CN110636281B - Real-time monitoring camera shielding detection method based on background model - Google Patents
Real-time monitoring camera shielding detection method based on background model Download PDFInfo
- Publication number
- CN110636281B CN110636281B CN201910899899.8A CN201910899899A CN110636281B CN 110636281 B CN110636281 B CN 110636281B CN 201910899899 A CN201910899899 A CN 201910899899A CN 110636281 B CN110636281 B CN 110636281B
- Authority
- CN
- China
- Prior art keywords
- monitoring camera
- background model
- detected
- monitoring
- shielded
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 84
- 238000001514 detection method Methods 0.000 title abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000011897 real-time detection Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 7
- 230000006978 adaptation Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a real-time detection method for shielding of a monitoring camera based on a background model, which aims to solve the technical problems that the shielding of the existing monitoring camera is difficult to judge in real time through human eyes, the detection by using the current computer vision technology auxiliary algorithm requires a large-scale server for adaptation, the firmware occupation is large, and the false alarm rate is high. The detection method comprises the following steps: firstly, establishing a background model under the condition of no shielding, then acquiring a monitoring image of a monitoring camera in real time, then carrying out image comparison, judging whether the monitoring camera is shielded, if so, notifying a user, and if not, updating the background model. The detection method is based on the background model technology, the latest environmental state information is timely overlapped, the extremely high accuracy of detection is realized, and meanwhile, the high-speed real-time high-accuracy detection of whether the monitoring camera is shielded or not is finally realized by combining the shielding judgment algorithm set in each step in a breakthrough manner.
Description
Technical Field
The invention belongs to the field of intelligent monitoring, and particularly relates to a real-time monitoring camera shielding detection method based on a background model.
Background
In order to ensure social security and maintain social stability, and carry out legal affair execution objectively and fairly, video monitoring becomes one of the very common technical means at present and is also an important component of a security system. Nowadays, aiming at the requirements of social security, the public security department is always dedicated to monitoring public areas, namely, the construction of a skynet monitoring project is completed, the skynet monitoring project is that a plurality of monitoring cameras are reasonably installed in the public areas, all-weather and all-around monitoring is realized on the areas through background control of a public security department, and currently, the world largest video monitoring network is built in China.
However, due to the influence of human or natural conditions, some monitoring cameras may be shielded by some objects under certain conditions, so that the normal use of video monitoring is influenced. In the total area, due to the existence of a large number of video monitoring cameras, the uninterrupted inspection of whether all the monitoring cameras are shielded is difficult to realize through the observation of human eyes, and the feasibility is extremely low; meanwhile, a computer vision technology auxiliary algorithm can be used for detection, but a detection method in the prior art cannot distinguish whether an object in a monitoring video is a normal object or a blocking object, so that the situation of false alarm often occurs.
Disclosure of Invention
(1) Technical problem to be solved
Aiming at the defects of the prior art, the invention aims to provide a monitoring camera shielding real-time detection method based on a background model, which aims to solve the technical problems that the shielding of the existing monitoring camera is difficult to judge in real time through human eyes, the detection by using the existing computer vision technology auxiliary algorithm needs a large-scale server for adaptation, the occupancy of firmware is large, and the false alarm rate is high; the detection method is based on the background model technology, the latest environmental state information is timely overlapped, the extremely high accuracy of detection is realized, and meanwhile, the high-speed real-time high-accuracy detection of whether the monitoring camera is shielded or not is finally realized by combining the shielding judgment algorithm set in each step in a breakthrough manner.
(2) Technical scheme
In order to solve the technical problem, the invention provides a real-time detection method for shielding of a monitoring camera based on a background model, which comprises the following specific steps:
firstly, establishing a background model M of a monitoring camera to be detected under the condition of no shielding when a system is initialized;
step two, acquiring the monitoring image of the monitoring camera to be detected in real time when the system normally operates;
comparing the background model M with the monitoring image of the monitoring camera to be detected, and judging whether the monitoring camera to be detected is shielded;
step four, if the monitoring camera to be detected is judged to be blocked, reminding a user; and if the monitoring camera to be detected is judged not to be shielded, updating the background model M according to the monitoring image acquired by the monitoring camera to be detected at present, and continuing to perform the step two.
The background model M for establishing the monitoring camera to be detected under the condition of no shielding can use various background modeling algorithms, such as Vibe background modeling, Gaussian mixture background modeling, CodeBook background modeling and the like.
Preferably, in the step one, the specific steps are as follows:
(1.1) acquiring an N-frame color image of the monitoring camera to be detected under the condition of no shielding when a system is initialized;
(1.2) converting the N-frame color image into a gray scale image, and recording as G ═ Gi|i∈[1,N]};
(1.3) calculating the average value of G in time series according to pixel positions, the background model isThereby obtaining a background model M of the monitoring camera to be detected under the condition of no shielding.
In the second step, the specific steps are as follows:
(2.1) acquiring K frame color images at the same time interval when the system is in normal operation;
(2.2) converting the K-frame color image into a gray scale map, which is recorded as G ═ G'i|i∈[1,K]And obtaining the monitoring image of the monitoring camera to be detected.
In the third step, the concrete steps are as follows:
(3.1) in the horizontal and vertical directions, the background model M is averagely divided into regions with the same size as the P block and the Q block, which are marked as { Mij|i∈[1,P],j∈[1,Q]};
(3.2) the K-frame grayscale map G 'is judged cyclically by the following steps (3.3) to (3.9) { G'i|i∈[1,K]Whether it is occluded;
(3.3) mixing g 'in horizontal and vertical directions'iAveragely cutting the P block and the Q block into regions to be detected with the same size, and recording the regions as { aij|i∈[1,P],j∈[1,Q]};
(3.4) the following steps (3.5) to (3.7) are repeated to judge aijWhether it is occluded or not;
(3.5) calculation of aijMean of gray scale Mean (a)ij) And standard deviation Std (a)ij);
(3.6) if Mean (a)ij) < Tm and Std (a)ij) < Ts, the area a is calculated by positionijWith background model MijThe absolute value of the difference, denoted as abs (a)ij-Mij);
(3.7) if Mean (abs (a)ij-Mij) Ta), then return to aijThe area is occluded, otherwise return to aijIs not occluded;
(3.8) if g'iIn which there is a certain area aijIs shielded and returns to g'iIs shielded, otherwise returns to g'iIs not occluded;
(3.9) calculating G 'blocked in G'iThe number is marked as L; and if L is more than Tl, returning to the monitoring camera to be shielded, otherwise, returning to the monitoring camera to be normal.
Wherein Mean () and Std () are Mean and standard deviation functions, respectively; tm and Ts are a mean threshold and a standard deviation threshold, respectively; ta is the fixed threshold in step (3.7), and Tl is the fixed threshold in step (3.9).
In the fourth step, if the monitored camera to be detected is judged to be blocked, the user is reminded, and the specific steps are as follows:
(4.11) reminding the user by calling a short message sending module, sending a short message notice to a specified mobile phone number, and/or popping up a window on a monitoring server for reminding;
and (4.12) calling the storage module to store the relevant information into the database.
In the fourth step, if it is determined that the monitoring camera to be detected is not shielded, the specific step of updating the background model M according to the monitoring image obtained by the current monitoring camera to be detected includes:
(4.21) calculating G ' ═ G ' by position in time series 'i|i∈[1,K]Mean of { fraction (v) }, denoted Mean (G');
(4.22) updating the background model according to the formula M ═ M + Mean (G')/2.
(3) Advantageous effects
Compared with the prior art, the invention has the beneficial effects that:
based on the background model technology, the invention utilizes the monitoring image obtained by the monitoring camera to be detected to update the background model in real time and timely update the latest environmental state information, thereby realizing extremely high accuracy of detection; meanwhile, by combining the shielding judgment algorithm set in each step in a breakthrough manner, the algorithm is low in calculation complexity, does not need a large-scale server for adaptation, is small in firmware occupation amount, can be used for rapidly detecting multiple paths of monitoring cameras in real time by one server, and finally realizes high-speed, real-time and high-accuracy detection on whether the monitoring cameras are shielded or not.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the technical solutions in the prior art will be briefly described below, it is obvious that the drawings in the following description are only one embodiment of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic view of a flow framework of an embodiment of a real-time monitoring camera occlusion detection method according to the present invention.
Detailed Description
In order to make the technical means, the original characteristics, the achieved purposes and the effects of the invention easily understood and obvious, the technical solutions in the embodiments of the present invention are clearly and completely described below to further illustrate the invention, and obviously, the described embodiments are only a part of the embodiments of the present invention, but not all the embodiments.
The embodiment is a method for detecting whether a monitoring camera is shielded in real time, a schematic flow frame diagram of a judging process is shown in fig. 1, and the specific process is as follows:
(1.1) acquiring an N-frame color image of the monitoring camera to be detected under the condition of no shielding when a system is initialized;
(1.2) converting the N-frame color image into a gray scale image, and recording as G ═ Gi|i∈[1,N]};
(1.3) calculating the average value of G in time series according to pixel positions, the background model isThereby obtaining a background model M of the monitoring camera to be detected under the condition of no shielding.
(2.1) acquiring K frame color images at the same time interval when the system is in normal operation;
(2.2) converting the K-frame color image into a gray scale map, which is recorded as G ═ G'i|i∈[1,K]And obtaining the monitoring image of the monitoring camera to be detected.
(3.1) in the horizontal and vertical directions, the background model M is averagely divided into regions with the same size as the P block and the Q block, which are marked as { Mij|i∈[1,P],j∈[1,Q]};
(3.2) the K-frame grayscale map G 'is judged cyclically by the following steps (3.3) to (3.9) { G'i|i∈[1,K]Whether it is occluded;
(3.3) mixing g 'in horizontal and vertical directions'iAveragely cutting the P block and the Q block into regions to be detected with the same size, and recording the regions as { aij|i∈[1,P],j∈[1,Q]};
(3.4) the following steps (3.5) to (3.7) are repeated to judge aijWhether it is occluded or not;
(3.5) calculation of aijMean of gray scale Mean (a)ij) And standard deviation Std (a)ij);
(3.6) if Mean (a)ij) < Tm and Std (a)ij) < Ts, the area a is calculated by positionijWith background model MijThe absolute value of the difference, denoted as abs (a)ij-Mij);
(3.7) if Mean (abs (a)ij-Mij) Ta), then return to aijThe area is occluded, otherwise return to aijIs not occluded;
(3.8) if g'iIn which there is a certain area aijIs shielded and returns to g'iIs shielded, otherwise returns to g'iIs not occluded;
(3.9) calculating G 'blocked in G'iThe number is marked as L; and if L is more than Tl, returning to the monitoring camera to be shielded, otherwise, returning to the monitoring camera to be normal.
(4.1) if the monitoring camera to be detected is judged to be blocked, reminding a user by calling a short message sending module to send a short message notice to a specified mobile phone number, or popping up a window on a monitoring server to remind, or both; and the storage module is called to store the relevant information in the database.
(4.2) if it is judged that the monitoring camera to be detected is not occluded, calculating G ' ═ G ' by position in time series 'i|i∈[1,K]Mean of { fraction (v) }, denoted Mean (G'); and updating the background model according to the formula M ═ (M + Mean (G'))/2.
Therefore, the background model is updated in real time based on the background model technology, and whether the monitoring camera is shielded or not is finally detected in real time at high speed and with high accuracy.
Having thus described the principal technical features and basic principles of the invention, and the advantages associated therewith, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description is described in terms of various embodiments, not every embodiment includes only a single embodiment, and such descriptions are provided for clarity only, and those skilled in the art will recognize that the embodiments described herein can be combined as a whole to form other embodiments as would be understood by those skilled in the art.
