The utility model content
The purpose of this utility model is to propose a kind of Internet of Things intelligent security guard gateway, Internet of Things intelligent security guard gateway with pedestrian detection and face identification functions is provided, can guarantee intelligent safety and defence system on original stable, practical basis, have the more accurately ability of pedestrian detection and identification
For reaching this purpose, the utility model by the following technical solutions:
A kind of Internet of Things intelligent security guard gateway comprises core cell and expanding element,
Wireless communication module in described core cell and the expanding element and GSM/GPRS module form wireless control system; Described core cell is electrically connected with radio-frequency module and GSM/GPRS module respectively, also is electrically connected with HDMI modular converter in the expanding element;
Described core cell, being used for utilizing AdaBoost pedestrian detection algorithm to carry out people's face detects, carry out recognition of face with the family's face database contrast based on HMM (Hidden Markov Model, HMM) foundation that is kept in the flash memory module, judge pedestrian's identity;
Described wireless communication module is for the result of the transmission of video images that will gather to core cell and feedback core cell;
Described GSM/GPRS module is for the information interaction that realizes management node and user node;
Described HDMI modular converter, the video image that is used for gathering is converted to high-definition image, carries out Real Time Monitoring for management node.
Described core cell comprises: core processor, sdram memory module and NAND type flash memory module, described core processor are electrically connected with sdram memory module and NAND type flash memory module respectively; Described core cell is used for the writing of completion system start-up code, selection of operation system, intermediate layer as hardware and application program, AdaBoost pedestrian detection algorithm and HMM face recognition algorithms are kept in the NAND type flash memory module, are dispatched in the sdram memory module by core processor and move.
Described wireless communication module comprises: radio-frequency module and/or ZigBee module.
Described GSM/GPRS module utilizes the mode of note or multimedia message to notify user mobile phone and subsequent treatment is carried out in the note order that receives the user, to realize that the user is to the gateway controlled in wireless.
Described expanding element also comprises:
USB interface, OTG interface, RS-232 interface, Ethernet interface, SD card interface, HDMI interface, bus expansion interface, keystroke interface, power input interface, audio output interface and WIFI module, infrared module and backup battery; Above-mentioned interface and module are according to the concrete respectively described core cell of access in parallel of needs of using.
Adopt the technical solution of the utility model, Internet of Things intelligent security guard gateway with pedestrian detection and face identification functions is provided, can guarantee that intelligent safety and defence system is on original stable, practical basis, has the more accurately ability of pedestrian detection and identification, the false alarm rate of reduction system, the reliability of enhancing system function and extensibility.
Embodiment
Further specify the technical solution of the utility model below in conjunction with accompanying drawing and by embodiment.
Fig. 1 is the structural representation of the Internet of Things intelligent security guard gateway that provides of the utility model embodiment.
Described Internet of Things intelligent security guard gateway comprises core cell and expanding element.
Described core cell is with wireless communication module and the GSM/GPRS module composition wireless control system in the described expanding element; Described core cell is electrically connected with radio-frequency module and GSM/GPRS module respectively, also is electrically connected with HDMI modular converter in the expanding element.
Described core cell utilizes AdaBoost pedestrian detection algorithm to extract the position of pedestrian in the video image that gathers, draws the pedestrian zone with rectangle frame; For the pedestrian's rectangle frame that exceeds certain threshold value, adopt people's face detection algorithm, detect people's face, then the family's face database with HMM foundation contrasts, and carries out recognition of face, judges pedestrian's identity;
Described wireless communication module, the transmission of video images that is used for gathering be to core cell, and the result of core cell is fed back to front end sensors;
Described GSM/GPRS module is for the information interaction that realizes management node and user node.
Described core cell comprises: core processor, sdram memory module and NAND type flash memory module, described core processor are electrically connected with sdram memory module and NAND type flash memory module respectively; Described core cell is used for the writing of completion system start-up code, selection of operation system, intermediate layer as hardware and application program, AdaBoost pedestrian detection algorithm and HMM face recognition algorithms are kept in the NAND type flash memory module, be dispatched in the sdram memory module by core processor and move, the speed of service is very fast.
Described AdaBoost pedestrian detection algorithm and HMM face recognition algorithms are existing the application, specifically can be with reference to Publication about Document:
Pedestrian detection method based on the Adaboost algorithm. Guo Lie, Wang Rongben, Zhang Mingheng, Gionee is given birth to. (Jilin University's traffic institute, Changchun 130025). and computer engineering, 2008,34(3): 201-204.
Automatic human face identification method based on HMM. Xu Yiqiong, Li Bicheng, Wang Bo. (School of Information Technology of information engineering university). computer application, 2004,24:225-227.
Described expanding element comprises: USB interface, OTG interface, RS-232 interface, Ethernet interface, SD card interface, HDMI interface, bus expansion interface, keystroke interface, power input interface, audio output interface and HDMI modular converter, WIFI module, infrared module, front end sensors module, wireless communication module, GSM/GPRS module and backup battery.
Above-mentioned interface and module can be distinguished the described core cell of access in parallel according to the concrete needs of using, as shown in Figure 2.Camera module can gather the pedestrian and the unusual personnel that enter within doors in a defence area; Propaganda directed to communicate in audio-frequency module realization scene; GSM/GPRS module realization front end node abnormal information is informed the transmitting-receiving of user and multimedia message; The SD card interface can access the SD card of maximum 4G capacity, is used for the dynamic data of storage system; USB interface can realize the unloading of data; WIFI module and ethernet module can be realized remote transmission of information etc.The driver of modules realizes in embedded OS that all application program only needs calling interface just can realize the normal operation of module.
Among the utility model embodiment, the core processor in the core cell can select the S3C2440A of ARM9 core processor or employing Samsung as core processor.
Core processor is arranged at main control system inside, the core processor outside be provided with radio-frequency module and therewith radio-frequency module be reciprocal relation, core processor is by radio-frequency module wireless connections front end sensors; Core processor is SD card, camera, WIFI module, inductive pick-up and the audio frequency peripheral hardware of access control main frame in parallel inside respectively, and in addition, core processor carries out wireless connections by GSM/GPRS module and user mobile phone.Operation principle: main control system realizes that by core processor control radio-frequency module the information of front end sensors gathers and processes, and utilize the mode of note or multimedia message to notify user mobile phone and receive the note order by the GSM/GPRS module and carry out subsequent treatment, realize the Internet of Things controlled in wireless with this.
Described wireless communication module is preferably radio-frequency module or ZigBee module.The Internet of Things intelligent wireless safety-protection system at described Internet of Things intelligent wireless safety-protection gateway place adopts by different level hub-and-spoke network topology structure.Front end sensors also claims radio sensing network node, and by selecting a kind of communication, radio-frequency module or ZigBee module are wirelessly transmitted to image data on the wireless communication module of core cell.Core processor by core cell carries out analyzing and processing by AdaBoost pedestrian detection algorithm and HMM face recognition algorithms to data, judgement makes decisions, result is also fed back to front end sensors by identical wireless transmission method, realize remote wireless monitoring.Simultaneously, system by AdaBoost pedestrian detection algorithm and HMM face recognition algorithms with the data of all front end sensors collections process by analysis, Weighted Fusion forms information, by the information interaction that realizes remote monitoring node and management node based on Internet the Internet and the GSM mobile communications network of WiFi.Management node is exactly user's PC usually, or the cell management center, is responsible for the user is connected to the network.The user only need just can realize in the IP address of internet browser input management node the control to management node, realizes the configuration of whole network, sets relevant monitoring task or the monitor message of checking all the sensors.
Described HDMI modular converter, the video image that is used for gathering is converted to high-definition image, carries out Real Time Monitoring for management node.Described HDMI modular converter can select VGA to turn the HDMI transducer, and the video of front end sensors collection is converted to high-definition format, is sent to the high definition monitor of management node by the HDMI interface of expanding element again, is used for the staff and carries out the realtime graphic monitoring.
Pedestrian detection is a characteristic of described Internet of Things intelligent security guard gateway.Utilize AdaBoost pedestrian detection algorithm to extract the position of pedestrian in the video sequence, draw the pedestrian zone with rectangle frame; For the pedestrian's rectangle frame that exceeds certain threshold value, adopt people's face detection algorithm, detect people's face.Then the family's face database with HMM foundation contrasts, and judges pedestrian's identity, for safety-protection system provides effective assurance.
Adopt the technical solution of the utility model, Internet of Things intelligent security guard gateway with pedestrian detection and face identification functions is provided, can guarantee that intelligent safety and defence system is on original stable, practical basis, has the more accurately ability of pedestrian detection and identification, the false alarm rate of reduction system, the reliability of enhancing system function and extensibility.
The above; it only is the better embodiment of the utility model; but protection range of the present utility model is not limited to this; anyly be familiar with the people of this technology in the disclosed technical scope of the utility model; the variation that can expect easily or replacement all should be encompassed within the protection range of the present utility model.Therefore, protection range of the present utility model should be as the criterion with the protection range of claim.