CN107358191A - Video alarm detection method and device - Google Patents

Video alarm detection method and device Download PDF

Info

Publication number
CN107358191A
CN107358191A CN201710549612.XA CN201710549612A CN107358191A CN 107358191 A CN107358191 A CN 107358191A CN 201710549612 A CN201710549612 A CN 201710549612A CN 107358191 A CN107358191 A CN 107358191A
Authority
CN
China
Prior art keywords
video data
video
alarm
image
warning message
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.)
Granted
Application number
CN201710549612.XA
Other languages
Chinese (zh)
Other versions
CN107358191B (en
Inventor
孙丰强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GUANGDONG ZHONGXING ELECTRONICS Co Ltd
Original Assignee
GUANGDONG ZHONGXING ELECTRONICS Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by GUANGDONG ZHONGXING ELECTRONICS Co Ltd filed Critical GUANGDONG ZHONGXING ELECTRONICS Co Ltd
Priority to CN201710549612.XA priority Critical patent/CN107358191B/en
Publication of CN107358191A publication Critical patent/CN107358191A/en
Application granted granted Critical
Publication of CN107358191B publication Critical patent/CN107358191B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/30232—Surveillance

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Alarm Systems (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a kind of video alarm detection method and device.This method includes：The Video processing intelligent platform utilizes machine learning algorithm, training set based on video data, training set is trained to generate the Alarm Detector of video data, using the Alarm Detector of video data, alarm detection processing is carried out to pending video data.

