Systems and methods for fallback tracking based on real-time tracking performance
A system can include one or more processors configured to execute a first object tracker to detect one or more objects in images received via a sensor of a device, monitor one or more metrics of the first object tracker, determine that the one or more metrics do not meet a criteria corresponding to a profile of the device, and use, responsive to the determination, a second object tracker instead of the first object tracker.
1. A method, comprising:
executing, by one or more processors of a device, a first object tracker to perform a detection of one or more objects in images received via a sensor of the device and an attachment of a tracker to the one or more objects;
monitoring, by the one or more processors, one or more metrics of the first object tracker, the one or more metrics comprising a time from the detection by the one or more processors of the device of the one or more objects to the attachment by the one or more processors of the device of the tracker to the one or more objects, the one or more metrics received at intervals;
determining, by the one or more processors, that the one or more metrics do not meet a criteria corresponding to a profile of the device; and
using, by the one or more processors, responsive to the determination, a second object tracker instead of the first object tracker.
2. The method of claim 1 , further comprising:
selecting, by the one or more processors, the second object tracker from a plurality of second object trackers based on the one or more metrics.
3. The method of claim 1 , further comprising:
receiving, by the one or more processors from a remote device, information to configure the second object tracker; and
configuring, by the one or more processors, the one or more processors to use the second object tracker responsive to the information.
4. The method of claim 1 , further comprising:
monitoring, by the one or more processors, the one or more metrics to determine whether the second object tracker meets the criteria; and
using, by the one or more processors, a third object tracker instead of the second object tracker responsive to the second object tracker not meeting the criteria.
5. The method of claim 1 , wherein monitoring the one or more metrics includes monitoring, by the one or more processors, a tracking success rate corresponding to a fraction of time that the time from the detection of the one or more objects to the attachment of the tracker is less than a threshold.
6. A system, comprising:
one or more processors configured to:
execute a first object tracker to perform a detection of one or more objects in images received via a sensor of a device and an attachment of a tracker to the one or more objects;
monitor one or more metrics of the first object tracker, the one or more metrics comprising a time from the detection of the one or more objects by the one or more processors to the attachment of the tracker to the one or more objects by the one or more processors, the one or more metrics received at intervals;
determine that the one or more metrics do not meet a criteria corresponding to a profile of the device; and
use, responsive to the determination, a second object tracker instead of the first object tracker.
7. The system of claim 6 , wherein the one or more processors are further configured to select the second object tracker from a plurality of second object trackers based on the one or more metrics.
8. The system of claim 6 , wherein the one or more processors are further configured to:
receive, from a remote device, information to configure the second object tracker; and
configure the one or more processors to use the second object tracker responsive to the information.
9. The system of claim 6 , wherein the one or more processors are configured to:
monitor the one or more metrics to determine whether the second object tracker meets the criteria; and
use a third object tracker instead of the second object tracker responsive to the second object tracker not meeting the criteria.
10. The system of claim 6 , wherein the one or more processors are configured to monitor the one or more metrics by monitoring a tracking success rate corresponding to a fraction of time that the time from the detection of the one or more objects to the attachment of the tracker is less than a threshold.
11. The method of claim 1 , wherein the one or more metrics comprise a delay from a time of loss of tracking of the one or more objects by the one or more processors of the device to a recovery of tracking of the one or more objects by the one or more processors of the device.