阅读说明：本技术 一种基于大数据的视频监控系统 (Video monitoring system based on big data ) 是由 岳建明 范英 董维 于 2018-06-29 设计创作，主要内容包括：本发明提供一种基于大数据的视频监控系统,包括视频智能分析系统、知识数据库、分布式云平台；分布式云平台包括前端和后台,前端包括感知器和预处理模块,后台包括网络模块和数据中心。本发明解决了解决了现有视频监控系统中存在的视频容积大、数据格式多样、单一文件价值低、处理速度慢问题；提高了数据存储的有效性、优化存储管理,满足最终用户的不同要求；实现了资源整合,为数据挖掘、语义推理等复杂的数据分析和应用提供了统一的计算和存储环境。(The invention provides a video monitoring system based on big data, which comprises a video intelligent analysis system, a knowledge database and a distributed cloud platform, wherein the video intelligent analysis system comprises a video monitoring system, a knowledge database and a distributed cloud platform; the distributed cloud platform comprises a front end and a background, wherein the front end comprises a sensor and a preprocessing module, and the background comprises a network module and a data center. The invention solves the problems of large video volume, various data formats, low single file value and low processing speed in the existing video monitoring system; the effectiveness of data storage is improved, the storage management is optimized, and different requirements of end users are met; the resource integration is realized, and a uniform computing and storing environment is provided for complex data analysis and application such as data mining, semantic reasoning and the like.)

1. A video monitoring system based on big data, its characterized in that: the system comprises a video intelligent analysis system, a knowledge database and a distributed cloud platform;

the video intelligent analysis system comprises a target detection module, a target tracking module, a behavior analysis module, an event analysis module, a structural description module, an image understanding module and a machine learning module, wherein an original video is connected with the target detection module, the target tracking module, the behavior analysis module, the event analysis module and the structural description module are sequentially connected, the image understanding module is connected with the target tracking module, and the machine learning module is connected with the behavior analysis module;

the knowledge database comprises a knowledge acquisition module, a knowledge base sample set, a knowledge discovery module, a knowledge expression module and a strategy knowledge base, wherein the knowledge acquisition module, the knowledge base sample set, the knowledge discovery module, the knowledge expression module and the strategy knowledge base are sequentially connected, and the knowledge base sample set is respectively connected with the image understanding module and the machine learning module through semantic information;

the distributed cloud platform comprises a human-computer interface, an application service interface, a virtualization module, a relational database, an index server and a virtualization file system, wherein the structural description module is connected with the human-computer interface, the strategy knowledge base is connected with the application service interface, the human-computer interface and the application service interface are respectively connected with the virtualization module, the virtualization module is connected with the relational database and the index server, and the relational database and the index server are respectively connected with the virtualization file system.

2. The video monitoring system based on big data as claimed in claim 1, wherein the distributed cloud platform comprises a front end and a back end, the front end comprises a sensor and a preprocessing module, and the back end comprises a network module and a data center; the information collected by the perceptron includes video, audio, structured data and unstructured data; the preprocessing module comprises audio and video coding, a semantic description model and a scheduling algorithm, and packages the information collected by the sensor in a uniform standard format through the audio and video coding, the semantic description model and the scheduling algorithm and transmits the information to a background data center through the network module; the data center realizes the resource integration of multiple information and provides a uniform computing and storing environment for the multiple data analysis and application of data mining and semantic reasoning.

3. The big data based video surveillance system of claim 2, wherein the network module comprises a 4G network, a wireless network, a wired network, and other channels.

4. The big data based video surveillance system of claim 2, wherein the front-end sensor comprises a video server and a camera.

5. The big data based video surveillance system of claim 4, wherein the camera is selected from 200 ten thousand pixel high definition gun, dome and ultra low illumination cameras.

Technical Field

The invention relates to the technical field of video monitoring, in particular to a video monitoring system based on big data.

Background

Video surveillance has become a major surveillance tool because it can provide rich, intuitive, and accurate information, and a large number of video surveillance systems have been established around the world. Video data has a very large volume, and for example, in a city where thousands of cameras are built, each camera collects about 24-48 GB of high-definition video every day, and data collection involves various data formats such as multimedia, images, and other unstructured data. Furthermore, valuable data is contained only in a few frames of massive video data called "key frames". However, the redundant system construction causes huge waste of resources, for example, a video monitoring system establishes independent software and hardware; sharing and uploading of a large amount of video data brings huge pressure to network bandwidth, and mass video resources are idle for a long time and cannot be effectively extracted.

Patent 201711191247.6 discloses an intelligent monitoring system based on big data technology, which includes a data receiving unit, a distribution station big data monitoring unit, a supervision and maintenance end and distribution monitoring substations arranged in each distribution station, wherein the distribution monitoring substations, the data receiving unit, the distribution station big data monitoring unit and the supervision and maintenance end are connected through wireless communication; by adopting Samza streaming type big data processing calculation and based on a streaming data processing technology, the real-time processing of the data of the power distribution station is realized, and the processing result is stored in an IMS database established by a hierarchical model. The patent 201711329053.8 relates to a network video monitoring system based on ARM9, the camera is connected with ARM9 processing board through data input, the Internet is connected with ARM9 processing board through NETCAM, the Internet is connected with laptop computer, the Internet is connected with computer through Clients, the user of the invention can remotely control the video monitoring system, the client program can be realized by Java Applet, and the Internet can realize real-time monitoring of remote video images on a browser. The method is simple to operate, low in hardware cost and capable of popularizing products; the system has the advantages that the retrieval service is conveniently, quickly and effectively provided, the operation data and the safety information of the power distribution station and the power distribution box are inquired and known in time, the normal work of power distribution is supervised and maintained, the working efficiency is improved, the occurrence of faults is reduced, and the safety is well guaranteed. However, the video monitoring system has the problems of large video volume, various data formats, low single file value, low processing speed and the like.

Disclosure of Invention

Technical problem to be solved

Aiming at the problems of large video volume, various data formats, low single file value and low processing speed in the conventional video monitoring system, the invention provides a video monitoring system based on big data.

(II) technical scheme

In order to achieve the purpose, the invention is realized by the following technical scheme:

a video monitoring system based on big data comprises a video intelligent analysis system, a knowledge database and a distributed cloud platform;

the video intelligent analysis system comprises a target detection module, a target tracking module, a behavior analysis module, an event analysis module, a structural description module, an image understanding module and a machine learning module, wherein an original video is connected with the target detection module;

the knowledge database comprises a knowledge acquisition module, a knowledge base sample set, a knowledge discovery module, a knowledge expression module and a strategy knowledge base, wherein the knowledge acquisition module, the knowledge base sample set, the knowledge discovery module, the knowledge expression module and the strategy knowledge base are sequentially connected, and the knowledge base sample set is respectively connected with the image understanding module and the machine learning module through semantic information;

the distributed cloud platform comprises a human-computer interface, an application service interface, a virtualization module, a relational database, an index server and a virtualization file system, wherein the structural description module is connected with the human-computer interface, the strategy knowledge base is connected with the application service interface, the human-computer interface and the application service interface are respectively connected with the virtualization module, the virtualization module is connected with the relational database and the index server, and the relational database and the index server are respectively connected with the virtualization file system.

Further, the distributed cloud platform comprises a front end and a background, wherein the front end comprises a sensor and a preprocessing module, and the background comprises a network module and a data center; the information collected by the perceptron includes video, audio, structured data and unstructured data; the preprocessing module comprises audio and video coding, a semantic description model and a scheduling algorithm, and performs uniform standard format packaging on information collected by the sensor through the audio and video coding, the semantic description model and the scheduling algorithm and transmits the information to a background data center through the network module; the data center realizes the resource integration of multiple information and provides a uniform computing and storing environment for multiple data analysis and application of data mining and semantic reasoning.

Further, the network module includes a 4G network, a wireless network, a wired network, and other channels.

Further, the front-end sensor comprises a video server and a camera.

Further, the camera adopts a camera with 200 ten thousand pixels, high definition gun type, spherical type and ultra-low illumination.

(III) advantageous effects

The invention has the beneficial effects that: a video monitoring system based on big data solves the problems of large video volume, various data formats, low single file value and low processing speed in the existing video monitoring system; the video intelligent analysis system, the knowledge database and the distributed cloud platform are adopted to provide storage environments for different types of structured and unstructured data, so that the effectiveness of data storage is improved, the storage management is optimized, and different requirements of end users are met; the distributed cloud platform comprises a front end and a background, the front end comprises a sensor and a preprocessing module, the background comprises a network module and a data center, resource integration is achieved, and a unified computing and storing environment is provided for complex data analysis and application such as data mining and semantic reasoning.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic block diagram of the present invention;

fig. 2 is a schematic block diagram of a distributed cloud platform.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