Description

Video alarm detection method and device
Technical field
The present invention relates to video detection technology field, more particularly to a kind of video alarm detection method and device.
Background technology
Video monitoring is enriched with its directly perceived, accurate, timely and information content and is widely used in many occasions.In recent years, With the rapid development of computer, network and Video processing, transmission technology, Video Supervision Technique there has also been significant progress. Video monitoring is the important component of safety and protection system, and traditional video monitoring system includes front-end camera, transmission line Cable and video monitoring platform.
Most important video monitoring is exactly video acquisition, and the information paid special attention in video pictures mainly includes：Environment, People, car, weather, invasion, natural calamity, traffic accident etc..
Video detection is to obtain effective information by analyzing video pictures, at present, also without a kind of effectively to video counts According to being detected, the method that generates the warning message of video data.
The content of the invention
The embodiment provides a kind of video alarm detection method and device, has to realize to video data The alarm detection of effect.
To achieve these goals, this invention takes following technical scheme.
An aspect of of the present present invention provides a kind of video alarm detection method based on Video processing intelligent platform, including： Video processing intelligent platform is trained to generate the report of video data using machine learning algorithm to the training set of video data Alert detector；Using the Alarm Detector of video data, alarm detection processing is carried out to pending video data.
Further, the training set of video data is trained using machine learning algorithm to obtain the alarm of video data Detector includes：Collect and store the video data in various video capture scenes；Set various visual classification factors and according to Classification factor is combined classification to the video data stored；Extract the exemplary video number in the video data of every kind of classification According to using exemplary video data as training set；Characteristic image extraction is carried out to training set to set report corresponding to this feature image Alert image；Characteristic image and its corresponding alarm image are trained to generate the report of video data using machine learning algorithm Alert detector, Alarm Detector includes various features image corresponding to the video data of every kind of classification and each characteristic image is corresponding Alarm image.
Further, using the Alarm Detector of video data, alarm detection processing is carried out to pending video data, Including：Pending video data is received, and pending video data is subjected to classification processing to obtain pending video Classification belonging to data；Pending video data is decomposed into multiple video pictures according to the time sequencing of setting, using waiting to locate Various features image corresponding to classification belonging to the video data of reason carries out characteristic image extraction to each video pictures, will be carried The each characteristic image taken is matched with corresponding alarm image, when matching result is the alarm threshold value that similarity is more than setting When, then generate warning message corresponding to this feature image；And synthesized warning message corresponding to each video pictures, obtain To warning message corresponding to video data to be detected.
Further, the video alarm detection method based on Video processing intelligent platform also includes：By video to be detected Warning message corresponding to data is converted to SVAC code streams, and SVAC code streams are sent into miscellaneous equipment by network.
Another aspect provides a kind of video alarm detection means based on Video processing intelligent platform, bag Include：Learning training unit, for being trained the training set of video data to generate the report of video data using machine learning algorithm Alert detector；Alarm detecting unit, for the Alarm Detector using video data, pending video data is alarmed Detection process.
Further, learning training unit includes：Training data collector unit, for collecting in various video capture scenes Video data；Memory cell, the video data for storing collected are deposited；Video data taxon, it is various for setting Visual classification factor is simultaneously combined classification according to various classification factors to the video data stored in memory cell；Video data Extraction unit, the exemplary video data in video data for extracting every kind of classification, using exemplary video data as training set； Characteristic image extraction unit, characteristic image extraction is carried out to training set to set alarm image corresponding to this feature image；Alarm Detector maturation unit, characteristic image and its corresponding alarm image are trained to generate video using machine learning algorithm The Alarm Detector of data, Alarm Detector include various features image and each feature corresponding to the video data of every kind of classification Alarm image corresponding to image.
Further, alarm detecting unit includes warning message synthesis unit, and warning message synthesis unit is used for：Reception is treated The video data of processing, and pending video data is subjected to classification processing to obtain point belonging to pending video data Class；Pending video data is decomposed into multiple video pictures according to the time sequencing of setting, uses pending video counts Characteristic image extraction is carried out to each video pictures according to various features image corresponding to affiliated classification, by each feature of extraction Image is matched with corresponding alarm image, and when matching result is the alarm threshold value that similarity is more than setting, then generation should Warning message corresponding to characteristic image；And synthesized warning message corresponding to each video pictures, obtain to be detected Warning message corresponding to video data.
Further, the video alarm detection means based on Video processing intelligent platform also includes：The conversion of SVAC code streams is single Member, for warning message corresponding to video data to be detected to be converted into SVAC code streams, and by communication network by SVAC codes Stream is sent to miscellaneous equipment.
The embodiment of the present invention is flat by using intelligence it can be seen from the technical scheme provided by embodiments of the invention described above Platform effectively can carry out Intelligent Measurement to video data, automatically generate the warning message of video data, reduce artificial participation ring Section.According to SVAC coding criterion, warning message can be converted to SVAC code streams, SVAC code streams are sent to miscellaneous equipment, To realize more applications.
The additional aspect of the present invention and advantage will be set forth in part in the description, and these will become from the following description Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, required use in being described below to embodiment Accompanying drawing be briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this For the those of ordinary skill of field, without having to pay creative labor, other can also be obtained according to these accompanying drawings Accompanying drawing.
Fig. 1 is a kind of place of the video alarm detection method based on Video processing intelligent platform provided in an embodiment of the present invention Manage flow chart；
Fig. 2 is a kind of knot of the video alarm detection means based on Video processing intelligent platform provided in an embodiment of the present invention Composition.
Embodiment
Embodiments of the present invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning Same or similar element is represented to same or similar label eventually or there is the element of same or like function.Below by ginseng The embodiment for examining accompanying drawing description is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one It is individual ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges Diction " comprising " refer to the feature, integer, step, operation, element and/or component be present, but it is not excluded that in the presence of or addition One or more other features, integer, step, operation, element, component and/or their groups.It should be understood that when we claim member Part is " connected " or during " coupled " to another element, and it can be directly connected or coupled to other elements, or there may also be Intermediary element.In addition, " connection " used herein or " coupling " can include wireless connection or coupling.Wording used herein "and/or" includes any cell of one or more associated list items and all combined.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art Language and scientific terminology) with the general understanding identical meaning with the those of ordinary skill in art of the present invention.Should also Understand, those terms defined in such as general dictionary, which should be understood that, to be had and the meaning in the context of prior art The consistent meaning of justice, and unless defined as here, will not be with idealizing or the implication of overly formal be explained.
For ease of the understanding to the embodiment of the present invention, done further by taking several specific embodiments as an example below in conjunction with accompanying drawing Explanation, and each embodiment does not form the restriction to the embodiment of the present invention.
Embodiment one
Fig. 1 provides a kind of handling process of the video alarm detection method based on Video processing intelligent platform.
Step S110：Video processing intelligent platform receives and stores video data.
Step S120：Video processing intelligent platform is classified to the video data of storage and extracted to generate training set, Using machine learning algorithm, the training set based on video data is trained to generate the Alarm Detector of video data.
Video processing intelligent platform is collected and stores the substantial amounts of video data in various video capture scenes, and setting is various Visual classification factor, is combined point according to one or more kinds of factors in various classification factors to the video data of storage Class, the classification factor can include reference object type (motion is either static), shooting time (daytime or evening), shooting day Gas (fine day either the various weather conditions that may cause video notable difference such as rainy day or snowy day or greasy weather), shooting are set Standby model, taking lens orientation etc..
Video processing intelligent platform extracts the exemplary video data in the video data of every kind of classification, by exemplary video number According to as training set, characteristic image extraction is carried out to training set, set each characteristic image corresponding to alarm image, utilize machine Learning algorithm is trained to characteristic image and its corresponding alarm image to generate the Alarm Detector of video data, the alarm Detector includes alarm image corresponding to various features image corresponding to the video data of every kind of classification and each characteristic image. Various features image can include corresponding to the video data of every kind of classification：Character image, character face's image, figure action figure Picture, certain objects image, road image, building object image, various animal paintings etc..
Step S130：Using the Alarm Detector of video data, alarm detection processing is carried out to video data to be detected, Generate the warning message of video data to be detected.
Video processing intelligent platform receives pending video data, and classification processing is carried out to pending video data, Obtain the classification belonging to pending video data.
Then, Video processing intelligent platform by pending video data according to the time sequencing of setting (such as when shooting Between after arrive first) be decomposed into multiple video pictures, extract first video pictures, use point belonging to pending video data Various features image corresponding to class carries out characteristic image extraction to first video pictures.By the characteristic image of extraction with it is corresponding Alarm image is matched, when matching result be similarity be more than setting alarm threshold value, then generate this feature image corresponding to Warning message；When the alarm threshold value that matching result is less than or equal to set for similarity, then do not generate and reported corresponding to this feature image Alert information.It will detect that all warning messages are synthesized corresponding to all characteristic images in first video pictures, obtain the Warning message corresponding to one video pictures.
Afterwards, second video pictures is extracted, according to the acquisition of warning message corresponding to above-mentioned first video pictures Journey, obtain warning message corresponding to second video pictures.The rest may be inferred, in all video pictures and each video pictures All characteristic images traveled through successively, warning message corresponding to all video pictures is obtained, finally, by all video pictures Corresponding warning message is synthesized, and obtains warning message corresponding to video data to be detected.
Step S140：Warning message corresponding to video data to be detected is converted into SVAC code streams.
SVAC (Surveillance Video and Audio Coding, supervising video and audio coding) is a kind of peace The audio/video coding specification in anti-field, and the coding standard of monitoring field, its specification is abundant can be supported to realize many applications Scheme.
Warning message corresponding to video data to be detected is converted to SVAC code streams by Video processing intelligent platform, by logical Above-mentioned SVAC code streams are sent to miscellaneous equipment by communication network, for example send a warning information to mobile phone gateway.
Embodiment two
Fig. 2 shows a kind of video alarm detection method device based on Video processing intelligent platform.Should be flat based on intelligence The video alarm detection means of platform includes learning training unit 210 and alarm detecting unit 220.Learning training unit 210 is used for The training set of video data is trained to generate the Alarm Detector of video data using machine learning algorithm.Alarm detecting unit 220 are used for the Alarm Detector using the video data, and alarm detection processing is carried out to pending video data.
Learning training unit 210 includes training data collector unit 211, memory cell 212, video data taxon 213rd, video data extraction unit 214, characteristic image extraction unit 215 and Alarm Detector generation unit 216.
Specifically, training data collector unit 211 is used to collect the video data in various video capture scenes.Storage is single Member 212 is used to store collected video data.Video data taxon 213 is used to set various visual classification factors, and The video data stored in memory cell 225 is combined according to one or more kinds of factors in various classification factors point Class.Video data extraction unit 214 is used to extract the exemplary video data in the video data of every kind of classification, by exemplary video number According to as training set.Characteristic image extraction unit 215 carries out characteristic image extraction to training set to set each characteristic image pair The alarm image answered.Alarm Detector generation unit 216 is used for using machine learning algorithm to characteristic image and its corresponding report Alert image is trained to generate the Alarm Detector of video data.The Alarm Detector includes the video data pair of every kind of classification Alarm image corresponding to the various features image and each characteristic image answered.
Alarm detecting unit 220 includes warning message synthesis unit 221.The warning message synthesis unit 221 is used to receive Pending video data, and pending video data is decomposed into multiple video pictures with right according to the time sequencing of setting Each video pictures carry out characteristic image extraction and are matched the characteristic image of extraction with corresponding alarm image.Work as matching As a result it is more than the alarm threshold value of setting for similarity, then generates warning message corresponding to this feature image；When matching result is phase Like alarm threshold value of the degree less than or equal to setting, then warning message corresponding to this feature image is not generated.By this way, to all All characteristic images in video pictures and each video pictures are traveled through successively, are obtained and are reported corresponding to all video pictures Alert information, warning message corresponding to all video pictures is synthesized, obtains alarm signal corresponding to video data to be detected Breath.
Further, being somebody's turn to do the video alarm detection means based on intelligent platform also includes：
SVAC code streams converting unit 230, for warning message corresponding to video data to be detected to be converted into SVAC codes Stream, miscellaneous equipment is sent to by communication network by SVAC code streams.
Detailed process and the foregoing side that the video alarm based on intelligent platform detects are carried out with the device of the embodiment of the present invention Method embodiment is similar, and here is omitted.
In summary, the embodiment of the present invention effectively can carry out intelligent inspection by using intelligent platform to video data Survey, automatically generate the warning message of video data, reduce artificial participation link.According to SVAC coding criterion, will can alarm Information is converted to SVAC code streams, and SVAC code streams are sent into miscellaneous equipment, to realize more applications.
Warning message inside Video processing intelligent platform can be shared mutually, progressive alternate.
One of ordinary skill in the art will appreciate that：Accompanying drawing is the schematic diagram of one embodiment, module in accompanying drawing or Flow is not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art can be understood that the present invention can Realized by the mode of software plus required general hardware platform.Based on such understanding, technical scheme essence On the part that is contributed in other words to prior art can be embodied in the form of software product, the computer software product It can be stored in storage medium, such as ROM/RAM, magnetic disc, CD, including some instructions are causing a computer equipment (can be personal computer, server, either network equipment etc.) performs some of each embodiment of the present invention or embodiment Method described in part.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment Divide mutually referring to what each embodiment stressed is the difference with other embodiment.Especially for device or For system embodiment, because it is substantially similar to embodiment of the method, so describing fairly simple, related part is referring to method The part explanation of embodiment.Apparatus and system embodiment described above is only schematical, wherein the conduct The unit that separating component illustrates can be or may not be it is physically separate, can be as the part that unit is shown or Person may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can root Factually border needs to select some or all of module therein realize the purpose of this embodiment scheme.Ordinary skill Personnel are without creative efforts, you can to understand and implement.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto, Any one skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in, It should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims It is defined.

Claims (10)

  1. A kind of 1. video alarm detection method, it is characterised in that including：
    The Video processing intelligent platform utilizes machine learning algorithm, and the training set based on video data is trained to be regarded to generate The Alarm Detector of frequency evidence；
    Using the Alarm Detector of the video data, alarm detection processing is carried out to pending video data.
  2. 2. according to the method for claim 1, it is characterised in that using machine learning algorithm, the training based on video data The Alarm Detector that collection is trained to obtain video data includes：
    Collect and store the video data in various video capture scenes；
    Set various visual classification factors and classification is combined to the video data stored according to classification factor；
    The exemplary video data in the video data of every kind of classification are extracted, using the exemplary video data as training set；
    Characteristic image extraction is carried out to the training set to set alarm image corresponding to this feature image；
    The characteristic image and its corresponding alarm image are trained to generate the video counts using machine learning algorithm According to Alarm Detector, various features image corresponding to the video data of the Alarm Detector including every kind of classification and each special Levy alarm image corresponding to image.
  3. 3. according to the method for claim 1, it is characterised in that using the Alarm Detector of the video data, treat place The video data of reason carries out alarm detection processing, including：
    Pending video data is received, and the pending video data is subjected to classification processing to obtain pending regard Frequency is according to affiliated classification；
    Pending video data is decomposed into multiple video pictures according to the time sequencing of setting, uses pending video data Various features image corresponding to affiliated classification carries out characteristic image extraction, each feature that will be extracted to each video pictures Image is matched with corresponding alarm image, and when matching result is the alarm threshold value that similarity is more than setting, then generation should Warning message corresponding to characteristic image；And
    Warning message corresponding to each video pictures is synthesized, obtains warning message corresponding to video data to be detected.
  4. 4. according to the method for claim 3, it is characterised in that also include：
    It will detect that all warning messages are integrated corresponding to all characteristic images in first video pictures, obtain first Warning message corresponding to video pictures；
    Second video pictures is extracted, according to the acquisition process of warning message corresponding to first video pictures, obtains the Warning message corresponding to two video pictures, the rest may be inferred, to all spies in all video pictures and each video pictures Sign image is traveled through successively, obtains warning message corresponding to all video pictures.
  5. 5. the method according to claim 3 or 4, it is characterised in that methods described also includes：
    Warning message corresponding to the video data to be detected is converted into SVAC code streams, by network by the SVAC code streams It is sent to miscellaneous equipment.
  6. A kind of 6. video alarm detection means, it is characterised in that including：
    Learning training unit, for using machine learning algorithm, the training set based on video data to be trained to generate video data Alarm Detector；
    Alarm detecting unit, for the Alarm Detector using the video data, pending video data is alarmed Detection process.
  7. 7. device according to claim 6, it is characterised in that the learning training unit includes：
    Training data collector unit, for collecting the video data in various video capture scenes；
    Memory cell, the video data for storing collected are deposited；
    Video data taxon, for setting various visual classification factors and according to various classification factors to the memory cell The video data of middle storage is combined classification；
    Video data extraction unit, the exemplary video data in video data for extracting every kind of classification, the typical case is regarded Frequency is according to as training set；
    Characteristic image extraction unit, characteristic image extraction is carried out to the training set to set alarm figure corresponding to this feature image Picture；
    Alarm Detector generation unit, the characteristic image and its corresponding alarm image are instructed using machine learning algorithm Practice to generate the Alarm Detector of the video data, the Alarm Detector includes each corresponding to the video data of every kind of classification Alarm image corresponding to kind characteristic image and each characteristic image.
  8. 8. device according to claim 7, it is characterised in that alarm detecting unit includes warning message synthesis unit, institute Warning message synthesis unit is stated to be used for：
    Pending video data is received, and the pending video data is subjected to classification processing to obtain pending regard Frequency is according to affiliated classification；
    The pending video data is decomposed into multiple video pictures according to the time sequencing of setting, regarded using pending Frequency carries out characteristic image extraction according to various features image corresponding to affiliated classification to each video pictures, by each of extraction Characteristic image is matched with corresponding alarm image, when matching result is the alarm threshold value that similarity is more than setting, is then given birth to Into warning message corresponding to this feature image；And
    Warning message corresponding to each video pictures is synthesized, obtains warning message corresponding to video data to be detected.
  9. 9. device according to claim 8, it is characterised in that the warning message synthesis unit is additionally operable to：
    It will detect that all warning messages are integrated corresponding to all characteristic images in first video pictures, obtain first Warning message corresponding to video pictures；
    Second video pictures is extracted, according to the acquisition process of warning message corresponding to first video pictures, obtains the Warning message corresponding to two video pictures, the rest may be inferred, to all spies in all video pictures and each video pictures Sign image is traveled through successively, obtains warning message corresponding to all video pictures.
  10. 10. device according to claim 8 or claim 9, it is characterised in that also include：
    SVAC code stream converting units, for warning message corresponding to the video data to be detected to be converted into SVAC code streams, And the SVAC code streams are sent to by miscellaneous equipment by communication network.
CN201710549612.XA 2017-07-07 2017-07-07 Video alarm detection method and device Active CN107358191B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710549612.XA CN107358191B (en) 2017-07-07 2017-07-07 Video alarm detection method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710549612.XA CN107358191B (en) 2017-07-07 2017-07-07 Video alarm detection method and device

Publications (2)

Publication Number Publication Date
CN107358191A true CN107358191A (en) 2017-11-17
CN107358191B CN107358191B (en) 2020-12-22

Family

ID=60291780

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710549612.XA Active CN107358191B (en) 2017-07-07 2017-07-07 Video alarm detection method and device

Country Status (1)

Country Link
CN (1) CN107358191B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108881708A (en) * 2017-12-18 2018-11-23 南通使爱智能科技有限公司 A kind of intelligent image processing unit
CN112383756A (en) * 2020-11-13 2021-02-19 珠海大横琴科技发展有限公司 Video monitoring alarm processing method and device
EP3968298A1 (en) * 2020-09-10 2022-03-16 PKE Holding AG Modelling of a situation

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008039130A1 (en) * 2008-08-21 2010-02-25 Billy Hou Automatic tracing and identification system for movable object e.g. human, in building, has safety monitoring sensor connected with safety monitoring system such that tracing camera receives desired data when sensor is operated
CN104253482A (en) * 2014-08-08 2014-12-31 济南大学 Image data base and inspection robot-based equipment trouble detection method
CN106097346A (en) * 2016-06-13 2016-11-09 中国科学技术大学 A kind of video fire hazard detection method of self study
CN106781236A (en) * 2016-12-29 2017-05-31 东南大学 A kind of based on person detecting and again remote alarming device and long-distance monitoring method of recognition methods
US20170178343A1 (en) * 2015-12-16 2017-06-22 Vi Dimensions Pte Ltd Video analysis methods and apparatus
US20170193810A1 (en) * 2016-01-05 2017-07-06 Wizr Llc Video event detection and notification

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008039130A1 (en) * 2008-08-21 2010-02-25 Billy Hou Automatic tracing and identification system for movable object e.g. human, in building, has safety monitoring sensor connected with safety monitoring system such that tracing camera receives desired data when sensor is operated
CN104253482A (en) * 2014-08-08 2014-12-31 济南大学 Image data base and inspection robot-based equipment trouble detection method
US20170178343A1 (en) * 2015-12-16 2017-06-22 Vi Dimensions Pte Ltd Video analysis methods and apparatus
US20170193810A1 (en) * 2016-01-05 2017-07-06 Wizr Llc Video event detection and notification
CN106097346A (en) * 2016-06-13 2016-11-09 中国科学技术大学 A kind of video fire hazard detection method of self study
CN106781236A (en) * 2016-12-29 2017-05-31 东南大学 A kind of based on person detecting and again remote alarming device and long-distance monitoring method of recognition methods

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
胡宪洋: ""监控视频中特定目标的检测与辨识方法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108881708A (en) * 2017-12-18 2018-11-23 南通使爱智能科技有限公司 A kind of intelligent image processing unit
EP3968298A1 (en) * 2020-09-10 2022-03-16 PKE Holding AG Modelling of a situation
CN112383756A (en) * 2020-11-13 2021-02-19 珠海大横琴科技发展有限公司 Video monitoring alarm processing method and device

Also Published As

Publication number Publication date
CN107358191B (en) 2020-12-22

Similar Documents

Publication Publication Date Title
CN106998444B (en) Big data face monitoring system
WO2019153193A1 (en) Taxi operation monitoring method, device, storage medium, and system
CN107205137A (en) One kind monitoring recognition methods and device
KR101937272B1 (en) Method and Apparatus for Detecting Event from Multiple Image
CN210691345U (en) Cloud intelligence safety inspection auxiliary system based on degree of depth learning
CN109460744B (en) Video monitoring system based on deep learning
CN113052029A (en) Abnormal behavior supervision method and device based on action recognition and storage medium
CN102750709B (en) Video is utilized to detect the method and apparatus of behavior of fighting
CN103366506A (en) Device and method for automatically monitoring telephone call behavior of driver when driving
CN107358191A (en) Video alarm detection method and device
CN107330414A (en) Act of violence monitoring method
CN107358190A (en) A kind of image key area management method and device
CN114202711A (en) Intelligent monitoring method, device and system for abnormal behaviors in train compartment
CN111046728A (en) Straw combustion detection method based on characteristic pyramid network
CN112084928A (en) Road traffic accident detection method based on visual attention mechanism and ConvLSTM network
CN110188617A (en) A kind of machine room intelligent monitoring method and system
CN110276398A (en) A kind of video abnormal behaviour automatic judging method
CN114724085A (en) Construction safety event detection and analysis method and system
CN107370985A (en) Pedestrian's dynamic display method and system
CN113920585A (en) Behavior recognition method and device, equipment and storage medium
CN113191274A (en) Oil field video intelligent safety event detection method and system based on neural network
CN1413417A (en) Image data processing
CN116248861A (en) Intelligent video detection method, system and device
CN116597394A (en) Railway foreign matter intrusion detection system and method based on deep learning
CN113645439B (en) Event detection method and system, storage medium and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant