point

The VisionAI format provides the points (2D) shape “point2d“ to describe individual objects. They can be expressed as an array of x and y-coordinate.

Example

"point2d": [{
        "name": "point2d_shape",
        "val": [400, 200],
        "stream": "camera1",
        "attributes" : {
            "boolean" : [{
                    "name" : "visible",
                    "val" : false
                }, {
                    "name" : "occluded",
                    "val" : false
                }
            ],
            "text" : [{
                    "name" : "brand",
                    "val" : "toyota"
                }, {
                    "name" : "color",
                    "val" : "red"
                }
            ]
        }
    ]
}

Schema

name	description	type	unit	required
${OBJECT_TYPE}	The name of this type. This case is “point2d”.	object	-	true
name	The name of this point2d. Usually to be "point2d_shape".	string	-	true
val	Meanings of each element in order. X-coordinate is at the element with odd order. Y-coordinate is at the even one.	even number elements array of int	px	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

<準備一張圖>

---

Use Case

point

To describe a point dataset with one camera sensor:

• sensor: camera (#camera1)

• ontology:

  • face

  • eye

  • mouth

  • nose

  • ear

Example Code

pagepoint