CN109598706A - A kind of camera lens occlusion detection method and system - Google Patents
A kind of camera lens occlusion detection method and system Download PDFInfo
- Publication number
- CN109598706A CN109598706A CN201811417308.0A CN201811417308A CN109598706A CN 109598706 A CN109598706 A CN 109598706A CN 201811417308 A CN201811417308 A CN 201811417308A CN 109598706 A CN109598706 A CN 109598706A
- Authority
- CN
- China
- Prior art keywords
- image
- camera lens
- video image
- blocked
- clarity
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 abstract description 9
- 230000015654 memory Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a kind of camera lens occlusion detection method and system, belong to security monitoring technology, the video image monitored including obtaining video camera；Calculate the clarity of the video image；According to the clarity of video image, determine whether camera lens are blocked.Whether the present invention is blocked according to the definition judgment camera lens of video image.Compared with existing algorithm, background modeling is carried out without the additional time, long and short buffer area is established without additional memory, all achieves in detection accuracy and detection time compared with much progress.
Description
Technical field
The present invention relates to security monitoring technology, in particular to a kind of camera lens occlusion detection method and system.
Background technique
The every field gone into the thick of life with intelligent video technology has greatly ensured the safety of people.But when camera shooting
Camera lens is artificially maliciously blocked, and monitoring personnel is found not in time, then will lead to monitoring failure.
Currently, camera lens occlusion detection method is roughly divided into two classes: detection method based on background modeling and being based on
The detection method of buffer area.Wherein:
Camera lens occlusion detection algorithm based on background modeling needs first to carry out background to monitoring scene before detection
Modeling, judges whether camera lens are blocked by comparing the difference of background image and current video image.By comparing
The comentropy of background image and current video image judges whether camera lens are blocked；Or by comparing background image
Judge whether camera lens are blocked with the grey level histogram of current video image.
Camera lens occlusion detection algorithm based on buffer area does not need to carry out monitoring scene background modeling, but needs
Establish two buffer storages: in short-term memory block and it is long when memory block, store respectively apart from current video image it is relatively close and
Video image in farther away a period of time.Then acquire respectively memory block in short-term and it is long when memory block every two frame between difference
Difference when different, long in memory block between every two frame, takes the intermediate value of two species diversity respectively, seeks its ratio, finally and threshold value comparison,
Judge whether camera lens are blocked.
The shortcomings that above two method, is mainly: it is more sensitive to the noise generated in video image, especially having greatly
Measuring in the scene of goal activities can not correctly judge whether camera lens are blocked；And algorithm when analyzing occupied memory and
It is larger to consume resource.
Summary of the invention
The purpose of the present invention is to provide a kind of camera lens occlusion detection method and system, to improve camera lens
The accuracy rate of occlusion detection and real-time rate.
In order to achieve the above object, the present invention uses a kind of camera lens occlusion detection method, include the following steps:
Obtain the video image that video camera is monitored；
Calculate the clarity of the video image；
According to the clarity of the video image, determine whether camera lens are blocked.
Preferably, the clarity for calculating the video image, comprising:
Gray processing processing is carried out to video image, obtains gray level image；
The Laplacian values of each pixel of the gray level image are extracted using Laplace operator；
The absolute value of the Laplacian values of each pixel is added, the clarity of the video image is obtained.
Preferably, the clarity according to video image, determines whether camera lens are blocked, comprising:
The clarity of the video image is compared with the threshold value of setting；
When the clarity of the video image is less than the threshold value of setting, determine that camera lens are blocked.
Preferably, further includes:
The clarity of the video image is compared with the threshold value of setting；
When the clarity of the video image is less than the threshold value of setting, determine that the video image is the image that is blocked；
When the frame number of the image that is blocked is greater than setting numerical value, determine that camera lens are blocked.
Preferably, the frame number of the image that is blocked is the frame number of image of being continuously blocked.
On the other hand, a kind of camera lens sheltering detection system is provided, comprising: obtain module, sharpness computation module
And determining module；
Module is obtained for obtaining the video image that video camera is monitored；
Sharpness computation module is used to calculate the clarity of the video image；
Determining module is used for the clarity according to the video image, determines whether camera lens are blocked.
Preferably, the sharpness computation module includes gray processing processing unit, Laplacian values computing unit and clear
Spend computing unit；
Gray processing processing unit is used to carry out gray processing processing to video image, obtains gray level image；
Laplacian values computing unit is used to extract each pixel of the gray level image using Laplace operator
Laplacian values；
Sharpness computation unit is used to for the absolute value of the Laplacian values of each pixel being added, and obtains the view
The clarity of frequency image.
Preferably, the determining module includes the first comparing unit and the first determination unit；
Comparing unit is for the clarity of the video image to be compared with the threshold value of setting；
Determination unit is used to determine that camera lens are hidden when the clarity of the video image is less than the threshold value of setting
Gear.
Preferably, the determining module further includes the second comparing unit and the second determination unit；
First determination unit is also used to when the clarity of the video image is less than the threshold value of setting, described in determination
Video image is the image that is blocked；
Second comparing unit is used to for the frame number of the image that is blocked being compared with setting numerical value；
Second determination unit is used to determine camera lens quilt when the frame number of the image that is blocked is greater than setting numerical value
It blocks.
Preferably, the frame number of the image that is blocked is the frame number of image of being continuously blocked.
Compared with prior art, there are following technical effects by the present invention: since camera lens are by collected after shield
The edge detail information of video image tails off, i.e., the clarity of image can reduce.Therefore the present invention is in real time to camera supervised
Video image is acquired, and calculates the clarity of video image, and the definition judgment camera lens according to video image are
It is no to be blocked.Compared with existing algorithm, background modeling is carried out without the additional time, long without additional memory foundation,
Short buffer area all achieves in detection accuracy and detection time compared with much progress.
Detailed description of the invention
With reference to the accompanying drawing, specific embodiments of the present invention will be described in detail:
Fig. 1 is a kind of li journey schematic diagram of camera lens occlusion detection method；
Fig. 2 is a kind of structural schematic diagram of camera lens sheltering detection system.
Specific embodiment
In order to further explain feature of the invention, reference should be made to the following detailed description and accompanying drawings of the present invention.Institute
Attached drawing is only for reference and purposes of discussion, is not used to limit protection scope of the present invention.
As shown in Figure 1, including the following steps S1 extremely present embodiment discloses a kind of camera lens occlusion detection method
S3:
S1, the video image that video camera is monitored is obtained；
S2, the clarity for calculating the video image；
S3, according to the clarity of the video image, determine whether camera lens are blocked.
It should be noted that the present embodiment passes through the monitoring area for determining video camera, video camera is obtained in monitoring area
The monitoring video information of shooting, and the clarity of video image is calculated, whether camera lens are detected according to the clarity of image
It is blocked, does not need additional time progress background modeling, do not need additional memory and establish long and short buffer area.It simultaneously can be with
Correctly judge whether camera lens are blocked in the scene for there are a large amount of goal activities, in detection accuracy and detection time all
There is biggish advantage.
Preferably, above-mentioned steps S2: calculating the clarity of the video image, includes the following steps S21 to S23:
S21, gray processing processing is carried out to video image, obtains gray level image；
Wherein, gray processing treatment process is carried out to RGB image are as follows:
Gray=R*0.299+G*0.587+B*0.114, * indicate product.
S22, extracted using Laplace operator the gray level image each pixel Laplacian values；
S23, the absolute value of the Laplacian values of each pixel is added, obtains the clear of the video image
Degree.
Wherein, the clarity V of video imageLCalculation formula it is as follows:
Wherein, VLIndicate the sum of the absolute value of Laplacian values of a width gray level image all pixels point, i.e. gray level image
Clarity.F (x, y) indicates gray value of the image at (x, y), and w, h respectively indicate the length and width of video image.
Preferably, above-mentioned steps S3: according to the clarity of video image, determining whether camera lens are blocked, including
Following steps S31 to S32:
S31, the clarity of the video image is compared with the threshold value T of setting；
S32, the video image clarity be less than setting threshold value when, determine that camera lens are blocked.
It should be noted that the threshold value T set in the present embodiment is that those skilled in the art obtain by many experiments
One numerical value being compared for the clarity of video image.Specially analyze a large amount of camera lens normal photographings scene image and
The scene image shot under occlusion carries out clarity analysis respectively, can be obtained normal and blocks under two kinds of different situations
Clarity is distributed in different zones, and threshold value T is separation between the two.
The clarity of the video image is compared with the threshold value T of setting；
When the clarity of the video image is less than the threshold value T of setting, determine that the video image is the image that is blocked；
When the frame number of the image that is blocked is greater than setting numerical value M, determine that camera lens are blocked.
It should be noted that the value of setting numerical value M is related with the scene of the frame per second of video camera and application, in ordinary circumstance
Under, it is that shielded image can determine that video camera is blocked that video camera, which collects image all, in 5 seconds to 10 seconds, so in this period
The frame number range of acquisition is the range of M.
It should be noted that using the clarity of Laplace operator quantization piece image in the present embodiment, and according to setting
Whether fixed threshold decision is shielded image；Continuously accumulating in shielded image to certain amount backsight is that camera lens are hidden
Gear, improves the accuracy rate of camera lens shadowing.
It should be noted that the setting numerical value in the present embodiment is that those skilled in the art pass through many experiments obtain one
A numerical value being compared for number of image frames.
Preferably, in the present embodiment set numerical value M can value as 10, i.e., when the frame number for the image that is blocked is greater than 10,
It can accurately judge that cam lens are blocked.
It should be understood that setting numerical value M can be adjusted according to different application scenarios, to guarantee recognition accuracy
Under the premise of, the speed for blocking camera lens identification is improved as far as possible.
Preferably, the frame number of the image that is blocked is the frame number of image of being continuously blocked.The present embodiment is connected by judgement
When the video image of continuous 10 frames is blocked, determines that camera lens are blocked, improve the accuracy rate of camera lens occlusion detection.
As shown in Fig. 2, present embodiment discloses a kind of camera lens sheltering detection system, including obtain module 10, clear
Clear degree computing module 20 and determining module 30；
Module 10 is obtained for obtaining the video image that video camera is monitored；
Sharpness computation module 20 is used to calculate the clarity of the video image；
Determining module 30 is used for the clarity according to the video image, determines whether camera lens are blocked.
Preferably, the sharpness computation module includes gray processing processing unit, Laplacian values computing unit and clear
Spend computing unit；
Gray processing processing unit is used to carry out gray processing processing to video image, obtains gray level image；
Wherein, gray processing treatment process is carried out to RGB image are as follows: Gray=R*0.299+G*0.587+B*0.114, * table
Show product.
Laplacian values computing unit is used to extract each pixel of the gray level image using Laplace operator
Laplacian values；
Sharpness computation unit is used to for the absolute value of the Laplacian values of each pixel being added, and obtains the view
The clarity of frequency image.
Specifically, the clarity V of video imageLCalculation formula it is as follows:
Wherein, VLIndicate the sum of the absolute value of Laplacian values of a width gray level image all pixels point, i.e. gray level image
Clarity.F (x, y) indicates gray value of the image at (x, y), and w, h respectively indicate the length and width of video image.
Preferably, the determining module includes the first comparing unit and the first determination unit；
Comparing unit is for the clarity of the video image to be compared with the threshold value of setting；
Determination unit is used to determine that camera lens are hidden when the clarity of the video image is less than the threshold value of setting
Gear.
Preferably, the determining module further includes the second comparing unit and the second determination unit；
First determination unit is also used to when the clarity of the video image is less than the threshold value of setting, described in determination
Video image is the image that is blocked；
Second comparing unit is used to for the frame number of the image that is blocked being compared with setting numerical value；
Second determination unit is used to determine camera lens quilt when the frame number of the image that is blocked is greater than setting numerical value
It blocks.
It should be noted that using the clarity of Laplace operator quantization piece image in the present embodiment, and according to setting
Whether fixed threshold decision is shielded image；Continuously accumulating in shielded image to certain amount backsight is that camera lens are hidden
Gear, improves the accuracy rate of camera lens shadowing.
More preferably, the frame number of the image that is blocked is the frame number of image of being continuously blocked.
More preferably, it is additionally provided with alarm module in this system, when system judges that camera lens are blocked, issued
Alarm.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of camera lens occlusion detection method characterized by comprising
Obtain the video image that video camera is monitored；
Calculate the clarity of the video image；
According to the clarity of the video image, determine whether camera lens are blocked.
2. camera lens occlusion detection method as described in claim 1, which is characterized in that described to calculate the video image
Clarity, comprising:
Gray processing processing is carried out to video image, obtains gray level image；
The Laplacian values of each pixel of the gray level image are extracted using Laplace operator；
The absolute value of the Laplacian values of each pixel is added, the clarity of the video image is obtained.
3. camera lens occlusion detection method as claimed in claim 2, which is characterized in that described according to the clear of video image
Clear degree, determines whether camera lens are blocked, comprising:
The clarity of the video image is compared with the threshold value of setting；
When the clarity of the video image is less than the threshold value of setting, determine that camera lens are blocked.
4. camera lens occlusion detection method as claimed in claim 3, which is characterized in that further include:
The clarity of the video image is compared with the threshold value of setting；
When the clarity of the video image is less than the threshold value of setting, determine that the video image is the image that is blocked；
When the frame number of the image that is blocked is greater than setting numerical value, determine that camera lens are blocked.
5. camera lens occlusion detection method as claimed in claim 4, which is characterized in that the frame number of the image that is blocked
For the frame number for the image that is continuously blocked.
6. a kind of camera lens sheltering detection system characterized by comprising obtain module, sharpness computation module and really
Cover half block；
Module is obtained for obtaining the video image that video camera is monitored；
Sharpness computation module is used to calculate the clarity of the video image；
Determining module is used for the clarity according to the video image, determines whether camera lens are blocked.
7. the camera lens sheltering detection system guarded such as claim 6, which is characterized in that the sharpness computation module
Including gray processing processing unit, Laplacian values computing unit and sharpness computation unit；
Gray processing processing unit is used to carry out gray processing processing to video image, obtains gray level image；
Laplacian values computing unit is used to extract the La Pu of each pixel of the gray level image using Laplace operator
Lars value；
Sharpness computation unit is used to for the absolute value of the Laplacian values of each pixel being added, and obtains the video figure
The clarity of picture.
8. camera lens sheltering detection system as claimed in claim 7, which is characterized in that the determining module includes first
Comparing unit and the first determination unit；
Comparing unit is for the clarity of the video image to be compared with the threshold value of setting；
Determination unit is used to determine that camera lens are blocked when the clarity of the video image is less than the threshold value of setting.
9. camera lens sheltering detection system as claimed in claim 7, which is characterized in that the determining module further includes
Two comparing units and the second determination unit；
First determination unit is also used to determine the video when the clarity of the video image is less than the threshold value of setting
Image is the image that is blocked；
Second comparing unit is used to for the frame number of the image that is blocked being compared with setting numerical value；
Second determination unit is used to determine that camera lens are hidden when the frame number of the image that is blocked is greater than setting numerical value
Gear.
10. camera lens sheltering detection system as claimed in claim 9, which is characterized in that the frame of the image that is blocked
It counts as the frame number for the image that is continuously blocked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811417308.0A CN109598706A (en) | 2018-11-26 | 2018-11-26 | A kind of camera lens occlusion detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811417308.0A CN109598706A (en) | 2018-11-26 | 2018-11-26 | A kind of camera lens occlusion detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598706A true CN109598706A (en) | 2019-04-09 |
Family
ID=65958827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811417308.0A Pending CN109598706A (en) | 2018-11-26 | 2018-11-26 | A kind of camera lens occlusion detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598706A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110049320A (en) * | 2019-05-23 | 2019-07-23 | 北京猎户星空科技有限公司 | Camera occlusion detection method, apparatus, electronic equipment and storage medium |
| CN111711762A (en) * | 2020-06-30 | 2020-09-25 | 云从科技集团股份有限公司 | Camera lens module shielding control method and device based on target detection and camera |
| CN112291551A (en) * | 2020-06-23 | 2021-01-29 | 广州红贝科技有限公司 | Video quality detection method based on image processing, storage device and mobile terminal |
| CN112927262A (en) * | 2021-03-22 | 2021-06-08 | 瓴盛科技有限公司 | Camera lens shielding detection method and system based on video |
| CN112924344A (en) * | 2021-01-22 | 2021-06-08 | 中煤科工集团重庆研究院有限公司 | Monitoring system and method for acquiring underground coal mine dust concentration based on image |
| CN113011216A (en) * | 2019-12-19 | 2021-06-22 | 合肥君正科技有限公司 | Multi-classification threshold self-adaptive occlusion detection method |
| CN117557969A (en) * | 2024-01-12 | 2024-02-13 | 盛视科技股份有限公司 | Real-time detection method for shielding monitoring |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102176244A (en) * | 2011-02-17 | 2011-09-07 | 东方网力科技股份有限公司 | Method and device for determining shielding condition of camera head |
| CN102903098A (en) * | 2012-08-28 | 2013-01-30 | 四川虹微技术有限公司 | Depth estimation method based on image definition difference |
| CN103136530A (en) * | 2013-02-04 | 2013-06-05 | 国核自仪系统工程有限公司 | Method for automatically recognizing target images in video images under complex industrial environment |
| CN103473776A (en) * | 2013-09-17 | 2013-12-25 | 深圳市华因康高通量生物技术研究院 | Method and system for comparing image definition and automatic focusing control method |
| CN104345520A (en) * | 2014-04-01 | 2015-02-11 | 项国彩 | Automatic shielding device for network camera lens |
| CN105744268A (en) * | 2016-05-04 | 2016-07-06 | 深圳众思科技有限公司 | Camera shielding detection method and device |
| CN106570028A (en) * | 2015-10-10 | 2017-04-19 | 比亚迪股份有限公司 | Mobile terminal, fuzzy image deletion method and fuzzy picture deletion device |
-
2018
- 2018-11-26 CN CN201811417308.0A patent/CN109598706A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102176244A (en) * | 2011-02-17 | 2011-09-07 | 东方网力科技股份有限公司 | Method and device for determining shielding condition of camera head |
| CN102903098A (en) * | 2012-08-28 | 2013-01-30 | 四川虹微技术有限公司 | Depth estimation method based on image definition difference |
| CN103136530A (en) * | 2013-02-04 | 2013-06-05 | 国核自仪系统工程有限公司 | Method for automatically recognizing target images in video images under complex industrial environment |
| CN103473776A (en) * | 2013-09-17 | 2013-12-25 | 深圳市华因康高通量生物技术研究院 | Method and system for comparing image definition and automatic focusing control method |
| CN104345520A (en) * | 2014-04-01 | 2015-02-11 | 项国彩 | Automatic shielding device for network camera lens |
| CN106570028A (en) * | 2015-10-10 | 2017-04-19 | 比亚迪股份有限公司 | Mobile terminal, fuzzy image deletion method and fuzzy picture deletion device |
| CN105744268A (en) * | 2016-05-04 | 2016-07-06 | 深圳众思科技有限公司 | Camera shielding detection method and device |
Non-Patent Citations (1)
| Title |
|---|
| 宋坤骏等: "基于特征筛选和轮廓分析的快速防遮挡视频人数分区统计算法", 《上海铁道科技》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110049320A (en) * | 2019-05-23 | 2019-07-23 | 北京猎户星空科技有限公司 | Camera occlusion detection method, apparatus, electronic equipment and storage medium |
| CN110049320B (en) * | 2019-05-23 | 2020-12-08 | 北京猎户星空科技有限公司 | Camera shielding detection method and device, electronic equipment and storage medium |
| CN113011216A (en) * | 2019-12-19 | 2021-06-22 | 合肥君正科技有限公司 | Multi-classification threshold self-adaptive occlusion detection method |
| CN113011216B (en) * | 2019-12-19 | 2024-04-02 | 合肥君正科技有限公司 | Multi-classification threshold self-adaptive shielding detection method |
| CN112291551A (en) * | 2020-06-23 | 2021-01-29 | 广州红贝科技有限公司 | Video quality detection method based on image processing, storage device and mobile terminal |
| CN111711762A (en) * | 2020-06-30 | 2020-09-25 | 云从科技集团股份有限公司 | Camera lens module shielding control method and device based on target detection and camera |
| CN112924344A (en) * | 2021-01-22 | 2021-06-08 | 中煤科工集团重庆研究院有限公司 | Monitoring system and method for acquiring underground coal mine dust concentration based on image |
| CN112927262A (en) * | 2021-03-22 | 2021-06-08 | 瓴盛科技有限公司 | Camera lens shielding detection method and system based on video |
| CN117557969A (en) * | 2024-01-12 | 2024-02-13 | 盛视科技股份有限公司 | Real-time detection method for shielding monitoring |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598706A (en) | A kind of camera lens occlusion detection method and system | |
| CN105894702B (en) | Intrusion detection alarm system based on multi-camera data fusion and detection method thereof | |
| US9245187B1 (en) | System and method for robust motion detection | |
| EP2801078B1 (en) | Context aware moving object detection | |
| CN104658152B (en) | A kind of moving object intrusion alarm method based on video | |
| CN106128022B (en) | A kind of wisdom gold eyeball identification violent action alarm method | |
| CN105574855B (en) | Infrared small target detection method under cloud background based on template convolution and false alarm rejection | |
| CN107133564B (en) | Tooling cap detection method | |
| WO2014092552A2 (en) | Method for non-static foreground feature extraction and classification | |
| CN105046719B (en) | A kind of video frequency monitoring method and system | |
| CN109145708A (en) | A kind of people flow rate statistical method based on the fusion of RGB and D information | |
| Srivastava et al. | Crowd flow estimation using multiple visual features for scenes with changing crowd densities | |
| CN105160297A (en) | Masked man event automatic detection method based on skin color characteristics | |
| CN103927519A (en) | Real-time face detection and filtration method | |
| CN113887445A (en) | Method and system for identifying standing and loitering behaviors in video | |
| CN105141923B (en) | A kind of video concentration method and device | |
| CN105427286A (en) | Gray scale and gradient segmentation-based infrared target detection method | |
| CN111047624A (en) | Image dim target detection method, device, equipment and storage medium | |
| Wang et al. | Early smoke detection in video using swaying and diffusion feature | |
| CN103475800A (en) | Method and device for detecting foreground in image sequence | |
| CN115631191A (en) | Coal blockage detection algorithm based on gray level features and edge detection | |
| CN101877135B (en) | Moving target detecting method based on background reconstruction | |
| CN104866844B (en) | A kind of crowd massing detection method towards monitor video | |
| CN103400148A (en) | Video analysis-based bank self-service area tailgating behavior detection method | |
| Ilao et al. | Crowd estimation using region-specific HOG With SVM |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |