View Source ExVision.Types.BBoxWithKeypoints (Ex Vision v0.4.0)
A struct describing the bounding box with keypoints returned by the keypoint detection model.
Summary
Types
A type describing the Bounding Box object.
Types
Exactly like t/1
, but doesn't put any constraints on the label
field:
@type t(label_t) :: %ExVision.Types.BBoxWithKeypoints{ keypoints: %{required(atom()) => %{x: number(), y: number(), score: number()}}, label: label_t, score: number(), x1: number(), x2: number(), y1: number(), y2: number() }
A type describing the Bounding Box object.
Bounding box is a rectangle encompassing the region. When used in object detectors, this box will describe the location of the object in the image. It also includes keypoints. Each keypoint has a predefined atom as its name.
x1
- x componenet of the upper left cornery1
- y componenet of the upper left cornerx2
- x componenet of the lower righty2
- y componenet of the lower rightlabel
- label assigned to this bounding boxscore
- confidence of the preditionkeypoints
- a map where keys are predefined names (represented as atoms) denoting the specific keypoints (body parts). The values associated with each key are another map, which contains the following::x
: The x-coordinate of the keypoint:y
: The y-coordinate of the keypoint:score
: The confidence score of the predicted keypoint
Keypoint atom names include:
:nose
:left_eye
:right_eye
:left_ear
:right_ear
:left_shoulder
:right_shoulder
:left_elbow
:right_elbow
:left_wrist
:right_wrist
:left_hip
:right_hip
:left_knee
:right_knee
:left_ankle
:right_ankle
Functions
Return the height of the bounding box
Return the width of the bounding box