CN111339366A - Big data video retrieval method and device, computer equipment and storage medium - Google Patents
Big data video retrieval method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111339366A CN111339366A CN201911365734.9A CN201911365734A CN111339366A CN 111339366 A CN111339366 A CN 111339366A CN 201911365734 A CN201911365734 A CN 201911365734A CN 111339366 A CN111339366 A CN 111339366A
- Authority
- CN
- China
- Prior art keywords
- data
- behavior
- monitoring
- suspicious
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of computer technology, in particular to a big data video retrieval method, a device, computer equipment and a storage medium, wherein the big data video retrieval method comprises the following steps: s10: acquiring historical monitoring videos, and acquiring suspicious monitoring video data from the historical monitoring data; s20: extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos; s30: if video monitoring data are acquired, extracting personnel behavior characteristics from the video monitoring data; s40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring the behavior identification corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information. The invention has the effect of acquiring possible behaviors in the crowd in time.
Description
Technical Field
The present invention relates to the technical field of computer technologies, and in particular, to a method and an apparatus for retrieving a big data video, a computer device, and a storage medium.
Background
At present, people pay more and more attention to public security, and most public places are provided with video monitoring systems, so that the public places can be well monitored, video data obtained by monitoring can be stored, and follow-up review is facilitated.
In the prior art, a chinese patent with an authorized publication number of CN106339428B discloses a method and an apparatus for identifying the identity of a suspect based on video big data, which includes: receiving suspect characteristic information sent by a user; clustering and searching moving targets matched with the feature information of the suspect from a moving target feature database, and extracting feature information corresponding to the moving targets; acquiring base station data in a moving range corresponding to the characteristic information according to the extracted characteristic information; extracting suspect identity information matched with the moving target from the identity information platform device according to the base station data in the moving range corresponding to the characteristic information; the comprehensive collision retrieval is carried out by combining various resources such as a moving target characteristic database, base station data, resident population data in an identity information platform device and the like, so that accurate video suspect identity information can be obtained, and the accuracy and success rate of suspect identity information identification are greatly improved; and moreover, a large-data analysis processing technology is adopted, a large number of high-speed and variable complex scenes can be processed, and the timeliness is good.
The above prior art solutions have the following drawbacks: the characteristic information can be extracted only by matching the suspect characteristics of the suspect received in advance in the moving target characteristic database, and then judgment is carried out, and some persons who execute suspicious behaviors are not recorded into a public security system, so that the persons cannot be timely obtained and prevented, and therefore, the improvement space is provided.
Disclosure of Invention
The invention aims to provide a method and a device for searching big data videos capable of timely acquiring behaviors of people, computer equipment and a storage medium.
The above object of the present invention is achieved by the following technical solutions:
a big data video retrieval method comprises the following steps:
s10: acquiring historical monitoring videos, and acquiring suspicious monitoring video data from the historical monitoring data;
s20: extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos;
s30: if video monitoring data are acquired, extracting personnel behavior characteristics from the video monitoring data;
s40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring the behavior identification corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information.
By adopting the technical scheme, the suspicious monitoring video data are obtained from the historical monitoring video in advance, the corresponding suspicious behavior characteristics and the corresponding behavior identifiers are extracted from the suspicious monitoring video, the personnel behavior characteristics can be extracted from the actually monitored video monitoring data during actual monitoring, the personnel behavior characteristics are used for traversal retrieval, the behavior of suspicious personnel can be obtained from an actual public place in time, and the safety of the public place is improved.
The invention is further configured to: step S10 includes:
s11: acquiring historical alarm data, and acquiring the corresponding historical monitoring video and the corresponding alarm behavior type from the historical alarm data;
s12: and after classifying the historical monitoring data according to the alarm behavior type, taking each type of the historical monitoring data as the suspicious monitoring video data.
By adopting the technical scheme, the corresponding historical monitoring videos are extracted from the historical alarm data, and then the classification is carried out according to the alarm behavior types corresponding to the historical monitoring videos, so that the corresponding suspicious behaviors can be better searched in a traversing manner, and the efficiency of alarm feedback is favorably improved.
The invention is further configured to: step S20 includes:
s21: setting the behavior identification according to the alarm behavior type;
s22: and after suspicious behavior characteristics are extracted from the suspicious behavior monitoring videos class by class, the suspicious behavior characteristics and the corresponding behavior identifications are associated through key-value.
By adopting the technical scheme, the suspicious behavior characteristics and the corresponding behavior identification are associated through key-value, and the corresponding behavior identification can be quickly acquired during traversal retrieval.
The invention is further configured to: step S30 includes:
s31: performing frame processing on the video monitoring data to obtain monitoring image data corresponding to each frame;
s32: acquiring the individual personnel data from each frame of the monitoring image;
s33: sequencing the monitoring image data according to the playing sequence of the video monitoring data to obtain a corresponding sequencing result;
s34: after the personnel single data are processed according to the sequencing result, personnel position data of the same personnel single data in the corresponding monitoring image data are obtained;
s35: and counting the personnel position data according to the playing sequence to obtain the corresponding personnel behavior characteristics.
By adopting the technical scheme, the monitoring video data is subjected to framing processing, and the corresponding individual personnel data can be obtained from the monitoring image data of each frame, so that the personnel condition can be obtained from the monitoring video data, and the personnel condition of a public place can be favorably analyzed from the monitoring video; the personnel single data in the monitoring image data of each frame in the playing sequence are arranged, so that the change trend of the corresponding personnel position data can be obtained to obtain the personnel behavior characteristics in the personnel.
The invention is further configured to: after step S40, the big data video retrieval method further includes:
s50: if an abnormal alarm signal is obtained, obtaining abnormal behavior data and a corresponding abnormal identifier from the abnormal alarm signal;
s60: and performing matching query in the behavior identifier by using the abnormal identifier, and if the matching fails, storing the abnormal alarm signal and the corresponding abnormal identifier into a preset database.
By adopting the technical scheme, the abnormal alarm signal and the corresponding abnormal identification which are carried out are stored in the preset database, so that the richness of suspicious behavior data is promoted, the monitoring effect is promoted, and the timely alarm effect is played.
The second aim of the invention is realized by the following technical scheme:
a big data video retrieval device, the big data video retrieval device comprising:
the historical video data acquisition module is used for acquiring historical monitoring videos and acquiring suspicious monitoring video data from the historical monitoring data;
the suspicious characteristic extraction module is used for extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos;
the behavior feature extraction module is used for extracting the behavior features of the personnel from the video monitoring data if the video monitoring data are obtained;
and the retrieval alarm module is used for performing traversal retrieval on the personnel behavior characteristics in the suspicious behavior characteristics, acquiring the behavior identification corresponding to the suspicious behavior characteristics after the traversal retrieval is successful, and generating corresponding alarm information.
By adopting the technical scheme, the suspicious monitoring video data are obtained from the historical monitoring video in advance, the corresponding suspicious behavior characteristics and the corresponding behavior identifiers are extracted from the suspicious monitoring video, the personnel behavior characteristics can be extracted from the actually monitored video monitoring data during actual monitoring, the personnel behavior characteristics are used for traversal retrieval, the behavior of suspicious personnel can be obtained from an actual public place in time, and the safety of the public place is improved.
The third object of the invention is realized by the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the big data video retrieval method when executing the computer program.
The fourth object of the invention is realized by the following technical scheme:
a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the big data video retrieval method described above.
In conclusion, the beneficial technical effects of the invention are as follows:
1. by acquiring suspicious monitoring video data from a historical monitoring video in advance and extracting corresponding suspicious behavior characteristics and corresponding behavior identifiers from the suspicious monitoring video, the personnel behavior characteristics can be extracted from the actually monitored video monitoring data during actual monitoring, traversal retrieval is carried out by using the personnel behavior characteristics, behaviors of suspicious personnel can be acquired from an actual public place in time, and the safety of the public place is improved;
2. the personnel single data in the monitoring image data of each frame in the playing sequence are arranged, so that the personnel flow condition in the personnel, namely the movement direction of the personnel, can be obtained according to the change trend of the personnel position data.
Drawings
FIG. 1 is a flow chart of a big data video retrieval method according to an embodiment of the present invention;
fig. 2 is a flowchart of the implementation of step S10 in the big data video retrieval method according to an embodiment of the present invention;
fig. 3 is a flowchart of the implementation of step S20 in the big data video retrieval method according to an embodiment of the present invention;
fig. 4 is a flowchart of the implementation of step S30 in the big data video retrieval method according to an embodiment of the present invention;
FIG. 5 is a flow chart of another implementation of a big data video retrieval method according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of a big data video retrieval device according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in an embodiment, as shown in fig. 1, the present invention discloses a big data video retrieval method, which specifically includes the following steps:
s10: and acquiring historical monitoring videos and suspicious monitoring video data from the historical monitoring data.
In this embodiment, the historical monitoring video refers to video data obtained by a monitoring device in a past period of time. The suspicious monitoring video data comprise monitoring videos of suspicious behaviors in the historical monitoring videos.
Specifically, the historical monitoring video is acquired from a large data platform corresponding to a database in which the historical monitoring video is stored. The historical monitoring video can be a public place which needs to be monitored actually, and can also be added into historical monitoring data in a public security system according to security requirements of the public place, such as banks, tax lobbies and other financial places.
Further, in the historical monitoring video, a monitoring video corresponding to a criminal action and a behavior of a criminal-action-implementing suspect at the location before the criminal action is implemented is obtained as the monitoring video data.
S20: and extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos.
In this embodiment, the suspicious behavior feature refers to a feature of a specific suspicious behavior in the suspicious surveillance video data. Behavior identification refers to the kind of specific suspicious behavior, such as wandering, tracking, stealing, and robbery.
Specifically, in the suspicious monitoring video, a person or a crowd performing suspicious behaviors is located, corresponding suspicious behavior features are extracted from the located person or crowd, and corresponding behavior identifiers are used for performing marking association according to the specific suspicious behaviors.
S30: and if the video monitoring data are acquired, extracting the behavior characteristics of the personnel from the video monitoring data.
In this embodiment, the video surveillance video refers to a real-time video monitored by a monitoring device in an actual public place. The person behavior feature refers to data of behavior of a person in the video surveillance data.
Specifically, by installing a monitoring device in a public place, corresponding video monitoring data is acquired through the monitoring device. Furthermore, the data of each individual person is extracted from the video monitoring data, so that the behavior of each individual person is obtained, and the characteristics of the behavior are extracted as the behavior characteristics of the person.
S40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring behavior identifications corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information.
Specifically, similarity is calculated between the personnel behavior features and each suspicious behavior feature, namely corresponding feature vectors are constructed between the personnel behavior features and the suspicious behavior features, and further, the similarity between the personnel behavior features and each suspicious behavior feature is calculated through cosine similarity.
Further, by setting a related similarity threshold, different similarity thresholds can be specifically set according to the security level of a specific position of a public place, and if the calculated similarity is not higher than the similarity threshold, the traversal retrieval is determined to be successful.
Further, behavior identification of suspicious behavior characteristics successfully searched by traversing the personnel behavior data is obtained, and the behavior identification, namely the specific suspicious behavior, and the location where the specific suspicious behavior is detected form alarm information.
In this embodiment, by acquiring suspicious monitoring video data from a historical monitoring video in advance and extracting corresponding suspicious behavior features and corresponding behavior identifiers from the suspicious monitoring video, the personnel behavior features can be extracted from the actually monitored video monitoring data during actual monitoring, and the personnel behavior features are used for traversal retrieval, so that behaviors of suspicious personnel can be acquired from an actual public place in time, and the safety of the public place is improved.
In an embodiment, as shown in fig. 2, in step S10, the method for acquiring historical monitoring videos and suspicious monitoring video data from historical monitoring data includes the following steps:
s11: and acquiring historical alarm data, and acquiring a corresponding historical monitoring video and a corresponding alarm behavior type from the historical alarm data.
In this embodiment, the historical alarm data refers to data that alarms over a period of time in the past. The alarm behavior type refers to an illegal or violation behavior in a specific alarm.
Specifically, historical monitoring videos corresponding to historical alarm data are obtained, and the corresponding historical monitoring videos are marked by using the alarm behavior types of the historical alarm data.
S12: and after classifying the historical monitoring data according to the alarm behavior types, taking each type of historical monitoring data as suspicious monitoring video data.
Specifically, the historical monitoring data corresponding to the same alarm behavior type is classified into one type, and each type of historical monitoring data is used as suspicious monitoring video data.
In an embodiment, as shown in fig. 3, in step S20, the method for extracting suspicious behavior features and behavior identifiers corresponding to the suspicious behavior features from the suspicious monitoring videos specifically includes the following steps:
s21: and setting a behavior identifier according to the alarm behavior type.
Specifically, the alarm behavior type is used as the behavior identifier.
S22: and after suspicious behavior characteristics are extracted from the suspicious behavior monitoring videos class by class, the suspicious behavior characteristics and the corresponding behavior identifications are associated through key-value.
Specifically, the existing feature extraction technology is adopted to extract the corresponding suspicious behavior features from the behavior of the person who implements the suspicious behavior class by class from the suspicious behavior monitoring data.
Furthermore, by means of a hash algorithm, the suspicious behavior feature is used as a key value, the corresponding behavior identifier is used as a value, and the suspicious behavior feature data is associated with the corresponding behavior identifier.
In an embodiment, as shown in fig. 4, in step S30, that is, if the video monitoring data is acquired, extracting the behavior characteristics of the person from the video monitoring data specifically includes the following steps:
s31: and performing frame processing on the video monitoring data to obtain monitoring image data corresponding to each frame.
In the present embodiment, the monitor image data refers to image data of each frame in the video monitor data.
Specifically, the framing processing is performed on the video monitoring data, and then the monitoring image data corresponding to each frame is obtained.
S32: and acquiring individual person data from each monitoring image.
Specifically, the person-by-person data is acquired in each of the monitor images using the technique of acquiring a suspicious person in step S22.
S33: and sequencing the monitoring image data according to the playing sequence of the video monitoring data to obtain a corresponding sequencing result.
In this embodiment, the sorting result refers to a result obtained by sorting the monitoring image data.
Specifically, after the video monitoring data is framed, the playing time corresponding to each frame in the video monitoring data is obtained, and the sequence from the front to the back of the playing time is used as the playing sequence of the monitoring image data. Further, the playing sequence is used for sequencing the monitoring image sequence of each frame to obtain the sequencing result.
S34: and after the individual personnel data are sorted according to the sorting result, acquiring the personnel position data of the same individual personnel data in the corresponding monitoring image data.
In this embodiment, the person position data refers to data of positions of persons in the public place monitored by the monitoring device.
Specifically, after the monitored image data is sorted, the corresponding individual person data is acquired from the monitored image data of each frame based on the sorting result. Further, the individual person data of the monitoring image data of each frame is subjected to feature identification and position identification, and the individual person data with the features and/or positions smaller than a certain range are used as the same individual person data.
Further, a coordinate system is established for the pictures which can be captured by the monitoring equipment, and the coordinate points of the same personnel single data in the coordinate system are used as personnel position data of the personnel single data in the frame monitoring image data.
S35: and counting the position data of the personnel according to the playing sequence to obtain the corresponding behavior characteristics of the personnel.
Specifically, for the same individual person data, the change condition of the individual person position data is counted in the playing sequence, the individual person position data corresponding to each frame is used as a coordinate point for the same individual person data, further, each coordinate point is arranged according to the playing sequence, the arranged sequence is used as the moving direction of the individual person, the coordinate points are connected to form a line, the connected line is used as the moving route of the individual person, and the moving direction and the moving route are used as the behavior characteristics of the individual person.
In an embodiment, as shown in fig. 5, after step S40, the big data video retrieval method further includes:
s50: and if the abnormal alarm signal is obtained, obtaining abnormal behavior data and a corresponding abnormal identifier from the abnormal alarm signal.
In this embodiment, the abnormal alarm signal is a signal that an abnormal behavior is generated by a person during actual monitoring. Abnormal behavior data refers to data of a specific abnormal behavior. The abnormal flag refers to the kind of abnormal behavior.
Specifically, if there is a worker in the actual public place to trigger the abnormal alarm signal, the worker may alarm the public, or trigger the abnormal alarm signal after actively discovering that there is an abnormal behavior, and after the worker handles the abnormal behavior, the worker takes the behavior data of the worker who has the abnormal behavior as the abnormal behavior data and marks the abnormal behavior data with the corresponding abnormal identifier.
S60: and performing matching query in the behavior identifier by using the abnormal identifier, and if the matching fails, storing the abnormal alarm signal and the corresponding abnormal identifier into a preset database.
Specifically, the abnormal identifier is used for performing matching query in the behavior identifier, if matching fails, it is indicated that no corresponding suspicious behavior feature is the same as the abnormal behavior data, the abnormal alarm signal and the corresponding abnormal identifier are stored in a preset database, and the database is used for storing the database after the suspicious behavior feature and the behavior identifier are associated through key-value, so as to achieve the purpose of enriching the types of suspicious behaviors in the database.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Example two:
in one embodiment, a big data video retrieval device is provided, and the big data video retrieval device corresponds to the big data video retrieval method in the above embodiments one to one. As shown in fig. 6, the big data video retrieval apparatus includes a history video data acquisition module 10, a suspicious feature extraction module 20, a behavior feature extraction module 30, and a retrieval alarm module 40. The functional modules are explained in detail as follows:
a history video data obtaining module 10, configured to obtain a history monitoring video, and obtain suspicious monitoring video data from the history monitoring data;
the suspicious characteristic extraction module 20 is configured to extract suspicious behavior characteristics and behavior identifiers corresponding to the suspicious behavior characteristics from the suspicious monitoring videos;
the behavior feature extraction module 30 is configured to extract a person behavior feature from the video monitoring data if the video monitoring data is acquired;
and the retrieval alarm module 40 is configured to perform traversal retrieval on the personnel behavior features in the suspicious behavior features, acquire a behavior identifier corresponding to the suspicious behavior features successfully subjected to traversal retrieval, and generate corresponding alarm information.
Preferably, the history recording data acquiring module 10 includes:
the historical data acquisition submodule 11 is configured to acquire historical alarm data, and acquire a corresponding historical monitoring video and a corresponding alarm behavior type from the historical alarm data;
and the classification submodule 12 is configured to classify the historical monitoring data according to the alarm behavior type, and then use each type of historical monitoring data as suspicious monitoring video data.
Preferably, the suspicious feature extraction module 20 comprises:
the identifier setting submodule 21 is used for setting a behavior identifier according to the alarm behavior type;
and the association submodule 22 is configured to, after extracting the suspicious behavior features from the suspicious behavior monitoring video class by class, associate the suspicious behavior features with the corresponding behavior identifiers through key-value.
Preferably, the behavior feature extraction module 30 includes:
a framing submodule 31, configured to perform framing processing on the video monitoring data to obtain monitoring image data corresponding to each frame;
the personnel data acquisition submodule 32 is used for acquiring individual personnel data from each frame of monitoring image;
the sorting submodule 33 is configured to sort the monitoring image data according to the playing order of the video monitoring data, so as to obtain a corresponding sorting result;
the position obtaining submodule 34 is used for obtaining the personnel position data of the same personnel monomer data in the corresponding monitoring image data after the personnel monomer data are processed according to the sequencing result;
and the counting submodule 35 is used for counting the position data of the personnel according to the playing sequence to obtain the corresponding personnel behavior characteristics.
Preferably, the big data video retrieval apparatus further comprises:
an abnormal signal obtaining module 50, configured to obtain abnormal behavior data and a corresponding abnormal identifier from the abnormal alarm signal if the abnormal alarm signal is obtained;
and the database updating module 60 is configured to perform matching query on the behavior identifier by using the abnormal identifier, and if the matching fails, store the abnormal alarm signal and the corresponding abnormal identifier in a preset database.
For specific limitations of the large data video retrieval apparatus, reference may be made to the above limitations of the large data video retrieval method, which is not described herein again. The modules in the big data video retrieval device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Example three:
in one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing historical monitoring data, suspicious behavior data and behavior identifications corresponding to the suspicious behavior data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a big data video retrieval method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s10: acquiring historical monitoring videos, and acquiring suspicious monitoring video data from historical monitoring data;
s20: extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring video;
s30: if the video monitoring data are acquired, extracting personnel behavior characteristics from the video monitoring data;
s40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring behavior identifications corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information.
