Stationary target detection by exploiting changes in background model

• US 10,586,113 B2
• Filed: 09/26/2017
• Issued: 03/10/2020
• Est. Priority Date: 09/04/2007
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: Avigilon Fortress Corporation
• Inventors: Hassan-Shafique, Khurram, Venetianer, Peter L., Yu, Li, Liu, Haiying
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US15/716,216
• Publication Number:
  US 20180089514A1
• Time in Patent Office: 896 Days
• Field of Search: 382103, 382170, 382171, 382209, 382206, 382282, 382284, 348143, 348149, 348161
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction

Abstract

Provided is a computer-implemented method for processing one or more video frames. The meth can include generating, by a processor, a change in value of one or more pixels obtained from the one or more video frames; classifying, by the processor, the change in value of the one or more pixels to produce one or more classes of the change in value of the one or more pixels, wherein the one or more classes include one or more of a stationary target, a moving target, a target insertion, a target removal, or a local change; and constructing, by the processor, a listing of detected targets based on the one or more classes.

Claims

1. A computer-implemented method for processing one or more video frames, comprising:

obtaining, by a computer, one or more video frames;

generating, by the computer, one or more blobs using the one or more video frames;

identifying each of the one or more blobs to be a respective one of a plurality of different target types, the identifying carried out by the computer; and

employing calibration information to filter, by the computer and based on size, each of the one or more blobs to confirm that each of the one or more blobs is the respective one of the plurality of different target types.

2. The computer-implemented method of claim 1, further comprising adding a blob from the one or more blobs to a list of detected targets when the blob is not in the list.

3. The computer-implemented method of claim 1, wherein the one or more blobs are identifiable as stationary targets when the computer determines a criteria of a length of time of insertion has been satisfied.

4. A system for processing one or more video frames, the system comprising:

a computer configured to;

obtain the one or more video frames;

generate one or more blobs using the one or more video frames;

identify each of the one or more blobs to be a respective one of a plurality of different target types; and

employ calibration information to filter, based on size, each of the one or more blobs to confirm that each of the one or more blobs is the respective one of the plurality of different target types.

5. The system as claimed in claim 4, wherein the computer is further configured to add a blob from the one or more blobs to a list of detected targets when the blob is not in the list.

6. The system as claimed in claim 4, wherein in order for a blob of the one or more blobs to be identified as a stationary target by the computer, the computer is configured to first determine criteria of a length of time of insertion having being satisfied.

7. A computer-readable medium comprising software, which software, when executed by a computer system, causes the computer system to perform operations for processing one or more video frames, the computer-readable medium comprising:

instructions for obtaining one or more video frames;

instructions for generating one or more blobs using the one or more video frames;

instructions for identifying each of the one or more blobs to be a respective one of a plurality of different target types; and

instructions for employing calibration information to filter, based on size, each of the one or more blobs to confirm that each of the one or more blobs is the respective one of the plurality of different target types.

8. The computer-readable medium of claim 7, further comprising instructions for adding a blob from the one or more blobs to a list of detected targets when the blob is not in the list.

9. The computer-readable medium of claim 7, further comprising instructions for determining a criteria of a length of time of insertion has been satisfied in order that the one or more blobs are capable of being identified as stationary targets.