CN114863364B - Security detection method and system based on intelligent video monitoring - Google Patents
Security detection method and system based on intelligent video monitoring Download PDFInfo
- Publication number
- CN114863364B CN114863364B CN202210557086.2A CN202210557086A CN114863364B CN 114863364 B CN114863364 B CN 114863364B CN 202210557086 A CN202210557086 A CN 202210557086A CN 114863364 B CN114863364 B CN 114863364B
- Authority
- CN
- China
- Prior art keywords
- target
- monitoring
- face
- time
- scenes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a security detection method based on intelligent video monitoring, which comprises the steps of collecting monitoring videos from different video collecting terminals, slicing the collected videos to obtain monitoring scenes, identifying targets from the monitoring scenes, obtaining unregistered targets to form a first target set, obtaining the regional association degree of each target in the first target set, obtaining a regional association degree set, receiving a space arrangement command, and removing or moving the monitoring scenes according to the regional association degrees. The invention realizes the flexible arrangement of the monitoring scenes and judges the monitoring scenes needing to be cleaned according to the storage space of the video acquisition terminal and the acquired monitoring scenes.
Description
Technical Field
The invention relates to the technical field of video monitoring, in particular to a security detection method and system based on intelligent video monitoring.
Background
The gridding management needs to monitor the personnel in the district under jurisdiction, including screening the personnel at each entrance and exit, the traditional manual registration has the problems of complicated procedures, untimely information updating and the like, the personnel in the district are extracted through face recognition by means of cameras in the district under jurisdiction and the community, the registered personnel in the district are combined, the working pressure of the traditional gridding management can be reduced, the efficiency is improved, and the fine management is realized. People in the area can be checked and screened in time when needed, and the management level is improved.
However, at the same time, the processing and storage of massive data will bring pressure, so a method is needed to intelligently manage the video monitoring content. In a conventional data storage manner, an administrator stores data through a local storage system of a client or stores data through a central server. Under the structure, as the demand for data storage increases, the capacity requirement on the local storage system or the central storage server increases, which will result in continuous upgrade of hardware of the local disk system or the central storage system, and at the same time, heavy burden is brought to the maintenance work of the data storage system, which is not beneficial to quick search of data.
Disclosure of Invention
The invention aims to provide a security detection method based on intelligent video monitoring, which aims to solve one or more technical problems in the prior art and at least provide a beneficial selection or creation condition.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a security detection method based on intelligent video monitoring comprises the following steps:
step 1, collecting monitoring videos from different video collecting terminals, and slicing the collected videos to obtain monitoring scenes;
step 2, identifying targets from the monitoring scene, obtaining unregistered targets and forming a first target set;
step 3, obtaining the regional relevance of each target in the first target set, and obtaining a regional relevance set;
and 4, receiving a spatial arrangement command, and removing or moving the monitoring scene according to the area association degree.
Further, in step 1, the substeps of acquiring monitoring videos from different video acquisition terminals and slicing the acquired videos to obtain monitoring scenes are as follows:
deploying a video acquisition terminal in a monitored target area, wherein the video acquisition terminal can acquire videos according to a certain interval or trigger video acquisition in linkage with security equipment;
the acquired video is sliced to obtain one or more monitoring scenes, and the slicing method can be to slice the acquired video according to a set rule, or according to one or more of a trigger signal from security equipment or manual trigger.
Preferably, the security equipment can be entrance guard's equipment, and when the user triggered entrance guard's equipment, video acquisition terminal began to gather the video.
Preferably, the video acquisition terminal can be an indoor pan-tilt camera, an outdoor dome camera, or a door lock or an entrance guard with built-in face recognition, or a handheld law enforcement recorder.
Preferably, the slicing method can be performed according to the record of the chinese patent application "a surveillance video slice storage method and system" in publication No. CN109361904 a.
Further, in step 2, identifying an object from the monitoring scene, and obtaining an unregistered object, the substep of forming the first object set is:
and extracting the face of each monitoring scene, identifying the monitoring scene with the face and extracting the face, wherein each extracted face forms a target sequence, elements in the target sequence comprise the time of the target appearing in the video acquisition terminal and the corresponding video acquisition terminal, and the target is a face image identified by the video acquisition terminal.
The unregistered target is a target which cannot be matched in a database in which target images are prestored;
at least one face exists in the stored pictures of each monitoring scene, and at least one frame in the pictures of the monitoring scenes comprises one or more faces; if the face does not exist in the scene picture, marking a blank monitoring scene; the blank monitoring scene is not stored in the video acquisition terminal;
and comparing each target of the target sequence with a target image prestored in a database, marking the targets in the non-local area, and obtaining the targets in the non-local area to form a first target set IDVA.
Preferably, the target of the region may be a face image of a user or a merchant or a worker in the region; the target of the region is registered in the database, namely the face image exists in the database; the non-local area is targeted to be the face image which does not exist in the database.
Further, in step 3, the sub-step of obtaining the region association degree of each target in the first target set and obtaining the region association degree set includes:
step 3, calculating the area association degree of each target:
in the formula, RL is the regional relevance of a target, nov is the current time, the earliest time when the face of the current target appears in all stored monitoring scenes is CapR, capLi is the last appearance time of the face of the ith target in all the monitoring scenes, (NOW-CapLi) is the time interval between the last appearance time of the face of the ith target and the current time when all the monitoring scenes appear, len is the average time of the face of the current target in all the monitoring scenes, the last appearance time of the face of the current target in all the monitoring scenes is CapL, N is the size of the set IDVA, capN is the earliest number of times that the current target appears in all the monitoring scenes stored by a video terminal, the first appearance time refers to the time when the face of the current target can be successfully identified in all the stored monitoring scenes, and the last appearance time refers to the last appearance time when the face of the current target appears in all the stored monitoring scenes; and sorting the relevance degrees of all the targets in a descending order to form an area relevance degree set RLSet.
( The beneficial effects are that: the regional relevance of the target effectively describes the earliest appearing time interval and the latest appearing time interval of the current target in all monitored scenes, and provides quantitative indexes for the later spatial arrangement action. )
Preferably, in step 3, the sub-step of obtaining the region association degree of each target in the first target set and obtaining the region association degree set may further include: all monitoring scenes from the same target are clustered by acquiring all monitoring scenes, and the monitoring scenes of all targets are sequenced according to the total duration of all monitoring scenes of each target to form a regional association degree set RLSet.
Further, in step 4, receiving a spatial arrangement command, and removing or moving the monitored scene according to the region association degree, the substep of:
step 4.1, after receiving the spatial arrangement command, each video acquisition terminal cleans the monitoring scene according to the sequence of the region association degree set, specifically:
step 4.1.1, removing the monitoring scenes belonging to the first target in the area association degree set in sequence, wherein the removing range is that the time which is farthest from the current time in the monitoring scenes stored by the current video acquisition terminal is taken as a starting point, the time distance from the time which is farthest from the current time to the time which is the latest acquired target in the current video acquisition terminal is taken as an end point is T1, and deleting the monitoring scenes which comprise the selected target and begin to move ahead by T1/2 time period from the current time; if the monitoring scene of the selected target closest to the current moment is smaller than a second threshold value till the current moment, uploading the monitoring scene of the selected target closest to the current moment to a central server, and if the monitoring scene of the selected target exists in the central server, replacing the monitoring scene existing in the central server; (the first target is a target corresponding to the first element in the region association degree set);
and (4) according to the sequence of the targets in the area association set, circularly executing the step of step 4.1.1 to clean the monitoring scene of the targets until the available space of each video acquisition terminal reaches a set range or the available space reaches 70% of the total storage space.
Preferably, in step 4, the substep of receiving a spatial arrangement command and removing or moving the monitored scene according to the region association degree may further be:
step 4.1, after receiving the spatial arrangement command, each video acquisition terminal cleans the monitoring scene according to the sequence of the region association degree set, specifically:
marking the moment when the space arrangement command is received as the current moment; the space arrangement instruction may be an instruction signal sent to each video capture terminal at regular time, or an instruction signal sent when the remaining capacity of the central server is less than 20%, or the remaining capacity of one or more video capture terminals is less than 20%, or manually triggered.
Initializing a variable j as 1,j ∈ len (RLSet), and taking RLSetj as the jth element in the region relevance set RLSet; setting an empty list as a removal list; the len () function is the number of elements in the collection taken;
step 4.2, vn (RLSetj) is the number of monitoring scenes of the jth element in the region relevance set RLSet, VL (RLSetj) is the length of all monitoring scenes of the jth element in the region relevance set RLSet, MAXL (RLSet) is the maximum value of the duration of the monitoring scenes in all targets in the relevance set RLSet, minimumof the duration of the monitoring scenes in all targets in the MINL (RLSet) relevance set RLSet, and the arithmetic mean of the durations of all monitoring scenes in all targets in the AVGL (RLSet) relevance set RLSet,
( The length of the monitoring scene is the total time of the appearance of the human face of the target corresponding to the element in all the monitoring scenes; the monitoring scene duration is the duration of the appearance of the face of the target corresponding to the element in the monitoring scene; )
Setting a first condition: VL (RLSetj)/VN (RLSetj) > AVGL (RLSet) and the time span of the monitored scene to which the current RLSetj belongs, the target of which is closest to the current time instant, is greater than (MAXL (RLSet) + VL (RLSetj)/VN (RLSetj)) × VN (RLSetj);
if RLSetj meets a first condition, putting monitoring scenes with a time span to the current moment larger than (MAXL (RLSet) -AVGL (RLSet)) × VN (RLSetj) into a removal list, and if the removal list comprises all monitoring scenes of the current target, keeping the monitoring scenes closest to the current moment, namely, removing the monitoring scenes closest to the current moment from the removal list;
if the first condition is not met, adding all monitoring scenes except the monitoring scene closest to the current moment of the current target in the monitoring scenes associated with the target to which the RLSetj belongs into a removal list;
if j < len (RLSet) increases the value of j by 1, the step 4.2 is restarted, otherwise, the step 4.3 is skipped;
step 4.3, deleting the monitoring scenes including the removal list in all the video acquisition terminals according to the removal list, and transmitting the monitoring scenes, which are closest to the current moment, of each target in all the video acquisition terminals to a central server; replacing the monitoring scenes of the corresponding targets already existing in the central server.
Wherein, the beneficial effect of step 4 is: according to the number of videos of a target and the length of a monitoring scene, a spatial arrangement strategy is adjusted, an old monitoring scene is removed from a discrete video acquisition terminal, a latest monitoring scene is reserved in a central server, dynamic video compression can be performed according to the actual duration of the target, useless target videos are eliminated to a certain extent according to the relevance, the storage efficiency is improved, and meanwhile data of the central server are reserved in a corresponding video acquisition terminal so as to be prevented from being mistaken or lost.
A security protection detecting system based on intelligent video monitoring, the system includes:
an acquisition module: the system comprises a video acquisition terminal, wherein the video acquisition terminal can acquire a monitoring video and slice the monitoring video;
a processing module: calculating the region association degree of each target, sequencing the region association degrees of all the targets, and outputting a region association degree set;
a distribution module: cleaning all video acquisition terminals according to the regional relevance set, and uploading a required monitoring scene to a central server;
the central server: the method is used for long-term storage of the monitoring scene.
In a third aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of the invention.
In a fourth aspect, the present invention provides an electronic device comprising: a memory having a computer program stored thereon; a processor for executing the computer program in the memory to implement the steps of the method provided by the present invention.
Compared with the prior art, the invention has the following beneficial technical effects:
the monitoring scenes are flexibly arranged, the monitoring scenes needing to be cleaned are judged according to the storage space of the video acquisition terminal and the acquired monitoring scenes, whether the monitoring scenes belong to registered personnel in the area or not is distinguished, and different strategies are adopted, so that the monitoring videos of the personnel in the area are effectively divided and managed.
Drawings
FIG. 1 is a flow chart of a security detection method based on intelligent video monitoring according to the present invention;
fig. 2 is a schematic block diagram of a security detection system based on intelligent video monitoring according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are merely illustrative of the invention and are not intended to be limiting.
It is also to be understood that the following examples are illustrative of the present invention and are not to be construed as limiting the scope of the invention, and that certain insubstantial modifications and adaptations of the invention by those skilled in the art in light of the foregoing description are intended to be included within the scope of the invention. The specific process parameters and the like of the following examples are also merely examples within a suitable range, i.e., those skilled in the art can select within a suitable range by the description herein, and are not limited to the specific values exemplified below.
The following exemplarily illustrates a security detection method based on intelligent video monitoring provided by the invention.
Fig. 1 is a flowchart of a security detection method based on intelligent video monitoring, and the following describes, with reference to fig. 1, a security detection method based on intelligent video monitoring according to an embodiment of the present invention, where the method includes the following steps:
a security detection method based on intelligent video monitoring comprises the following steps:
step 1, collecting monitoring videos from different video collecting terminals, and slicing the collected videos to obtain monitoring scenes;
step 2, identifying targets from the monitoring scene, obtaining unregistered targets and forming a first target set;
step 3, obtaining the regional relevancy of each target in the first target set and obtaining a regional relevancy set;
and 4, receiving a space arrangement command, and removing or moving the monitored scene according to the area association degree.
Further, in step 1, the substeps of acquiring monitoring videos from different video acquisition terminals and slicing the acquired videos to obtain monitoring scenes are as follows:
deploying a video acquisition terminal in a monitored target area, wherein the video acquisition terminal can acquire videos according to a certain interval or trigger video acquisition in linkage with security equipment;
the acquired video is sliced to obtain one or more monitoring scenes, and the slicing method can be to slice the acquired video according to a set rule, or according to one or more of a trigger signal from security equipment or manual trigger.
Preferably, the security equipment can be entrance guard's equipment, and when the user triggered entrance guard's equipment, video acquisition terminal began to gather the video.
Preferably, the video acquisition terminal can be an indoor pan-tilt camera, an outdoor dome camera, or a door lock or an entrance guard with built-in face recognition, or a handheld law enforcement recorder.
Preferably, the slicing method can be performed according to the record of the chinese patent application "a surveillance video slice storage method and system" in publication No. CN109361904 a.
Further, in step 2, identifying an object from the monitoring scene to obtain an unregistered object, and forming a first object set includes the following substeps:
and extracting the face of each monitoring scene, identifying the monitoring scene with the face and extracting the face, wherein each extracted face forms a target sequence, and the target sequence comprises the time when the target appears in the video acquisition terminal and the corresponding video acquisition terminal.
The unregistered target is a target which cannot be matched in a database in which target images are prestored;
at least one face exists in the stored pictures of each monitoring scene, and at least one frame in the pictures of the monitoring scenes comprises one or more faces; if the face does not exist in the scene picture, marking a blank monitoring scene; the blank monitoring scene is not stored in the video acquisition terminal;
and comparing each target of the target sequence with a target image prestored in a database, marking the targets in the non-local area, and obtaining the targets in the non-local area to form a first target set IDVA.
Preferably, the target of the area can be a user or a business, a staff; the object of the present region is registered in the database, i.e., the face image exists in the database.
Further, in step 3, the sub-step of obtaining the region association degree of each target in the first target set and obtaining the region association degree set includes:
step 3, calculating the area association degree of each target:
in the formula, RL is the regional relevance of a target, nov is the current time, the earliest time when the face of the current target appears in all stored monitoring scenes is CapR, capLi is the last appearance time of the face of the ith target in all the monitoring scenes, (NOW-CapLi) is the time interval between the last appearance time of the face of the ith target and the current time when all the monitoring scenes appear, len is the average time of the face of the current target in all the monitoring scenes, the last appearance time of the face of the current target in all the monitoring scenes is CapL, N is the size of the set IDVA, capN is the earliest number of times that the current target appears in all the monitoring scenes stored by a video terminal, the first appearance time refers to the time when the face of the current target can be successfully identified in all the stored monitoring scenes, and the last appearance time refers to the last appearance time when the face of the current target appears in all the stored monitoring scenes; and sorting the relevance of all the targets in a descending order to form an area relevance set RLSet.
The regional relevance of the target effectively describes the earliest occurring time interval and the latest occurring time interval of the current target in all monitored scenes, and provides quantitative indexes for the subsequent spatial arrangement action.
Preferably, the area relevancy can also cluster the monitoring scenes from the same target by acquiring all the monitoring scenes, and sort the monitoring scenes of all the targets according to the total duration of all the monitoring scenes of each target to form an area relevancy set RLSet.
Further, in step 4, receiving a spatial arrangement command, and removing or moving the monitored scene according to the region association degree, the substep of:
step 4.1, after receiving the spatial arrangement command, each video acquisition terminal cleans the monitoring scene according to the sequence of the region association degree set, specifically:
step 4.1.1, removing the monitoring scenes belonging to the first target in the area association degree set in sequence, wherein the removing range is that the time which is farthest away from the current time in the monitoring scenes stored in the current video acquisition terminal is taken as a starting point, the time distance from the time which is farthest away from the current time to the time which is obtained most recently in the current video acquisition terminal and is taken as an end point is T1, and deleting the monitoring scenes which comprise the selected targets and begin to move forward at the current time within a time period of T1/2; if the monitoring scene of the selected target closest to the current moment is smaller than a second threshold value till the current moment, uploading the monitoring scene of the selected target closest to the current moment to a central server, and if the monitoring scene of the selected target exists in the central server, replacing the monitoring scene existing in the central server; (the first target is a target corresponding to the first element in the region association degree set);
and (4) according to the sequence of the targets in the area association set, circularly executing the step of step 4.1.1 to clean the monitoring scene of the targets until the available space of each video acquisition terminal reaches a set range or the available space reaches 70% of the total storage space.
Preferably, the second threshold includes an average time length of all the targets appearing in the monitored scene, and may also be T1/2.
Preferably, in step 4, the substep of receiving a spatial arrangement command and removing or moving the monitored scene according to the region association degree may further be:
step 4.1, after receiving the spatial arrangement command, each video acquisition terminal cleans the monitoring scene according to the sequence of the region association degree set, specifically:
marking the moment when the space arrangement command is received as the current moment; the spatial arrangement instruction can be sent to each video acquisition terminal at regular time, or sent when the residual capacity of the central server is less than 20%, or the residual capacity of one or more video acquisition terminals is less than 20%, or triggered manually.
Initializing a variable j as 1,j ∈ len (RLSet), and taking RLSetj as the jth element in the region relevance set RLSet; setting an empty list as a removal list; the len () function is the number of elements in the collection taken;
step 4.2, vn (RLSetj) is the number of monitoring scenes of the jth element in the region relevance set RLSet, VL (RLSetj) is the length of all monitoring scenes of the jth element in the region relevance set RLSet, MAXL (RLSet) is the maximum value of the duration of the monitoring scenes in all targets in the relevance set RLSet, MINL (RLSet) is the minimum value of the duration of the monitoring scenes in all targets in the relevance set RLSet, and AVGL (RLSet) is the arithmetic mean of the durations of all monitoring scenes in all targets in the relevance set RLSet, and the first condition is set: VL (RLSetj)/VN (RLSetj) > AVGL (RLSet) and the time span of the monitored scene to which the current RLSetj belongs, the target of which is closest to the current time instant, is greater than (MAXL (RLSet) + VL (RLSetj)/VN (RLSetj)) × VN (RLSetj);
if RLSetj meets a first condition, putting monitoring scenes with a time span to the current moment larger than (MAXL (RLSet) -AVGL (RLSet)) × VN (RLSetj) into a removal list, and if the removal list comprises all monitoring scenes of the current target, keeping the monitoring scenes closest to the current moment, namely, removing the monitoring scenes closest to the current moment from the removal list;
if the first condition is not met, adding all monitoring scenes of the monitoring scenes which are associated with the target to which the RLSetj belongs, except the monitoring scene of the current target and the monitoring scene which is closest to the current moment, into a removal list;
if j < len (RLSet) increases the value of j by 1, the step 4.2 is restarted, otherwise, the step 4.3 is skipped;
step 4.3, deleting the monitoring scenes including the removal list in all the video acquisition terminals according to the removal list, and transmitting the monitoring scenes, which are closest to the current moment, of each target in all the video acquisition terminals to a central server; replacing the monitoring scenes of the corresponding targets already existing in the central server.
The beneficial effects of the step 4 are: according to the number of videos of a target, the length of a monitoring scene is adjusted to a spatial arrangement strategy, an old monitoring scene is removed from a separate video acquisition terminal, a latest monitoring scene is reserved in a central server, and meanwhile, data of the central server are reserved in a corresponding video acquisition terminal so as to avoid errors or loss.
Fig. 2 is a schematic block diagram of a security detection system based on intelligent video monitoring according to an embodiment of the present invention.
A security protection detecting system based on intelligent video monitoring, the system includes:
an acquisition module: the system comprises a video acquisition terminal, wherein the video acquisition terminal can acquire a monitoring video;
a processing module: calculating the region association degree of each target, sequencing the region association degrees of all the targets, and outputting a region association degree set;
a distribution module: cleaning all video acquisition terminals according to the regional association degree set, and uploading a required monitoring scene to a central server;
the central server: for persisting the monitoring scenario.
The security detection system based on intelligent video monitoring can be operated in computing equipment such as desktop computers, notebooks, palm computers and cloud servers. The security detection system based on intelligent video monitoring can operate by comprising a processor and a memory. Those skilled in the art will appreciate that the example is merely an example of a security detection system based on intelligent video surveillance, and does not constitute a limitation of the security detection system based on intelligent video surveillance, and may include more or less components than the others, or combine some components, or different components, for example, the security detection system based on intelligent video surveillance may further include an input and output device, a network access device, a bus, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can also be any conventional processor and the like, the processor is a control center of the security detection system operation system based on intelligent video monitoring, and various interfaces and lines are utilized to connect all parts of the whole security detection system operable system based on intelligent video monitoring.
The memory can be used for storing the computer program and/or the module, and the processor realizes various functions of the security detection system based on intelligent video monitoring by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Although the present invention has been described in considerable detail and with reference to certain illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the invention. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalents thereto.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (6)
1. A security detection method based on intelligent video monitoring is characterized by comprising the following steps:
step 1, collecting monitoring videos from different video collecting terminals, and slicing the collected videos to obtain monitoring scenes;
step 2, identifying targets from the monitoring scene, obtaining unregistered targets and forming a first target set;
step 3, obtaining the regional relevance of each target in the first target set, and obtaining a regional relevance set;
step 4, receiving a space arrangement command, and removing or moving the monitoring scene according to the area association degree;
in step 2, identifying an object from the monitoring scene, and obtaining an unregistered object, wherein the substep of forming the first object set is as follows: extracting the face of each monitoring scene, identifying the monitoring scene with the face and extracting the face, wherein each extracted face forms a target sequence, and the target sequence comprises the time when the target appears in the video acquisition terminal and the corresponding video acquisition terminal;
the unregistered target is a target which cannot be matched in a database in which target images are prestored;
at least one face exists in each stored picture of the monitoring scene, and at least one frame in the pictures of the monitoring scene comprises one or more faces; if the face does not exist in the scene picture, marking a blank monitoring scene; the blank monitoring scene is not stored in the video acquisition terminal;
comparing each target of the target sequence with a target image prestored in a database, marking the targets in the non-local area, and obtaining the targets in the non-local area to form a first target set IDVA;
in step 3, obtaining the regional relevance of each target in the first target set, and obtaining the regional relevance set comprises the following substeps: calculating the area association degree of each target:
in the formula, RL is the regional relevance of a target, nov is the current time, the earliest time when the face of the current target appears in all stored monitoring scenes is CapR, capLi is the last appearance time of the face of the ith target in all the monitoring scenes, (NOW-CapLi) is the time interval between the last appearance time of the face of the ith target and the current time when all the monitoring scenes appear, len is the average time of the face of the current target in all the monitoring scenes, the last appearance time of the face of the current target in all the monitoring scenes is CapL, N is the size of the set IDVA, capN is the earliest number of times that the current target appears in all the monitoring scenes stored by a video terminal, the first appearance time refers to the time when the face of the current target can be successfully identified in all the stored monitoring scenes, and the last appearance time refers to the last appearance time when the face of the current target appears in all the stored monitoring scenes; sorting the relevance degrees of all the targets in a descending order to form a region relevance degree set RLSet;
the regional relevance of the target effectively describes the earliest occurring time interval and the latest occurring time interval of the current target in all monitored scenes, and provides quantitative indexes for the subsequent spatial arrangement action.
2. The security detection method based on intelligent video monitoring as claimed in claim 1, wherein in step 1, the substeps of acquiring monitoring videos from different video acquisition terminals and slicing the acquired videos to obtain monitoring scenes are as follows:
deploying a video acquisition terminal in a monitored target area, wherein the video acquisition terminal can acquire videos according to a certain interval or trigger video acquisition in linkage with security equipment;
the acquired video is sliced to obtain one or more monitoring scenes, and the slicing method can be to slice the acquired video according to a set rule, or according to one or more of a trigger signal from security equipment or manual trigger.
3. The security detection method based on intelligent video monitoring as claimed in claim 1, wherein in step 4, a spatial arrangement command is received, and the substep of removing or moving the monitored scene according to the region association degree is as follows:
step 4.1, after receiving the spatial arrangement command, each video acquisition terminal cleans the monitoring scene according to the sequence of the region association degree set, specifically:
step 4.1.1, removing the monitoring scenes belonging to the first target in the area association degree set in sequence, wherein the removing range is that the time which is farthest from the current time in the monitoring scenes stored by the current video acquisition terminal is taken as a starting point, the time distance from the time which is farthest from the current time to the time which is the latest acquired target in the current video acquisition terminal is taken as an end point is T1, and deleting the monitoring scenes which comprise the selected targets and are in the time period of T1/2 before the current time; if the monitoring scene of the selected target closest to the current moment is smaller than a second threshold value by the current moment, uploading the monitoring scene of the selected target closest to the current moment to a central server, and replacing the monitoring scene existing in the central server if the monitoring scene of the selected target exists in the central server;
and (3) according to the sequence of the targets in the area association set, circularly executing the step 4.1.1 to clean the monitoring scene of the targets until the available space of each video acquisition terminal reaches a set range or the available space reaches 70% of the total storage space.
4. The utility model provides a security protection detecting system based on intelligent video monitoring which characterized in that, the system includes:
an acquisition module: the system comprises a video acquisition terminal, wherein the video acquisition terminal can acquire a monitoring video;
a processing module: calculating the region association degree of each target, sequencing the region association degrees of all the targets, and outputting a region association degree set;
the substep of obtaining the region association degree of each target in the first target set and obtaining the region association degree set comprises: identifying targets from a monitoring scene, and obtaining unregistered targets, wherein the substep of forming a first target set is as follows:
extracting the face of each monitoring scene, identifying the monitoring scene with the face and extracting the face, wherein each extracted face forms a target sequence, and the target sequence comprises the time when the target appears in the video acquisition terminal and the corresponding video acquisition terminal;
the unregistered target is a target which cannot be matched in a database in which target images are prestored;
at least one face exists in the stored pictures of each monitoring scene, and at least one frame in the pictures of the monitoring scenes comprises one or more faces; if the face does not exist in the picture of the scene, marking a blank monitoring scene; the blank monitoring scene is not stored in the video acquisition terminal;
comparing each target of the target sequence with a target image prestored in a database, marking the targets in the non-local area, and obtaining the targets in the non-local area to form a first target set IDVA;
calculating the area association degree of each target:
in the formula, RL is the regional relevance of a target, nov is the current time, the earliest time when the face of the current target appears in all stored monitoring scenes is CapR, capLi is the last appearance time of the face of the ith target in all the monitoring scenes, (NOW-CapLi) is the time interval between the last appearance time of the face of the ith target and the current time when all the monitoring scenes appear, len is the average time of the face of the current target in all the monitoring scenes, the last appearance time of the face of the current target in all the monitoring scenes is CapL, N is the size of the set IDVA, capN is the earliest number of times that the current target appears in all the monitoring scenes stored by a video terminal, the first appearance time refers to the time when the face of the current target can be successfully identified in all the stored monitoring scenes, and the last appearance time refers to the last appearance time when the face of the current target appears in all the stored monitoring scenes; sorting the relevance degrees of all the targets in a descending order to form a region relevance degree set RLSet;
the regional relevance of the target effectively describes the earliest appearing time interval and the latest appearing time interval of the current target in all monitored scenes, and provides a quantitative index for the subsequent spatial arrangement action;
a distribution module: cleaning all video acquisition terminals according to the regional relevance set, and uploading a required monitoring scene to a central server;
the central server: for persisting monitoring scenarios.
5. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 3.
6. An electronic device, comprising: a memory having a computer program stored thereon; a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210557086.2A CN114863364B (en) | 2022-05-20 | 2022-05-20 | Security detection method and system based on intelligent video monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210557086.2A CN114863364B (en) | 2022-05-20 | 2022-05-20 | Security detection method and system based on intelligent video monitoring |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114863364A CN114863364A (en) | 2022-08-05 |
CN114863364B true CN114863364B (en) | 2023-03-07 |
Family
ID=82639699
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210557086.2A Active CN114863364B (en) | 2022-05-20 | 2022-05-20 | Security detection method and system based on intelligent video monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114863364B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117528028B (en) * | 2023-11-08 | 2024-04-19 | 广州雄风信息技术有限公司 | Security video monitoring system based on Internet of things |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109361904A (en) * | 2018-11-21 | 2019-02-19 | 佛山市云团科技有限公司 | A kind of monitor video slice storage method and system |
CN110008797A (en) * | 2018-10-08 | 2019-07-12 | 杭州中威电子股份有限公司 | A kind of multiple-camera plurality of human faces video connects acquisition device and method |
CN110719437A (en) * | 2018-07-13 | 2020-01-21 | 视联动力信息技术股份有限公司 | Monitoring video processing method and device based on video network |
CN110876035A (en) * | 2018-08-31 | 2020-03-10 | 杭州海康威视***技术有限公司 | Scene updating method and device based on video and electronic equipment |
CN111126152A (en) * | 2019-11-25 | 2020-05-08 | 国网信通亿力科技有限责任公司 | Video-based multi-target pedestrian detection and tracking method |
CN111222373A (en) * | 2018-11-26 | 2020-06-02 | 深圳云天励飞技术有限公司 | Personnel behavior analysis method and device and electronic equipment |
CN112601050A (en) * | 2020-12-09 | 2021-04-02 | 张兴莉 | Smart city video monitoring method and device |
CN112689132A (en) * | 2021-03-15 | 2021-04-20 | 成都点泽智能科技有限公司 | Target object monitoring method and monitoring equipment |
CN113656243A (en) * | 2021-07-28 | 2021-11-16 | 连连(杭州)信息技术有限公司 | Service index monitoring method, device, equipment and storage medium |
CN114095734A (en) * | 2021-10-26 | 2022-02-25 | 陈正跃 | User data compression method and system based on data processing |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101854516B (en) * | 2009-04-02 | 2014-03-05 | 北京中星微电子有限公司 | Video monitoring system, video monitoring server and video monitoring method |
CN111160380A (en) * | 2018-11-07 | 2020-05-15 | 华为技术有限公司 | Method for generating video analysis model and video analysis system |
CN110196914B (en) * | 2019-07-29 | 2019-12-27 | 上海肇观电子科技有限公司 | Method and device for inputting face information into database |
JP2022503373A (en) * | 2019-09-29 | 2022-01-12 | 北京市商▲湯▼科技▲開▼▲發▼有限公司 | Data processing methods, devices and storage media |
CN112580397A (en) * | 2019-09-29 | 2021-03-30 | 北京市商汤科技开发有限公司 | Data processing method, device and storage medium |
-
2022
- 2022-05-20 CN CN202210557086.2A patent/CN114863364B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110719437A (en) * | 2018-07-13 | 2020-01-21 | 视联动力信息技术股份有限公司 | Monitoring video processing method and device based on video network |
CN110876035A (en) * | 2018-08-31 | 2020-03-10 | 杭州海康威视***技术有限公司 | Scene updating method and device based on video and electronic equipment |
CN110008797A (en) * | 2018-10-08 | 2019-07-12 | 杭州中威电子股份有限公司 | A kind of multiple-camera plurality of human faces video connects acquisition device and method |
CN109361904A (en) * | 2018-11-21 | 2019-02-19 | 佛山市云团科技有限公司 | A kind of monitor video slice storage method and system |
CN111222373A (en) * | 2018-11-26 | 2020-06-02 | 深圳云天励飞技术有限公司 | Personnel behavior analysis method and device and electronic equipment |
CN111126152A (en) * | 2019-11-25 | 2020-05-08 | 国网信通亿力科技有限责任公司 | Video-based multi-target pedestrian detection and tracking method |
CN112601050A (en) * | 2020-12-09 | 2021-04-02 | 张兴莉 | Smart city video monitoring method and device |
CN112689132A (en) * | 2021-03-15 | 2021-04-20 | 成都点泽智能科技有限公司 | Target object monitoring method and monitoring equipment |
CN113656243A (en) * | 2021-07-28 | 2021-11-16 | 连连(杭州)信息技术有限公司 | Service index monitoring method, device, equipment and storage medium |
CN114095734A (en) * | 2021-10-26 | 2022-02-25 | 陈正跃 | User data compression method and system based on data processing |
Non-Patent Citations (3)
Title |
---|
基于数据仓库冗余数据的监控和清理策略;吴英 等;《煤炭技术》;第29卷(第9期);第51-53页 * |
基于智能视频监控的安防***设计;陈为民等;《江西理工大学学报》(第01期);第78-81+93页 * |
实现故障监控的智能预警;李虹 等;《软件》;第41卷(第6期);第237-241页 * |
Also Published As
Publication number | Publication date |
---|---|
CN114863364A (en) | 2022-08-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210357624A1 (en) | Information processing method and device, and storage medium | |
CN109635146B (en) | Target query method and system based on image characteristics | |
CN111368622B (en) | Personnel identification method and device and storage medium | |
TWI740537B (en) | Information processing method, device and storage medium thereof | |
CN107958220B (en) | Face library compression processing method based on face recognition and intelligent device thereof | |
US20130329059A1 (en) | Person detection system | |
CN111291682A (en) | Method and device for determining target object, storage medium and electronic device | |
CN109800664B (en) | Method and device for determining passersby track | |
CN109800329B (en) | Monitoring method and device | |
CN109784220B (en) | Method and device for determining passerby track | |
CN114863364B (en) | Security detection method and system based on intelligent video monitoring | |
CN112579593A (en) | Population database sorting method and device | |
CN112883213B (en) | Picture archiving method and device and electronic equipment | |
CN111708906B (en) | Visiting retrieval method, device and equipment based on face recognition and storage medium | |
WO2023124134A1 (en) | File processing method and apparatus, electronic device, computer storage medium and program | |
CN106777215A (en) | A kind of image searching result display methods and device | |
WO2022057773A1 (en) | Image storage method and apparatus, computer device and storage medium | |
WO2021129491A1 (en) | Pedestrian search method, server, and storage medium | |
CN112613396B (en) | Task emergency degree processing method and system | |
CN111563479B (en) | Concurrent person weight removing method, partner analyzing method and device and electronic equipment | |
CN105320704B (en) | Trans-regional similar vehicle search method and device | |
CN110309878B (en) | Information processing method and device and storage medium | |
CN111818296B (en) | Monitoring target identification method and distributed monitoring system | |
CN111753756A (en) | Object identification-based deployment alarm method and device and storage medium | |
CN111368115A (en) | Data clustering method and device, clustering server and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |