Method for Training a Machine Learning Algorithm to Assign a Confidence Value to Each of a Plurality of Object Detection Results
AssigneeRobert Bosch GmbH
InventorKoba Natroshvili
Life of this patent
Estimating the term…
Loading patent…
AssigneeRobert Bosch GmbH
InventorKoba Natroshvili
Estimating the term…
A method is for training a machine-learning algorithm to assign a confidence value to each of a plurality of object detection results. The method includes providing training data for training the machine-learning algorithm. The training data includes a plurality of object detection results. The plurality of object detection results respectively denote the same object. Each of the plurality of object detection results is based on a different combination of object detections generated based on sensor data from at least two different sensors, as well as ground truth information regarding the object.
A method for training a machine-learning algorithm to assign a confidence value to each of a plurality of object detection results, the method comprising:
A control device for training a machine-learning algorithm to assign a confidence value to each of a plurality of object detection results, and the control device comprising:
Dependencies are inferred from the claim text.