With reference to fig. 1, a video monitoring system based on big data includes a video intelligent analysis system, a knowledge database, and a distributed cloud platform;

the video intelligent analysis system comprises a target detection module, a target tracking module, a behavior analysis module, an event analysis module, a structural description module, an image understanding module and a machine learning module, wherein an original video is connected with the target detection module;

the knowledge database comprises a knowledge acquisition module, a knowledge base sample set, a knowledge discovery module, a knowledge expression module and a strategy knowledge base, wherein the knowledge acquisition module, the knowledge base sample set, the knowledge discovery module, the knowledge expression module and the strategy knowledge base are sequentially connected, and the knowledge base sample set is respectively connected with the image understanding module and the machine learning module through semantic information;

the distributed cloud platform comprises a human-computer interface, an application service interface, a virtualization module, a relational database, an index server and a virtualization file system, wherein the structural description module is connected with the human-computer interface, the strategy knowledge base is connected with the application service interface, the human-computer interface and the application service interface are respectively connected with the virtualization module, the virtualization module is connected with the relational database and the index server, and the relational database and the index server are respectively connected with the virtualization file system.

The video intelligent analysis system is used for processing an original video, object detection, target tracking, behavior analysis and event analysis are carried out on the original video through a target detection module, a target tracking module, a behavior analysis module and an event analysis module, valuable information is found from large-scale video data, then standardized description structured description is carried out through a structured description module, the processing result of the structured description module is that some data frames containing people and vehicles are contained, and all data are packaged in a unified standard format and are transmitted to a distributed cloud platform.

The knowledge database is used for data mining, information description and knowledge reasoning, and can provide a real case for prediction. The knowledge database utilizes a knowledge collection module to collect knowledge, namely, existing cases, policies and regulations are collected and analyzed; the knowledge collection module puts the collected knowledge into a knowledge base sample set; the knowledge discovery module applies machine learning to the cases and rules in the knowledge base sample set to perform data mining and clustering, and main knowledge is obtained through analysis; the knowledge expression module expresses the main knowledge and rules obtained by the knowledge discovery module by using a uniform format such as RDFS, OWL and SWRL, stores the main knowledge and rules in a policy knowledge base and is used for supporting training models, semantic retrieval, reasoning and prediction.

The distributed cloud platform provides an efficient computing environment and provides a storage environment for different types of structured and unstructured data. The cloud platform analyzes video content, performs semantic modeling and reasoning by using a human-computer interface and an application service interface, and processes related tasks by using a virtualization module (MapReduce, Spark, Storm), a relational database, an index server and a virtualization file system.

Due to limited bandwidth, in conjunction with fig. 2, the distributed cloud platform includes a front end and a back end, the front end includes a sensor and a preprocessing module, and the back end includes a network module and a data center; the information collected by the perceptron includes video, audio, structured data and unstructured data; the preprocessing module comprises audio and video coding, a semantic description model and a scheduling algorithm, and performs uniform standard format packaging on information collected by the sensor through the audio and video coding, the semantic description model and the scheduling algorithm and transmits the information to a background data center through the network module; the network module comprises a 4G network, a wireless network, a wired network and other channels; the data center has strong storage and calculation capacity and can support more complex calculation and application, realize multi-information resource integration and provide a uniform calculation and storage environment for multi-data analysis and application of data mining and semantic reasoning.

The front-end perceptron comprises a video server and a camera. The camera adopts a 200 ten thousand pixel high-definition gun type, spherical and ultra-low illumination camera. The gun-shaped camera is used for observing a fixed-position area; the dome camera is used in a wide or complex place of the surrounding environment, and the position and the focal length of the dome camera can be adjusted to obtain a required video picture; ultra-low light cameras are used in critical areas where ambient light is limited.

In summary, the embodiment of the present invention provides a video monitoring system based on big data, which solves the problems of large video volume, various data formats, low single file price and low processing speed in the existing video monitoring system; the video intelligent analysis system, the knowledge database and the distributed cloud platform are adopted to provide storage environments for different types of structured and unstructured data, so that the effectiveness of data storage is improved, the storage management is optimized, and different requirements of end users are met; the distributed cloud platform comprises a front end and a background, the front end comprises a sensor and a preprocessing module, the background comprises a network module and a data center, resource integration is achieved, and a unified computing and storing environment is provided for complex data analysis and application such as data mining and semantic reasoning.

The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.