CN113014744B - Method for detecting shielding of monitoring picture in vehicle - Google Patents
Method for detecting shielding of monitoring picture in vehicle Download PDFInfo
- Publication number
- CN113014744B CN113014744B CN201911318972.4A CN201911318972A CN113014744B CN 113014744 B CN113014744 B CN 113014744B CN 201911318972 A CN201911318972 A CN 201911318972A CN 113014744 B CN113014744 B CN 113014744B
- Authority
- CN
- China
- Prior art keywords
- background
- frame difference
- image
- frame
- background frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
- H04N5/21—Circuitry for suppressing or minimising disturbance, e.g. moiré or halo
- H04N5/213—Circuitry for suppressing or minimising impulsive noise
Abstract
The invention provides a method for detecting monitoring picture occlusion in a vehicle, which comprises the following steps: buffering multi-frame background frame differences; linear smoothing processing is carried out on the fluctuating frame differences through linear smoothing processing of background frame differences, namely, the weighted mean of the cached frame differences is calculated, and unequal weights are adopted to balance the influence of the frame differences at different moments in the cache; and (5) filtering light flicker. Before the step of buffering the background frame differences of the multiple frames, the method further comprises: initializing parameters, and further comprising: initializing a background, wherein a counter cn is equal to 0, and creating a background frame difference buffer null vector; and calculating the background frame difference. After the step of light ray flicker filtering, the method also comprises the steps of returning a detection result, waiting for the next frame and calculating the background frame difference.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring video processing, in particular to a method for detecting shielding of a monitoring picture in a vehicle.
Background
With the continuous development of science and technology, particularly the development of intelligent technology and the wide application of the Internet, particularly in recent years, the promises of the Internet appointment vehicle provide convenience for the travel of the masses, and in order to guarantee the personal safety of people in the vehicle, a monitoring camera is additionally arranged in the vehicle, so that lawless persons can be deterred, the on-site information in the vehicle can be effectively saved, and a powerful evidence is provided for criminal pursuits. The in-vehicle monitoring camera generally determines whether the frame is blocked by comparing whether the frame difference between the current frame and the original non-blocked frame reaches a predetermined threshold. However, during the running of the vehicle, the environment outside the window is always in the change; in addition, sunlight can enter the vehicle through vehicle windows and the like in the daytime to cause the phenomenon of flickering of picture light; light flicker and the change of the external environment of the vehicle window at any moment can cause unstable fluctuation of the background frame difference value. In the frame difference fluctuation process, if the frame difference exceeds a set threshold value within a period of time, a blocking alarm is triggered, so that a blocking false alarm is generated. Particularly, in the daytime, sunlight passes through a vehicle window to cause a phenomenon of light ray flickering in the vehicle, and factors such as time change of a scene outside the vehicle window can cause the frame difference between the current frame image and the background image to generate an accumulation benefit, so that the frame difference fluctuates, and occlusion misinformation is easily caused.
Disclosure of Invention
In order to solve the above problems, particularly to a problem of accumulated frame difference fluctuation caused by time change of a scene outside a vehicle window and light flicker interference, the invention provides a method for detecting shielding of a monitoring picture in a vehicle, comprising: buffering multi-frame background frame differences; linear smoothing processing is carried out on the fluctuating frame differences through linear smoothing processing of background frame differences, namely, the weighted mean of the cached frame differences is calculated, and unequal weights are adopted to balance the influence of the frame differences at different moments in the cache; and (5) light ray flicker filtering.
Before the step of buffering the background frame differences of the multiple frames, the method further comprises: initializing parameters, and further comprising: initializing a background, wherein a counter cn is 0, and creating a background frame difference buffer empty vector; and calculating the background frame difference.
After the step of filtering the light ray flicker, the method also comprises the steps of returning a detection result, waiting for the next frame, and calculating the background frame difference.
Thus, the application has the advantages that:
(1) by buffering multi-frame background frame differences and performing linear smoothing, the problem of large frame difference fluctuation caused by vehicle window scene change, light ray flicker and other problems can be solved.
(2) A linear smoothing processing method of unequal weight weighted average is provided, wherein the set unequal weight takes the time from the current frame as the basis: the closer to the current frame, the greater the weight and vice versa. Compared with the equal-weight average, the setting of the unequal weight can better reflect the influence of the frame difference in the cache and better accord with the actual situation.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principle of the invention.
