CN109509190A - Video monitoring image screening technique, device, system and storage medium - Google Patents
Video monitoring image screening technique, device, system and storage medium Download PDFInfo
- Publication number
- CN109509190A CN109509190A CN201811553254.0A CN201811553254A CN109509190A CN 109509190 A CN109509190 A CN 109509190A CN 201811553254 A CN201811553254 A CN 201811553254A CN 109509190 A CN109509190 A CN 109509190A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- video
- monitoring
- video data
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 84
- 238000012216 screening Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000015654 memory Effects 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 13
- 238000011156 evaluation Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000039 congener Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention provides a kind of video monitoring image screening technique, device, system and storage medium, this method comprises: acquiring and storing video data;Real-time monitoring trigger signal;When monitoring trigger signal, target image is determined according to the inter-frame information of frame image each in video data;All target images are extracted, the target image of preset threshold is reached using the quality screening quality that picture quality optimizing algorithm assesses all target images.By being automatically analyzed to sequence image in video data, target image is determined according to the inter-frame information in continuous multiple frames image, all target image screening quality, which are assessed, using picture quality optimizing algorithm reaches preset threshold, the target image is screened when it reaches preset threshold to export to server and management platform, investigate and collect evidence when video data being facilitated to return rapidly to react in real time, improve video passback rate, reduce memory usage, the efficiency of searched targets image is improved, so that video monitoring system tends to be intelligent.
Description
Technical field
The present invention relates to a kind of video image technical fields, more particularly to a kind of video monitoring image screening technique, dress
It sets, system and storage medium.
Background technique
Video monitoring is universally present in bank, market, parking lot and traffic intersection etc., but existing video monitoring
System, is generally only capture, storage and distribution video image, these do not pass through the uncorrected data of any video analysis, do not fill
The monitoring supervisory role of real-time active is waved in distribution.
However, generally requiring manual retrieval when needing to investigate and collect evidence and returning video, transmission of video speed is slowly and in occupancy
Big, locking purpose that can not be real-time quick is deposited, the amount of labour of staff is increased.In addition, screening target using manual retrieval
Image needs intensive concentration and vigilance, since there is the physiology weakness of mankind itself as supervisor by the mankind, so that respectively
The more or less presence alarm poor accuracy of class video monitoring system, wrong report and failing to report phenomenon is more, Video data analysis difficulty
The defects of, so as to cause whole system safety and practicability reduction.
Summary of the invention
In view of the foregoing deficiencies of prior art, the purpose of the present invention is to provide a kind of video monitoring image screening sides
Method, device, system and storage medium, can not be fast in real time when returning calling for solving video monitoring image in the prior art
Fast lock onto target, the problem for causing the slow committed memory of transmission of video big.
In order to achieve the above objects and other related objects, the present invention provides a kind of video monitoring image screening technique, comprising:
It acquires and stores video data;
Real-time monitoring trigger signal;
When monitoring the trigger signal, target figure is determined according to the inter-frame information of frame image each in the video data
Picture;
All target images are extracted, screen quality using the quality that picture quality optimizing algorithm assesses all target images
Reach the target image of preset threshold.
Another object of the present invention is to provide video monitoring image screening plants, comprising:
Video collector, for acquiring and storing video data;
Monitoring modular is used for real-time monitoring trigger signal;
Target determination module, for when monitoring the trigger signal, according to frame image each in the video data
Inter-frame information determines target image;
Object filtering module assesses all targets using picture quality optimizing algorithm for extracting all target images
The quality screening quality of image reaches the target image of preset threshold.
Another object of the present invention is to provide a kind of video monitoring systems, comprising:
Video collector, for acquiring and storing video data;
Monitoring modular is used for real-time monitoring trigger signal;
Target determination module, for when monitoring the trigger signal, according to frame image each in the video data
Inter-frame information determines target image;
Object filtering module assesses all targets using picture quality optimizing algorithm for extracting all target images
The target image that the quality screening quality of image reaches preset threshold is sent to server and management platform;
Server is connected with the video collector and external data base, for according to the received target image
The target image information is identified with its related information, and recognition result is sent to management platform;
Platform is managed, is connected with the object filtering module with server, is used for according to the target image to video counts
According to progress intelligent management.
Further object of the present invention is to provide a kind of computer readable storage medium, be stored with for video monitoring image
The computer program of screening, the computer program are performed above-mentioned video monitoring image screening technique.
As described above, video monitoring image screening technique, device, system and storage medium of the invention, have with following
Beneficial effect:
By automatically analyzing to sequence image in video data, mesh is determined according to the inter-frame information in continuous multiple frames image
Logo image assesses all target image screening quality using picture quality optimizing algorithm and reaches preset threshold, when it reaches default
It screens the target image when threshold value to export to server and management platform, investigating and collecting evidence when video data being facilitated to return can be real-time
Rapidly reaction, meanwhile, video passback rate is improved, reduces memory usage, improves the efficiency of searched targets image,
So that video monitoring system tends to be intelligent.
Detailed description of the invention
Fig. 1 is shown as a kind of video monitoring image screening technique flow chart provided by the invention;
Fig. 2 is shown as step S3 flow chart in a kind of video monitoring image screening technique provided by the invention;
Fig. 3 is shown as step S4 flow chart in a kind of video monitoring image screening technique provided by the invention;
Fig. 4 is shown as a kind of video monitoring image screening plant structural block diagram provided by the invention;
Fig. 5 is shown as a kind of one implementation example figure of video monitoring image screening plant provided by the invention;
Fig. 6 is shown as a kind of another implementation example figure of video monitoring image screening plant provided by the invention;
Fig. 7 is shown as a kind of video monitoring image system structure diagram provided by 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.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 in the absence of conflict, following embodiment and implementation
Feature in example can be combined with each other.
It should be noted that illustrating the basic structure that only the invention is illustrated in a schematic way provided in following embodiment
Think, only shown in schema then with related component in the present invention rather than component count, shape and size when according to actual implementation
Draw, when actual implementation kenel, quantity and the ratio of each component can arbitrarily change for one kind, and its assembly layout kenel
It is likely more complexity.
Referring to Fig. 1, the present invention provides a kind of frequency monitoring image screening technique flow chart, comprising:
Step S1 is acquired and is stored video data;
Wherein, video data is acquired using photographing module;The photographing module is the camera of installation throughout, for example is pacified
At the public places such as market, station camera acquisition corresponding region image information, the camera can for it is a variety of not
The analog signal of acquisition is converted to digital signal by video camera, according to the Video coding lattice of standard by congener video camera
Formula and communication protocol return (transmission) by network implementations video data.
The video data of acquisition is carried out distributed storage, camera shooting by the memory module (memory) connecting with photographing module
Module can be connected to the network with memory module, and solving random disk read-write and disk fragments in conventional store causes storage performance to decline
The problem of, it is ensured that the safety and reliability of video data storage.
In addition, can also be stored as desired to local video data placement formula in addition to network transmission video data.
Step S2, real-time monitoring trigger signal;
Wherein, the trigger signal includes video time (the included timestamp of video) or/and target signature, wherein institute
Stating target signature is one or more in face characteristic, geometrical characteristic, shape feature, textural characteristics and color characteristic, can basis
Demand sets trigger signal, trigger signal and target image automatically, and there are relevances, to improve the accuracy and efficiency of screening.
Step S3, when monitoring the trigger signal, the inter-frame information according to frame image each in the video data is true
Set the goal image;
Step S4 extracts all target images, and the quality of all target images is assessed using picture quality optimizing algorithm
Screening quality reaches the target image of preset threshold.
In the present embodiment, by being automatically analyzed to sequence image in video data, according in continuous multiple frames image
Inter-frame information determines target image, assesses all target image screening quality using picture quality optimizing algorithm and reaches default threshold
Value is screened the target image when it reaches preset threshold and is exported to the server on backstage and management platform, and just video data returns
Investigate and collect evidence when biography rapidly to react in real time, meanwhile, video passback rate is improved, reduces memory usage, improves
The efficiency of searched targets images, so that video monitoring system tends to be intelligent.
Referring to Fig. 2, being step S3 flow chart in a kind of video monitoring image screening technique provided by the invention, it is described in detail such as
Under:
Step S301 utilizes continuous multiple frames in video sequence in the video data when monitoring the trigger signal
Image and difference image determine the common objective image between continuous multiple frames;
Step S302 distinguishes foreground target and background, by determining target according to common objective image setting threshold value
Target image in contours extract image.
