CN112907803A - Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method - Google Patents
Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method Download PDFInfo
- Publication number
- CN112907803A CN112907803A CN202110047184.7A CN202110047184A CN112907803A CN 112907803 A CN112907803 A CN 112907803A CN 202110047184 A CN202110047184 A CN 202110047184A CN 112907803 A CN112907803 A CN 112907803A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- sends
- face
- processor module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/38—Individual registration on entry or exit not involving the use of a pass with central registration
Abstract
The invention discloses an automatic AI (Artificial intelligence) adjustment intelligent access control system and an access control detection method. The sensor module detects that a human body approaches, the image acquisition module sends a real-time video image to the processor module, the processor module identifies the position of face data in the real-time video image in a video picture, the visual angle range of the image acquisition module is adjusted according to the position, the face image is adjusted to completely appear in the video picture, the processor module compares the adjusted face image, and an access control command is output to the access control module. The invention can automatically identify the face data without contact, control the door opening, and adjust the position of the image acquisition module in real time through image comparison, thereby ensuring the adaptability to visitors with different heights, improving the user friendliness of the access control system and improving the identification rate.
Description
Technical Field
The invention relates to the field of intelligent access control, in particular to an automatic AI (Artificial intelligence) adjusting intelligent access control system and an access control detection method.
Background
The intelligent entrance guard system is a modern safety management system, integrates microcomputer automatic identification technology and modern safety management measures, and relates to various new technologies such as electronics, machinery, optics, computer technology, communication technology, biotechnology and the like. The intelligent control system is suitable for various essential departments, such as banks, hotels, machine rooms, military machine depots, offices, intelligent districts, factories and the like.
With the development of the biometric technology, the intelligent access control system has gained a leap-type development, and various types of intelligent access control systems such as a fingerprint access control system, a face recognition access control system, an iris access control system and the like are developed, and the application is more and more extensive.
However, in the use process of the current products, most intelligent access control systems are installed in a fixed installation mode, and when the biological identification verification is carried out, the situation that the identification cannot be achieved or is not accurate appears, so that the problem that how to adapt to the verification and the identification of people with different heights is solved.
Disclosure of Invention
One of the technical problems to be solved by the invention is as follows: overcome the above-mentioned defect that prior art exists, provide an automatic adjust AI intelligent access control system, contain image acquisition module, sensor module, display module, voice module, processor module, storage module, access control module, communication module, wherein:
the processor module is respectively connected with the display module, the image acquisition module, the sensor module, the voice module, the storage module, the entrance guard control module and the communication module;
the image acquisition module sends acquired real-time video images to the processor module and receives position adjustment instructions and video acquisition instructions sent by the processor module;
the sensor module sends the human body approach detection data to the processor module in real time and receives a parameter configuration instruction sent by the processor module;
the voice module sends the collected audio data to the processor module and receives the audio collection instruction, the playing control instruction and the playing content data sent by the processor module;
the display module sends the running state data to the processor module and receives the video image and the processing information data sent by the processor module;
the access control module receives an access control instruction sent by the processor module and sends state data of an external access control system to the processor module;
the storage module receives the video image and the processing information data sent by the processor module and sends the storage state data and the preset processing flow data to the processor module;
the communication module receives the video image and the processing information data sent by the processor module, and sends the face data, the entrance guard control instruction data and the parameter configuration data sent by the remote server to the processor module.
Preferably, the image acquisition module contains infrared camera, cloud platform module and stop device, wherein:
the infrared camera is connected with the holder module, receives the position adjusting instruction sent by the processor module and sends the position adjusting instruction to the holder module, the holder module receives the position adjusting instruction to adjust the position and feeds back position adjusting state data to the infrared camera, and the infrared camera sends the position adjusting state data to the processor module; the limiting devices are arranged at two ends of the stroke of the cradle head module and used for limiting the stroke of the cradle head module, and the position of the cradle head module can be adjusted only within the range of the limiting devices.
Preferably, the sensor module is a human body proximity sensor.
Preferably, the processor module comprises a central processing unit and an AI intelligent module, the central processing unit sends an analysis instruction to the AI intelligent module, simultaneously, a video acquisition instruction is sent to the image acquisition module, an audio acquisition instruction is sent to the voice module, the AI intelligent module receives an analysis instruction sent by the central processing unit, and meanwhile, receiving the real-time video image collected by the image collection module and the audio data collected by the voice module, carrying out characteristic data detection and identification on the real-time video image by the AI intelligent module according to a preset intelligent analysis rule, sending identification result data to the central processing unit, carrying out voiceprint analysis and identification on the audio data by the AI intelligent module, sending the identification result data to the central processing unit, receiving the identification result data by the central processing unit, and acquiring different preset processing flow data stored by the storage module according to the content contained in the identification result data.
Preferably, the communication module adopts a network RJ45 interface, a 5G data transmission module and a WIFI module, and respectively receives and transmits data through a network cable, a 5G transmission network and a WIFI transmission network.
The invention also provides an automatic AI regulation intelligent access control detection method, which comprises the following steps:
s1: the sensor module detects whether a human body approaches in real time;
s2: if the human body is detected to approach, the sensor module sends human body approach detection data to the processor module, the processor module sends a video acquisition instruction to the image acquisition module after receiving the human body approach detection data, the image acquisition module sends acquired real-time video images to the processor module, and the step S3 is executed, if the human body approach is not detected, the sensor module sends no human body approach detection data to the processor module, and the step S1 is continuously executed;
s3: the processor module analyzes the received real-time video image, judges whether complete face data exists in the real-time video image, executes the step S5 if the complete face data exists, executes the step S4 if the complete face data exists but is incomplete, and sends prompt information to the display module if no face data exists, and returns to execute the step S1;
s4: the processor module judges the position of the face in the real-time video image, sends a position adjusting instruction to the image acquisition module according to the position information, and adjusts the position of the image acquisition module;
s5: the processor module compares the collected face data with face data of an authorized face library in a remote server transmitted by the communication module, if the comparison and verification are successful, the step S6 is executed, if the comparison and verification are failed, the processor module sends a playing control instruction and voice audio data to the voice module, sends prompt information to the display module, stores the processing information and video images of the access control detection process to the storage module, and ends the access control detection;
s6: the processor module sends an audio acquisition instruction, a play control instruction and play content data to the voice module, and sends prompt information for confirming opening of the door to the display module, the voice module starts audio data acquisition after receiving the instruction, the voice module packages the acquired audio data and sends the packaged audio data to the processor module after confirming the acquisition of the audio data, the processor module performs voiceprint analysis and identification on the received audio data to obtain audio content data, if the audio content data contains confirmation information, the processor module sends an entrance guard control instruction to the entrance guard control module, and simultaneously sends the play control instruction and the play content data to the voice module, sends prompt information to the display module, then stores the processing information and video images of the entrance guard detection process to the storage module, finishes the detection, and if the audio content data does not contain the confirmation opening information, the processor module sends a play control instruction and voice audio data to the voice module, sends prompt information to the display module, stores the processing information and the video image of the access control detection process to the storage module, and ends the access control detection.
Preferably, the step S3 includes the following steps:
s31: the processor module extracts a plurality of video key frames in a preset time interval from the real-time video image;
s32: extracting face information in the plurality of video key frames, if no face information exists, ending the comparison operation, sending prompt information to a display module, executing step S1, and if face information exists, combining the plurality of video key frames into a single-frame image;
s33: extracting the face key point data of the single-frame image, wherein the data comprises position coordinate information of the face key point in the video image;
s34: comparing the confirmed face key point data with preset face key points, if the extracted face key points are complete, the face data is complete face data, ending the comparison operation, and executing the step S5, otherwise executing the step S35;
s35: judging whether the key points of the human face on the y axis of the coordinate axis in the video image are complete, if so, sending a prompting message of the left-right translation of the personnel to a display module, returning to execute the steps S31-S34, and otherwise, executing the step S36;
s36: and judging specific face key points missing on a coordinate axis y axis in the video image, acquiring the positions of the faces in the video image according to the positions of the remaining face key points, finishing the comparison operation, and executing the step S4.
Preferably, the step S4 includes the steps of:
s41: the processor module acquires the position of the human face in the video image obtained in the step S3;
s42: if the face position is in the lower half part of the video image, further judging whether a face key point at the bottommost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, executing step S5, if the face position is in the upper half part of the video image, further judging whether a face key point at the topmost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, and executing step S5;
and S43, sending a position adjusting instruction to the image acquisition module.
