US 12,080,074 B2
Center-based detection and tracking
Qian Song, San Mateo, CA (US); and Benjamin Isaac Zwiebel, Burlingame, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Nov. 30, 2021, as Appl. No. 17/537,920.
Prior Publication US 2023/0169777 A1, Jun. 1, 2023
Int. Cl. G06V 20/58 (2022.01); B60W 60/00 (2020.01); G06N 20/00 (2019.01); G06T 7/20 (2017.01); G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/75 (2022.01)
CPC G06V 20/58 (2022.01) [B60W 60/001 (2020.02); G06N 20/00 (2019.01); G06T 7/20 (2013.01); G06T 7/70 (2017.01); G06V 10/25 (2022.01); G06V 10/751 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving sensor data from a sensor associated with an autonomous vehicle in an environment;
determining, based at least in part on the sensor data, first multichannel data;
inputting the first multichannel data to a machine-learned model;
determining, by the machine-learned model, Gaussian confidence values for pixels associated with an object in the environment;
determining, based at least in part on the Gaussian confidence values, a plurality of proposed center pixels from the pixels associated with the object;
determining candidate detection boxes for individual pixels of plurality of proposed center pixels;
determining, based at least in part on non-maximum suppression, an output detection box based at least in part on the candidate detection boxes;
generating, based at least in part on a center pixel associated with the output detection box, second multichannel data representing the object;
tracking, as a tracked object, the object based at least in part on the second multichannel data; and
controlling the autonomous vehicle based at least in part on the tracked object.