A moving shadow detection method based on computer vision
A technology of computer vision and shadow detection, which is applied in computing, image analysis, instruments, etc., can solve problems such as difficult to obtain good detection results, long time-consuming shadow detection, tracking, and identification effects, etc., to achieve accurate real-time motion shadow detection, good Alternative shadow area detection effect, real-time and detection accuracy improvement effects
Inactive Publication Date: 2019-09-27
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] Moving shadows are often misjudged because they have similar characteristics to moving objects, which will affect the extraction of moving objects, as well as follow-up operations such as tracking and recognition.
The existing shadow detection methods, such as the normalized mutual coefficient method, are difficult to obtain better detection results in order to ensure real-time performance; or the support vector machine method, which makes shadow detection time-consuming in order to improve the detection effect, is difficult to achieve. Applied in practical engineering
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0025] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.
[0026] A moving shadow detection method based on computer vision of the present invention, the computer vision mainly refers to the use of image processing means to solve the moving shadow detection problem, which is different from other non-image processing methods, the moving shadow detection method is as follows figure 1 shown, including the following steps:
[0027] Step S1, read the video frame, perform motion foreground detection on the video frame, and obtain a binary image of the motion foreground.
[0028] In this embodiment, a camera with a fixed field of view is used, and video frames can be obtained directly from a video stream, or from a video file saved by the camera.
[0029] Si...
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
Login to View More Abstract
The invention discloses a moving shadow detection method based on computer vision. The method includes following steps: step 1, reading a video frame, performing moving foreground detection on the video frame, and obtaining a moving foreground binary image; step 2, respectively calculating a normalization cross-correlation coefficient and a local cross entropy on pixel points of the moving foreground image, obtaining corresponding shadow areas, and taking an intersection of the two shadow areas as an alternative shadow area; and step 3, traversing the contour of the alternative shadow area, and eliminating false detection shadow areas by employing the fact that whether neighborhood information of contour pixel points contains target pixel points. According to the method, the intersection of the shadow areas obtained by the normalization cross-correlation coefficient method and the local cross entropy method is taken so that the credibility of the obtained shadow area is ensured, and a better alternative shadow area detection effect can be obtained; and a false detection filtering mechanism is additionally provided so that accurate and real-time moving shadow detection is realized, and the engineering application prospect is good.
Description
technical field [0001] The invention relates to the technical field of moving object detection, in particular to a computer vision-based moving shadow detection method. Background technique [0002] Moving shadows are often misjudged because they have similar characteristics to moving objects, which will affect the extraction of moving objects, as well as follow-up operations such as tracking and recognition. The existing shadow detection methods, such as the normalized mutual coefficient method, are difficult to obtain better detection results in order to ensure real-time performance; or the support vector machine method, which makes shadow detection time-consuming in order to improve the detection effect, is difficult to achieve. applied in practical engineering. Contents of the invention [0003] The purpose of the present invention is to overcome the deficiencies in the prior art, providing a method for detecting moving shadows based on computer vision, technical prob...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/254G06T7/194
Inventor 徐贵力张泽宏姜斌程月华徐扬谢瑒
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS