Device and method for detecting specific object in image sequence as well as video camera equipment

A technology for detecting specific objects and images, applied in the field of pattern recognition, it can solve the problems of lack of consideration, poor accuracy, and difficulty in tracking, so as to reduce false positives and improve accuracy.

Inactive Publication Date: 2012-04-11
SONY CORP
View PDF1 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods all require a tracking process, and real scenes are often more complex, and it is very difficult to track all moving objects
Therefore, the accuracy of this type of method is poor, and it is difficult to be practical
The title of the invention is "a method for detecting abandoned objects without tracking process", the publication number is CN101635026A, and the publication date is January 27, 2010. Although the Chinese patent application proposes a method for detecting abandoned objects without tracking process, the The method does not take into account many difficulties in real scenes, such as occlusion, etc., so the method has many false positives and false negatives

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Device and method for detecting specific object in image sequence as well as video camera equipment
  • Device and method for detecting specific object in image sequence as well as video camera equipment
  • Device and method for detecting specific object in image sequence as well as video camera equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Embodiments of the present invention will be described below with reference to the drawings. It should be noted that in order to avoid obscuring the present invention due to unnecessary details, only the device structure and / or processing steps closely related to the solution according to the present invention are shown in the accompanying drawings, while the components having little relation to the present invention are omitted. other details. In each drawing, the same or similar constituent elements or parts are denoted by the same or similar reference numerals.

[0029] figure 1 A simplified block diagram of the structure of the apparatus 100 for detecting a specific object in an image sequence according to an embodiment of the present invention is shown. like figure 1As shown, the device 100 includes: a suspected object region detection unit 110, which is configured to use background modeling to construct a foreground template of each frame of image in the image ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a device and method for detecting a specific object in an image sequence. The device comprises a suspected object region detection unit, a misinformation high-occurrence region modeling unit and a post-processing unit, wherein, the suspected object region detection unit constructs a foreground template for an image of each frame in the image sequence within a preset time interval, and carries out interframe differential processing on the foreground template; if at least one suspected object region is detected by interframe differential processing, the misinformation high-occurrence region modeling unit determines a region meeting preset conditions in at least one suspected object region to be a misinformation high-occurrence region and constructs a misinformation high-occurrence region model so as to generate a misinformation high-occurrence region model library; the post-processing unit is used for matching each suspected object region which is not determined as the misinformation high-occurrence region with a corresponding model in the misinformation high-occurrence region model library so as to detect the specific object based on the unmatched suspected object region sequence; and if no suspected object region is detected by interframe differential processing, no specific object is determined to exist. The device and the method provided by the invention have the advantages of enhancing robustness for specific object detection and improving detection accuracy.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to technologies such as image processing and computer vision, and more specifically, relates to a device, a method and corresponding video camera equipment for detecting a specific object in an image sequence. Background technique [0002] Detection of specific objects in video image sequences is often of great value. For example, if a specific object is an abandoned object, the detection of this abandoned object is important for maintaining safety in public places. The abandoned object detection mentioned here refers to the detection of backpacks, briefcases, etc. that are intentionally discarded, placed in public places or some vital parts, and may contain explosives. Usually terrorists detonate the bomb contained in the bag by timing or remote control after placing such a package. This method of committing crimes has low cost, great harm, and high difficulty in prevention and d...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06K9/00H04N5/225
CPCG06K9/00771H04N7/18G06V20/52
Inventor刘舟吴伟国
OwnerSONY CORP