Image processing apparatus and method and monitoring system

• US 10,445,590 B2
• Filed: 05/16/2017
• Issued: 10/15/2019
• Est. Priority Date: 05/18/2016
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Yang, Qin, Zhao, Xuyu
• Primary Examiner(s): Le, Peter D
• Application Number:
  US15/597,040
• Publication Number:
  US 20170337431A1
• Time in Patent Office: 882 Days
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 10/758 Involving statistics of pixels or of feature values, e.g. histogram matching
• 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
• CPC Class Codes: H04N 7/181 for receiving images from a plurality of remote sources
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

One of the aspects of the present invention discloses an image processing apparatus. The apparatus comprises: a unit configured to acquire a current image and a background image; a unit configured to detect a foreground object from the current image according to the background image; a unit configured to determine a first parameter according to luminance information of the foreground object in the current image and luminance information of portion corresponding to the foreground object in the background image, wherein the first parameter represents change degree of luminance direction of the portion corresponding to the foreground object from the background image to the foreground image; and a unit configured to identify whether the foreground object is a false foreground object or not according to the first parameter. According to the present invention, the accuracy of identifying the false foreground objects will be improved.

Claims

1. An image processing apparatus, comprising:

a processor; and

memory communicatively coupled to the processor, for storing computer-executable instructions that, when executed by the processor, perform operations of;

an acquirement unit configured to acquire a current image and a background image, wherein the background image is obtained according to images acquired in a predefined duration time previous to the current image;

a foreground object detection unit configured to detect a foreground object from the current image according to the background image;

a parameter determination unit configured to determine a first parameter and a second parameter, according to luminance information of the foreground object in the current image and luminance information of a portion corresponding to the detected foreground object in the background image,

wherein the first parameter represents a ratio of a number of visual elements, which have a dominant luminance direction changed from the background image to the detected foreground object of the current image, to a number of foreground visual elements in the portion corresponding to the detected foreground object, and the second parameter represents a difference value between variance of the luminance values of the foreground visual elements of the detected foreground object in the current image and variance of the luminance values of corresponding visual elements of the portion corresponding to the detected foreground object in the background image; and

a foreground object identification unit configured to determine that the foreground object is a false foreground object if the ratio as the first parameter is larger than a first predefined threshold and the difference as the second parameter is less than a second predefined threshold.

2. The image processing apparatus according to claim 1, wherein the parameter determination unit further comprises:

a variance determination unit configured to determine first mean variance of the luminance values of the visual elements in the current image and calculate second mean variance of the luminance values of the visual elements in the background image; and

a difference determination unit configured to determine the difference value between the first mean variance and the second mean variance as the second parameter.

3. The image processing apparatus according to claim 1, wherein the foreground object identification unit determines that the foreground object is a false foreground object in a case where the first parameter is larger than or equal to a first predefined threshold.

4. A camera, comprising:

an image acquiring device configured to acquire images or videos;

a storage device configured to store the acquired images or videos; and

the image processing apparatus according to claim 1, configured to determine whether the foreground objects detected from the current image or frame are false foreground objects or not.

5. An image processing method, comprising:

an acquirement step of acquiring a current image and a background image;

wherein the background image is obtained according to images acquired in a predefined duration time previous to the current image,

a foreground object detection step of detecting a foreground object from the current image according to the background image;

a parameter determination step of determining a first parameter and a second parameter, according to luminance information of the foreground object in the current image and luminance information of a portion corresponding to the detected foreground object in the background image,

wherein the first parameter represents a ratio of a number of visual elements, which have a dominant luminance direction changed from the background image to the detected foreground object of the current image, to a number of foreground visual elements in the portion corresponding to the detected foreground object, and the second parameter represents a difference value between variance of the luminance values of the foreground visual elements of the detected foreground object in the current image and variance of the luminance values of corresponding visual elements of the portion corresponding to the detected foreground object in the background image; and

a foreground object identification step of determining that the foreground object is a false foreground object if the ratio as the first parameter is larger than a first predefined threshold and the difference as the second parameter is less than a second predefined threshold.

6. The image processing method according to claim 5, wherein the parameter determination step further comprises:

a variance determination step of determining first mean variance of the luminance values of the visual elements in the current image and calculate second mean variance of the luminance values of the visual elements in the background image; and

a difference determination step of determining the difference value between the first mean variance and the second mean variance as the second parameter.

7. The image processing method according to claim 5, wherein, in the foreground object identification step, the foreground object is determined to be a false foreground object in a case where the first parameter is larger than or equal to a first predefined threshold.