Preferably, the step S42 includes the steps of:
s421: the processor module acquires position coordinates of key points of the human face;
s422: selecting one face key point, and calculating the distance between the face key point and other face key points;
s423: selecting a preset face key point, and performing position matching of the key point to obtain a position coordinate of a complete key point corresponding to the current face key point in a video picture;
s434: the processor module acquires the current visual angle position of the image acquisition module, and calculates the rotation angle of the image acquisition module from the current position to the missing human face key point position according to the y-axis coordinate in the missing human face key point coordinate axis and the current visual angle position of the image acquisition module.
Preferably, the number of the face key points is 5.
The invention has the following beneficial effects: the invention independently develops an automatic adjustment AI intelligent access control system and an access control detection method, automatically adjusts the height of an image acquisition module through real-time video picture face detection, solves the problem that people with different heights cannot be identified or are not accurately identified during biological identification verification, and simultaneously authorizes door opening through face comparison, thereby improving the identification accuracy and the accuracy of access control.
Drawings
FIG. 1 is an overall block diagram of an automatic AI regulation intelligent access control system provided by the present invention;
fig. 2 is a flowchart of an automatic AI adjustment intelligent access control detection method provided by the present invention.
Detailed Description
In order to make the technical solutions of the present invention more clear and definite, the present invention is further described in detail below with reference to the embodiments and the drawings, it should be noted that the embodiments and features of the embodiments of the present application can be combined with each other without conflict.
Referring to fig. 1, fig. 1 is a diagram of an automatic AI (Artificial Intelligence) intelligent access control system provided in this embodiment, where the system includes a processor module 100, a display module 101, an image acquisition module 102, a voice module 103, a sensor module 104, a storage module 105, a communication module 106, and an access control module 107, where the processor module 100 is respectively connected to the display module 101, the image acquisition module 102, the sensor module 104, the voice module 103, the storage module 105, the access control module 107, and the communication module 106;
the sensor module 104 sends the human body proximity detection data detected in real time to the processor module 100, the processor module 100 receives the data and analyzes and processes the data, when the detection data containing the human body proximity appears in the received data, the processor module 100 sends a video acquisition instruction to the image acquisition module 102, the image acquisition module 102 sends the acquired real-time video image to the processor module 100 after receiving the video acquisition instruction, the processor module 100 receives the real-time video image sent by the image acquisition module 102 and analyzes the real-time video image according to a preset intelligent analysis rule, the processor module 100 sends a position adjustment instruction to the image acquisition module 102 according to the analysis result, simultaneously sends a play control instruction and play content data to the voice module 103 and sends prompt information to the display module 101, and the image acquisition module 102 receives the position adjustment instruction sent by the processor module 100 for position adjustment, after the adjustment is completed, the image acquisition module 102 sends the acquired real-time video image to the processor module 100, the processor module 100 analyzes the received real-time video image according to a preset intelligent analysis rule, the processor module 100 sends a play control command, play content data and an audio acquisition command to the voice module 103 according to the analysis result and sends prompt information to the display module 101, the processor module 100 receives the audio data acquired by the voice module 103 and analyzes the data according to the preset intelligent analysis rule, the processor module 100 sends an entrance guard control command to the entrance guard control module 107 according to the analysis result and sends the play control command and the play content data to the voice module 103 at the same time and sends prompt information to the display module 101, and the processor module 100 finally sends the processing information and the real-time video data to the storage module 105 for storage, and meanwhile, the processing information and the video image are sent to a remote server through the communication module 106.
Further, the processor module 100 comprises a central processing unit, an AI intelligent module, the central processing unit sends an analysis command to the AI intelligent module, and sends a video acquisition command to the image acquisition module 102, and sends an audio acquisition command to the voice module 103, the AI intelligent module receives the analysis command sent by the central processing unit, and starts to receive the real-time video image acquired by the image acquisition module 102 and the audio data acquired by the voice module 103, the AI intelligent module detects and identifies the feature data of the real-time video image according to the preset intelligent analysis rule, and sends the identification result data to the central processing unit, the AI intelligent module further performs voiceprint analysis and identification on the audio data, and then sends the identification result data to the central processing unit, the central processing unit receives the identification result data, and acquires different preset processing flow data stored in the storage module 105 according to the content included in the identification result data, then, according to the processing flow, the central processing unit sends different control instructions and data to the display module 101, the access control module 107, the voice module 103, the storage module 105 and the communication module 106; the AI intelligent module adopts a MeiG intelligent module, comprises a high-performance and low-power consumption algorithm chip, supports the functions of face detection, face recognition, facial expression analysis, object detection, recognition, license plate recognition, voiceprint recognition and the like, and a central processing unit adopts a domestic chip and an operating system of the central processing unit adopts Linux4.9.
Further, the display module 101 receives the video image and the processing information data sent by the processor module 100, and sends the running state data to the processor module 100, and the display module 101 adopts 5-inch 720 x 1280 touch display.
Further, the image acquisition module 102 sends the acquired real-time video image to the processor module 100 and receives a position adjustment command and a video acquisition command sent by the processor module 100, the image acquisition module 102 comprises an infrared camera and a pan-tilt module, the infrared camera is connected with the pan-tilt module, the infrared camera receives the pan-tilt control command sent by the processor module 100 and sends the pan-tilt control command to the pan-tilt module, the pan-tilt module is driven by a vertical motor in the vertical direction, the pan-tilt module decodes the received pan-tilt control command and converts the decoded command into a control signal for controlling the motor to operate, the vertical motor in the pan-tilt module is driven to perform corresponding actions according to the control signal, a limiting device is added at two ends of a vertical rotating stroke of the pan-tilt module, the pan-tilt module is controlled to perform vertical adjustment within a specified stroke range, and the infrared, connected to the processor module 100 via USB and onboard data channels.
Further, the voice module 103 sends collected audio data to the processor module 100 and receives an audio collection instruction, a play control instruction and play content data sent by the processor module 100, the voice module 103 includes a sound pickup device and an audio play device, the sound pickup device is connected with the voice recognition device and sends the collected audio data to the processor module 100, the processor module 100 sends the play control instruction and the play content data to the audio play device, and the audio play device receives the audio data sent by the processor module 100.
Further, the sensor module 104 sends the human body proximity detection data to the processor module 100 in real time, and receives the parameter setting instruction sent by the processor module 100, and the sensor module 104 is a human body proximity sensor.
Further, the storage module 105 receives the video image and the processing information data sent by the processor module 100, and sends the storage state data and the preset processing flow data to the processor module 100;
further, communication module 106 receives the video image and the processing information data that processor module 100 sent, and the face data that will send the far-end server, entrance guard control instruction data and parameter configuration data send to processor module 100, communication module 106 adopts network RJ45 interface, 5G data transmission module and WIFI module, respectively through the net twine, data are received and dispatched to 5G transmission network and WIFI transmission network, 5G data transmission module is MeiG 5G data transmission module, net twine transmission efficiency is 100Mbps, 5G transmission rate is 300Mbps, the WIFI transmission accords with 2.4G 802.11 b/G/n.
Further, the access control module 107 receives an access control instruction sent by the processor module 100, and sends the state data of the external access control system to the processor module 100.
Referring to fig. 2, fig. 2 is a diagram illustrating an automatic AI adjustment intelligent access control detection method provided by the present invention, which includes the following steps:
s1: the sensor module 104 detects whether a human body approaches in real time, and in the detection process, only if human body approach signals exist in a preset acquisition time interval, the human body approaches, and meanwhile, the human body approach signals are switching value signals;
s2: if a human body approaches, the sensor module 104 sends human body approach detection data to the processor module 100, the processor module 100 sends a video acquisition instruction to the image acquisition module 102 according to the human body approach detection data, the image acquisition module 102 sends acquired real-time video images to the processor module 100, step S3 is executed, if no human body approaches, the sensor module 104 sends no human body approach detection data to the processor module 100, and step S1 is continuously executed;
s3: the processor module 100 analyzes the received real-time video image, determines whether complete face data exists in the real-time video image, if the complete face data exists, executes step S5, if the face data exists but is incomplete, executes step S4, and if no face data exists, sends a prompt message to the display module 101, and returns to execute step S1, which specifically includes the following steps:
s31: the processor module 100 extracts a plurality of video key frames within a preset time interval from the real-time video image, wherein the preset time interval is determined according to the requirement on real-time performance and the buffer size, and is set to be 1 second;
s32: extracting face information in the plurality of video key frames, if no face information exists, ending the comparison operation, sending prompt information to the display module 101, executing the step S1, and if face information exists, combining the plurality of video key frames into a single-frame image;
s33: extracting face key point data of the single-frame image, wherein the data comprises position coordinate information of the face key points in a video picture, and the number of the face key points is 5;
s34: comparing the confirmed face key point data with preset face key points, if the extracted face key points are complete, the face data is complete face data, ending the comparison operation, and executing the step S5, otherwise executing the step S35;
s35: judging whether the key points of the human face on the y axis of the coordinate axis of the video picture are complete, if so, sending a prompting message of left-right translation of the personnel to the display module 101, returning to execute the steps S31-S34, and otherwise, executing the step S36;
s36: and judging specific face key points missing on the y axis of the coordinate axis of the video picture, acquiring the positions of the faces in the video picture according to the positions of the remaining face key points, finishing the comparison operation, and executing the step S4.
