CN109241977A - A kind of camera lens occlusion detection method - Google Patents
A kind of camera lens occlusion detection method Download PDFInfo
- Publication number
- CN109241977A CN109241977A CN201810871895.4A CN201810871895A CN109241977A CN 109241977 A CN109241977 A CN 109241977A CN 201810871895 A CN201810871895 A CN 201810871895A CN 109241977 A CN109241977 A CN 109241977A
- Authority
- CN
- China
- Prior art keywords
- image frame
- depth
- camera lens
- foreground image
- determining
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Abstract
A kind of camera lens occlusion detection method provided by the invention, is primarily characterized in that, comprising: step 1: determining the monitoring area of video camera, acquires monitoring video information;Step 2: determining foreground image frame, the foreground image frame includes depth information;Step 3: determining the depth histogram of the foreground image frame according to the depth information;Step 4: determining the difference of the depth histogram of the foreground image frame and the depth histogram of background model, the background model is determined according to background image frame, and the background image frame includes depth information;Step 5: determining whether camera lens is blocked according to the difference;Step 6: after determination is blocked, alert.A kind of camera lens occlusion detection method provided by the invention is based on depth information using depth histogram come Statistic analysis foreground depth and background depth, can effectively improve the accuracy of camera lens occlusion detection, have important application value.
Description
Technical field
The invention belongs to security monitoring technologies, more particularly to a kind of camera lens occlusion detection method.
Background technique
Currently, the safety defense monitoring system of the various scales of China's every profession and trade is very universal, in addition to public security, finance,
Outside the special dimensions such as bank, traffic, army and port, community, office building, hotel, public place are also mounted mostly
Safety monitoring equipment.When the camera lens in safety monitoring equipment are artificially maliciously blocked, if monitoring personnel fails in time
It was found that when, then it will lead to monitoring failure.
The method for solving the camera lens occlusion detection in the prior art is to obtain contextual data by camera lens, is established
RGB background model counts the difference of foreground and background to judge whether camera lens is blocked.Since the collected data of camera lens are
RGB data, the image restored are two-dimensional image, can not judge that prospect arrives the distance of camera lens, so indistinguishable prospect
Pixel variation is caused by being blocked as camera lens, or due to objects many in scene move at, for example, if using one
When the photo of background blocks camera lens, scene and the real background seen in camera lens are no different, and are hidden due to can not preferably restore camera lens
The physical process of gear is only the conjecture based on panel data variation, therefore will lead to the accuracy rate of camera lens occlusion detection
It is lower, preferable safety monitoring effect is not achieved.
Summary of the invention
In consideration of it, a kind of camera lens occlusion detection method provided by the invention, can effectively solve the above problems.
A kind of camera lens occlusion detection method provided by the invention, comprising the following steps:
Step 1: determining the monitoring area of video camera, monitoring video information is acquired;
Step 2: determining foreground image frame, the foreground image frame includes depth information;
Step 3: determining the depth histogram of the foreground image frame according to the depth information;
Step 4: determining the difference of the depth histogram of the foreground image frame and the depth histogram of background model, the back
Scape model is determined according to background image frame, and the background image frame includes depth information;
Step 5: determining whether camera lens is blocked according to the difference;
Step 6: after determination is blocked, alert.
The beneficial effects of the present invention are: a kind of camera lens occlusion detection method provided by the invention utilizes depth
Histogram, come Statistic analysis foreground depth and background depth, and then detects whether camera lens is maliciously blocked based on depth information.
Compared with the prior art the technical solution that camera lens is blocked, due to the increased depth information, pair of detection are judged using RGB information in
As becoming three-dimensional from two dimension, the content of detection is more abundant preferably to restore the essence that camera lens block comprehensively, can
The accuracy of camera lens occlusion detection is effectively improved, provides reliable guarantee for security protection work, applies valence with important
Value.
Detailed description of the invention
It, below will be to embodiment in order to illustrate more clearly of the invention patent embodiment or technical solution in the prior art
Or attached drawing used in description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is flow diagram of the invention.
Specific embodiment
Illustrate embodiments of the present invention below by way of specific specific example, those skilled in the art can be by this specification
Other advantages and efficacy of the present invention can be easily understood for disclosed content, and the present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints and application, without departing from
Various modifications or alterations are carried out under spirit of the invention.
It should be noted that the basic conception that only the invention is illustrated in a schematic way is illustrated provided in the present embodiment,
Only display and related component in the present invention in schematic diagram, its assembly layout kenel may also be increasingly complex when actual implementation.
A kind of camera lens occlusion detection method provided by the invention, comprising the following steps:
Step S101: determining the monitoring area of video camera, acquires monitor video image information;
Step S102: determine that foreground image frame, the foreground image frame include depth information;
Step S103: the depth histogram of the foreground image frame is determined according to the depth information;
Step S104: determining the difference of the depth histogram of the foreground image frame and the depth histogram of background model, described
Background model is determined according to background image frame, and the background image frame includes depth information;
Step S105: determine whether camera lens are blocked according to the difference;
Step S106: after determining that camera lens are blocked, alert.
Further, determine that foreground image frame, the foreground image frame include in depth information, using mixed in step S102
It closes Gauss model and establishes background model, the foreground image frame can be determined according to predetermined period.
Further, in the depth histogram that step S103 determines the foreground image frame according to the depth information,
The depth histogram of the foreground image frame can be according to background model scaled down.
Further, the depth histogram of the foreground image frame and the depth histogram of background model are determined in step S104
In the difference of figure, the difference of depth histogram is compared by way of given threshold.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention, any ripe
The personage for knowing this technology all without departing from the spirit and scope of the present invention, carries out modifications and changes to above-described embodiment, because
This, institute is complete without departing from the spirit and technical ideas disclosed in the present invention by those of ordinary skill in the art such as
At all equivalent modifications or change, should be covered by the claims of the present invention.
Claims (4)
1. a kind of camera lens occlusion detection method, is primarily characterized in that, comprising:
Step 1: determining the monitoring area of video camera, monitoring video information is acquired;
Step 2: determining foreground image frame, the foreground image frame includes depth information;
Step 3: determining the depth histogram of the foreground image frame according to the depth information;
Step 4: determining the difference of the depth histogram of the foreground image frame and the depth histogram of background model, the back
Scape model is determined according to background image frame, and the background image frame includes depth information;
Step 5: determining whether camera lens is blocked according to the difference;
Step 6: after determination is blocked, alert.
2. a kind of camera lens occlusion detection method according to claim 1, is primarily characterized in that: determining prospect
Picture frame, the foreground image frame include to establish background model, the prospect using mixed Gauss model in depth information step
Picture frame can be determined according to predetermined period.
3. a kind of camera lens occlusion detection method according to claim 1, is primarily characterized in that: according to
Depth information determines in the depth histogram step of the foreground image frame that the depth histogram of the foreground image frame can root
According to background model scaled down.
4. a kind of camera lens occlusion detection method according to claim 1, is primarily characterized in that: described in determination
In the difference step of the depth histogram of the depth histogram and background model of foreground image frame, by way of given threshold come
Compare the difference of depth histogram.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810871895.4A CN109241977A (en) | 2018-08-02 | 2018-08-02 | A kind of camera lens occlusion detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810871895.4A CN109241977A (en) | 2018-08-02 | 2018-08-02 | A kind of camera lens occlusion detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109241977A true CN109241977A (en) | 2019-01-18 |
Family
ID=65072820
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810871895.4A Pending CN109241977A (en) | 2018-08-02 | 2018-08-02 | A kind of camera lens occlusion detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109241977A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110647858A (en) * | 2019-09-29 | 2020-01-03 | 上海依图网络科技有限公司 | Video occlusion judgment method and device and computer storage medium |
US11551465B2 (en) | 2020-06-30 | 2023-01-10 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Method and apparatus for detecting finger occlusion image, and storage medium |
-
2018
- 2018-08-02 CN CN201810871895.4A patent/CN109241977A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110647858A (en) * | 2019-09-29 | 2020-01-03 | 上海依图网络科技有限公司 | Video occlusion judgment method and device and computer storage medium |
US11551465B2 (en) | 2020-06-30 | 2023-01-10 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Method and apparatus for detecting finger occlusion image, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107509059A (en) | Camera lens occlusion detection method | |
CN102231223B (en) | Foreign object blocking and alarming method used for camera | |
CN104657993B (en) | A kind of camera lens occlusion detection method and device | |
CN105940430B (en) | Personnel's method of counting and its device | |
CN102750709B (en) | Video is utilized to detect the method and apparatus of behavior of fighting | |
CN103729858B (en) | A kind of video monitoring system is left over the detection method of article | |
CN106878670B (en) | A kind of method for processing video frequency and device | |
CN105404888A (en) | Saliency object detection method integrated with color and depth information | |
CN101883261A (en) | Method and system for abnormal target detection and relay tracking under large-range monitoring scene | |
CN107316312A (en) | A kind of video image occlusion detection method and system | |
CN108694741A (en) | A kind of three-dimensional rebuilding method and device | |
CN109740444A (en) | Flow of the people information displaying method and Related product | |
CN104506850B (en) | A kind of video shelter determination methods and device | |
CN109598706A (en) | A kind of camera lens occlusion detection method and system | |
CN112530021A (en) | Method, apparatus, device and storage medium for processing data | |
CN106295557B (en) | A kind of method and device of crowd density estimation | |
CN110348343A (en) | A kind of act of violence monitoring method, device, storage medium and terminal device | |
CN109241977A (en) | A kind of camera lens occlusion detection method | |
CN207233038U (en) | Face is called the roll and number system | |
CN114037087B (en) | Model training method and device, depth prediction method and device, equipment and medium | |
CN106815567A (en) | A kind of flame detecting method and device based on video | |
CN105930814A (en) | Method for detecting personnel abnormal gathering behavior on the basis of video monitoring platform | |
CN107301373B (en) | Data processing method, device and storage medium | |
CN104349125A (en) | Area monitoring method and device | |
CN111274888B (en) | Helmet and work clothes intelligent identification method based on wearable mobile glasses |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190118 |