CN115272924A

CN115272924A - Treatment system based on modularized video intelligent analysis engine

Info

Publication number: CN115272924A
Application number: CN202210875184.0A
Authority: CN
Inventors: 覃文; 岑道岸
Original assignee: Guangzhou Hantele Communication Co ltd
Current assignee: Guangzhou Hantele Communication Co ltd
Priority date: 2022-07-20
Filing date: 2022-07-20
Publication date: 2022-11-01

Abstract

The application discloses based on modularization video intelligent analysis engine treatment system, this application belongs to thing networking technology field. The intelligent analysis engine of the modularized video in the system comprises: an image acquisition unit for acquiring image information; the image identification unit is used for identifying key elements of the image; an image processing unit for processing an image; the intelligent engine unit is used for creating a database, storing the key elements, receiving an index instruction, retrieving the business types of the key elements according to the index instruction and performing fusion analysis; the management module comprises: the database management unit is used for managing a database; the deep learning module is used for carrying out deep learning based on key elements, service types and alarm information in the intelligent engine unit; and the alarm module is used for responding the fusion analysis result and giving an alarm. According to the technical scheme, the illegal event information is timely sent and alarmed in combination with the management business process, and the city management efficiency is improved.

Description

Treatment system based on modularized video intelligent analysis engine

Technical Field

The application belongs to the technical field of the Internet of things, and particularly relates to a treatment system based on a modularized video intelligent analysis engine.

Background

With the continuous acceleration of city development process, the intelligent monitoring and management of cities also face more and more challenges.

At present, in city management, the information of the violation event is collected in real time, the violation event is identified, and the image of the violation event is intercepted, so that an image evidence is provided for a management department to inquire, the violation event information is not sent and alarmed in time in combination with a management business process, a large amount of labor of law enforcement personnel is consumed, and the management efficiency cannot be guaranteed. Therefore, the technical problem to be solved urgently by the technical personnel in the field is that the acquisition of the violation event information is not timely, the labor cost is high, the labor shortage in city management is caused, and the city operation efficiency is low.

Disclosure of Invention

The purpose of this application embodiment is that the modularization video intelligent analysis engine grid that provides administers device can solve the problem that violation event information acquisition is not in time, and manpower resources consumes greatly, has improved city management efficiency.

In a first aspect, an embodiment of the present application provides a treatment system based on a modular video intelligent analysis engine, where the system includes the modular video intelligent analysis engine, a management module, an alarm module, and a deep learning module, and the modular video intelligent analysis engine includes:

the image acquisition unit is used for acquiring an image acquired by the image acquisition equipment;

the image identification unit is used for identifying key elements of the image;

an image processing unit for performing structuring and semi-structuring processing on the image;

the intelligent engine unit is used for creating a database and storing the key elements;

the control unit is used for generating an index instruction and sending the index instruction to the intelligent engine unit if the image recognition unit recognizes the key elements;

the intelligent engine unit is also used for receiving the index instruction, retrieving the business type to which the key element belongs according to the index instruction, and performing fusion analysis;

the management module comprises:

the database management unit is used for managing the database, wherein the database management unit is used for managing the static database and the special element pictures in the static database and carrying out classification management on the scene model;

the deep learning module is used for performing deep learning based on the key elements and the service types in the intelligent engine unit;

the alarm module is used for responding to the fusion analysis result and giving an alarm;

the deep learning module is further used for receiving alarm information and carrying out deep learning based on the alarm information.

Further, the image recognition unit is specifically configured to:

and carrying out specific identification on the key elements according to the scene model and the service type, and determining the identification capability of the acquisition equipment.

Further, the image processing unit is specifically configured to:

processing key elements in the historical images by using technologies such as deep learning, computer vision, image processing and the like;

and combining the key elements of different scenes to construct a scene model.

Further, the control unit is specifically configured to:

if the image identification module identifies the key element, judging the scene and the type of the key element;

and generating an index instruction according to the scene or type of the key element, and sending the index instruction to the intelligent engine unit.

Further, the apparatus further comprises:

the device configuration module is used for configuring a capability set for the acquisition device according to different rules, wherein the capability set comprises a set of human face recognition capability and vehicle speed recognition capability;

and the data backup module is connected with the equipment configuration module and backs up the configuration information of the acquisition equipment, wherein the configuration information comprises the capability set.

Further, the configuration information includes device alias information, device information, and capability set of device settings.

In a second aspect, an embodiment of the present application provides a method for intelligent analysis based on modular video, where the method includes:

acquiring an image acquired by image acquisition equipment through an image acquisition unit;

carrying out structuring and semi-structuring processing on the image through an image recognition unit;

performing key element identification on the image through an image processing unit;

creating a database and storing the key elements through an intelligent engine unit;

if the image identification module identifies key elements, generating an index instruction and sending the index instruction to the intelligent engine module;

receiving the index instruction through the capability engine unit, retrieving the business type of the key element according to the index instruction, and performing fusion analysis;

managing the database through a database management unit, wherein the database management unit manages a static database and special element pictures in the static database, and manages scene models in a classified manner;

performing deep learning based on the key elements and the service types in the intelligent engine module through a deep learning module;

responding to the fusion analysis result and alarming through an alarm module;

and receiving the alarm information through a deep learning module, and performing deep learning based on the alarm information.

In a third aspect, embodiments of the present application provide an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, and when executed by the processor, the program or instructions implement the steps of the method according to the second aspect.

In a fourth aspect, embodiments of the present application provide a readable storage medium on which a program or instructions are stored, which when executed by a processor, implement the steps of the method according to the second aspect.

In a fifth aspect, embodiments of the present application provide a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method according to the first aspect.

In the embodiment of the application, image information is acquired through an image acquisition unit; performing key element identification on the image through an image identification unit; processing the image by an image processing unit; creating a database and storing the key elements through an intelligent engine unit, receiving an index instruction, retrieving the service types of the key elements according to the index instruction, and performing fusion analysis; the management module comprises: managing the database through a database management unit; performing deep learning based on key elements, service types and alarm information in the intelligent engine unit through a deep learning module; and responding the fusion analysis result and giving an alarm through an alarm module. According to the technical scheme, the violation event information is timely sent and alarmed in combination with the management business process, and the urban management efficiency is improved.

Drawings

FIG. 1 is a schematic structural diagram of a modular video intelligent analysis engine-based abatement system according to an embodiment of the present disclosure;

FIG. 2 is a schematic structural diagram of a modular video intelligent analysis engine-based abatement system according to an embodiment of the present disclosure;

fig. 3 is a schematic flowchart of a modular video-based intelligent analysis method provided in the second embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the relevant portions of the present application are shown in the drawings. Before discussing exemplary embodiments in greater detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. A process may be terminated when its operations are completed, but may have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

The technical solutions in the embodiments of the present application will be described clearly below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present disclosure.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The following describes in detail an abatement system, a method, an electronic device and a storage medium based on a modular video intelligent analysis engine provided in the embodiments of the present application through specific embodiments and application scenarios thereof with reference to the accompanying drawings.

The first embodiment is as follows:

the treatment system based on the modular video intelligent analysis engine can execute the modular video intelligent analysis method, can be realized in a hardware and/or software mode, and is integrated in computer equipment. As shown in fig. 1, the system includes: the system comprises a modular intelligent video analysis engine 11, a management module 12, an alarm module 13 and a deep learning module 14, wherein the modular intelligent video analysis engine 11 comprises:

an image acquisition unit 111 for acquiring an image acquired by the image acquisition device;

an image recognition unit 112 for performing key element recognition on the image;

an image processing unit 113 for performing structuring and semi-structuring processing on the image;

the intelligent engine unit 114 is used for creating a database and storing the key elements;

a control unit 115, configured to generate an index instruction and send the index instruction to the smart engine unit if the image recognition unit 112 recognizes a key element;

the intelligent engine unit 114 is further configured to receive the index instruction, retrieve the service type to which the key element belongs according to the index instruction, and perform fusion analysis;

the management module 12 includes:

the database management unit 121 is configured to manage a database, where the management includes managing a static database and a special element picture in the static database, and performing classification management on a scene model;

the deep learning module 13 is configured to perform deep learning based on the key elements and the service types in the intelligent engine unit 114;

the alarm module 14 is used for responding to the fusion analysis result and giving an alarm;

and the deep learning module 13 is further configured to receive alarm information and perform deep learning based on the alarm information.

According to the scheme, a scene system manager identifies the violation event through a management system of a modular video intelligent analysis engine installed on an intelligent terminal, and sends the violation event information to a relevant management department. Specifically, the management department can receive violation event information sent by the modular video intelligent analysis engine management system by installing a special application program on the intelligent terminal, and display the violation event information on a screen of the intelligent terminal. The intelligent terminal equipment can be a mobile phone, a computer and the like.

The following description will be made taking the system as an execution subject.

The illegal event can be motor vehicle illegal parking, disorderly setting of advertising boards, lane occupation management, illegal setting of banners and the like. The management department can be a city management department, a traffic management department, a community security protection department and the like.

In this embodiment, the image may be a road image, an image inside a community, an image of a public place, an image of a production shop, or the like. The image acquisition device may be a camera or a still camera or the like. The image acquisition equipment can be installed above urban roads, in communities, in public places and the like, and can also be carried about, such as cameras and the like. The mode of acquiring the image can be that the acquisition equipment is connected with the system through a network, the image acquired in real time is sent to the system, and the image reported by the masses can be received through a webpage or application software.

The key elements may be a person, a vehicle, and an object, and may be a behavior of the person, a state of the vehicle, a state of the object, and the like. The key element identification can be carried out by means of face identification, object identification, behavior identification, scene identification, character identification and the like.

The structured processing can be to split the video according to a certain rule, extract a section of video with an illegal event, and classify the section of video, wherein the video can be classified according to the requirements of different management departments, and can be classified into a city management type, a community security protection type, a traffic management type, a safety production type and the like. The requirements of the management department can be requirements of the traffic management department on behaviors of running red light of motor vehicles, behaviors of the city management department on messy sundries, behaviors of disorderly arranging advertising boards and the like. Illustratively, if the time length of a road image acquired by the system is 20 minutes, an illegal event that a motor vehicle runs a red light exists, the image time length of the illegal event is 10 seconds, when the image is subjected to structural processing, only a 10-second video of the motor vehicle running the red light is captured, and the video is stored in a department of traffic management.

Semi-structured video may also be a process of splitting an image, but in this embodiment, some key elements that cannot be clearly classified are processed separately. For example, when a special crowd is found through a camera face recognition mode or a body type recognition mode, all people in a collected image need to be collected and analyzed, only pictures of all people are extracted through semi-structured processing, and specific image segments cannot be extracted according to behaviors of people.

Specifically, a database is created based on the key elements identified by the image identifying unit 112, and classified and stored. The classified storage mode can be divided according to the behaviors of people and people, the states of vehicles and the states of objects and objects in the key elements.

The index instruction can greatly increase the data retrieval speed, and in the embodiment, the index instruction can be a key element instruction, and can include a human instruction, a vehicle instruction, a human-vehicle combination instruction and the like. The indexing instructions may also be scene instructions and business instructions. The scene instructions can comprise a motor vehicle reverse driving scene instruction, an illegal airing scene instruction and the like; the service command may include a traffic management service command, a city management service command, and the like. The service types can comprise a city management type, a community security protection type, a safety production type, a traffic management type and the like. The fusion analysis can be based on the retrieved key elements and the business types to which the key elements belong. For example, if the received index command is a command of a vehicle, the type of the business to which the received index command belongs is searched in the database according to the command of the vehicle, and the business is analyzed according to the state of the vehicle, the position of the vehicle, the speed of the vehicle and the like. Such as whether the position of the vehicle occupies a fire fighting lane, whether the speed of the vehicle exceeds the speed, whether the vehicle condition of the vehicle has potential safety hazard, and the like.

The static library can be used for storing the key elements and the business types to which the key elements belong or the characteristics of the key elements. The key elements may be characterized by the license plate number of the vehicle, the height of the person, etc. The special element pictures can be pictures of special people groups, pictures of special vehicles and the like, such as pictures of escaping suspects, pictures of vehicles escaping in trouble and the like.

The database can be managed by adding and deleting the key elements and the data types of the key elements in the database. For example, when the hit-and-run vehicle has been caught, the vehicle information is not required to be continuously stored in the database, and the database resources are not occupied, the vehicle information can be deleted from the database.

The scene model may be a model constructed based on human behavior, vehicle state, and object state. The method can be used for illegal airing scenes, disorderly billboard scenes, road occupation management scenes, messy sundry scenes, motor vehicle parking violation scenes and the like. In the present embodiment, the scene model may be a model constructed based on historical image data. The classification management can divide a scene into a plurality of types, for example, the random sundry scene can be divided into a city management service type and a community security service type.

Deep learning is learning based on key elements, scene models, and business types. In this embodiment, a large number of historical images are subjected to structuring and semi-structuring processing, processed videos, pictures and characters are managed, deep learning is performed, and accuracy of an algorithm is improved.

The fusion analysis result may be the presence or absence of a violation. For example, if the motor vehicle stops at the fire fighting lane, the result of fusion analysis is that there is an illegal behavior; and if the motor vehicle is normally stopped in the parking space, fusing the analysis result to ensure that no violation behavior exists. And when the result of the fusion analysis is that the violation behavior exists, immediately alarming. The alarming mode can be that the illegal event information is displayed in a pop-up window mode on the screen of the intelligent terminal of the management department, and the alarming mode can also be that the alarming mode is realized in a voice mode by combining the event information in the pop-up window. The violation event information may be the time and place of occurrence of the violation event, the key elements involved, and the like.

The alarm information can be the time of alarm and the illegal event information of alarm, and the deep learning is carried out on the alarm information. Specifically, the time of alarming and the occurrence time, the place and the related key elements of the violation event are deeply learned based on a large amount of historical alarming information. The method is favorable for mastering the timeliness of alarming and is also convenient for knowing the probability of various illegal events occurring at various times and places. And the violation events with high probability occurring at the same time or place are marked, so that the implementation efficiency of subsequent work is improved conveniently.

In the embodiment of the application, image information is acquired through an image acquisition unit; performing key element identification on the image through an image identification unit; processing the image by an image processing unit; the method is beneficial to saving the identification time and improving the identification efficiency; the intelligent engine unit is used for creating a database, storing the key elements, receiving the index instruction, retrieving the business types to which the key elements belong according to the index instruction, performing fusion analysis, determining the affiliation relationship between the key elements and the business types and saving the distribution time of the business types; the database is managed through the database management unit, so that the occupation of database resources is avoided, and the data acquisition speed is ensured; performing deep learning based on key elements, service types and alarm information in the intelligent engine unit through a deep learning module; and the alarm module is used for responding to the fusion analysis result and giving an alarm, so that the illegal events can be timely found and processed, and the urban management efficiency is improved.

In each of the above technical solutions, the image recognition unit 112 is specifically configured to:

The specific recognition may be recognition of a specific person, vehicle, object and specific behavior according to a point requirement, such as recognition of a license plate of a vehicle, recognition of a person's appearance, recognition of a scene, and the like. The recognition capability of the acquisition device may be a face recognition capability, a vehicle speed recognition capability, an object recognition capability, and the like.

Illustratively, when a scene of stacking sundries appears at the same position in the community image for multiple times, the position of the sundries needs to be specifically identified, and whether the position of the sundries is a normal sundry stacking position or not is judged, so that the identification capability of the acquisition equipment can be determined to be the object position identification capability. In another possible embodiment, the acquisition equipment capacity of a certain location can be determined as the capacity of identifying the busy operation scene if the need of city management business requires the management of the busy operation to be strengthened for the certain location.

In the technical scheme, the image recognition unit is used for specifically recognizing the key elements according to the scene model and the service type and determining the recognition capability of the acquisition equipment, so that each region of a city can be managed in a targeted manner, and the recognition accuracy and the management timeliness are improved.

In each of the above technical solutions, the image processing unit 113 is specifically configured to:

processing key elements in the historical images by using deep learning, computer vision and image processing technologies;

and combining the key elements of different scenes to construct a scene model.

The computer vision can be machine vision which utilizes the acquisition equipment to replace human eyes to identify, track and measure the target, such as measuring speed, distance, number of people and the like. The image processing technology may be a technology for processing image information by a computer, and may include image segmentation, image restoration, image enhancement, image data encoding, and the like.

Illustratively, the vehicles in the historical images are identified, the speed of the vehicles is detected by using computer vision, and whether the speed limit regulations are met is judged. If the speed limit regulation is not met, the image of the overspeed vehicle can be processed technically.

In this embodiment, the scene model may also be a model that is constructed by a system administrator through combined application operations according to different key elements such as people, vehicles, objects, and the like, for example, a scene in which a person makes a call during driving, a scene in which a person drives many people by riding a bicycle, and the like.

In the technical scheme, the key elements in the historical image are processed by utilizing deep learning, computer vision and image processing technologies, so that the accuracy of illegal event identification is improved, and managers can process the illegal events in time; the scene model is constructed by combining the key elements of different scenes, so that the construction speed of the scene model is improved, and the key elements for judging the violation events can be flexibly adjusted.

In each of the above technical solutions, the control unit 115 is specifically configured to:

if the image recognition unit 112 recognizes a key element, determining a scene model and a service type to which the key element belongs;

and generating an index instruction according to the scene model or the service type to which the key element belongs, and sending the index instruction to the intelligent engine unit 114.

For example, if the key element identified by the image identification unit 112 is a behavior of a person in an illegal airing, it may be determined according to the management rule of the management department that the behavior of the illegal airing belongs to an illegal airing scene and a city management service type, and then a city management instruction or an illegal airing scene instruction is generated. The service type to which the key element instruction belongs can be determined by the scene model to which the key element instruction belongs, so that one of the scene instruction or the service instruction can be generated according to the scene model to which the key element belongs, and the generated index instruction is sent to the intelligent engine unit 114.

In the technical scheme, the image identification unit 112 identifies the key elements, judges the scene model and the service type of the key elements and correspondingly generates the index instruction, so that the service type of the key elements can be quickly determined according to the index instruction, and the efficiency of the management department for acquiring the violation event information is further improved.

Fig. 2 is a schematic structural diagram of an abatement system based on a modular video intelligent analysis engine according to an embodiment of the present application, and referring to fig. 2, the apparatus includes:

the device configuration module 15 is configured to configure a capability set for the acquisition device according to different rules, where the capability set includes a set of face recognition capability and vehicle speed recognition capability;

and the data backup module 16 is connected with the device configuration module 15 and backs up configuration information of the acquisition device, wherein the configuration information includes the capability set.

In this embodiment, different rules may be formulated according to different requirements of different management departments, or different rules may be formulated according to different times and places. For example, traffic control departments regulate the driving speed of vehicles according to road conditions, such as the speed limit of 80 km/h. The capability set may be a set of capabilities configured differently for each acquisition device according to the rules of the management department, and may include a set of two or more capabilities. The capability set may include a set of character recognition capability and vehicle speed recognition capability, a set of behavior recognition capability and face recognition capability, and so on. In this embodiment, optionally, the capability set includes a set of a face recognition capability and a vehicle speed recognition capability.

For example, a traffic management department may make a regulation of speed limit of 80 km/h for some road sections according to road conditions, so a collection of character recognition capability and vehicle speed recognition capability is configured for a collection device of the speed limit road section for recognizing vehicle speed and license plate number on the speed limit road section.

The configuration information of the acquisition device can include electronic fence information, preset point information, capability set parameters and the like. The electronic fence information may be used to indicate the acquisition range of the acquisition device, which may be 20-30 meters. The preset point information may also be used to indicate the collection range of the collection device, but may be small relative to the collection range of the electronic fence information, and may be 5-10 meters. The capability set reference refers to specific parameters of key elements, such as the speed of the vehicle, the height of a person and the like. In this solution, optionally, the configuration information includes device alias information, device information, and a capability set of the device setting. The device alias information may be a code assigned to an individual, such as 001. The alias of the device is provided for the purpose of facilitating management of the device, and devices having the same function or the same area may be collectively managed. For example, the acquisition devices configured for face recognition capability may be named as A1, A2, etc., and the acquisition devices configured for scene recognition capability may be named as B1, B2, etc. The device information may include location information, accuracy information, brightness information, and the like of the acquisition device. In this embodiment, the configuration information of the acquisition device is backed up, so that the security of the configuration information of the acquisition device is ensured, and information can be quickly recovered when the information is lost, thereby providing a guarantee for city management.

In the technical scheme, the capacity set is configured for the acquisition equipment according to different rules through the equipment configuration module, so that the acquisition capacity is ensured, the use of the acquisition equipment is reduced, and the cost of city management is saved; and backing up the configuration information of the acquisition equipment through a data backup module. The method is beneficial to the unified management of the acquisition equipment and provides guarantee for city management.

Example two:

fig. 3 is a schematic flowchart of a modular video-based intelligent analysis method provided in the second embodiment of the present application, and with reference to fig. 3, the method includes:

s301, acquiring an image acquired by image acquisition equipment through an image acquisition unit;

s302, performing key element identification on the image through an image identification unit;

s303, carrying out structuring and semi-structuring processing on the image through an image processing unit; s304, creating a database and storing the key elements through an intelligent engine unit;

s305, if the image recognition module recognizes the key elements, generating an index instruction and sending the index instruction to the intelligent engine module;

s306, receiving the index instruction through the capability engine unit, retrieving the business type of the key element according to the index instruction, and performing fusion analysis;

s307, managing the database through a database management unit, wherein the management comprises the management of the static database and the special element pictures in the static database, and the classification management of the scene model;

s308, deep learning is carried out through a deep learning module based on the key elements and the service types in the intelligent engine module;

s309, responding to the fusion analysis result and alarming through an alarm module;

s310, receiving alarm information through a deep learning module, and carrying out deep learning based on the alarm information.

Optionally, the image recognition unit performs specific recognition on the key elements according to the scene model and the service type, and determines the recognition capability of the acquisition device.

Optionally, the image processing unit processes key elements in the historical image by using deep learning, computer vision and image processing technologies;

and combining the key elements of different scenes to construct a scene model.

Optionally, if the image recognition unit recognizes a key element, the scene model and the service type to which the key element belongs are determined;

and generating an index instruction according to the scene model or the service type of the key element, and sending the index instruction to the intelligent engine unit.

Optionally, a device configuration module configures a capability set for the acquisition device according to different rules, where the capability set includes a set of face recognition capability and vehicle speed recognition capability;

Optionally, the configuration information includes device alias information, device information, and a capability set of the device setting.

In the embodiment of the application, image information is acquired through an image acquisition unit; processing the image by an image processing unit; the key elements of the image are identified through the image identification unit, so that the identification time is saved, and the identification efficiency is improved; the intelligent engine unit is used for creating a database, storing the key elements, receiving the index instruction, retrieving the business types to which the key elements belong according to the index instruction, performing fusion analysis, determining the affiliation relationship between the key elements and the business types and saving the distribution time of the business types; the database is managed through the database management unit, so that the occupation of database resources is avoided, and the data acquisition speed is ensured; performing deep learning based on key elements, service types and alarm information in the intelligent engine unit through a deep learning module; and the alarm module is used for responding to the fusion analysis result and giving an alarm, so that the violation events can be timely found and processed, and the urban management efficiency is improved.

Example three:

fig. 4 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.

The embodiment of the application further provides a computer device, and the computer device can integrate the treatment system based on the modularized video intelligent analysis engine provided by the embodiment of the application. Fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present application. Referring to fig. 4, the computer apparatus includes: an input device 43, an output device 44, a memory 42, and one or more processors 41; the memory 42 for storing one or more programs; when executed by the one or more processors 41, the one or more programs cause the one or more processors 41 to implement the method for modular video-based intelligent analysis as described in the above embodiments. The input device 43, the output device 44, the memory 42 and the processor 41 may be connected by a bus or other means, and fig. 4 illustrates the connection by the bus as an example.

Memory 42 is provided as a computing device readable storage medium that may be used to store software programs, computer executable programs, and modules, such as the modular video intelligence analysis engine based abatement system described in any of the embodiments of the present application. The memory 42 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 for at least one function; the storage data area may store data created according to use of the device, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 42 may further include memory located remotely from processor 41, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 43 may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the apparatus. The output device 44 may include a display device such as a display screen.

The processor 41 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 42, that is, implements the above-described abatement system based on the modular video intelligent analysis engine.

The treatment system and the computer based on the modular video intelligent analysis engine can be used for executing the modular video intelligent analysis method based on any embodiment, and have corresponding functions and beneficial effects.

Example four:

embodiments of the present application further provide a storage medium containing computer executable instructions, which when executed by a computer processor, are configured to execute the modular video intelligent analysis engine-based abatement system provided in the above embodiments, the modular video intelligent analysis engine-based abatement system including: acquiring image information through an image acquisition unit; performing key element identification on the image through an image identification unit; processing the image by an image processing unit; creating a database and storing the key elements through an intelligent engine unit, receiving an index instruction, retrieving the business types of the key elements according to the index instruction, and performing fusion analysis; managing the database through a database management unit; performing deep learning based on key elements, service types and alarm information in the intelligent engine unit through a deep learning module; and responding the fusion analysis result and giving an alarm through an alarm module. According to the technical scheme, the illegal event information is timely sent and alarmed in combination with the management business process, and the urban management efficiency is improved.

Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in a first computer system in which the program is executed, or may be located in a different second computer system connected to the first computer system through a network (such as the internet). The second computer system may provide program instructions to the first computer for execution. The term "storage media" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.

Of course, the storage medium provided in the embodiments of the present application contains computer-executable instructions, and the computer-executable instructions are not limited to the method for intelligent analysis based on modular video as described above, and may also perform related operations in the method for intelligent analysis based on modular video as provided in any embodiment of the present application.

The administration system, the device and the storage medium based on the modular video intelligent analysis engine provided in the above embodiments may execute the modular video intelligent analysis method provided in any embodiment of the present application, and reference may be made to the modular video intelligent analysis method provided in any embodiment of the present application without detailed technical details described in the above embodiments.

The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A modular video-based intelligent analysis engine governance system, the system comprising a modular video intelligent analysis engine, a management module, an alarm module and a deep learning module, the modular intelligent analysis engine comprising:

the image acquisition unit is used for acquiring the image acquired by the image acquisition equipment;

the image processing unit is used for carrying out structural and semi-structural processing on the image;

the management module comprises:

and the deep learning module is also used for receiving the alarm information and carrying out deep learning based on the alarm information.

2. The apparatus according to claim 1, wherein the image recognition unit is specifically configured to:

3. The apparatus according to claim 1, wherein the image processing unit is specifically configured to:

and combining the key elements of different scenes to construct a scene model.

4. The device according to claim 1, wherein the control unit is specifically configured to:

if the image identification unit identifies the key element, judging a scene model and a service type of the key element;

5. The apparatus of claim 1, further comprising:

6. The apparatus of claim 5, wherein the configuration information comprises device alias information, device information, capability set of device settings.

7. A modular video-based intelligent analysis method is characterized by comprising the following steps:

performing key element identification on the image through an image identification unit;

performing, by an image processing unit, structuring and semi-structuring processing on the image;

if the image recognition module recognizes the key elements, generating an index instruction and sending the index instruction to the intelligent engine module;

responding the fusion analysis result and alarming through an alarm module;

8. An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the modular video-based intelligent analysis method of claim 7.

9. A readable storage medium storing thereon a program or instructions which, when executed by a processor, implements the modular video-based intelligent analysis method of claim 7.