Example four:
in one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: acquiring historical monitoring videos, and acquiring suspicious monitoring video data from historical monitoring data;
s20: extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring video;
s30: if the video monitoring data are acquired, extracting personnel behavior characteristics from the video monitoring data;
s40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring behavior identifications corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A big data video retrieval method is characterized by comprising the following steps:
s10: acquiring historical monitoring videos, and acquiring suspicious monitoring video data from the historical monitoring data;
s20: extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos;
s30: if video monitoring data are acquired, extracting personnel behavior characteristics from the video monitoring data;
s40: and traversing and searching the personnel behavior characteristics in the suspicious behavior characteristics, acquiring the behavior identification corresponding to the suspicious behavior characteristics which are successfully traversed and searched, and generating corresponding alarm information.
2. The big data video retrieval method of claim 1, wherein step S10 includes:
s11: acquiring historical alarm data, and acquiring the corresponding historical monitoring video and the corresponding alarm behavior type from the historical alarm data;
s12: and after classifying the historical monitoring data according to the alarm behavior type, taking each type of the historical monitoring data as the suspicious monitoring video data.
3. The big data video retrieval method of claim 2, wherein the step S20 includes:
s21: setting the behavior identification according to the alarm behavior type;
s22: and after suspicious behavior characteristics are extracted from the suspicious behavior monitoring videos class by class, the suspicious behavior characteristics and the corresponding behavior identifications are associated through key-value.
4. The big data video retrieval method of claim 1, wherein step S30 includes:
s31: performing frame processing on the video monitoring data to obtain monitoring image data corresponding to each frame;
s32: acquiring the individual personnel data from each frame of the monitoring image;
s33: sequencing the monitoring image data according to the playing sequence of the video monitoring data to obtain a corresponding sequencing result;
s34: after the personnel single data are processed according to the sequencing result, personnel position data of the same personnel single data in the corresponding monitoring image data are obtained;
s35: and counting the personnel position data according to the playing sequence to obtain the corresponding personnel behavior characteristics.
5. The big data video retrieval method of claim 1, wherein after step S40, the big data video retrieval method further comprises:
s50: if an abnormal alarm signal is obtained, obtaining abnormal behavior data and a corresponding abnormal identifier from the abnormal alarm signal;
s60: and performing matching query in the behavior identifier by using the abnormal identifier, and if the matching fails, storing the abnormal alarm signal and the corresponding abnormal identifier into a preset database.
6. A big data video retrieval apparatus, comprising:
the historical video data acquisition module is used for acquiring historical monitoring videos and acquiring suspicious monitoring video data from the historical monitoring data;
the suspicious characteristic extraction module is used for extracting suspicious behavior characteristics and behavior identifications corresponding to the suspicious behavior characteristics from the suspicious monitoring videos;
the behavior feature extraction module is used for extracting the behavior features of the personnel from the video monitoring data if the video monitoring data are obtained;
and the retrieval alarm module is used for performing traversal retrieval on the personnel behavior characteristics in the suspicious behavior characteristics, acquiring the behavior identification corresponding to the suspicious behavior characteristics after the traversal retrieval is successful, and generating corresponding alarm information.
7. The big data video retrieval device of claim 6, wherein the video historian data acquisition module comprises:
the historical data acquisition submodule is used for acquiring historical alarm data and acquiring the corresponding historical monitoring video and the corresponding alarm behavior type from the historical alarm data;
and the classification submodule is used for classifying the historical monitoring data according to the alarm behavior type and then taking each type of the historical monitoring data as the suspicious monitoring video data.
8. The big data video retrieval device of claim 7, wherein the suspicious feature extraction module comprises:
the identification setting submodule is used for setting the behavior identification according to the alarm behavior type;
and the association submodule is used for associating the suspicious behavior characteristics with the corresponding behavior identification through key-value after the suspicious behavior characteristics are extracted from the suspicious behavior monitoring video class by class.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the big data video retrieval method according to any of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the big data video retrieval method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911365734.9A CN111339366A (en) | 2019-12-26 | 2019-12-26 | Big data video retrieval method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911365734.9A CN111339366A (en) | 2019-12-26 | 2019-12-26 | Big data video retrieval method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111339366A true CN111339366A (en) | 2020-06-26 |
Family
ID=71181398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911365734.9A Pending CN111339366A (en) | 2019-12-26 | 2019-12-26 | Big data video retrieval method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339366A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985413A (en) * | 2020-08-22 | 2020-11-24 | 深圳市信诺兴技术有限公司 | Intelligent building monitoring terminal, monitoring system and monitoring method |
| CN113537166A (en) * | 2021-09-15 | 2021-10-22 | 北京科技大学 | Alarm method, alarm device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130266193A1 (en) * | 2012-04-09 | 2013-10-10 | Accenture Global Services Limited | Biometric matching technology |
| CN105653690A (en) * | 2015-12-30 | 2016-06-08 | 武汉大学 | Video big data rapid searching method and system constrained by abnormal behavior early-warning information |
| CN107404494A (en) * | 2017-08-21 | 2017-11-28 | 北京奇安信科技有限公司 | Abnormal events information processing method and processing device |
| CN108629322A (en) * | 2018-05-11 | 2018-10-09 | 中国联合网络通信集团有限公司 | Monitoring method, device and the computer readable storage medium of a suspect |
| CN109767322A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction analysis method, apparatus and computer equipment based on big data |
| CN109858365A (en) * | 2018-12-28 | 2019-06-07 | 深圳云天励飞技术有限公司 | A kind of special population Assembling Behavior analysis method, device and electronic equipment |
-
2019
- 2019-12-26 CN CN201911365734.9A patent/CN111339366A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130266193A1 (en) * | 2012-04-09 | 2013-10-10 | Accenture Global Services Limited | Biometric matching technology |
| CN105653690A (en) * | 2015-12-30 | 2016-06-08 | 武汉大学 | Video big data rapid searching method and system constrained by abnormal behavior early-warning information |
| CN107404494A (en) * | 2017-08-21 | 2017-11-28 | 北京奇安信科技有限公司 | Abnormal events information processing method and processing device |
| CN108629322A (en) * | 2018-05-11 | 2018-10-09 | 中国联合网络通信集团有限公司 | Monitoring method, device and the computer readable storage medium of a suspect |
| CN109767322A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction analysis method, apparatus and computer equipment based on big data |
| CN109858365A (en) * | 2018-12-28 | 2019-06-07 | 深圳云天励飞技术有限公司 | A kind of special population Assembling Behavior analysis method, device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985413A (en) * | 2020-08-22 | 2020-11-24 | 深圳市信诺兴技术有限公司 | Intelligent building monitoring terminal, monitoring system and monitoring method |
| CN113537166A (en) * | 2021-09-15 | 2021-10-22 | 北京科技大学 | Alarm method, alarm device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109710780B (en) | Archiving method and device | |
| CN108038176B (en) | Method and device for establishing passerby library, electronic equipment and medium | |
| CN109426785B (en) | Human body target identity recognition method and device | |
| CN110493181B (en) | User behavior detection method and device, computer equipment and storage medium | |
| US10262209B2 (en) | Method for analyzing video data | |
| CN111953697A (en) | APT attack identification and defense method | |
| CN111339366A (en) | Big data video retrieval method and device, computer equipment and storage medium | |
| CN112464030B (en) | Suspicious person determination method and suspicious person determination device | |
| CN109800329B (en) | Monitoring method and device | |
| CN111539317A (en) | Vehicle illegal driving detection method and device, computer equipment and storage medium | |
| CN112528716A (en) | Event information acquisition method and device | |
| CN109963113B (en) | Method and device for monitoring interested target | |
| CN111191506A (en) | Personnel flow statistical method and device, computer equipment and storage medium | |
| CN113535823B (en) | Abnormal access behavior detection method and device and electronic equipment | |
| CN112148920B (en) | Data management method | |
| CN110968719B (en) | Face clustering method and device | |
| CN114022926A (en) | Face recognition method, device, equipment and storage medium | |
| CN111738059B (en) | Face recognition method oriented to non-inductive scene | |
| CN109783663B (en) | Archiving method and device | |
| CN111970272A (en) | APT attack operation identification method | |
| CN116612498A (en) | Bird recognition model training method, bird recognition method, device and equipment | |
| CN111291595A (en) | Information relevance processing method, device and system | |
| CN110826460B (en) | Abnormal testimony of a witness information identification method, device and storage medium | |
| CN111160314B (en) | Violent sorting identification method and device | |
| CN109815369B (en) | Filing method and 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 |