IP Library › Granted Patent US 12682753
Granted Patent B1
US 12682753 · App. 18/501,112 · Granted Jul 14, 2026

Object-model based event detection system

Inventors: Saleh ElHattab (San Francisco, CA); Justin Joel Delegard (West Chester, OH); Bodecker John DellaMaria (San Francisco, CA); Brian Tuan (Cupertino, CA); Jennifer Winnie Leung (Berkeley, CA); Sylvie Lee (Pittsburgh, PA); Jesse Michael Chen (San Francisco, CA)
Assignee: Samsara Inc.
G08G1/09623B60C9/00B60Q9/00G06F18/251G06V20/40G06V20/41G06V20/46G06V20/582G06V20/597G08G1/052G06V20/44
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12682753
App. No.
18/501,112
Granted
Jul 14, 2026
Kind
B1
Abstract

Example embodiments described herein therefore relate to an object-model based event detection system that comprises a plurality of sensor devices, to perform operations that include: generating sensor data at the plurality of sensor devices; accessing the sensor data generated by the plurality of sensor devices; detecting an event, or precursor to an event, based on the sensor data, wherein the detected event corresponds to an event category; accessing an object model associated with the event type in response to detecting the event, wherein the object model defines a procedure to be applied by the event detection system to the sensor data; and streaming at least a portion of a plurality of data streams generated by the plurality of sensor devices to a server system based on the procedure, wherein the server system may perform further analysis or visualization based on the portion of the plurality of data streams.

Claims (55)

1 . A system comprising:

a plurality of sensor devices that generate sensor data that comprises a plurality of data streams;

a memory; and

at least one hardware processor to perform operations comprising:

accessing sensor data generated by a sensor device from among the plurality of sensor devices of a vehicle at a first data rate;

detecting a feature within the sensor data that corresponds with a precursor to an event;

determining an event type of the event based on the feature;

accessing a set of procedures that correspond with the event type, the set of procedures defining a second data rate that is higher than the first data rate, display instructions for the sensor data, and a set of criteria associated with the event;

accessing the sensor data generated by the sensor device at the second data rate that is higher than the first data rate based on the set of procedures;

validating the event based on the set of criteria and the sensor data generated by the sensor device at the second data rate; and

generating a visualization of the sensor data based on the display instructions defined by the set of procedures, responsive to the validating the event based on the sensor data generated by the sensor device at the second data rate.

2 . The system of claim 1 , wherein the sensor data includes video data that comprises a set of video frames.

3 . The system of claim 2 , wherein the detecting the feature within the sensor data includes:

detecting an object within a video frame from among the set of video frames of the video data.

4 . The system of claim 1 , further comprising:

causing display of a notification that includes the visualization of the sensor data at a client device.

5 . The system of claim 4 , wherein the display instructions of the object model include an identification of the client device.

6 . The system of claim 1 , wherein the sensor data includes one or more of:

video data;

audio data;

inertial data; and

location data.

7 . A method comprising:

accessing sensor data generated by a sensor device from among the plurality of sensor devices of a vehicle at a first data rate;

detecting a feature within the sensor data that corresponds with a precursor to an event;

determining an event type of the event based on the feature;

accessing a set of procedures that correspond with the event type, the set of procedures defining a second data rate that is higher than the first data rate, display instructions for the sensor data, and a set of criteria associated with the event;

accessing the sensor data generated by the sensor device at the second data rate that is higher than the first data rate based on the set of procedures;

validating the event based on the set of criteria and the sensor data generated by the sensor device at the second data rate; and

generating a visualization of the sensor data based on the display instructions defined by the set of procedures, responsive to the validating the event based on the sensor data generated by the sensor device at the second data rate.

8 . The method of claim 7 , wherein the sensor data includes video data that comprises a set of video frames.

9 . The method of claim 7 , wherein the detecting the feature within the sensor data includes:

detecting an object within a video frame from among the set of video frames of the video data.

10 . The method of claim 7 , further comprising:

causing display of a notification that includes the visualization of the sensor data at a client device.

11 . The method of claim 10 , wherein the display instructions of the object model include an identification of the client device.

12 . The method of claim 7 , wherein the sensor data includes one or more of:

video data;

audio data;

inertial data; and

location data.

13 . A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing sensor data generated by a sensor device from among the plurality of sensor devices of a vehicle at a first data rate;

detecting a feature within the sensor data that corresponds with a precursor to an event;

determining an event type of the event based on the feature;

accessing a set of procedures that correspond with the event type, the set of procedures defining a second data rate that is higher than the first data rate, display instructions for the sensor data, and a set of criteria associated with the event;

accessing the sensor data generated by the sensor device at the second data rate that is higher than the first data rate based on the set of procedures;

validating the event based on the set of criteria and the sensor data generated by the sensor device at the second data rate; and

generating a visualization of the sensor data based on the display instructions defined by the set of procedures, responsive to the validating the event based on the sensor data generated by the sensor device at the second data rate.

14 . The non-transitory machine-readable storage medium of claim 13 , wherein the sensor data includes video data that comprises a set of video frames.

15 . The non-transitory machine-readable storage medium of claim 13 , wherein the detecting the feature within the sensor data includes:

detecting an object within a video frame from among the set of video frames of the video data.

16 . The non-transitory machine-readable storage medium of claim 13 , further comprising:

causing display of a notification that includes the visualization of the sensor data at a client device.

17 . The non-transitory machine-readable storage medium of claim 16 , wherein the display instructions of the object model include an identification of the client device.