Claims (1)
1. A real-time detection method for shielding of a monitoring camera based on a background model is characterized by comprising the following specific steps:
firstly, establishing a background model M of a monitoring camera to be detected under the condition of no shielding when a system is initialized;
step two, acquiring the monitoring image of the monitoring camera to be detected in real time when the system normally operates;
comparing the background model M with the monitoring image of the monitoring camera to be detected, and judging whether the monitoring camera to be detected is shielded;
step four, if the monitoring camera to be detected is judged to be blocked, reminding a user; if the monitoring camera to be detected is judged not to be shielded, updating the background model M according to the monitoring image obtained by the monitoring camera to be detected at present, and continuing to perform the step two;
wherein, in the step one, the concrete steps are as follows:
(1.1) acquiring an N-frame color image of the monitoring camera to be detected under the condition of no shielding when a system is initialized;
(1.2) converting the N-frame color image into a gray scale image, and recording as G ═ Gi|i∈[1,N]};
(1.3) calculating the average value of G in time series according to pixel positions, the background model isThereby obtaining a background model M of the monitoring camera to be detected under the condition of no shielding;
in the second step, the specific steps are as follows:
(2.1) acquiring K frame color images at the same time interval when the system is in normal operation;
(2.2) converting the K-frame color image into a gray scale map, which is recorded as G ═ G'i|i∈[1,K]Obtaining a monitoring image of the monitoring camera to be detected;
in the third step, the concrete steps are as follows:
(3.1) in the horizontal and vertical directions, the background model M is averagely divided into regions with the same size as the P block and the Q block, which are marked as { Mij|i∈[1,P],j∈[1,Q]};
(3.2) the K-frame grayscale map G 'is judged cyclically by the following steps (3.3) to (3.9) { G'i|i∈[1,K]Whether it is occluded;
(3.3) mixing g 'in horizontal and vertical directions'iAveragely cutting the P block and the Q block into regions to be detected with the same size, and recording the regions as { aij|i∈[1,P],j∈[1,Q]};
(3.4) the following steps (3.5) to (3.7) are repeated to judge aijWhether it is occluded or not;
(3.5) calculation of aijMean of gray scale Mean (a)ij) And standard deviation Std (a)ij);
(3.6) if Mean (a)ij) < Tm and Std (a)ij) < Ts, the area a is calculated by positionijWith background model MijThe absolute value of the difference, denoted as abs (a)ij-Mij);
(3.7) if Mean (abs (a)ij-Mij) Ta), then return to aijThe area is occluded, otherwise return to aijIs not occluded;
(3.8) if g'iIn which there is a certain area aijIs shielded and returns to g'iIs shielded, otherwise returns to g'iIs not occluded;
(3.9) calculating G 'blocked in G'iThe number is marked as L; if L is larger than Tl, returning to the monitoring camera to be shielded, otherwise returning to the monitoring camera to be normal;
in the fourth step, if the monitored camera to be detected is judged to be blocked, the user is reminded, and the specific steps are as follows:
(4.11) reminding the user by calling a short message sending module, sending a short message notice to a specified mobile phone number, and/or popping up a window on a monitoring server for reminding;
(4.12) calling a storage module to store the related information into a database;
in the fourth step, if it is determined that the monitoring camera to be detected is not shielded, the specific step of updating the background model M according to the monitoring image obtained by the current monitoring camera to be detected includes:
(4.21) calculating G ' ═ G ' by position in time series 'i|i∈[1,K]Mean of { fraction (v) }, denoted Mean (G');
(4.22) updating the background model according to the formula M ═ M + Mean (G')/2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910899899.8A CN110636281B (en) | 2019-09-23 | 2019-09-23 | Real-time monitoring camera shielding detection method based on background model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910899899.8A CN110636281B (en) | 2019-09-23 | 2019-09-23 | Real-time monitoring camera shielding detection method based on background model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110636281A CN110636281A (en) | 2019-12-31 |
CN110636281B true CN110636281B (en) | 2021-06-18 |
Family
ID=68972365
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910899899.8A Active CN110636281B (en) | 2019-09-23 | 2019-09-23 | Real-time monitoring camera shielding detection method based on background model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110636281B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112261402B (en) * | 2020-09-22 | 2022-08-16 | 北京紫光展锐通信技术有限公司 | Image detection method and system and camera shielding monitoring method and system |
CN112422953B (en) * | 2020-10-22 | 2023-03-03 | 深圳云天励飞技术股份有限公司 | Method and device for identifying whether camera is shielded or not and terminal equipment |
CN112597952A (en) * | 2020-12-28 | 2021-04-02 | 深圳市捷顺科技实业股份有限公司 | Method, device and system for identifying monitoring state of camera and storage medium |
CN117557969B (en) * | 2024-01-12 | 2024-05-03 | 盛视科技股份有限公司 | Real-time detection method for shielding monitoring |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231223A (en) * | 2011-06-02 | 2011-11-02 | 深圳中兴力维技术有限公司 | Foreign object blocking and alarming method used for camera |
CN104079886A (en) * | 2014-07-09 | 2014-10-01 | 李任鸿 | Method for detecting whether monitoring camera shielded or disturbed |
CN107316312A (en) * | 2017-06-30 | 2017-11-03 | 深圳信路通智能技术有限公司 | A kind of video image occlusion detection method and system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2009032922A1 (en) * | 2007-09-04 | 2009-03-12 | Objectvideo, Inc. | Stationary target detection by exploiting changes in background model |
CN206894785U (en) * | 2017-07-13 | 2018-01-16 | 来邦科技股份公司 | The talkback unit that the guard mechanism and camera of a kind of camera can block |
-
2019
- 2019-09-23 CN CN201910899899.8A patent/CN110636281B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102231223A (en) * | 2011-06-02 | 2011-11-02 | 深圳中兴力维技术有限公司 | Foreign object blocking and alarming method used for camera |
CN104079886A (en) * | 2014-07-09 | 2014-10-01 | 李任鸿 | Method for detecting whether monitoring camera shielded or disturbed |
CN107316312A (en) * | 2017-06-30 | 2017-11-03 | 深圳信路通智能技术有限公司 | A kind of video image occlusion detection method and system |
Also Published As
Publication number | Publication date |
---|---|
CN110636281A (en) | 2019-12-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110636281B (en) | Real-time monitoring camera shielding detection method based on background model | |
CN103729858B (en) | A kind of video monitoring system is left over the detection method of article | |
CN107948465B (en) | A kind of method and apparatus that detection camera is disturbed | |
CN101615295B (en) | Image processing system, image processing method | |
CN109147368A (en) | Intelligent driving control method device and electronic equipment based on lane line | |
CN111047818A (en) | Forest fire early warning system based on video image | |
CN112800860B (en) | High-speed object scattering detection method and system with coordination of event camera and visual camera | |
US20210248817A1 (en) | Data processing method and apparatus | |
KR20210078530A (en) | Lane property detection method, device, electronic device and readable storage medium | |
CN108629316A (en) | A kind of video accident detection method of various visual angles | |
CN111339905B (en) | CIM well lid state visual detection system based on deep learning and multiple visual angles | |
CN103763515A (en) | Video anomaly detection method based on machine learning | |
CN101835035A (en) | Regional invasion real-time detection method | |
CN109886219A (en) | Shed object detecting method, device and computer readable storage medium | |
CN107705326A (en) | A kind of intrusion detection method that crosses the border in security sensitive region | |
CN107610393A (en) | A kind of intelligent office monitoring system | |
CN110348343A (en) | A kind of act of violence monitoring method, device, storage medium and terminal device | |
CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
CN111461078A (en) | Anti-fishing monitoring method based on computer vision technology | |
CN108846852A (en) | Monitor video accident detection method based on more examples and time series | |
CN112530021A (en) | Method, apparatus, device and storage medium for processing data | |
CN112927178B (en) | Occlusion detection method, occlusion detection device, electronic device, and storage medium | |
CN117612060A (en) | Video early warning system, method, equipment and medium based on artificial intelligent detection | |
CN111461076A (en) | Smoke detection method and smoke detection system combining frame difference method and neural network | |
CN112883768A (en) | Object counting method and device, equipment and storage medium |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Real Time Occlusion Detection Method for Surveillance Cameras Based on Background Model Effective date of registration: 20231107 Granted publication date: 20210618 Pledgee: Agricultural Bank of China Co.,Ltd. Ganzhou Zhanggong Sub branch Pledgor: JIANGXI YIYUAN MULTI-MEDIA TECHNOLOGY Co.,Ltd. Registration number: Y2023980064612 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |