Disclosure of Invention
In view of this, embodiments of the present invention provide a security inspection robot and a security inspection method, so as to solve the problems that, in the inspection process of the existing security inspection robot, external information in a navigation line cannot be effectively analyzed and utilized, and the existing security inspection requirements of the security inspection robot cannot be met.
The first aspect of the embodiment of the invention provides a security inspection robot, which comprises a video acquisition and analysis unit, a voice acquisition and analysis unit, a navigation obstacle avoidance unit, a main control analysis unit, an alarm unit and a robot chassis motion unit;
the video acquisition and analysis unit is used for acquiring images of a security inspection area, performing face recognition and abnormal behavior analysis according to the images, and sending a face recognition result and an abnormal behavior analysis result to the main control analysis unit;
the voice acquisition and analysis unit is used for acquiring voice of the security inspection area, performing abnormal semantic analysis according to the voice and sending an abnormal semantic analysis result to the main control analysis unit;
the navigation obstacle avoidance unit comprises a navigation obstacle avoidance sensor unit and a navigation obstacle avoidance analysis unit, and the navigation obstacle avoidance analysis unit determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit and sends the navigation obstacle avoidance scheme to the main control analysis unit;
and the master control analysis unit is used for controlling the alarm unit to give an alarm according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, and controlling the robot chassis motion unit to work according to the navigation obstacle avoidance scheme.
Optionally, the security inspection robot further comprises a mobile terminal information acquisition unit;
the mobile terminal information acquisition unit is used for acquiring the identification code of the mobile terminal in the security inspection area and uploading the identification code to the background server, so that the server monitors specific personnel according to a preset mobile terminal information base and the identification code, and monitors personnel in and out and gathering the personnel in the specific area.
Optionally, the performing, by the video acquisition and analysis unit, face recognition and abnormal behavior analysis according to the image includes:
the video acquisition and analysis unit captures a face image from the image, performs face recognition according to the similarity between the pre-stored face image and the captured face image, acquires depth three-dimensional information of a target person from the image based on a depth vision algorithm, and performs abnormal behavior analysis according to the depth three-dimensional information of the target person.
Optionally, the performing, by the speech acquisition and analysis unit, abnormal semantic analysis according to the speech includes:
and the voice acquisition and analysis unit converts the voice into characters and performs abnormal semantic analysis on the characters according to a deep learning algorithm and preset abnormal keywords.
Optionally, the navigation obstacle avoidance analysis unit determines that the navigation obstacle avoidance scheme includes, according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit:
the navigation obstacle avoidance analysis unit determines the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit corresponding to the current scene of the security inspection area according to the priority of the scene and the priority of the navigation obstacle avoidance sensor, and determines the navigation obstacle avoidance scheme based on a navigation obstacle avoidance algorithm, the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit and output information.
Optionally, the controlling and analyzing unit controls the alarm unit to alarm according to the face recognition result, the abnormal behavior analysis result, and the abnormal semantic analysis result, and controls the robot chassis motion unit to work according to the navigation obstacle avoidance scheme, including:
the main control analysis unit determines the current mode of the security inspection area according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, determines an alarm scheme corresponding to the current mode of the security inspection area according to the corresponding relation between the mode and the alarm scheme, controls the alarm unit to alarm according to the determined alarm scheme, and determines a target working chassis in the robot chassis motion unit according to the navigation obstacle avoidance scheme; and controlling the target working chassis to work according to the road condition environment of the security inspection area.
Optionally, the Navigation obstacle avoidance sensor unit includes a radar, a binocular vision sensor, an ultrasonic sensor, an inertial Navigation sensor, and a differential Global Navigation Satellite System (GNSS).
A second aspect of the embodiments of the present invention provides a security inspection method, including:
controlling an alarm unit to give an alarm according to a face recognition result and an abnormal behavior analysis result of a video acquisition and analysis unit and an abnormal semantic analysis result of a voice acquisition and analysis unit, wherein the face recognition result and the abnormal behavior analysis result are obtained by performing face recognition and abnormal behavior analysis according to an image of a security inspection area after the video acquisition and analysis unit acquires the image, and the abnormal semantic analysis result is obtained by performing abnormal semantic analysis according to the voice after the voice acquisition and analysis unit acquires the voice of the security inspection area;
and controlling the robot chassis motion unit to work according to a navigation obstacle avoidance scheme of the navigation obstacle avoidance unit, wherein the navigation obstacle avoidance unit comprises a navigation obstacle avoidance sensor unit and a navigation obstacle avoidance analysis unit, and the navigation obstacle avoidance scheme is determined by the navigation obstacle avoidance analysis unit according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit.
Optionally, the controlling the alarm unit to alarm according to the face recognition result and the abnormal behavior analysis result of the video acquisition and analysis unit and the abnormal semantic analysis result of the voice acquisition and analysis unit includes:
determining the current mode of the security inspection area according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result;
and determining an alarm scheme corresponding to the current mode of the security inspection area according to the corresponding relation between the mode and the alarm scheme, and controlling the alarm unit to alarm according to the determined alarm scheme.
Optionally, the controlling the robot chassis motion unit to work according to the navigation obstacle avoidance scheme of the navigation obstacle avoidance unit includes:
determining a target working chassis in the robot chassis motion unit according to the navigation obstacle avoidance scheme;
and controlling the target working chassis to work according to the road condition environment of the security inspection area.
Compared with the prior art, the embodiment of the invention has the following beneficial effects: the embodiment of the invention provides an intelligent security inspection robot with various information acquisition, intelligent analysis and autonomous decision, wherein a video acquisition and analysis unit is used for acquiring images of a security inspection area, a face recognition and abnormal behavior analysis are carried out according to the images, a voice acquisition and analysis unit is used for acquiring voices of the security inspection area and carrying out abnormal semantic analysis according to the voices, a navigation obstacle avoidance analysis unit in a navigation obstacle avoidance unit determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit, a main control analysis unit controls an alarm unit to give an alarm according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, controls a robot chassis motion unit to work according to the navigation obstacle avoidance scheme, and can effectively analyze and utilize external information in a navigation line, meanwhile, the workload of security patrol personnel is greatly reduced, a fixed monitoring camera is well supplemented, and the existing security patrol requirement of the security patrol robot is met.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Referring to fig. 1, fig. 1 is a schematic block diagram of a security inspection robot according to an embodiment of the present invention, which solves the problem that, in the inspection process of the conventional security inspection robot, external information in a navigation line cannot be effectively analyzed and utilized, and the conventional security inspection requirement of the security inspection robot cannot be met. As shown in fig. 1, the security inspection robot 100 of the present embodiment includes a video collecting and analyzing unit 101, a voice collecting and analyzing unit 102, a navigation obstacle avoiding unit 103, a main control analyzing unit 104, an alarm unit 105, and a robot chassis moving unit 106. The navigation obstacle avoidance unit 103 includes a navigation obstacle avoidance sensor unit 1031 and a navigation obstacle avoidance analysis unit 1032.
The video acquisition and analysis unit 101 is configured to acquire images of a security inspection area, perform face recognition and abnormal behavior analysis according to the images, and send a face recognition result and an abnormal behavior analysis result to the main control analysis unit 104.
Here, the video capture analysis unit 101 may include a binocular pan-tilt camera and an intelligent vision analysis module. The binocular tripod head is provided with two cameras of visible light and infrared thermal imaging, and can operate in all weather. The intelligent visual analysis module can analyze image information acquired by the camera in real time based on a deep visual algorithm, can finish face recognition and abnormal behavior analysis, wherein abnormal behaviors comprise border crossing, entering/leaving of areas, regional invasion, wandering, personnel focusing, rapid movement, illegal parking, object leaving/taking and the like, and transmits analysis results to the main control analysis unit, and deep learning refers to an algorithm set for solving various problems such as images, texts and the like by applying various machine learning algorithms on a multilayer neural network. The core of deep learning is feature learning, and aims to obtain hierarchical feature information through a hierarchical network, so that the important problem that features need to be designed manually in the past is solved. Deep learning is a framework, and comprises a plurality of important algorithms, such as a Convolutional Neural Network (CNN), a Deep Belief Network (DBN), a Recursive Neural Network (RNN) and the like, and for different problems (images, voice and text), different Network models are required to achieve better effects.
The voice collecting and analyzing unit 102 is configured to collect voice of the security inspection area, perform abnormal semantic analysis according to the voice, and send an abnormal semantic analysis result to the main control analyzing unit 104.
Specifically, the voice collecting and analyzing unit 102 includes an omnidirectional high-sensitivity sound pickup and an intelligent voice analyzing module. The omnidirectional high-sensitivity pickup can collect voice information in a certain range around a patrol route. The intelligent voice analysis module can complete the analysis and recognition of abnormal semantics such as dispute, call for help and the like based on a deep learning algorithm, and transmit the analysis result to the main control analysis unit 104, wherein abnormal semantic keywords such as rescue, robbery and the like can be set in advance according to actual needs, the intelligent voice analysis module can convert voice into characters after the voice is collected by the omnidirectional high-sensitivity sound pickup, and the converted characters are subjected to abnormal semantic analysis based on the deep learning algorithm and the abnormal semantic keywords.
The navigation obstacle avoidance unit 103 comprises a navigation obstacle avoidance sensor unit 1031 and a navigation obstacle avoidance analysis unit 1032, wherein the navigation obstacle avoidance analysis unit 1032 determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit 1031, and sends the navigation obstacle avoidance scheme to the main control analysis unit 104.
Here, the navigation obstacle avoidance unit 103 may include various navigation obstacle avoidance sensors and an intelligent navigation obstacle avoidance analysis unit. The navigation obstacle avoidance sensor comprises a laser radar/millimeter wave radar, a binocular vision sensor, an ultrasonic sensor, an inertial navigation sensor and a high-precision differential GNSS. The navigation obstacle avoidance analysis unit intelligently generates an optimal navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each sensor, wherein the current scene of the security inspection area can be input by related technical personnel, the navigation obstacle avoidance sensors corresponding to different scenes have different priorities, for example, in scene 1, the navigation obstacle avoidance sensor with the highest priority is a laser radar/millimeter wave radar, and in scene 2, the navigation obstacle avoidance sensor with the highest priority is a high-precision differential GNSS. The navigation obstacle avoidance analysis unit firstly determines the priority of each navigation obstacle avoidance sensor according to the current scene of the security inspection area, and then generates the optimal navigation obstacle avoidance scheme according to the priority and the output information of each navigation obstacle avoidance sensor, for example, in the scene 1, the priority of the laser radar/millimeter wave radar is the highest, and the navigation obstacle avoidance analysis unit mainly refers to the output information of the laser radar/millimeter wave radar to generate the navigation obstacle avoidance scheme.
The main control analysis unit 104 is configured to control the alarm unit 105 to alarm according to the face recognition result, the abnormal behavior analysis result, and the abnormal semantic analysis result, and control the robot chassis motion unit 106 to work according to the navigation obstacle avoidance scheme.
Specifically, the alarm unit 105 includes a multi-mode alarm module (operator network/private network/trunking communication network, etc.), a tweeter for warning information broadcast, and a high-decibel noise diffuser for local personnel dissipation. After receiving the control information of the master analysis unit 104, an appropriate processing scheme may be selected through a variety of setting modes.
The robot chassis moving unit 106 is a walking mechanism of the inspection robot, and can be selectively configured into a wheel type or crawler type chassis according to different navigation obstacle avoidance schemes. And the main control analysis unit 104 combines the control information output by the navigation obstacle avoidance unit 103 to control.
The main control analysis unit 104 is used as a central control center of the whole inspection robot, and is responsible for processing the output information of the navigation obstacle avoidance unit 103, and outputting a control instruction to the robot chassis motion unit 106 to control the robot to operate. And acquiring the acquisition and analysis results of the video acquisition and analysis unit 101 and the voice acquisition and analysis unit 102 on the peripheral information, and determining whether to perform local processing or transmit the results to a background analysis unit through a communication unit according to the analysis results.
The video acquisition and analysis unit 101, the voice acquisition and analysis unit 102, the navigation obstacle avoidance unit 103, the main control and analysis unit 104, the alarm unit 105 and the robot chassis motion unit 106 are communicated with each other through a communication unit, and specifically, the communication unit adopts a communication mode of multiple systems as redundant backup, and is used for video information, bidirectional voice information, control of the robot, transmission of state information and the like, and can be controlled by the main control and analysis unit.
From the above description, the security inspection robot in the embodiment of the invention can effectively analyze and utilize the external information in the navigation line, greatly reduce the workload of security inspection personnel, well supplement the fixed monitoring camera, and meet the security inspection requirement of the existing security inspection robot.
Referring to fig. 2, fig. 2 is a schematic block diagram of a security inspection robot according to another embodiment of the present invention. The security inspection robot 200 of the embodiment includes a video acquisition and analysis unit 201, a voice acquisition and analysis unit 202, a navigation obstacle avoidance unit 203, a main control analysis unit 204, an alarm unit 205, a robot chassis motion unit 206, and a mobile terminal information acquisition unit 207. The navigation obstacle avoidance unit 203 includes a navigation obstacle avoidance sensor unit 2031 and a navigation obstacle avoidance analysis unit 2032.
Specifically, please refer to the video collecting and analyzing unit 201, the voice collecting and analyzing unit 202, the navigation obstacle avoidance unit 203, the main control analyzing unit 204, the alarm unit 205, and the robot chassis moving unit 206 in the embodiments corresponding to fig. 1 and fig. 1, and the video collecting and analyzing unit 101, the voice collecting and analyzing unit 102, the navigation obstacle avoidance unit 103, the main control analyzing unit 104, the alarm unit 105, and the robot chassis moving unit 106 in the embodiments corresponding to fig. 1 and fig. 1, and the navigation obstacle avoidance sensor unit 2031 and the navigation obstacle avoidance analyzing unit 2032 specifically refer to the navigation obstacle avoidance sensor unit 1031 and the navigation obstacle avoidance analyzing unit 1032 in the embodiments corresponding to fig. 1 and fig. 1, which is not repeated here.
Further, the mobile terminal information acquisition unit 207 is used for acquiring the identification code of the mobile terminal in the security inspection area, and uploading the identification code to the background server, so that the server monitors specific personnel according to a preset mobile terminal information base and the identification code, and monitors personnel in and out and gathering the specific area.
Here, the mobile terminal information collecting unit 207 may collect the mobile terminal information around the patrol route, and upload the collected information to a background server for analysis in real time, or perform analysis locally. Through combining the comparison of the mobile terminal information base, the monitoring of specific personnel can be realized in real time, and the monitoring of personnel gathering and exiting abnormally in specific areas is realized, so that the dangerous condition can be conveniently found in advance.
Further, the video acquisition and analysis unit 201 performing face recognition and abnormal behavior analysis according to the image includes:
the video acquisition and analysis unit 201 captures a face image from the image, performs face recognition according to the similarity between the pre-stored face image and the captured face image, acquires depth three-dimensional information of a target person from the image based on a depth vision algorithm, and performs abnormal behavior analysis according to the depth three-dimensional information of the target person.
Specifically, the video acquisition and analysis unit 201 calculates the similarity between the captured face image and a pre-stored face image, determines that the face recognition is successful if the similarity between the captured face image and a pre-stored image reaches a preset similarity threshold, and determines the information of the captured face image according to the pre-stored image information.
The video acquisition and analysis unit 201 acquires depth three-dimensional information (target height information, accuracy of target behavior analysis and multi-target detection, target position information, multi-target detection, especially target distance detection, target depth information, and judgment of multi-target position distance) of a target person from the image based on a depth vision algorithm, and realizes abnormal behavior analysis such as border crossing, entering/leaving area, area intrusion, loitering, person focusing, quick movement, illegal parking, article leaving/taking and the like.
Further, the performing, by the speech acquisition and analysis unit 202, abnormal semantic analysis according to the speech includes:
the voice acquisition and analysis unit 202 converts the voice into words, and performs abnormal semantic analysis on the words according to a deep learning algorithm and preset abnormal keywords.
Here, the preset abnormal keyword may be set according to actual needs, and after the voice is converted into a character by the voice acquisition and analysis unit 202, based on the deep learning algorithm and the preset abnormal keyword, the abnormal semantic analysis and recognition such as dispute, call for help, and the like may be completed.
Further, the navigation obstacle avoidance analyzing unit 2032 determines, according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit 2031, that the navigation obstacle avoidance scheme includes:
the navigation obstacle avoidance analysis unit 2032 determines the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit 2031 corresponding to the current scene of the security inspection area according to the priority of the scene and the navigation obstacle avoidance sensor, and determines the navigation obstacle avoidance scheme based on the navigation obstacle avoidance algorithm, the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit 2031 and the output information.
Specifically, the navigation obstacle avoidance algorithm may include a visual graph method, an artificial potential field method, a VFH histogram, and the like, and the navigation obstacle avoidance analysis unit 2032 determines the priority of each navigation obstacle avoidance sensor according to the current scene of the security inspection area, and then generates the optimal navigation obstacle avoidance scheme based on the navigation obstacle avoidance algorithm, the priority of each navigation obstacle avoidance sensor, and the output information.
Further, the controlling and analyzing unit 204 controls the alarming unit 205 to alarm according to the face recognition result, the abnormal behavior analysis result, and the abnormal semantic analysis result, and controls the robot chassis moving unit 206 to work according to the navigation obstacle avoidance scheme, including:
the main control analysis unit 204 determines the current mode of the security inspection area according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, determines an alarm scheme corresponding to the current mode of the security inspection area according to the corresponding relation between the mode and the alarm scheme, controls the alarm unit 205 to alarm according to the determined alarm scheme, determines a target working chassis in the robot chassis motion unit according to the navigation obstacle avoidance scheme, and controls the target working chassis to work according to the road condition environment of the security inspection area.
Here, the current mode includes a current scenario and a network mode of the security inspection area, where the current scenario may include whether a specific person appears in the security inspection area, whether an abnormal behavior occurs, whether an abnormal voice occurs, and the like, and the network mode may include an operator network/a private network/a trunking communication network, and the like. Alarm unit 105 contains multi-mode alarm module for warning information broadcast's high pitch horn, be used for the high decibel noise ware of dispelling of local personnel. After receiving the control information of the master analysis unit 104, an appropriate processing scheme may be selected through a variety of setting modes. The robot chassis motion unit 106 is a walking mechanism of the inspection robot, can be selectively configured into a wheel type or crawler type chassis according to different navigation obstacle avoidance schemes, and is controlled by the main control analysis unit 104 in combination with the control information output by the navigation obstacle avoidance unit 103.
Further, the navigation obstacle avoidance sensor unit 2031 includes a radar, a binocular vision sensor, an ultrasonic sensor, an inertial navigation sensor, and a high-precision differential GNSS, where the radar is a laser radar or a millimeter wave radar.
As can be seen from the above description, the embodiment of the present invention provides an intelligent security inspection robot with multiple information collection, intelligent analysis and autonomous decision, wherein a video collection and analysis unit collects an image of a security inspection area, a face recognition and abnormal behavior analysis are performed according to the image, a voice collection and analysis unit collects voice of the security inspection area, abnormal semantic analysis is performed according to the voice, a navigation obstacle avoidance analysis unit in the navigation obstacle avoidance unit determines a navigation obstacle avoidance scheme according to a current scene of the security inspection area and output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit, a main control analysis unit controls an alarm unit to alarm according to a face recognition result, an abnormal behavior analysis result and an abnormal semantic analysis result, controls a chassis motion unit of the robot to work according to the navigation obstacle avoidance scheme, and can effectively analyze and utilize external information in a navigation line, meanwhile, the workload of security patrol personnel is greatly reduced, a fixed monitoring camera is well supplemented, and the existing security patrol requirement of the security patrol robot is met.
Corresponding to the security inspection robot described in the above embodiments, fig. 3 shows a schematic flow chart of a security inspection method provided in an embodiment of the present invention. The security inspection robot 100 of the above embodiment includes units for performing the steps in the embodiment corresponding to fig. 3, and please refer to fig. 1 and the description of the embodiment corresponding to fig. 1 for details, which are not repeated herein.
As shown in fig. 3, in this embodiment, the angle triggering of the main control analysis unit is taken as an example for explanation, here, the main control analysis unit may perform information interaction with the video acquisition analysis unit, the voice acquisition analysis unit, the navigation obstacle avoidance unit, the alarm unit, and the robot chassis motion unit. As shown in fig. 3, in this embodiment, the process of the master analysis unit may include the following steps:
s301: according to the face recognition result and the abnormal behavior analysis result of the video acquisition and analysis unit and the abnormal semantic analysis result of the voice acquisition and analysis unit, the alarm unit is controlled to give an alarm, wherein the face recognition result and the abnormal behavior analysis result are obtained by performing face recognition and abnormal behavior analysis on the image after the video acquisition and analysis unit acquires the image of the security inspection area, and the abnormal semantic analysis result is obtained by performing abnormal semantic analysis on the voice after the voice acquisition and analysis unit acquires the voice of the security inspection area.
S302: and controlling the robot chassis motion unit to work according to a navigation obstacle avoidance scheme of the navigation obstacle avoidance unit, wherein the navigation obstacle avoidance unit comprises a navigation obstacle avoidance sensor unit and a navigation obstacle avoidance analysis unit, and the navigation obstacle avoidance scheme is determined by the navigation obstacle avoidance analysis unit according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit.
From the above description, the security inspection method according to the embodiment of the invention can effectively analyze and utilize the external information in the navigation line, greatly reduce the workload of security inspection personnel, well supplement the fixed monitoring camera, and meet the security inspection requirement of the existing security inspection robot.
In addition, in a specific example, the controlling an alarm unit to alarm according to the face recognition result and the abnormal behavior analysis result of the video acquisition and analysis unit and the abnormal semantic analysis result of the voice acquisition and analysis unit includes:
determining the current mode of the security inspection area according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result;
and determining an alarm scheme corresponding to the current mode of the security inspection area according to the corresponding relation between the mode and the alarm scheme, and controlling the alarm unit to alarm according to the determined alarm scheme.
In addition, in a specific example, the controlling the robot chassis motion unit to operate according to the navigation obstacle avoidance scheme of the navigation obstacle avoidance unit includes:
determining a target working chassis in the robot chassis motion unit according to the navigation obstacle avoidance scheme;
and controlling the target working chassis to work according to the road condition environment of the security inspection area.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Referring to fig. 4, fig. 4 is a schematic block diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 4, the terminal device 40 of this embodiment includes: a processor 400, a memory 401, and a computer program 402, such as a security patrol program, stored in the memory 401 and operable on the processor 400. The processor 400, when executing the computer program 402, implements the steps in the above-described embodiment of the security inspection method, such as the steps 301 to 302 shown in fig. 3. Alternatively, the processor 400, when executing the computer program 402, implements the functions of the units in the above-described device embodiments, such as the functions of the units 201 to 207 shown in fig. 2.
The computer program 402 may be divided into one or more modules/units, which are stored in the memory 401 and executed by the processor 400 to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program 402 in the terminal device 40. For example, the computer program 402 may be divided into a video acquisition and analysis unit, a voice acquisition and analysis unit, a navigation obstacle avoidance unit, a main control and analysis unit, an alarm unit, a robot chassis motion unit, and a mobile terminal information acquisition unit. The navigation obstacle avoidance unit comprises a navigation obstacle avoidance sensor unit and a navigation obstacle avoidance analysis unit, and the specific functions of the units are as follows:
the video acquisition and analysis unit is used for acquiring images of a security inspection area, performing face recognition and abnormal behavior analysis according to the images, and sending a face recognition result and an abnormal behavior analysis result to the main control analysis unit;
the voice acquisition and analysis unit is used for acquiring voice of the security inspection area, performing abnormal semantic analysis according to the voice and sending an abnormal semantic analysis result to the main control analysis unit;
the navigation obstacle avoidance unit comprises a navigation obstacle avoidance sensor unit and a navigation obstacle avoidance analysis unit, and the navigation obstacle avoidance analysis unit determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit and sends the navigation obstacle avoidance scheme to the main control analysis unit;
and the master control analysis unit is used for controlling the alarm unit to give an alarm according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, and controlling the robot chassis motion unit to work according to the navigation obstacle avoidance scheme.
Further, the mobile terminal information acquisition unit is used for acquiring the identification code of the mobile terminal in the security inspection area and uploading the identification code to the background server, so that the server monitors specific personnel according to a preset mobile terminal information base and the identification code, and monitors personnel in and out and gathering the specific area.
Further, the video acquisition and analysis unit performing face recognition and abnormal behavior analysis according to the image comprises:
the video acquisition and analysis unit captures a face image from the image, performs face recognition according to the similarity between the pre-stored face image and the captured face image, acquires depth three-dimensional information of a target person from the image based on a depth vision algorithm, and performs abnormal behavior analysis according to the depth three-dimensional information of the target person.
Further, the performing, by the speech acquisition and analysis unit, abnormal semantic analysis according to the speech includes:
and the voice acquisition and analysis unit converts the voice into characters and performs abnormal semantic analysis on the characters according to a deep learning algorithm and preset abnormal keywords.
Further, the navigation obstacle avoidance analysis unit determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit, and the navigation obstacle avoidance analysis unit includes:
the navigation obstacle avoidance analysis unit determines the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit corresponding to the current scene of the security inspection area according to the priority of the scene and the priority of the navigation obstacle avoidance sensor, and determines the navigation obstacle avoidance scheme based on a navigation obstacle avoidance algorithm, the priority of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit and output information.
Further, the controlling and analyzing unit controls the alarming unit to alarm according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, and controls the robot chassis moving unit to work according to the navigation obstacle avoidance scheme, including:
the main control analysis unit determines the current mode of the security inspection area according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, determines an alarm scheme corresponding to the current mode of the security inspection area according to the corresponding relation between the mode and the alarm scheme, controls the alarm unit to alarm according to the determined alarm scheme, determines a target working chassis in the robot chassis movement unit according to the navigation obstacle avoidance scheme, and controls the target working chassis to work according to the road condition environment of the security inspection area.
The scheme provides an intelligent security inspection robot with various information acquisition, intelligent analysis and autonomous decision, wherein a video acquisition and analysis unit acquires images of a security inspection area, a face recognition and abnormal behavior analysis are carried out according to the images, a voice acquisition and analysis unit acquires voices of the security inspection area and carries out abnormal semantic analysis according to the voices, a navigation obstacle avoidance analysis unit in a navigation obstacle avoidance unit determines a navigation obstacle avoidance scheme according to the current scene of the security inspection area and the output information of each navigation obstacle avoidance sensor in the navigation obstacle avoidance sensor unit, a main control analysis unit controls an alarm unit to give an alarm according to the face recognition result, the abnormal behavior analysis result and the abnormal semantic analysis result, controls a robot chassis motion unit to work according to the navigation obstacle avoidance scheme, and can effectively analyze and utilize external information in a navigation line, meanwhile, the workload of security patrol personnel is greatly reduced, a fixed monitoring camera is well supplemented, and the existing security patrol requirement of the security patrol robot is met.
The terminal device 40 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 400, a memory 401. Those skilled in the art will appreciate that fig. 4 is merely an example of a terminal device 40 and does not constitute a limitation of terminal device 40 and may include more or fewer components than shown, or some components may be combined, or different components, for example, the terminal device may also include input output devices, network access devices, buses, etc.
The Processor 400 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 401 may be an internal storage unit of the terminal device 40, such as a hard disk or a memory of the terminal device 40. The memory 401 may also be an external storage device of the terminal device 40, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 40. Further, the memory 401 may also include both an internal storage unit and an external storage device of the terminal device 40. The memory 401 is used for storing the computer program and other programs and data required by the terminal device. The memory 401 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media which may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.