Unusual event detection using motion activity descriptors

• US 6,823,011 B2
• Filed: 11/19/2001
• Issued: 11/23/2004
• Est. Priority Date: 11/19/2001
• Status: Expired due to Fees

• Current Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Original Assignee: Mitsubishi Electric Research Laboratories, Inc. (Mitsubishi Electric Corporation)
• Inventors: Radhakrishnan, Regunathan, Divakaran, Ajay
• Primary Examiner(s): DIEP, NHON THANH
• Application Number:
  US09/997,497
• Publication Number:
  US 20030095602A1
• Time in Patent Office: 1,100 Days
• Field of Search: H04/N.712, 375/16, 375/28, 375/8, 375/11, 375/23, 375/4, 375/18, 382/236, 382/239, 382/245, 382/246
• US Class Current: 375/240.16
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• 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: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 19/142 Detection of scene cut or scene change
• CPC Class Codes: H04N 19/179 the unit being a scene or a shot
• CPC Class Codes: H04N 19/46 Embedding additional information in the video signal during the compression process H04N19/517, H04N19/68, H04N19/70 take precedence
• CPC Class Codes: H04N 19/503 involving temporal prediction adaptive coding with adaptive selection between spatial and temporal predictive coding H04N19/107; adaptive coding with adaptive selection among a plurality of temporal predictive coding modes H04N19/109
• CPC Class Codes: H04N 19/517 by encoding
• CPC Class Codes: H04N 19/87 involving scene cut or scene change detection in combination with video compression

Abstract

A method detects an unusual event in a video. Motion vectors are extracted from each frame in a video acquired by a camera of a scene. Zero run-length parameters are determined for each frame from the motion vectors. The zero run-length parameters are summed over predetermined time intervals of the video, and a distance is determined between the sum of the zero run-lengths of a current time interval and the sum of the zero run-lengths of a previous time interval. Then, the unusual event is detected if the distance is greater than a predetermined threshold.

Claims

1. A method for detecting an unusual event in a video, comprising:

extracting motion vectors from each frame in a video;

determine zero run-length parameters for each frame from the motion vectors;

summing the zero run-length parameters over predetermined time intervals of the video;

determining a distance between the sum of the zero run-lengths of a current time interval and the sum of the zero run-lengths of a previous time interval;

signalling the unusual event if the distance is greater than a predetermined threshold.

2. The method of claim 1 wherein the zero run-length parameters are classified into short, medium and long zero run-lengths.

3. The method of claim 2 wherein the zero run-length parameters are normalized with respect to a width of each frame of the video.

4. The method of claim 2 wherein short zero run-lengths are defined to be one third the width of the frame or less, medium zero run-lengths are greater than one third and less than two thirds of the width of the frame, and long zero run-lengths are equal to or greater than the width of the frame.

5. The method of claim 1 wherein the zero run-length parameters express the number, size, and shape of distinct moving objects in the video.

6. The method of claim 2 wherein the distance is an absolute difference of the short run-lengths sums.

7. The method of claim 2 wherein the distance is a difference of squares of the short and long zero run-lengths.

8. The method of claim 1 wherein the video is of a scene without moving objects, and the unusual event is a moving object entering the scene in the video.

9. The method of claim 1 wherein the video is of a scene including vehicle traffic on a highway, and the unusual event is stalled traffic.

10. The method of claim 1 wherein the stalled traffic is due to an out-of-scene accident.

11. The method of claim 1 wherein the unusual event is inferred but not directly observed.

12. The method of claim 1 further comprising:

detecting the unusual event in a real-time video.

13. A system for detecting an unusual event in a video, comprising:

a camera acquiring a video of a scene;

means for extracting motion vectors from each frame in the video;

means for determine zero run-length parameters for each frame from the motion vectors;

means for summing the zero run-length parameters over predetermined time intervals of the video;

means for determining a distance between the sum of the zero run-lengths of a current time interval and the sum of the zero run-lengths of a previous time interval; and

an alarm device for signalling the unusual event if the distance is greater than a predetermined threshold.