METHOD AND SYSTEM FOR MODIFYING COMPRESSIVE SENSING BLOCK SIZES FOR VIDEO MONITORING USING DISTANCE INFORMATION

• US 20160021390A1
• Filed: 07/15/2014
• Published: 01/21/2016
• Est. Priority Date: 07/15/2014
• Status: Active Grant

• Current Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Original Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Inventors: HAIMI-COHEN, Raziel
• Granted Patent: US 9,894,324 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources

Abstract

A method and a system for using compression sensing to provide low data rate transmission and low computational complexity to determine anomalies in video data obtained by a video camera or other motion detection device. The video data is divided into varying sized video blocks based on an anticipated size of objects of interest within the video, and based on a distance between a video camera and the objects of interest. Features are extracted from the video data of each block to detect anomalies if a feature vector is outside of an “allowed range.” By utilizing varying sized video blocks, anomalies are more effectively and efficiently detected in the video data.

Claims

1. A method of generating a measurement vector to detect an anomaly, comprising:

acquiring, by at least one device controlled by one or more processors, video data;

dividing, by the one or more processors, the video data into a plurality of video blocks,

determining, by the one or more processors, at least a first block size of at least a first video block of the plurality of video blocks, the first block size being based on distance information;

generating, by the one or more processors, a set of compressive measurements by applying a sensing matrix to the first video block; and

generating, by the one or more processors, a measurement vector based on the set of compressive measurements, the measurement vector being used to detect an anomaly in the first video block.

2. The method of claim 1, further comprising:

transmitting the measurement vector to a server for further processing to detect the anomaly, the measurement vector representing a portion of the video data associated with the first video block.

3. The method of claim 1, wherein the dividing of the video data into a plurality of video blocks includes using different block sizes for the video blocks, wherein each of the block sizes of the video blocks is based on the distance information.

4. The method of claim 1, further comprising:

measuring a distance to an object in the video data in order to obtain the distance information,

the first block size further being based on an expected size of the object within the first video block.

5. The method of claim 4, further comprising:

estimating a speed of the object to obtain speed information,

wherein the first block size is further based on the obtained speed information.

6. The method of claim 4, wherein the measuring of the distance to the object includes,

using a distance sensor to measure the distance.

7. The method of claim 4, wherein the measuring of the distance to the object and includes,

acquiring the video data at different vantage points,

applying at least one of a stereoscopic method and a triangulation method to measure the distance.

8. The method of claim 4, wherein,

the measuring the distance to the object includes continuously measuring the distance to the object as the object moves, in order to obtain changing distance information,

wherein the first block size is continuously updated based on the changing distance information.

21. The method of claim 1, wherein,

the at least one device is an image capture mechanism,

the image capture mechanism acquires the video data by capturing the video data rather than receiving the video data from another separate device.

9. A method of detecting an anomaly, comprising:

receiving, at a server, at least one measurement vector of compressive measurements for an object in a video block of data, the at least one measurement vector being derived by applying a sensing matrix to the video block;

estimating, at the server, actual speed information of an object in the video block based on the measurement vector, the actual speed information being based on distance information for the object; and

detecting an anomaly of the video block based on the actual speed information.

10. The method of claim 9, further comprising:

estimating a distance to the object, the estimated distance being the distance information;

determining a relative speed of the object based on the measurement vector; and

converting the relative speed to actual speed information for the object based on the distance information and the relative speed.

11. The method of claim 9, further comprising:

receiving the distance information from an image capture device used to capture the video data;

determining a relative speed of the object based on the measurement vector; and

converting the relative speed to actual speed information for the object based on the distance information and the relative speed.

12. A system for generating a measurement vector to detect an anomaly, comprising:

at least one device configured to,

acquire video data,

divide the video data into a plurality of video blocks,

determine at least a first block size of at least a first video block of the plurality of video blocks, the first block size being based on distance information,

generate a set of compressive measurements by applying a sensing matrix to the first video block, and

generate a measurement vector based on the set of compressive measurements, the measurement vector being used to detect an anomaly in the first video block.

13. The system of claim 12, wherein the at least one device is further configured to:

transmit the measurement vector to a server for further processing to detect the anomaly, the measurement vector representing a portion of the video data associated with the first video block.

14. The system of claim 12, wherein,

different block sizes are used for the for the video blocks,

each of the block sizes of the video blocks is based on an expected size of the object.

15. The system of claim 12, wherein the at least one device is further configured to:

measure a distance to the object in order to obtain the distance information, the first block size further being based on an expected size of the object.

16. The system of claim 15, wherein the at least one device is further configured to:

estimate a speed of the object to obtain speed information,

wherein the first block size is further based on the obtained speed information.

17. The system of claim 12, further comprising:

a distance sensor to measure a distance to the object in order to obtain distance information.

18. The system of claim 15, wherein the at least device is further configured to:

acquire the video data at different vantage points,

apply at least one of a stereoscopic method and a triangulation method to measure the distance.

19. The system of claim 15, wherein the at least one device is further configured to:

continuously measure the distance to the object as the object moves, in order to obtain changing distance information,

continuously update the first block size based on the changing distance information.

22. The system of claim 12, wherein,

the at least one device is an image capture mechanism,

the image capture mechanism is configured to acquire the video data by capturing the video data rather than receiving the video data from another separate device.

20. A server for detecting an anomaly, configured to:

receive at least one measurement vector of compressive measurements for an object in a video block of data, the at least one measurement vector being derived by applying a sensing matrix to the video block,

estimate actual speed information of an object in the video block based on the measurement vector, the actual speed information being based on distance information for the object, and

detect an anomaly of the video block based on the actual speed information.