S4: the processor module 100 determines the position of the face in the video image in the real-time video image, sends a position adjustment instruction to the image acquisition module 102 according to the position information, and adjusts the position of the image acquisition module 102, specifically including the following steps:
s41: the processor module 100 acquires the position of the face in the video image obtained in the step S3;
s42: if the face position is in the lower half part of the video image, further judging whether a face key point at the bottommost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, executing step S5, if the face position is in the upper half part of the video image, further judging whether a face key point at the topmost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, and executing step S5; the method specifically comprises the following steps:
s421: the processor 100 module obtains the position coordinates of the key points of the human face;
s422: selecting one face key point, and calculating the distance between the face key point and other face key points;
s423: selecting a preset face key point, and performing position matching of the key point to obtain a position coordinate of a complete key point corresponding to the current face key point in a video picture;
s424: the processor module 100 acquires the current view position of the image acquisition module 102, and calculates the rotation angle of the image acquisition module 102 from the current position to the missing face key point position according to the y-axis coordinate in the missing face key point coordinate axis and the current view position of the image acquisition module 102.
And S43, sending a position adjustment instruction to the image acquisition module 102.
S5: the processor module 100 compares and verifies the acquired face data with the face data of the authorized face library in the remote server transmitted through the communication module 106, if the comparison and verification are successful, step S6 is executed, if the comparison and verification are failed, the processor module 100 sends a play control instruction and voice audio data to the voice module 103, sends prompt information to the display module 101, stores the processing information and video images of the access control detection process to the storage module 105, and ends the access control detection;
s6: the processor module 100 sends an audio acquisition instruction, a play control instruction and play content data to the voice module, and sends a prompt message for confirming opening of the door to the display module 101, the voice module 103 starts audio data acquisition after receiving the instruction, after confirming that the audio data is acquired, the voice module 103 sends the acquired audio data to the processor module 100, the processor module 100 performs voiceprint analysis and identification on the received audio data to obtain audio content data, if the audio content data contains the confirmation information, the processor module 100 sends an access control instruction to the access control module 107, and simultaneously sends the play control instruction and the play content data to the voice module 103, and sends the prompt message to the display module 101, and then stores the processing information and the video image of the access detection process to the storage module 105, finishes the access detection, and if the audio content data does not contain the confirmation opening information, the processor module 100 sends a play control instruction and voice audio data to the voice module 103, sends a prompt message to the display module 101, stores the processing information and the video image of the access control detection process to the storage module 105, and ends the access control detection.
Further, the processor module 100 periodically transmits the data of the storage module 105 to a remote server via the communication module 106.
In the description above, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore should not be construed as limiting the scope of the present invention.
In conclusion, although the present invention has been described with reference to the preferred embodiments, it should be noted that, although various changes and modifications may be made by those skilled in the art, they should be included in the scope of the present invention unless they depart from the scope of the present invention.