In the present embodiment, the common objective image that continuous multiple frames are determined by inter-frame information is distinguished according to setting threshold value
Foreground target and background, so that it is determined that target image profile, convenient for extracting all target images, by will be in all frame images
Reach necessarily required image with target image contour similarity, be all regarded as target image, increases the screening base of image
Number.
Referring to Fig. 3, being step S4 flow chart in a kind of video monitoring image screening technique provided by the invention, it is described in detail such as
Under:
Step S401 extracts all target images in video sequence correspondence image;Based on picture quality optimizing algorithm from
Illumination, fuzzy, all target images of assessment in terms of angle quality;
Wherein, based on picture quality optimizing algorithm can for gradient, Hessian matrix, Lagrange's multiplier, simplex method,
Gradient descent method etc., will not repeat them here.
Step S402 screens the target image that mass fraction reaches preset threshold based on preset threshold.
In the present embodiment, subjective evaluation method can be used, in certain circumstances (including illumination, observed range, image sequence
The controlled factordiseases such as the selection of column and display interval), according to scoring criterion given in advance, from brightness, angle, clarity, noise
Degree etc. accounts for image and provides evaluation marking, obtains the subjective assessment of purpose image by counting and being weighted and averaged
Marking value, to set preset threshold, quantization needs the target image of quality of evaluation, achievees the purpose that screen target image.
Alternatively, evaluating using picture quality of the method for objectively evaluating to target image, e.g., pass through mathematics and engineering side
Formula is found an ideal mathematical model and is evaluated picture quality, evaluation result is obtained with subjective evaluation result
Unanimously, human visual system's perceptual image even video quality is simulated and replaces, e.g., entirely with reference to evaluation assessment, partially with reference to evaluation
Method carries out quantization judgement to target image without modes such as reference evaluation assessments, achievees the purpose that screen target image.
Analytical judgment target image is carried out by the way that threshold value is arranged, the precision of target image retrieval is improved, by using matter
The preferable target image of optimizing algorithm preferred mass is measured, using modularization, layering isolation method, it is ensured that video monitoring image screening
The safety and stablization of method are run.
Referring to Fig. 4, being a kind of video monitoring image screening plant structural block diagram provided by the invention, comprising:
Video collector 1, for acquiring and storing video data;
Photographing module 11 acquires video data using photographing module;
The video data of acquisition is carried out distributed storage using memory by memory module 12.
Monitoring modular 2 is used for real-time monitoring trigger signal;
Specifically, the trigger signal includes video time or/and target signature, wherein the target signature is face
It is one or more of in feature, geometrical characteristic, shape feature, textural characteristics and color characteristic.
Target determination module 3, for when monitoring the trigger signal, according to frame image each in the video data
Inter-frame information determines target image;
First object determination unit 31, for utilizing video in the video data when monitoring the trigger signal
Continuous multiple frames image and difference image determine the common objective image between continuous multiple frames in sequence;
Second target determination unit 32, for distinguishing foreground target and back according to common objective image setting threshold value
Scape passes through the target image in determining contour extraction of objects image.
Specifically, it is detailed in attached drawing 5, the common objective image of continuous multiple frames is determined by inter-frame information, according to setting threshold value
Foreground target and background are distinguished, so that it is determined that target image profile, convenient for extracting all target images, by by all frame figures
Reach necessarily required image with target image contour similarity as in, target image is all regarded as, using originally determined mesh
Logo image increases the screening radix of all images.
Object filtering module 4 assesses all targets using picture quality optimizing algorithm for extracting all target images
The quality screening quality of image reaches the target image of preset threshold;
First object screening unit 41, for extracting all target images in video sequence correspondence image;Based on image
Quality optimizing algorithm is from illumination, fuzzy, all target images of assessment in terms of angle quality;
Second object filtering unit 42, the target for reaching preset threshold for screening mass fraction based on preset threshold
Image.
Specifically, it is detailed in attached drawing 6, analytical judgment target image is carried out by the way that threshold value is arranged, improves target image retrieval
Precision, by using the preferable target image of quality optimizing algorithm preferred mass, using modularization, layering isolation method, really
Protect the safety and stablization operation of video monitoring image screening technique.
Since the video monitoring image screening plant and video monitoring image screening technique are one-to-one relationship, it is related to
The details such as specific embodiment and technical effect will not repeat them here.
Referring to Fig. 7, being a kind of video monitoring image system structure diagram provided by the invention, comprising:
Video collector 1, for acquiring and storing video data;
Monitoring modular 3 is used for real-time monitoring trigger signal;
Target determination module 3, for when monitoring the trigger signal, according to frame image each in the video data
Inter-frame information determines target image;
Object filtering module 4 assesses all targets using picture quality optimizing algorithm for extracting all target images
The target image that the quality screening quality of image reaches preset threshold is sent to server and management platform;
Server 5, in the video collector memory module and external data base be connected, for according to received institute
It states target image and matches its related information identification target image information, and recognition result is sent to management platform;
Wherein, (public security system database, emphasis personnel manage library, again to server with memory module, external data base respectively
Want the information banks such as substance repository) network connection, after receiving target image, server is according to target image in memory module
Or/and external data base carries out unified matching, rapid recognition target image information is fed back to management platform, is convenient for work
Personnel are in management platform subsequent processing.
Platform 6 is managed, is connected with the object filtering module with server, is used for according to the target image to video counts
According to progress intelligent management.
Wherein, management platform is controlled uniformly received video data, can be into during data are further processed
The operation such as preview, downloading, alarm, maintenance of row target image, for example, can be instructed by sending when receiving target image
It calls the target image of storage to video information, carries out preview or downloading;Similarly, alert if can be set in management platform,
When detect meet alert if when, then trigger warning message and reminded;By the way that security alarm list is arranged in management platform
Member can alarm immediately when monitoring abnormal conditions, avoid failing to report, reporting phenomenon by mistake for personal monitoring, improve peace
Quan Xing.It in the present embodiment, can be quick by carrying out intelligent, networking analysis and judgement to original video data
It filters out valuable video data and audient is showed by video display unit.
In addition, on that basi of the above embodiments, there are also a kind of computer readable storage medium structural block diagrams, comprising: storage
There is the computer program for video monitoring image screening, the computer program is performed above-mentioned video monitoring image screening
Step in method.For example, step S1 to S4 shown in FIG. 1.Alternatively, the computer program realized when being executed by processor it is above-mentioned
The function of each unit in each Installation practice, such as the function of module 1 to 4 shown in Fig. 3.
In embodiments of the present invention, the storage medium by executing above-mentioned computer program or with above-mentioned functional module,
The computer readable storage medium is analyzed video data automatically, by the interframe for analyzing continuous multiple frames image
Information reaches the initial purpose of determining target image, then, meets threshold value by the numerous target images screenings of preset threshold screening and wants
The target image asked is screened, to have the function that target automatic screening in video monitoring image, effectively avoids view
The slow committed memory of efficiency high problem when frequency data back calls, investigating and collecting evidence when video data being facilitated to return can in real time rapidly
Reaction.
The computer readable storage medium of the embodiment of the present invention may include can carry computer program code any
Entity or device, recording medium, for example, the memories such as ROM/RAM, disk, CD, flash memory.
In addition, each embodiment of the application can pass through the data processing journey by data processing equipment such as computer execution
Sequence is realized.Obviously, data processor constitutes the application.In addition, being commonly stored at data in one storage medium
Reason program is by directly reading out storage medium for program or by installing or copying to depositing for data processing equipment for program
It stores up in equipment (such as hard disk and/or memory) and executes.Therefore, such storage medium also constitutes the application, present invention also provides
A kind of non-volatile memory medium, wherein being stored with data processor, this data processor can be used for executing the application
Any one of above method embodiment embodiment.
In conclusion the present invention is by automatically analyzing sequence image in video data, according in continuous multiple frames image
Inter-frame information determine target image, assess all target images screening quality using picture quality optimizing algorithm and reach default threshold
Value screens the target image when it reaches preset threshold and exports to server and manage platform, when video data being facilitated to return
Investigation and evidence collection can rapidly react in real time, meanwhile, video passback rate is improved, reduces memory usage, improves inspection
The efficiency of rope target image, so that video monitoring system tends to be intelligent.So the present invention effectively overcome it is in the prior art
Various shortcoming and have high industrial utilization value.
The above-described embodiments merely illustrate the principles and effects of the present invention, and is not intended to limit the present invention.It is 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.Cause
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 (12)
1. a kind of video monitoring image screening technique, which is characterized in that the described method comprises the following steps:
It acquires and stores video data;
Real-time monitoring trigger signal;
When monitoring the trigger signal, target image is determined according to the inter-frame information of frame image each in the video data;
All target images are extracted, are reached using the quality screening quality that picture quality optimizing algorithm assesses all target images
The target image of preset threshold.
2. video monitoring image screening technique according to claim 1, which is characterized in that the acquisition simultaneously stores video counts
According to the step of include:
Video data is acquired using photographing module;
The video data of acquisition is subjected to distributed storage using memory.
3. video monitoring image screening technique according to claim 1, which is characterized in that the trigger signal includes video
Time or/and target signature, wherein the target signature is face characteristic, geometrical characteristic, shape feature, textural characteristics and face
It is one or more of in color characteristic.
4. video monitoring image screening technique according to claim 1, which is characterized in that described to receive the triggering
When signal, the step of target image is determined according to the inter-frame information of frame image each in the video data, comprising:
When monitoring the trigger signal, continuous multiple frames image and difference diagram in video sequence in the video data are utilized
As determining the common objective image between continuous multiple frames;
Foreground target and background are distinguished, by determining in contour extraction of objects image according to common objective image setting threshold value
Target image.
5. video monitoring image screening technique according to claim 1, which is characterized in that described to extract all target figures
Picture reaches the target image of preset threshold using the quality screening quality that picture quality optimizing algorithm assesses all target images
Step, comprising:
All target images are extracted in video sequence correspondence image;Based on picture quality optimizing algorithm from illumination, fuzzy, angle
Aspect assesses the quality of all target images;
The target image that mass fraction reaches preset threshold is screened based on preset threshold.
6. a kind of video monitoring image screening plant, which is characterized in that described device the following steps are included:
Video collector, for acquiring and storing video data;
Monitoring modular is used for real-time monitoring trigger signal;
Target determination module, for when monitoring the trigger signal, according to the interframe of frame image each in the video data
Information determines target image;
Object filtering module assesses all target images using picture quality optimizing algorithm for extracting all target images
Quality screening quality reach the target image of preset threshold.
7. video monitoring image screening plant according to claim 6, which is characterized in that the video collector is further
Include:
Photographing module acquires video data using photographing module;
The video data of acquisition is carried out distributed storage using memory by memory module.
8. video monitoring image screening plant according to claim 6, which is characterized in that the trigger signal includes video
Time or/and target signature, wherein the target signature is face characteristic, geometrical characteristic, shape feature, textural characteristics and face
It is one or more of in color characteristic.
9. video monitoring image screening plant according to claim 6, which is characterized in that the target determination module is into one
Step includes:
First object determination unit, for when monitoring the trigger signal, using in video sequence in the video data
Continuous multiple frames image and difference image determine the common objective image between continuous multiple frames;
Second target determination unit, for distinguishing foreground target and background according to common objective image setting threshold value, passing through
Determine the target image in contour extraction of objects image.
10. video monitoring image screening plant according to claim 6, which is characterized in that the object filtering module into
One step includes:
First object screening unit, for extracting all target images in video sequence correspondence image;It is sought based on picture quality
Excellent algorithm is from illumination, fuzzy, all target images of assessment in terms of angle quality;
Second object filtering unit, the target image for reaching preset threshold for screening mass fraction based on preset threshold.
11. a kind of video monitoring system, which is characterized in that the system comprises:
Video collector, for acquiring and storing video data;
Monitoring modular is used for real-time monitoring trigger signal;
Target determination module, for when monitoring the trigger signal, according to the interframe of frame image each in the video data
Information determines target image;
Object filtering module assesses all target images using picture quality optimizing algorithm for extracting all target images
Quality screening quality reach preset threshold target image be sent to server and management platform;
Server is connected with the video collector and external data base, for matching it according to the received target image
Related information identifies the target image information, and recognition result is sent to management platform;
Manage platform, be connected with the object filtering module with server, be used for according to the target image to video data into
Row intelligent management.
12. a kind of computer readable storage medium, is stored with the computer program for video monitoring image screening, feature exists
In the computer program is performed the screening technique for realizing the described in any item video monitoring images of claim 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811553254.0A CN109509190A (en) | 2018-12-19 | 2018-12-19 | Video monitoring image screening technique, device, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811553254.0A CN109509190A (en) | 2018-12-19 | 2018-12-19 | Video monitoring image screening technique, device, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109509190A true CN109509190A (en) | 2019-03-22 |
Family
ID=65753595
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811553254.0A Pending CN109509190A (en) | 2018-12-19 | 2018-12-19 | Video monitoring image screening technique, device, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109509190A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111353851A (en) * | 2020-02-27 | 2020-06-30 | 携程计算机技术(上海)有限公司 | Hotel sorting recommendation method and device, electronic equipment and storage medium |
CN111836102A (en) * | 2019-04-23 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Video frame analysis method and device |
CN112948627A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Alarm video generation method, display method and device |
CN113612970A (en) * | 2021-07-30 | 2021-11-05 | 国电汉川发电有限公司 | Safety event intelligent analysis management and control platform for industrial monitoring video |
CN113625603A (en) * | 2021-07-27 | 2021-11-09 | 金鹏电子信息机器有限公司 | Security monitoring management system and management method based on big data |
CN113780196A (en) * | 2021-09-15 | 2021-12-10 | 江阴市浩华新型复合材料有限公司 | Abnormal data real-time reporting system |
CN114285914A (en) * | 2021-10-19 | 2022-04-05 | 南方电网数字电网研究院有限公司 | Video data processing system, method and device based on electric power safety |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050103849A1 (en) * | 2003-11-13 | 2005-05-19 | Xiaoxun Zhu | Automatic hand-supportable image-based bar code symbol reader having image-processing based bar code reading subsystem employing simple decode image processing operations applied in an outwardly-directed manner referenced from the center of a captured narrow-area digital image of an object bearing a 1D bar code symbol |
CN201134166Y (en) * | 2007-10-24 | 2008-10-15 | 北京万集科技有限责任公司 | Number plate of vehicle recognition system |
CN102421008A (en) * | 2011-12-07 | 2012-04-18 | 浙江捷尚视觉科技有限公司 | Intelligent video quality detecting system |
CN103634552A (en) * | 2012-08-28 | 2014-03-12 | 华为技术有限公司 | Monitoring video storage method, system and central management server |
CN105049810A (en) * | 2015-08-07 | 2015-11-11 | 虎扑(上海)文化传播股份有限公司 | Intelligent video monitoring method and video device |
CN107071344A (en) * | 2017-01-22 | 2017-08-18 | 深圳英飞拓科技股份有限公司 | A kind of large-scale distributed monitor video data processing method and device |
CN107844779A (en) * | 2017-11-21 | 2018-03-27 | 重庆邮电大学 | A kind of video key frame extracting method |
CN108875542A (en) * | 2018-04-04 | 2018-11-23 | 北京旷视科技有限公司 | A kind of face identification method, device, system and computer storage medium |
CN108985176A (en) * | 2018-06-20 | 2018-12-11 | 北京优酷科技有限公司 | image generating method and device |
-
2018
- 2018-12-19 CN CN201811553254.0A patent/CN109509190A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050103849A1 (en) * | 2003-11-13 | 2005-05-19 | Xiaoxun Zhu | Automatic hand-supportable image-based bar code symbol reader having image-processing based bar code reading subsystem employing simple decode image processing operations applied in an outwardly-directed manner referenced from the center of a captured narrow-area digital image of an object bearing a 1D bar code symbol |
CN201134166Y (en) * | 2007-10-24 | 2008-10-15 | 北京万集科技有限责任公司 | Number plate of vehicle recognition system |
CN102421008A (en) * | 2011-12-07 | 2012-04-18 | 浙江捷尚视觉科技有限公司 | Intelligent video quality detecting system |
CN103634552A (en) * | 2012-08-28 | 2014-03-12 | 华为技术有限公司 | Monitoring video storage method, system and central management server |
CN105049810A (en) * | 2015-08-07 | 2015-11-11 | 虎扑(上海)文化传播股份有限公司 | Intelligent video monitoring method and video device |
CN107071344A (en) * | 2017-01-22 | 2017-08-18 | 深圳英飞拓科技股份有限公司 | A kind of large-scale distributed monitor video data processing method and device |
CN107844779A (en) * | 2017-11-21 | 2018-03-27 | 重庆邮电大学 | A kind of video key frame extracting method |
CN108875542A (en) * | 2018-04-04 | 2018-11-23 | 北京旷视科技有限公司 | A kind of face identification method, device, system and computer storage medium |
CN108985176A (en) * | 2018-06-20 | 2018-12-11 | 北京优酷科技有限公司 | image generating method and device |
Non-Patent Citations (2)
Title |
---|
PATEL K等: "Live face video vs. spoof face video: Use of moiré patterns to detect replay video attacks", 《2015 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB)》 * |
李吉成等: "图像目标的自动识别和快速筛选技术", 《二〇〇六年全国光电技术学术交流会》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111836102A (en) * | 2019-04-23 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Video frame analysis method and device |
CN111836102B (en) * | 2019-04-23 | 2023-03-24 | 杭州海康威视数字技术股份有限公司 | Video frame analysis method and device |
CN112948627A (en) * | 2019-12-11 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Alarm video generation method, display method and device |
CN112948627B (en) * | 2019-12-11 | 2023-02-03 | 杭州海康威视数字技术股份有限公司 | Alarm video generation method, display method and device |
CN111353851A (en) * | 2020-02-27 | 2020-06-30 | 携程计算机技术(上海)有限公司 | Hotel sorting recommendation method and device, electronic equipment and storage medium |
CN113625603A (en) * | 2021-07-27 | 2021-11-09 | 金鹏电子信息机器有限公司 | Security monitoring management system and management method based on big data |
CN113625603B (en) * | 2021-07-27 | 2023-06-23 | 金鹏电子信息机器有限公司 | Security monitoring management system and method based on big data |
CN113612970A (en) * | 2021-07-30 | 2021-11-05 | 国电汉川发电有限公司 | Safety event intelligent analysis management and control platform for industrial monitoring video |
CN113780196A (en) * | 2021-09-15 | 2021-12-10 | 江阴市浩华新型复合材料有限公司 | Abnormal data real-time reporting system |
CN114285914A (en) * | 2021-10-19 | 2022-04-05 | 南方电网数字电网研究院有限公司 | Video data processing system, method and device based on electric power safety |
CN114285914B (en) * | 2021-10-19 | 2023-10-20 | 南方电网数字电网研究院有限公司 | Video data processing system, method and device based on power safety |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109509190A (en) | Video monitoring image screening technique, device, system and storage medium | |
CN211293956U (en) | AI-based identification and alarm system for abnormal agent on construction site | |
CN103108159B (en) | Electric power intelligent video analyzing and monitoring system and method | |
CN104200671B (en) | A kind of virtual bayonet socket management method based on large data platform and system | |
CN109299683B (en) | Security protection evaluation system based on face recognition and behavior big data | |
CN109858365A (en) | A kind of special population Assembling Behavior analysis method, device and electronic equipment | |
CN109377713B (en) | Fire early warning method and system | |
CN112163572A (en) | Method and device for identifying object | |
CN109389794A (en) | A kind of Intellectualized Video Monitoring method and system | |
CN111476964A (en) | Remote forest fire prevention monitoring system and method | |
KR20200052418A (en) | Automated Violence Detecting System based on Deep Learning | |
CN109410497A (en) | A kind of monitoring of bridge opening space safety and alarm system based on deep learning | |
CN110012271A (en) | A kind of intelligent monitoring security system and its application method | |
CN112906488A (en) | Security protection video quality evaluation system based on artificial intelligence | |
CN116055690A (en) | Method and equipment for processing machine room monitoring video | |
KR101547255B1 (en) | Object-based Searching Method for Intelligent Surveillance System | |
CN117978969A (en) | AI video management platform applied to aquaculture | |
CN113052125B (en) | Construction site violation image recognition and alarm method | |
CN105095891A (en) | Human face capturing method, device and system | |
CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
CN116886874A (en) | Ecological garden security monitoring and early warning data acquisition method and system | |
CN116934674A (en) | Large-granularity silicon material detection and removal system based on YOLOv8 network | |
CN203883934U (en) | Intelligent self-help bank video monitoring system | |
CN116208633A (en) | Artificial intelligence service platform system, method, equipment and medium | |
CN209845141U (en) | Video monitoring system with automatic image screening function |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190322 |