Analytics based power management for cameras

Patent metadata

Field	Value
Publication number	US-2019273866-A1
Application number	US-201815909487-A
Country	US
Kind code	A1
Filing date	Mar 1, 2018
Priority date	Mar 1, 2018
Publication date	Sep 5, 2019
Grant date	—

Abstract

Systems and methods are disclosed for managing power use of a camera and/or camera system. In response to a wakeup trigger, contents of a scene are captured by the camera. Based on a received energy budget for the camera, a scene analysis is performed on the scene, where the contents of the scene are analyzed according to one or more analytics models. Based on the output of the one or more analytics models and the received energy budget for the camera, it is determined whether the camera should continue capturing the contents of the scene or enter a power state lower than a previous power state (e.g., go to sleep).

First claim

What is claimed is:

1 . A method of managing power use of a camera, the method comprising:
performing an initial analysis on at least a portion of captured contents of a scene by one or more analytics models, wherein the one or more analytics models output information regarding contents of the scene; and determining, by a camera, whether to continue capturing the contents of the scene or to enter a low power state based on the output information regarding the contents of the scene and an energy budget for the camera.

2 . The method of claim 1 , further comprising:
determining that further analysis of captured contents of the scene should not be performed by the camera when the energy budget is less than an amount of energy needed for perfoming the further anlaysis on the camera.

3 . The method of claim 1 , wherein the one or more analytics models output information that the captured contents of the scene includes a first area and a second area, the method further comprising:
determining that the further analysis for the first area should not be performed by the camera when the energy budget is less than an amount of energy needed for perfoming the further anlaysis on the camera; and determining that the further analysis for the second area should be performed by the camera.

4 . The method of claim 1 , further comprising:
predicting an energy usage of the camera based on historical power consumption data; and based on predicting the energy usage of the camera, configuring the energy budget for the camera to last at least a specified period of time by reducing one or more of frame rate, image fidelity, or ending recording to capture images only.

5 . The method of claim 1 , the method comprising:
transmitting the information regarding the contents of the scene to a second camera so that the second camera can determine whether to further capture the contents of the scene.

6 . The method of claim 1 , the method comprising:
receiving the contents of the scene from a second camera, wherein the second camera did not have the energy budget to perform the initial analysis on the at least the portion of captured contents of the scene.

7 . A camera comprising:
at least one processor and at least one memory containing instructions that, when executed, cause the at least one processor to: perform an initial analysis on at least a portion of captured contents of a scene by one or more analytics models, wherein the one or more analytics models output information regarding contents of the scene; and determine, by the camera, whether to continue capturing the contents of the scene or to enter a low power state based on the output information regarding the contents of the scene and an energy budget for the camera.

8 . The camera of claim 7 , wherein the at least one processor is further configured to:
determine that further analysis of captured contents of the scene should not be performed by the camera when the energy budget is less than an amount of energy needed for perfoming the further anlaysis on the camera.

9 . The camera of claim 7 , wherein the scene includes a first area and a second area, and wherein the at least one processor is further configured to:
determine that the further analysis for the first area should not be performed by the camera when the energy budget is less than an amount of energy needed for perfoming the further anlaysis on the camera; and determine that the further analysis for the second area should be performed by the camera.

10 . The camera of claim 7 , wherein the at least one processor is further configured to:
predict an energy usage of the camera based on historical power consumption data; and based on the predicted energy usage of the camera, configure the energy budget for the camera to last at least a specified period of time by reducing one or more of frame rate, image fidelity, or ending recording to capture images only.

11 . The camera of claim 7 , wherein the at least one processor is further configured to:
transmit the output information regarding the contents of the scene to a second camera so that the second camera can determine whether to further capture the contents of the scene.

12 . The camera of claim 7 , wherein the at least one processor is further configured to:
receive the contents of the scene from a second camera, wherein the second camera did not have the energy budget to perform the initial analysis on the at least the portion of captured contents of the scene.

13 . A system for managing power use of a camera system, comprising:
a first camera configured to:
capture contents of a first scene in response to a first wakeup trigger;
perform a first initial analysis on at least a portion of captured contents of the first scene by one or more analytics models, wherein the analytics models output information regarding contents of the first scene; and determine, by the first camera, whether to continue capturing the contents of the first scene or to enter a low power state based on first output information regarding the contents of the first scene and an energy budget for the first camera.

14 . The system of claim 13 , further comprising:
a second camera in communication with the first camera, the second camera configured to:
capture contents of a second scene in response to a second wakeup trigger;
perform a second initial analysis on at least a portion of captured contents of the second scene by one or more analytics models, wherein the analytics models output information regarding contents of the second scene; and
determine, by the second camera, whether to continue capturing the contents of the second scene or to enter a low power state based on second output information regarding the contents of the second scene and an energy budget for the second camera.

15 . The system of claim 14 , wherein a portion of the first scene overlaps with a portion of the second scene, and the second camera is configured to:
receive a communication from the first camera informing the second camera that the first camera will not perform further analysis on captured contents of the first scene; and perform further analysis on captured contents of the first scene based on the received communication from the first camera.

16 . The system of claim 14 , wherein a portion of the first scene overlaps with a portion of the second scene, and the portion of the first scene that overlaps with the portion of the second scene, the first camera and second camera are configured to:
determine that the first camera will perform further analysis on a first area and the second camera will peform further analysis on a second area based on a determination that the second area requires more processing than the first area, and the second camera has more processing capabilities than the first camera.

17 . The system of claim 14 , wherein a portion of the first scene overlaps with a portion of the second scene, and wherein the second camera is configured to:
communicate identified contents of the second scene to the first camera, and the second camera is configured to: determine to enter the low power state rather than perform further anlaysis on the captured contents of the first scene based in part of the identified contents of the second scene.

18 . The system of claim 14 , further comprising a server in communication with the first camera and the second camera to:
determine that the further analysis should not be performed by the first camera based on the energy budget be

Assignees

• Cisco Tech Inc

Inventors

• Abalos Nicholas Dye
• Snyder Ian Matthew

Classifications

• H04N23/65 Primary

  Control of camera operation in relation to power supply · CPC title

• H04N23/62

  Control of parameters via user interfaces · CPC title

• G08B13/196 Primary

  using television cameras · CPC title

• H04N23/66

  Remote control of cameras or camera parts, e.g. by remote control devices · CPC title

• H04N23/651

  for reducing power consumption by affecting camera operations, e.g. sleep mode, hibernation mode or power off of selective parts of the camera · CPC title