Fig. 1 is a schematic block diagram of a method to which the present invention relates.
Fig. 2 is a schematic flow chart of an embodiment of the present invention.
Fig. 3 is a block flow diagram of a particular embodiment of the method to which the present invention relates.
Detailed Description
In order that the technical contents and advantages of the present invention can be more clearly understood, the present invention will now be described in further detail with reference to the accompanying drawings.
As shown in fig. 1, the present invention relates to a method for detecting a monitoring picture occlusion in a vehicle, the method comprising: buffering multi-frame background frame differences; linear smoothing processing is carried out on the fluctuating frame differences through linear smoothing processing of background frame differences, namely, the weighted mean of the cached frame differences is calculated, and unequal weights are adopted to balance the influence of the frame differences at different moments in the cache; and (5) light ray flicker filtering.
In particular, as shown in fig. 2, the steps of the method of the present invention can be expressed as follows:
the method comprises the following implementation steps:
s1, parameter initialization, including: initializing a background, wherein a counter cn is equal to 0, and creating a background frame difference buffer null vector; initializing related threshold values, wherein the initialization values of the threshold value 1, the threshold value 2 and the threshold value 3 are 0.5,0.4 and 10 respectively;
s2, solving a background frame difference;
s3, caching the background frame difference of n frames;
s4, linear smoothing processing of background frame difference;
s5, light ray flicker filtering;
s6, returning a detection result, waiting for the next frame, and executing the step S2.
Wherein, S2 includes:
2.1, according to a formula (1), making a difference between the background gray image and the current frame gray image and taking an absolute value to obtain a frame difference gray image;
d (I, j) ═ dbs (B (I, j) -I (I, j)) 0. ltoreq. i.ltoreq.M, 0. ltoreq. j.ltoreq.N formula (1)
Wherein: m and N are respectively the size of the row and the column of the image; b (i, j) represents the pixel value of the ith row and the jth column of the background gray-scale image; i (I, j) represents the pixel value of the ith row and the jth column of the current frame gray image; d (i, j) represents the pixel value of the ith row and the jth column of the frame difference gray level image;
2.2, carrying out binarization, corrosion and other treatments on the frame difference gray level image;
2.3, carrying out non-zero pixel accumulation on the frame difference binary image after corrosion;
wherein, S3 includes:
3.1, solving the background frame difference buffer vector size vector, namely the background frame difference of how many frames are buffered;
3.2 if the vector _ size is larger than or equal to n, indicating that the buffer is full, deleting the background frame difference stored at the head of the vector, and then storing the background frame difference of the current frame image at the tail of the vector; otherwise, indicating that the buffer is not full, and directly storing the background frame difference of the current frame image at the tail part;
wherein, S4 includes:
4.1 calculating the weighted average value of the buffered n frames of background frame differences according to the formula (2);
4.2 wherein the expression of the weighting function in equation (2) is shown in equation (3);
wherein, S5 includes:
5.1 if the background frame difference of the current frame image is greater than a set threshold 1 and the buffered n frames of background frame difference mean value is greater than a set threshold 2, the counter cn is cn + 1; otherwise cn is 0;
5.2 if cn is greater than the set threshold 3, the detection result is that the current frame image is blocked; otherwise, the detection result is that the current frame image is not shielded.
The flow of the specific embodiment of the method of the present invention is shown in fig. 3, wherein the main implementation steps of the method are as follows:
step 2, calculating the background frame difference
2.1, according to the formula (1), making a difference between the background gray image and the current frame gray image and taking an absolute value to obtain a frame difference gray image;
d (I, j) ═ abs (B (I, j) -I (I, j))0 ≦ I ≦ M, 0 ≦ j ≦ N equation (1)
Wherein: m and N are respectively the size of the row and the column of the image; b (i, j) represents the pixel value of the ith row and the jth column of the background gray-scale image; i (I, j) represents the pixel value of the ith row and the jth column of the current frame gray image; d (i, j) represents the pixel value of the ith row and the jth column of the frame difference gray image;
2.2, carrying out binarization, corrosion and other treatments on the frame difference gray level image;
2.3, carrying out non-zero pixel accumulation on the frame difference binary image after corrosion;
step 3, buffering the background frame difference of n frames
3.1, solving the background frame difference buffer vector size vector _ size, namely the background frame difference of how many frames are buffered;
3.2 if the vector _ size is larger than or equal to n, indicating that the buffer is full, deleting the background frame difference stored at the head of the vector, and then storing the background frame difference of the current frame image at the tail of the vector; otherwise, indicating that the buffer is not full, and directly storing the background frame difference of the current frame image at the tail part;
step 4, linear smoothing processing of background frame difference
Calculating a buffered n-frame background frame difference weighted mean value according to a formula (2);
wherein: w is a weight vector satisfying
Considering that the weight of the background frame difference is larger closer to the current frame time, the weight function expression is set in the method as shown in formula (3);
step 5, light ray flicker filtering
5.1 if the background frame difference of the current frame image is greater than a set threshold 1 and the buffered n frames of background frame difference mean value is greater than a set threshold 2, the counter cn is cn + 1; otherwise cn ═ 0;
5.2 if cn is greater than the set threshold 3, the detection result is that the current frame image is blocked; otherwise, the detection result is that the current frame image is not shielded;
and 6, returning a detection result, waiting for the next frame, and executing the step 2.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A method for checking the shielding of monitoring pictures in a vehicle is characterized in that:
step 1, initializing parameters, including: initializing a background, wherein a counter cn is equal to 0, and creating a background frame difference buffer null vector; initializing related threshold values, wherein the initialization values of the threshold value 1, the threshold value 2 and the threshold value 3 are 0.5,0.4 and 10 respectively;
step 2, solving the background frame difference;
2.1, according to a formula (1), making a difference between the background gray image and the current frame gray image and taking an absolute value to obtain a frame difference gray image;
d (I, j) ═ abs (B (I, j) -I (I, j)) 0. ltoreq. i.ltoreq.M, 0. ltoreq. j.ltoreq.N formula (1)
Wherein: m and N are the size of the row and the column of the image respectively; b (i, j) represents the pixel value of the ith row and the jth column of the background gray-scale image; i (I, j) represents the pixel value of the ith row and the jth column of the current frame gray image; d (i, j) represents the pixel value of the ith row and the jth column of the frame difference gray image;
2.2, carrying out binarization, corrosion and other treatments on the frame difference gray level image;
2.3, carrying out non-zero pixel accumulation on the frame difference binary image after corrosion;
step 3, caching the background frame difference of n frames;
3.1, solving the background frame difference buffer vector size vector, namely the background frame difference of how many frames are buffered;
3.2 if the vector _ size is larger than or equal to n, indicating that the buffer is full, deleting the background frame difference stored at the head of the vector, and then storing the background frame difference of the current frame image at the tail of the vector; otherwise, indicating that the buffer is not full, and directly storing the background frame difference of the current frame image at the tail part;
step 4, linear smoothing processing of background frame difference;
calculating a buffered n-frame background frame difference weighted mean value according to a formula (2);
wherein: w is a weight vector satisfying
Considering that the weight of the background frame difference at the time closer to the current frame is larger, the weight function expression is set in the method as shown in formula (3);
step 5, light ray flicker filtering;
5.1 if the background frame difference of the current frame image is greater than a set threshold 1 and the buffered n frames of background frame difference mean value is greater than a set threshold 2, the counter cn is cn + 1; otherwise cn ═ 0;
5.2 if cn is greater than the set threshold 3, the detection result is that the current frame image is blocked; otherwise, the detection result is that the current frame image is not shielded;
and 6, returning a detection result, waiting for the next frame, and executing the step 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318972.4A CN113014744B (en) | 2019-12-19 | 2019-12-19 | Method for detecting shielding of monitoring picture in vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911318972.4A CN113014744B (en) | 2019-12-19 | 2019-12-19 | Method for detecting shielding of monitoring picture in vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113014744A CN113014744A (en) | 2021-06-22 |
| CN113014744B true CN113014744B (en) | 2022-07-22 |
Family
ID=76382221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911318972.4A Active CN113014744B (en) | 2019-12-19 | 2019-12-19 | Method for detecting shielding of monitoring picture in vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113014744B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
| CN107249122A (en) * | 2017-07-26 | 2017-10-13 | 杨建伟 | A kind of moving target monitoring system for intelligent monitoring |
| CN108765393A (en) * | 2018-05-21 | 2018-11-06 | 西南交通大学 | A kind of high-speed railway touching net vibration behavioral value method |
| CN109063602A (en) * | 2018-07-13 | 2018-12-21 | 北京理工大学 | Method for tracking target and device under Celestial Background based on path continuity function |
| CN110233991A (en) * | 2019-06-03 | 2019-09-13 | 上海眼控科技股份有限公司 | A kind of detection method and system for video shelter in video monitoring |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7505604B2 (en) * | 2002-05-20 | 2009-03-17 | Simmonds Precision Prodcuts, Inc. | Method for detection and recognition of fog presence within an aircraft compartment using video images |
| CN103150736A (en) * | 2012-11-16 | 2013-06-12 | 佳都新太科技股份有限公司 | Camera motion detecting method based on video monitoring |
| US10462445B2 (en) * | 2016-07-19 | 2019-10-29 | Fotonation Limited | Systems and methods for estimating and refining depth maps |
| CN107274674B (en) * | 2017-06-28 | 2020-04-24 | 深圳市金溢科技股份有限公司 | Parking area management method, device and system based on video identification |
-
2019
- 2019-12-19 CN CN201911318972.4A patent/CN113014744B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102111532A (en) * | 2010-05-27 | 2011-06-29 | 周渝斌 | Camera lens occlusion detecting system and method |
| CN107249122A (en) * | 2017-07-26 | 2017-10-13 | 杨建伟 | A kind of moving target monitoring system for intelligent monitoring |
| CN108765393A (en) * | 2018-05-21 | 2018-11-06 | 西南交通大学 | A kind of high-speed railway touching net vibration behavioral value method |
| CN109063602A (en) * | 2018-07-13 | 2018-12-21 | 北京理工大学 | Method for tracking target and device under Celestial Background based on path continuity function |
| CN110233991A (en) * | 2019-06-03 | 2019-09-13 | 上海眼控科技股份有限公司 | A kind of detection method and system for video shelter in video monitoring |
Non-Patent Citations (2)
| Title |
|---|
| The Research and Implementation of Moving Object Detecting and Tracking in Intelligence Video Monitor System;Ma Li等;《2011 International Conference on Multimedia and Signal Processing》;20110718;全文 * |
| 基于单目视觉的运动目标跟踪算法研究与实现;马艳;《中国优秀硕士学位论文全文数据库（电子期刊）》;20190515;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113014744A (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9454805B2 (en) | Method and apparatus for reducing noise of image | |
| CN109859126B (en) | Video noise reduction method and device, electronic equipment and storage medium | |
| CN105631831B (en) | Video image enhancing method under the conditions of a kind of haze | |
| JP4203736B2 (en) | Image motion detection apparatus and computer program | |
| CN113286194A (en) | Video processing method and device, electronic equipment and readable storage medium | |
| CN104658152B (en) | A kind of moving object intrusion alarm method based on video | |
| CN111539265B (en) | Method for detecting abnormal behavior in elevator car | |
| US5999634A (en) | Device and method for analyzing an electronic image signal | |
| CN111582300A (en) | High-dynamic target detection method based on event camera | |
| CN108877009A (en) | A kind of intelligent access control system based on recognition of face | |
| CN111160237A (en) | Head pose estimation method and apparatus, electronic device, and storage medium | |
| CN112561946B (en) | Dynamic target detection method | |
| CN104796580B (en) | A kind of real-time steady picture video routing inspection system integrated based on selection | |
| JP2006238440A (en) | Global motion adaptive system having motion value correction on luminance level | |
| CN113014744B (en) | Method for detecting shielding of monitoring picture in vehicle | |
| KR20100036601A (en) | Apparatus and method for removing noise-image | |
| JP2015158796A (en) | Object detection device | |
| JP2001119683A (en) | Image sensor device | |
| EP0603276B1 (en) | Image analyser | |
| CN111062272A (en) | Image processing and pedestrian identification method and device based on color recovery and readable storage medium | |
| JPH10302171A (en) | Monitoring picture recording device | |
| Wu et al. | Video object tracking method based on normalized cross-correlation matching | |
| CN111582031B (en) | Multi-model collaborative violence detection method and system based on neural network | |
| CN108961293A (en) | A kind of method, apparatus of background subtraction, equipment and storage medium | |
| CN113011216B (en) | Multi-classification threshold self-adaptive shielding detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |