Stopped object detection

• US 9,154,747 B2
• Filed: 12/22/2010
• Issued: 10/06/2015
• Est. Priority Date: 12/22/2010
• Status: Active Grant

• Current Assignee: Pelco (Schneider Electric SE)
• Original Assignee: Pelco (Schneider Electric SE)
• Inventors: Su, Wei, Wang, Lei, Aghdasi, Farzin, Yang, Shu
• Primary Examiner(s): Pe, Geepy
• Application Number:
  US12/976,957
• Publication Number:
  US 20120162416A1
• Time in Patent Office: 1,749 Days
• Field of Search: 348/159, 348/135, 348/142, 348/160
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30232 Surveillance
• CPC Class Codes: G06T 2207/30236 Traffic on road, railway or crossing
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source
• CPC Class Codes: H04N 7/185 from a mobile camera, e.g. for remote control

Abstract

A video surveillance system includes: an input configured to receive indications of images each comprising a plurality of pixels; a memory; and a processing unit communicatively coupled to the input and the memory and configured to: analyze the indications of the images; compare the present image with a short-term background image stored in the memory; compare the present image with a long-term background image stored in the memory; provide an indication in response to an object in the present image being disposed in a first location in the present image, in a second location in, or absent from, the short-term background image, and in a third location in, or absent from, the long-term background image, where the first location is different from both the second location and the third location.

Claims

1. A stopped object detection system comprising:

capturing means for capturing images of an area;

background means, communicatively coupled to the capturing means, for storing a short-term background image and a long-term background image;

motion detection means, communicatively coupled to the capturing means, for determining that an object is an in-motion object based on images captured by the capturing means; and

stopped object detection means, communicatively coupled to the motion detection means and the background means, for determining that a previously-moving object has stopped by comparing current-image information with the short-term background image and the long-term background image;

wherein the background means are further for analyzing a video quality of the images and updating the short-term background image by resetting the short-term background image in response to the video quality being poor.

2. The system of claim 1 further comprising small-motion means, communicatively coupled to the motion detection means, for determining whether an amount of motion of the in-motion object is less than a threshold motion.

3. The system of claim 1 wherein the stopped object detection means are further for determining that the previously-moving object has stopped only if the previously-moving object is in a first location in the present image, in a second location in, or absent from, the short-term background image, and in a third location in, or absent from, the long-term background image, wherein the first location is different from both the second location and the third location.

4. The system of claim 3 wherein the stopped object detection means are further for determining whether the previously-moving object is within a zone of concern of the images.

5. The system of claim 4 wherein the stopped object detection means are further for triggering an alarm in response to the previously-moving object being stopped for longer than an alarm-triggering threshold within the zone of concern.

6. A method for detecting a stopped object, the method comprising:

capturing images of an area using a camera;

producing a short-term background image and a long-term background image using the captured images;

determining that an object is an in-motion object based on the captured images;

producing a stopped-object indication in response to determining that a previously-moving object has stopped by comparing current-image information with the short-term background image and the long-term background image; and

updating the short-term background image by analyzing a video quality of the images and resetting the short-term background image in response to the video quality being poor.

7. The method of claim 6 further comprising determining whether an amount of motion of the in-motion object is less than a threshold motion.

8. The method of claim 6 wherein determining that the previously-moving object has stopped comprises determining whether the previously-moving object is in a first location in the present image, in a second location in, or absent from, the short-term background image, and in a third location in, or absent from, the long-term background image, wherein the first location is different from both the second location and the third location.

9. The method of claim 8 further comprising determining whether the previously-moving object is within a zone of concern of the images.

10. The method of claim 9 further comprising actuating an alarm in response to the previously-moving object being stopped for longer than an alarm-triggering threshold within the zone of concern.

11. A computer program product residing on a non-transitory processor-readable medium and comprising instructions configured to cause a processor to:

produce a short-term background image and a long-term background image from images captured by a camera;

determine that an object is an in-motion object based on the captured images;

determine that a previously-moving object has stopped by comparing current-image information with the short-term background image and the long-term background image;

produce a stopped-object indication in response to determining that the previously-moving object has stopped; and

update the short-term background image by analyzing a video quality of the images and resetting the short-term background image in response to the video quality being poor.

12. The computer program product of claim 11 further comprising instructions configured to cause the processor to determine whether an amount of motion of the in-motion object is less than a threshold motion.

13. The computer program product of claim 11 wherein the instructions configured to cause the processor to determine that the previously-moving object has stopped comprise instructions configured to cause the processor to determine whether the previously-moving object is in a first location in the present image, in a second location in, or absent from, the short-term background image, and in a third location in, or absent from, the long-term background image, wherein the first location is different from both the second location and the third location.

14. The computer program product of claim 13 further comprising instructions configured to cause the processor to determine whether the previously-moving object is within a zone of concern of the images.

15. The computer program product of claim 14 further comprising instructions configured to cause the processor to actuate an alarm in response to the previously-moving object being stopped for longer than an alarm-triggering threshold within the zone of concern.