Park security system based on computer vision

Abstract

The invention, which relates to the technical field of security management, discloses a computer-vision-based park security system comprising a park monitoring system, a monitoring data processing system, an emergency alarm system, an intelligent power supply system and a park monitoring terminal. According to the invention, the image data analysis module processes and analyzes the image data obtained by monitoring based on the computer vision technology, so that abnormal behaviors and events in the image are automatically identified from the image monitoring data, and the parameter data analysis module compares and analyzes the parameter data obtained by monitoring. Parameter abnormity in the parameter data is automatically identified, corresponding alarm and fire-fighting emergency measures are timely executed through an emergency alarm system according to processing and analysis results of the monitoring data, intelligent security and protection management and control of the park are realized, real-time monitoring of the park does not need to be depended on manpower, manpower is saved, manual danger identification is not needed, and the safety of the park is improved. And the intelligent degree is high.

Description

Technical Field

[0001] The present invention relates to the technical field of security management, and in particular to a campus security system based on computer vision. Background Art

[0002] A park refers to a designated area that is centrally and uniformly planned, where a certain type of industry or form of enterprise or company is specially set up for unified management. At present, parks are mainly divided into various types, including industrial parks, agricultural parks, science and technology parks, logistics parks, and cultural and creative industry parks. As an important carrier of regional economic development, the definition, type, creation and management methods, and development trends of parks all reflect their important role in promoting industrial upgrading, urbanization construction, and the gathering of innovative resources.

[0003] With the development and progress of society, people have higher and higher requirements for the safety of the park, and have begun to gradually improve the level of park safety management through corresponding technical means, reduce the occurrence of safety accidents, and protect the assets and personnel safety in the park. The park security system is the key to ensuring the safety of the park. The park security system refers to a series of security protection measures and technical equipment deployed in the park to ensure the safety of people, property and information in the park. Its design and implementation need to comprehensively consider the specific needs of the park, technological development trends and cost factors.

[0004] Most of the existing park security systems have a single function and only have a single video surveillance function. They rely too much on the park's monitoring personnel to manually identify dangers, which consumes too much security manpower. It is difficult to monitor the surveillance video in real time, and it is not possible to implement effective intelligent analysis of the surveillance video. It cannot automatically identify dangerous situations in the park, and it is even more impossible to accurately and timely alarm after discovering dangerous situations in the park, and take corresponding emergency measures. It is impossible to carry out safe and effective security management and control of the park. Therefore, the present invention proposes a park security system based on computer vision to solve the problems existing in the prior art. Summary of the invention

[0005] In response to the above problems, the purpose of the present invention is to propose a campus security system based on computer vision to solve the problems that the existing campus security system relies too much on the campus monitoring personnel to manually identify dangers, thereby consuming too much security manpower, and it is difficult to monitor the surveillance video in real time. It is also impossible to implement effective intelligent analysis of the surveillance video, and it is impossible to automatically identify dangerous situations in the campus, and it is even more impossible to accurately and promptly alarm after discovering dangerous situations in the campus.

[0006] In order to achieve the purpose of the present invention, the present invention is implemented by the following technical solutions: a campus security system based on computer vision, including a campus monitoring system, a monitoring data processing system, an emergency alarm system, an intelligent power supply system and a campus monitoring terminal;

[0007] The park monitoring system includes an environment monitoring module for monitoring the park environment, an equipment monitoring module for monitoring the park equipment, and a data sending module for sending each monitoring data to the monitoring data processing system;

[0008] The monitoring data processing system includes a data receiving module for receiving each monitoring data, a data classification module for classifying each received monitoring data, an image data analysis module for processing and analyzing image data obtained after classification, a parameter data analysis module for processing and analyzing parameter data obtained after classification, and a database module pre-stored with standard parameter data;

[0009] The emergency alarm system includes a risk assessment module for assessing the danger of the park according to the data processing results of the monitoring data processing system, an automatic alarm module for determining whether to alarm according to the results of the park risk assessment, and an emergency firefighting module for providing an emergency firefighting function for the park;

[0010] The intelligent power supply system supplies power to the entire park security system, and the park monitoring terminal includes an intelligent mobile terminal for providing a remote mobile monitoring function and an intelligent fixed terminal for providing a remote fixed-point monitoring function.

[0011] Further improvements are: the environmental monitoring module includes an image acquisition unit for video monitoring of the park, a gas monitoring unit for monitoring harmful gases in the park, and a flame monitoring unit for monitoring whether there is a fire in the park; the equipment monitoring module includes a temperature and humidity monitoring unit for monitoring the temperature and humidity of each electrical equipment in the park, and an electrical parameter monitoring unit for monitoring the electrical parameters of each electrical equipment in the park.

[0012] A further improvement is that the data sending module includes a data compression unit for compressing each monitoring data and a data sending antenna for wirelessly transmitting the compressed data packet to the monitoring data processing system, and the data receiving module includes a data receiving antenna for receiving the data packet and a data decompression unit for decompressing the received data packet.

[0013] A further improvement is that the data classification module includes a data sorting unit for sorting the data received by the data receiving module and a data classification unit for classifying the sorted data. The data sorting unit uses a data cleaning algorithm to clean up missing values, abnormal values ​​and duplicate data in the data. The data classification unit classifies the sorted data into image data and parameter data based on a neural network algorithm.

[0014] A further improvement is that the image data analysis module includes an image data preprocessing unit for preprocessing the image data obtained after classification, an image feature extraction unit for extracting features from the preprocessed image data, and an image anomaly recognition unit for identifying abnormal features based on the image features. The image data preprocessing unit performs scaling, cropping and normalization preprocessing on the image data, the image feature extraction unit extracts features from the preprocessed image data based on a convolutional neural network, and the image anomaly recognition unit uses a target detection algorithm to identify abnormal behaviors and events in the extracted features.

[0015] A further improvement is that the parameter data analysis module includes a parameter data preprocessing unit for preprocessing the parameter data obtained after classification, a parameter comparison unit for comparing and analyzing the preprocessed parameter data with the standard parameter data stored in the database module, and a parameter anomaly identification unit for identifying abnormal parameters based on the parameter comparison and analysis results.

[0016] Further improvements are: the danger assessment module includes an information reading unit for reading the data analysis results of the image data analysis module and the parameter data analysis module, and a danger judgment unit for judging whether there is danger in the park based on the data analysis results; the automatic alarm module includes an alarm triggering unit for triggering an alarm phone and an alarm execution unit for issuing an alarm prompt in the park; the emergency fire fighting module includes a park broadcasting unit for playing voice prompt broadcasts in the park, an automatic fire extinguishing unit for automatically extinguishing open flames, an automatic smoke exhaust unit for indoor ventilation and smoke exhaust, and an evacuation indication unit for providing instructions for indoor crowd evacuation.

[0017] Further improvements are: the intelligent power supply system includes a new energy power supply module for providing backup power for the park security system and a mains power supply module for providing mains power for the park security system, the new energy power supply module includes a wind power generation unit using wind power generation, a solar power generation unit using solar photovoltaic power generation and a backup power storage unit for storing new energy electricity, and the mains power supply module includes a mains access unit and a mains frequency conversion unit.

[0018] Further improvements are: the smart mobile terminal includes smart phones and tablet computers carried by the park security personnel, the smart fixed terminal includes a desktop computer and an LCD screen installed in the park monitoring room, and the smart mobile terminal and the smart fixed terminal are both installed with a remote control APP for controlling the park security system.

[0019] The beneficial effects of the present invention are as follows: the present invention first monitors the park environment and the operating parameters of the electrical equipment in the park respectively through the environment monitoring module and the equipment monitoring module, and then the image data analysis module processes and analyzes the image data obtained by the monitoring based on computer vision technology, so as to automatically identify abnormal behaviors and events in the image from the image monitoring data, and the parameter data analysis module compares and analyzes the parameter data obtained by the monitoring, so as to automatically identify parameter anomalies in the parameter data, and then according to the processing and analysis results of each monitoring data, the emergency alarm system promptly executes corresponding alarm and fire emergency measures to realize intelligent security management and control of the park, without relying on manual real-time monitoring of the park, saving manpower, and without manual identification of danger, with a high degree of intelligence, capable of real-time and effective intelligent analysis of the monitoring data, realizing automatic identification of dangerous situations in the park, and at the same time, being able to accurately and timely alarm after discovering dangerous situations, and respond to corresponding emergency measures, thereby greatly improving the safety of the park and worthy of wide promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a structural schematic diagram of the campus security system based on computer vision of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 , this embodiment provides a campus security system based on computer vision, including a campus monitoring system for monitoring a campus, a monitoring data processing system for processing and analyzing the campus monitoring data, an emergency alarm system for executing corresponding emergency measures according to the results of the processing and analysis of the campus monitoring data, an intelligent power supply system for powering the campus security system, and a campus monitoring terminal for remotely controlling the campus security system;

