Method and apparatus for determining and classifying at least one object in a sensing area of a sensor
AssigneeCariad SE
InventorMartin Schumann
Life of this patent
Estimating the term…
Abstract
In a method for determining and classifying at least one object in a sensing area of a sensor, a two- or three-dimensional image of the sensing area is captured by means of the sensor. Sensor data corresponding to the image is generated. The object in the image is determined by means of the sensor data and by means of first template data of at least one first template object using a neural network. The neural network has been trained using the first template data. The first template data corresponds to an image of the first template object. At least one first object class is associated with the first template object. The object is classified by the neural network determining whether the object belongs to the first object class or not.
Claims13
A method for determining and classifying at least one object in a sensing area of at least one sensor, comprising:
- capturing a two- or three-dimensional image of the sensing area using the at least one sensor,
- generating sensor data corresponding to the image, and
- determining the object in the image using the sensor data and first template data of at least one first template object using a neural network,
- wherein the neural network has been trained using the first template data,
- wherein the first template data corresponds to an image of the first template object,
- wherein at least a first object class is assigned to the first template object, and
- wherein the object is classified by the neural network determining whether the object is to be assigned to the first object class or not to be assigned to the first object class.
An apparatus for determining and classifying at least one object in a sensing area of at least one sensor, apparatus comprising:
- the sensor, which is designed to sense a two- or three-dimensional image of the sensing area,
- an image processing and evaluation unit, which is designed to generate sensor data corresponding to the image, and determine the object in the image using the sensor data and first template data of at least a first template object using a neural network,
- wherein the neural network as been trained using the first template data,
- wherein the first template data corresponds to an image of the first template object,
- wherein at least a first object class is assigned to the first template object, and
- wherein the object is classified by the neural network determining whether the object is to be assigned to the first object class or not to the first object class.
Dependencies are inferred from the claim text.