Object tracking by unsupervised learning
First Claim
Patent Images
1. A method, comprising:
- updating one or more current objects based on applying Bayesian probabilities, conditioned on previously determined objects, to a joint object model that models point cloud data points and a plurality of objects, including each current object, based on individual attributes of each of the plurality of objects; and
piloting a vehicle based on the one or more current objects.
1 Assignment
0 Petitions
Accused Products
Abstract
A computing device in a vehicle can determine one or more objects based on 3D data points by determining a joint Bayesian probability of each of the one or more objects, conditioned on previously determined objects, and pilot the vehicle based on the determined one or more objects, wherein the objects have parameters including locations, sizes, poses, speeds, directions and predicted paths.
23 Citations
20 Claims
-
1. A method, comprising:
-
updating one or more current objects based on applying Bayesian probabilities, conditioned on previously determined objects, to a joint object model that models point cloud data points and a plurality of objects, including each current object, based on individual attributes of each of the plurality of objects; and piloting a vehicle based on the one or more current objects. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. An apparatus, comprising:
-
a processor; a memory, the memory storing instructions executable by the processor to; update one or more current objects based on applying Bayesian probabilities, conditioned on previously determined objects, to a joint object model that models point cloud data points and a plurality of objects, including each current object, based on individual attributes of each of the plurality of objects; and pilot a vehicle based on the one or more current objects. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
-
Specification