ZYX order equivalent to yaw-pitch-roll order).
${OBJECT_TYPE}
The name of this type. This case is “cuboid”.
object
-
true
name
The name of this bounding box. Usually to be "cuboid_shape"
string
-
true
val
Meanings of each element in order as a 9-dimensional vector [x, y, z, rx, ry, rz, sx, sy, sz]. Please refer to the table below.
9 elements array of int
as below
true
stream
Represents which stream this shape is on.
string
-
true
confidence_score
The confidence score of model prediction of this object. Ground truth does not have this attribute.
number
-
false
attributes
attributes this bounding box has
object
-
false
x
x-coordinate of the cuboid center
m
y
y-coordinate of the cuboid center
m
z
z-coordinate of the cuboid center
m
rx
rotation on x direction, Euler angles, rx = roll.
rad
ry
rotation on y direction, Euler angles, ry = pitch.
rad
rz
rotation on z direction, Euler angles, rz = yaw.
rad
sx
size x dimension of the cuboid in x-coordinate
m
sy
size y dimension of the cuboid in y-coordinate
m
sz
size z dimension of the cuboid in z-coordinate
m
<準備一張圖>
Position and size are defined as 3-vectors, while rotation can be expressed in two alternative forms, using 4-vector quaternion notation or 3-vector Euler notation (to be applied in ZYX order equivalent to yaw-pitch-roll order).
To describe a dataset with one camera sensor (bbox annotation) and one lidar sensor (cuboid annotation) in the coordinate system of iso8855-1:
sensor: camera (#camera1), lidar (#lidar1)
ontology:
people
ischild - boolean (static info)
direction - front, left, right, back (dynamic info)
age - number (static info)
car
color - white, silver, blue, red, black (static info)
truck
bus
Example Code