Determination of ambient light level changes in visual images

• US 5,151,945 A
• Filed: 09/11/1990
• Issued: 09/29/1992
• Est. Priority Date: 09/11/1990
• Status: Expired due to Fees

• Current Assignee: The Research Foundation for The State University of New York (State University of New York)
• Original Assignee: The Research Foundation for The State University of New York (State University of New York)
• Inventors: Lee, George C., Sun, Xianyi
• Primary Examiner(s): Razavi, Michael
• Application Number:
  US07/580,629
• Time in Patent Office: 749 Days
• Field of Search: 382/1, 382/4, 382/2, 382/37, 382/38, 382/39, 382/42, 358/105, 358/108, 358/109, 358/101
• US Class Current: 382/103
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G08B 13/19602 Image analysis to detect motion of the intruder, e.g. by frame subtraction
• CPC Class Codes: G08B 13/19634 Electrical details of the system, e.g. component blocks for carrying out specific functions

Abstract

A visual image comparison method is provided, including the steps of: obtaining a first digital representation of a first visual image, where the first digital representation comprises a first plurality of pixels, and each pixel has a gray scale indicative of light intensity; obtaining a second digital representation of a second visual image, where the second digital representation comprises a second plurality of pixels, and each pixel has a gray scale indicative of light intensity; and selectively making a first predetermined number of comparisons of corresponding pixels from the first and second digital representations to determine whether a difference in ambient light intensity exists between the first and second visual images, and, selectively making a second predetermined number of comparisons of corresponding pixels from the first and second digital representations if and only if no difference in ambient light intensity exists between the first and second visual images, and indicating an alarm condition when a percentage of the second predetermined number of comparisons result in pixels having a difference in gray scale of a predetermined amount. Apparatus is also described for the purpose of implementing the method.

Claims

1. A visual image comparison method for automated video surveillance, comprising the steps of:

a. obtaining a first digital representation of a first visual image, said first digital representation comprising a first plurality of pixels, wherein each pixel has a gray scale indicative of light intensity;

b. obtaining a second digital representation of a second visual image, said second digital representation comprising a second plurality of pixels, wherein each pixel has a gray scale indicative of light intensity;

c. selectively making a first predetermined number of first comparisons of corresponding remotely displaced pixels from said first and second digital representations to determine whether a difference in ambient light intensity exists between said first and second visual images, wherein said difference in ambient light intensity is defined to exist when a first percentage of said first predetermined number of first remotely displaced comparisons result in pixels having a difference in gray scale of a first predetermined amount; and

,

d. selectively making a second predetermined number of second comparisons of corresponding near neighboring pixels from said first and second digital representations if and only if no significant difference in ambient light intensity exists between said first and second visual images,

e. and indicating an alarm condition when a second percentage of said second predetermined number of second near neighboring comparisons result in pixels having a difference in gray scale of a second predetermined amount.

2. A method as described in claim 1 wherein said second predetermined amount of difference in gray scale is defined as "K2" and K2 is determined automatically based on an average gray scale value of ambient light within the visual images being compared in said first comparison, wherein said average gray scale value is defined as "AGA", and wherein the average gray scale of the ambient is determined by adding all of the individual gray scales values (G'"'"'s) of each considered pixel and then dividing this total by the number of pixels considered wherein K2 is determined according to Table I herebelow:

space="preserve" listing-type="tabular"> TABLE I ______________________________________ AGA 1 2 3 4 5 6 7 8 9 10 K -2 1 2 4 7 9 12 14 16 16 16 AGA 11 12 13 14 15 16 17 18 19 20 K -2 16 16 16 16 16 16 17 17 17 17 AGA 21 22 23 24 25 26 27 28 29 30 K -2 18 18 18 18 18 19 19 19 19 19 AGA 31 32 33 34 35 36 37 38 39 40 K -2 20 20 20 20 21 21 21 21 21 21 AGA 51 52 53 54 55 56 57 58 59 60 K -2 26 26 26 27 27 27 28 28 29 29 AGA 61 62 63 K -2 30 31 32 ______________________________________

3. A visual comparison apparatus, comprising:

a. means for obtaining a first digital representation of a first visual image, said first digital representation comprising a first plurality of pixels, wherein each pixel has a gray scale indicative of light intensity;

b. means for obtaining a second digital representation of a second visual image, said second digital representation comprising a second plurality of pixels, wherein each pixel has a gray scale indicative of light intensity;

c. means for selectively making a first predetermined number of first remotely displaced comparisons of corresponding pixels from said first and second digital representations to determine whether a difference in ambient light intensity exists between said first and second visual images, wherein said difference in ambient light intensity is defined to exist when a first percentage of said first predetermined number of first remotely displaced comparisons result in pixels having a difference in gray scale of a first predetermined amount; and

,

d. means for selectively making a second predetermined number of second comparisons of corresponding near neighboring pixels from said first and second digital representations if and only if no significant difference in ambient light intensity is found to exist,

e. and indicating an alarm condition when a second percentage of said second predetermined number of second near neighboring comparisons result in pixels having a difference in gray scale of a second predetermined amount.