[0024] The park monitoring system includes an environment monitoring module, an equipment monitoring module and a data sending module, wherein the environment monitoring module is used to monitor the park environment, the equipment monitoring module is used to monitor the operating parameters of the park equipment, and the data sending module is used to send each monitoring data to the monitoring data processing system;

[0025] The monitoring data processing system includes a data receiving module, a data classification module, an image data analysis module, a parameter data analysis module and a database module, wherein the data receiving module is used to receive various monitoring data, the data classification module is used to classify the received monitoring data according to image data and parameter data, the image data analysis module processes and analyzes the image data obtained after classification based on computer vision technology, the parameter data analysis module is used to process and analyze the parameter data obtained after classification, and the database module pre-stores standard parameter data for subsequent comparative analysis;

[0026] The emergency alarm system includes a danger assessment module, an automatic alarm module and an emergency fire fighting module, wherein the danger assessment module is used to assess the danger of the park according to the data processing results of the monitoring data processing system, the automatic alarm module is used to determine whether to alarm according to the danger assessment results of the park, and the emergency fire fighting module is used to provide emergency fire fighting functions in the park;

[0027] The intelligent power supply system serves as the power source of the park security system and supplies power to the entire park security system. The park monitoring terminals include intelligent mobile terminals and intelligent fixed terminals. The intelligent mobile terminals are used to provide remote mobile monitoring functions, and the intelligent fixed terminals are used to provide remote fixed-point monitoring functions.

[0028] The environmental monitoring module includes an image acquisition unit, a gas monitoring unit and a flame monitoring unit, wherein the image acquisition unit is a high-definition camera arranged at different locations in the park for video monitoring of the park, the gas monitoring unit is a harmful gas sensor arranged at a location in the park where harmful gas leakage is likely to occur, for monitoring harmful gases in the park, and the flame monitoring unit is a flame detector arranged at different locations in the park for monitoring whether there is a fire in the park;

[0029] The equipment monitoring module includes a temperature and humidity monitoring unit and an electrical parameter monitoring unit. The temperature and humidity monitoring unit is a temperature and humidity sensor arranged on each electrical equipment in the park, which is used to monitor the temperature and humidity of each electrical equipment in the park. The electrical parameter monitoring unit is a voltage sensor, a current sensor and a resistance sensor arranged on each electrical equipment in the park, which is used to monitor the electrical parameters of each electrical equipment in the park, including voltage, current and resistance.

[0030] The data sending module includes a data compression unit and a data sending antenna, wherein the data compression unit uses lossless compression technology to compress the monitoring data obtained by the environment monitoring module and the equipment monitoring module into packets, and the data sending antenna transmits the compressed data packets to the data receiving module of the monitoring data processing system by wireless transmission. The data receiving module includes a data receiving antenna and a data decompression unit, wherein the data receiving antenna is used to receive compressed data packets, and the data decompression unit uses lossless decompression technology to decompress the received compressed data packets for subsequent processing and analysis.

[0031] The data classification module includes a data sorting unit and a data classification unit. The data sorting unit uses a data cleaning algorithm to clean up missing values, abnormal values ​​and duplicate data in the data to achieve data sorting. The data classification unit classifies the data after sorting according to image data and parameter data based on a neural network algorithm to achieve data classification.

[0032] The image data analysis module includes an image data preprocessing unit, an image feature extraction unit and an image anomaly recognition unit, wherein the image data preprocessing unit performs scaling, cropping and normalization preprocessing on the image data to facilitate subsequent feature extraction of the image data, thereby realizing preprocessing of the image data; the image feature extraction unit extracts features from the preprocessed image data based on a convolutional neural network; the image anomaly recognition unit uses a target detection algorithm to identify abnormal behaviors and events in the extracted features, thereby realizing image data analysis and processing based on computer vision, and can automatically identify abnormal behaviors and events in images from image monitoring data, indicating that there is a dangerous situation at the corresponding location of the park.

[0033] The parameter data analysis module includes a parameter data preprocessing unit, a parameter comparison unit and a parameter anomaly identification unit. The parameter data preprocessing unit preprocesses the parameter data obtained after classification by means of data cleaning, data conversion and data planning, so that the data can be convenient for subsequent processing and analysis. The parameter comparison unit is used to compare and analyze the preprocessed parameter data with the standard parameter data stored in the database module. The parameter anomaly identification unit is used to identify parameter anomalies in the parameter data according to the parameter comparison and analysis results. If the preprocessed parameter data is inconsistent with the standard parameter data, it indicates that the monitored parameter data is abnormal, thereby realizing intelligent and automatic identification of park anomalies.

[0034] The danger assessment module includes an information reading unit and a danger judgment unit, wherein the information reading unit is used to read the data analysis results of the image data analysis module and the parameter data analysis module, and the danger judgment unit is used to judge whether there is danger in the park according to the data analysis results, and a range value is preset. If the analysis result exceeds the preset range value, it means that there is a danger in the corresponding position of the park, otherwise it means that there is no danger in the corresponding position of the park, thereby realizing intelligent automatic identification of danger in the park;

[0035] The automatic alarm module includes an alarm trigger unit and an alarm execution unit. The alarm trigger unit automatically triggers an alarm call when the danger judgment unit analyzes and judges that there is a danger in the park. The alarm execution unit is used to issue an alarm prompt in the park to remind park personnel that there is a danger and pay attention to prevention. Specifically, it includes a danger warning light and a buzzer alarm.

[0036] The emergency fire fighting module includes a park broadcasting unit, an automatic fire extinguishing unit, an automatic smoke exhaust unit and an evacuation indication unit. The park broadcasting unit is a loudspeaker used to play voice prompts in the park to inform park personnel of the specific situation of the danger. The automatic fire extinguishing unit is a fire sprinkler used to extinguish open flames in the park. The automatic smoke exhaust unit is a ventilation and smoke exhaust equipment installed in the park building, which is used for indoor ventilation and smoke exhaust. The evacuation indication unit is an LED prompt light board set in the park building, which is used to provide instructions for indoor crowd evacuation. The emergency fire fighting module composed of the above units can provide timely and effective emergency treatment after a dangerous accident occurs in the park, reduce safety hazards, and maximize personnel safety.

[0037] The intelligent power supply system includes a new energy power supply module and a mains power supply module, wherein the new energy power supply module is used to provide backup power for the park security system, and the mains power supply module includes a mains access unit and a mains frequency conversion unit, wherein the mains access unit is used to connect to the mains, and the mains frequency conversion unit is used to convert the frequency of the connected mains and provide power supply of corresponding frequency for the park security system. By providing two different power supply modes for the park security system, it can not only save electricity to a certain extent, but also provide a period of backup power supply for the park security system when the mains power is urgently cut off. The new energy power supply module includes a wind power generation unit, a solar power generation unit and a backup power storage unit, wherein the wind power generation unit is a wind power generation equipment and generates electricity by converting wind energy, the solar power generation unit is a solar photovoltaic panel and generates electricity by converting solar energy, and the backup power storage unit is a battery and is used to store new energy electricity.

[0038] Smart mobile terminals include smart phones and tablets, which are carried by park security personnel to improve portability. Smart fixed terminals include desktop computers and LCD screens, which are installed in the park monitoring room to facilitate monitoring by park security personnel. Both smart mobile terminals and smart fixed terminals are installed with remote control APPs for controlling the park security system, thereby realizing remote control of the park security system.

[0039] When the park security system based on computer vision is actually used, the environment monitoring module and the equipment monitoring module in the park monitoring system are first used to monitor the park environment and the operating parameters of the electrical equipment in the park respectively, and the corresponding monitoring data are obtained and sent to the monitoring data processing system by the data sending module, and then the data receiving module in the monitoring data processing system is used to receive each monitoring data. After receiving, the data classification module classifies each monitoring data into image data and parameter data, and then the image data analysis module and the parameter data analysis module are used to process and analyze the above image data and parameter data respectively, and the abnormal behavior and events in the image are automatically identified from the image monitoring data, and the corresponding parameter anomalies are identified from the parameter data. Subsequently, the danger assessment module in the emergency alarm system assesses the danger of the park according to the data processing results of the monitoring data processing system, and the automatic alarm module determines whether to alarm according to the danger assessment results of the park, and finally, according to the above identified danger of the park, the emergency fire fighting module is used to provide the emergency fire fighting function of the park.

[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A campus security system based on computer vision, characterized by: Including park monitoring system, monitoring data processing system, emergency alarm system, intelligent power supply system and park monitoring terminal; The park monitoring system includes an environment monitoring module for monitoring the park environment, an equipment monitoring module for monitoring the park equipment, and a data sending module for sending each monitoring data to the monitoring data processing system; The monitoring data processing system includes a data receiving module for receiving each monitoring data, a data classification module for classifying each received monitoring data, an image data analysis module for processing and analyzing image data obtained after classification, a parameter data analysis module for processing and analyzing parameter data obtained after classification, and a database module pre-stored with standard parameter data; The emergency alarm system includes a risk assessment module for assessing the danger of the park according to the data processing results of the monitoring data processing system, an automatic alarm module for determining whether to alarm according to the results of the park risk assessment, and an emergency firefighting module for providing an emergency firefighting function for the park; The intelligent power supply system supplies power to the entire park security system, and the park monitoring terminal includes an intelligent mobile terminal for providing a remote mobile monitoring function and an intelligent fixed terminal for providing a remote fixed-point monitoring function.

2. A campus security system based on computer vision according to claim 1, characterized in that: The environmental monitoring module includes an image acquisition unit for video monitoring of the park, a gas monitoring unit for monitoring harmful gases in the park, and a flame monitoring unit for monitoring whether there is a fire in the park. The equipment monitoring module includes a temperature and humidity monitoring unit for monitoring the temperature and humidity of each electrical equipment in the park, and an electrical parameter monitoring unit for monitoring the electrical parameters of each electrical equipment in the park.

3. The campus security system based on computer vision according to claim 1, characterized in that: The data sending module includes a data compression unit for compressing each monitoring data and a data sending antenna for transmitting the compressed data packet to the monitoring data processing system in a wireless transmission manner. The data receiving module includes a data receiving antenna for receiving the data packet and a data decompression unit for decompressing the received data packet.

4. The campus security system based on computer vision according to claim 1, characterized in that: The data classification module includes a data sorting unit for sorting the data received by the data receiving module and a data classification unit for classifying the sorted data. The data sorting unit uses a data cleaning algorithm to clean up missing values, abnormal values ​​and duplicate data in the data. The data classification unit classifies the sorted data into image data and parameter data based on a neural network algorithm.

5. The campus security system based on computer vision according to claim 1, characterized in that: The image data analysis module includes an image data preprocessing unit for preprocessing the image data obtained after classification, an image feature extraction unit for extracting features from the preprocessed image data, and an image anomaly recognition unit for identifying abnormal features based on the image features. The image data preprocessing unit performs scaling, cropping and normalization preprocessing on the image data, the image feature extraction unit extracts features from the preprocessed image data based on a convolutional neural network, and the image anomaly recognition unit uses a target detection algorithm to identify abnormal behaviors and events in the extracted features.

6. The campus security system based on computer vision according to claim 1, characterized in that: The parameter data analysis module includes a parameter data preprocessing unit for preprocessing the parameter data obtained after classification, a parameter comparison unit for comparing and analyzing the preprocessed parameter data with the standard parameter data stored in the database module, and a parameter anomaly identification unit for identifying abnormal parameters according to the parameter comparison and analysis results.

7. The campus security system based on computer vision according to claim 1, characterized in that: The hazard assessment module includes an information reading unit for reading the data analysis results of the image data analysis module and the parameter data analysis module, and a hazard judgment unit for judging whether there is danger in the park based on the data analysis results. The automatic alarm module includes an alarm triggering unit for triggering an alarm phone and an alarm execution unit for issuing an alarm prompt in the park. The emergency fire fighting module includes a park broadcasting unit for playing voice prompt broadcasts in the park, an automatic fire extinguishing unit for automatically extinguishing open flames, an automatic smoke exhaust unit for indoor ventilation and smoke exhaust, and an evacuation indication unit for providing instructions for indoor crowd evacuation.

8. The campus security system based on computer vision according to claim 1, characterized in that: The intelligent power supply system includes a new energy power supply module for providing backup power for the park security system and a mains power supply module for providing mains power for the park security system. The new energy power supply module includes a wind power generation unit using wind power generation, a solar power generation unit using solar photovoltaic power generation and a backup power storage unit for storing new energy electricity. The mains power supply module includes a mains access unit and a mains frequency conversion unit.

9. The campus security system based on computer vision according to claim 1, characterized in that: The smart mobile terminal includes smart phones and tablet computers carried by the park security personnel, and the smart fixed terminal includes a desktop computer and a liquid crystal display installed in the park monitoring room. Both the smart mobile terminal and the smart fixed terminal are installed with a remote control APP for controlling the park security system.

Images