Predicting external events from digital video content

Patent metadata

Field	Value
Publication number	US-10007849-B2
Application number	US-201615167701-A
Country	US
Kind code	B2
Filing date	May 27, 2016
Priority date	May 29, 2015
Publication date	Jun 26, 2018
Grant date	Jun 26, 2018

Abstract

Computerized methods and systems, including computer programs encoded on a computer storage medium, may detect event shown within digital video content captured by one or more video cameras, and correlate these detected events to real-world conditions that may not be captured within the digital video data. For example, a computing system may detect events shown within digital video content captured by one or more video cameras, and may obtain data that identifies at least one external event. The computer system may establish a predictive model that correlates values of event parameters that characterize the detected and external events during a first time period, and may apply the predictive model to an event parameter that characterizes an additional event detected during a second time period. Based on an outcome of the predictive model, the computing system may determine an expected value of the external event parameter during the second time period.

First claim

What is claimed is:

1. A system, comprising:
one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
detecting events shown within image frames of digital video content captured by one or more video cameras, the detected events being associated with corresponding event parameters and detection times within a first time period;
obtaining first data that identifies at least one external event, the obtained data comprising observed values of an external event parameter that characterize the external event during the first time period, wherein the first data is not derived from the digital video content;
establishing a predictive model that correlates the values of the external event parameters to values of the event parameters that characterize a portion of the detected events during the first time period, including establishing an existence of a time-varying pattern among the event parameters of the detected events during the first time period by applying a machine learning algorithm to data identifying the events and the values of the event parameters;
detecting an additional event shown within the digital video content, the additional event being associated with a corresponding additional event parameter and a second detection time;
in response to the detection of the additional event, applying the predictive model to a value of the additional event parameter;
determining an expected value of the external event parameter at the second detection time, based on an outcome of applying the predictive model to the value of the additional event parameter;
based on the time-varying pattern, generating data identifying expected occurrences of one or more of the events during a second time period that includes the second detection time, the second time period occurring after the first time period; and
transmitting, over a data communications network, data identifying the expected value of the external event parameter to a communications device having a display, the communications device configured to present a representation of the expected value of the external event parameter to a user through a corresponding interface of the display.

2. The system of claim 1 , wherein:
the one or more computers further perform the operation of receiving a portion of the video content from the one or more video cameras; and
the one or more video cameras comprise at least one of a pan-zoom-tilt video camera or a camera having a fixed field-of-view.

3. The system of claim 2 , wherein detecting the additional event comprises:
receiving an additional video content from the one or more video cameras; and
detecting the additional event within the additional video content captured by the one or more video cameras.

4. The system of claim 1 , wherein the one or more computers further perform the operation of applying one or more video analytics to portions of the digital video content, the applied video analytics comprising at least one of an image acquisition process, an object detection process, an object classification process, an object recognition process, an event detection process, or an object tracking process.

5. The system of claim 4 , wherein:
detecting the event comprises, based on an outcome of applying the video analytics to the portions of the digital video content, detecting at least one of the events and establishing the value of at least one of the event parameters; and
detecting the additional event comprises, based on an outcome of applying the video analytics to the portions of the digital video content, detecting the additional event and establishing the value of the additional event parameter.

6. The system of claim 1 , wherein the at least one external event is not shown within the digital video content captured by the one or more cameras.

7. The system of claim 1 , wherein the establishing the predictive model comprises:
applying a second machine learning algorithm to data identifying the values of the external event parameters and the values of the event parameters that characterize the portion of the detected events during the first time period; and
establishing a correlation between the values of the external event parameters and the event parameters, based on an outcome of the second machine learning algorithm.

8. The system of claim 1 , wherein the one or more computers further perform the operations of:
obtaining second data specifying an observed value of the external event parameter at the second detection time;
determining an existence of a variance between the actual and expected values of the external event parameters; and
modifying the predictive model in accordance with the determined variance.

9. The system of claim 1 , wherein:
the external event comprises at least one of a number of customer inquiries or orders, a total number of individuals within a restricted area, or a total number of vehicles disposed within a restricted area;
the detected events comprise at least one of queued individuals, individuals entering a restricted area through a corresponding entrance, or vehicles entering the restricted area through a corresponding entrance; and
the event parameters comprise at least one of a number of the queued individuals, a number of the individuals that enter the restricted area through the corresponding entrance, or a number of the vehicles that enter the restricted area through the corresponding entrance.

10. The system of claim 1 , wherein, in response to the transmitted data, the communications device is further configured to allocate one or more resources in accordance with the expected value of the expected event parameter.

11. A system comprising:
one or more computers; and
one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
detecting events shown within digital video content captured by one or more video cameras, the detected events being associated with corresponding event parameters and detection times within a first time period;
obtaining first data that identifies at least one external event, the obtained data comprising observed values of an external event parameter that characterize the external event during the first time period, wherein the first data is not derived from the digital video content;
establishing a predictive model that correlates the values of the external event parameters to values of the event parameters that characterize a portion of the detected events during the first time period;
detecting an additional event shown within the digital video content, the additional event being associated with a corresponding additional event parameter and a second detection time;
in response to the detection of the additional event, applying the predictive model to a value of the additional event parameter;
determining an expected value of the external event parameter at the second detection time, based on an outcome of applying the predictive model to the value of the additional event parameter;
transmitting data identifying the expected value of external event parameter to a communications device, the communications device configured to present a representation of the expected value of the external event parameter to a user through a corresponding interface;
establishing an existence of a time-varying pattern among the event parameters of the events detected during the first time period;
based on the time-varying pattern, generating data identifying expected occurrences of one or

Assignees

• Accenture Global Solutions Ltd

Inventors

• Bataller Cyrille
• Astrom Anders

Classifications

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title

• G06V20/49

  Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G08B13/19608

  Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position · CPC title

• H04N7/18

  Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast · CPC title