Method for Automatically Ignoring Cast Self Shadows to Increase the Effectiveness of Video Analytics Based Surveillance Systems

• US 20110304729A1
• Filed: 06/11/2010
• Published: 12/15/2011
• Est. Priority Date: 06/11/2010
• Status: Active Grant

• Current Assignee: Avinash Nehemah, Gianni Arcaini, Prem Kuchi
• Original Assignee: Avinash Nehemah, Gianni Arcaini, Prem Kuchi
• Inventors: Kuchi, Prem, Arcaini, Gianni, Nehemah, Avinash
• Granted Patent: US 8,665,329 B2
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 5/94 based on local image properties, e.g. for local contrast enhancement
• 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: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

One of the challenges in video surveillance system is the detection of unwanted intruders in secure zones. These zones may be in large facilities such as airports, train stations, port facilities or warehouses. Because many of these locations are outdoors, the presence of shadows is detected on images. In order to effectively eliminate these shadows which will therefore result in a usable figure, these shadows must be eliminated. This is accomplished by forming a contour box around the image and then reducing the shadows based on preset parameters in the software.

Claims

1. A method and apparatus for automatically ignoring cast self shadows to increase the effectiveness of video-based surveillance systems comprised of video capture equipment;

wherein the video capture equipment captures images of a object;

software;

wherein the software processes the captured video image;

wherein the software creates a boundary box around the captured image;

said boundary box is rectangular;

said software produces a drop histogram;

said drop histogram is comprised of a series of vectors;

said vectors extend from the top line of the boundary box to predetermined points on the captured image;

wherein the software reconfigures the image within the boundary box based on the drop histogram;

wherein the software reconfigures the width of the boundary box based on the drop histogram;

wherein the software creates a vertical line through the approximate center of the image in the edited boundary box;

wherein a line is placed on the bottom line of the boundary box to create an edited boundary box;

said angle determines the angle of the shadow;

said software eliminates the shadow.

2. The method and apparatus as described in claim 1 wherein the video capture equipment operates in dim lighting conditions.

3. The method and apparatus as described in claim 1 wherein the video capture equipment has infrared capability.

4. The method and apparatus as described in claim 1 wherein the drop histogram is further comprised of:

a series of vectors that extend from the top line of the boundary box to predetermined points on the captured image;

said first point is the top most point on the captured image;

wherein the software detects the amount of distance between points from the top most point on the captured image and other predetermined points on the captured image.

6. The method and apparatus as described in claim 1 wherein the alarm is sent to a remote location.

7. The method and apparatus as described in claim 1 wherein the image is transmitted to a remote location.

5. A method for automatically ignoring cast self shadows to increase the effectiveness of video-based surveillance systems that is comprised of the following steps:

a. capturing a image;

b. integrating software;

c. creating a box around the captured image;

d. employing a drop histogram;

e. adjusting the height of the image in the box based on the histogram;

said height adjustment resulting in a reconfigured boundary box;

f. placing a vertical line through the center of the image in the reconfigured boundary box;

g. placing a line on the bottom line of the bounding box;

h. said line forming an angle to demonstrate the angle formed by the shadow;

i. eliminating the area that is covered by the angle;

j. tracking the image within the configured bounding box;

k. transmitting an alarm based on a preset configuration in the software.