US 11,983,928 B1
Dynamically composable object tracker configuration for intelligent video analytics systems
Joonhwa Shin, Santa Clara, CA (US); Fangyu Li, San Jose, CA (US); Zheng Liu, Los Altos, CA (US); and Kaustubh Purandare, San Jose, CA (US)
Assigned to Nvidia Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Oct. 15, 2021, as Appl. No. 17/503,183.
Int. Cl. G06V 20/40 (2022.01); G06F 18/22 (2023.01); G06V 20/10 (2022.01)
CPC G06V 20/49 (2022.01) [G06F 18/22 (2023.01); G06V 20/10 (2022.01); G06V 20/46 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
executing a first set of application modules for an object tracking application configured to track, based on images depicting an environment, a state of one or more objects included in the environment, wherein the first set of application modules is associated with a first object tracker type of a set of object tracker types, the set of object tracker types comprising two or more of: a location-based object tracker type, a simple, online, real-time (SORT) object tracker type, a visual feature-based object tracker type, or a discriminative correlation feature (DCF) object tracker type;
receiving a request to configure the object tracking application to execute a second set of application modules associated with a second object tracker type of the set of object tracker types, wherein the second object tracker type is different from the first object tracker type;
configuring the object tracking application to execute the second set of application modules in accordance with the request; and
executing the second set of application modules for the object tracking application to track, based on the images depicting the environment, the state of the objects included in the environment.