Claims (10)
1. The utility model provides an automatic adjust AI intelligent access control system which characterized in that contains processor module, display module, image acquisition module, voice module, sensor module, storage module, communication module, access control module, wherein:
the processor module is respectively connected with the display module, the image acquisition module, the sensor module, the voice module, the storage module, the entrance guard control module and the communication module;
the image acquisition module sends acquired real-time video images to the processor module and receives position adjustment instructions and video acquisition instructions sent by the processor module;
the sensor module sends the human body approach detection data to the processor module in real time and receives a parameter configuration instruction sent by the processor module;
the voice module sends the collected audio data to the processor module and receives the audio collection instruction, the playing control instruction and the playing content data sent by the processor module;
the display module sends the running state data to the processor module and receives the video image and the processing information data sent by the processor module;
the access control module receives an access control instruction sent by the processor module and sends state data of an external access control system to the processor module;
the storage module receives the video image and the processing information data sent by the processor module and sends the storage state data and the preset processing flow data to the processor module;
the communication module receives the video image and the processing information data sent by the processor module, and sends the face data, the entrance guard control instruction data and the parameter configuration data sent by the remote server to the processor module.
2. The AI intelligent access control system of claim 1, wherein the image acquisition module comprises an infrared camera, a pan-tilt module and a position limiting device, wherein:
the infrared camera is connected with the holder module, receives the position adjusting instruction sent by the processor module and sends the position adjusting instruction to the holder module, the holder module receives the position adjusting instruction to adjust the position and feeds back position adjusting state data to the infrared camera, and the infrared camera sends the position adjusting state data to the processor module;
and the limiting devices are arranged at two ends of the vertical stroke of the holder module and are used for limiting the stroke of the holder module.
3. The AI smart gate inhibition system according to claim 1, wherein said sensor module is a human proximity sensor.
4. The AI intelligent gate inhibition system according to claim 1, wherein the processor module comprises a central processing unit and an AI intelligent module, the central processing unit sends an analysis command to the AI intelligent module, and sends a video acquisition command to the image acquisition module, and sends an audio acquisition command to the voice module, the AI intelligent module receives the analysis command sent by the central processing unit, and starts to receive the real-time video image acquired by the image acquisition module and the audio data acquired by the voice module, the AI intelligent module detects and identifies the characteristic data of the real-time video image according to the preset intelligent analysis rule, and sends the identification result data to the central processing unit, the AI intelligent module further performs voiceprint analysis and identification on the audio data, and sends the identification result data to the central processing unit, and the central processing unit receives the identification result data, and different preset processing flow data stored in the storage module are obtained according to the preset processing flow data.
5. The automatic adjust AI intelligent access control system of claim 1, wherein the communication module employs a network RJ45 interface, a 5G data transmission module and a WIFI module, and respectively transmits and receives data through a network cable, a 5G transmission network and a WIFI transmission network.
6. An automatic AI regulation intelligent access control detection method is characterized by comprising the following steps:
s1: the sensor module detects whether a human body approaches in real time;
s2: if the human body is detected to approach, the sensor module sends human body approach detection data to the processor module, the processor module sends a video acquisition instruction to the image acquisition module after receiving the human body approach detection data, the image acquisition module sends acquired real-time video images to the processor module, and the step S3 is executed, if the human body approach is not detected, the sensor module sends no human body approach detection data to the processor module, and the step S1 is continuously executed;
s3: the processor module analyzes the received real-time video image, judges whether complete face data exists in the real-time video image, executes the step S5 if the complete face data exists, executes the step S4 if the complete face data exists but is incomplete, and sends prompt information to the display module if no face data exists, and returns to execute the step S1;
s4: the processor module judges the position of the face in the real-time video image, sends a position adjusting instruction to the image acquisition module according to the position information, and adjusts the position of the image acquisition module;
s5: the processor module compares the collected face data with face data of an authorized face library in a remote server transmitted by the communication module, if the comparison and verification are successful, the step S6 is executed, if the comparison and verification are failed, the processor module sends a playing control instruction and voice audio data to the voice module, sends prompt information to the display module, stores the processing information and video images of the access control detection process to the storage module, and ends the access control detection;
s6: the processor module sends an audio acquisition command, a play control command and play content data to the voice module, and sends a prompt message for confirming opening of the door to the display module, the voice module starts audio data acquisition after receiving the command, the voice module packages the acquired audio data and sends the audio data to the processor module after confirming the acquisition of the audio data, the processor module performs voiceprint analysis and identification on the received audio data to obtain audio content data, if the audio content data contains confirmation information, the processor module sends an entrance guard control command to the entrance guard control module to confirm opening of the door, and simultaneously sends the play control command and the play content data to the voice module, sends the prompt message to the display module, then stores the processing information and video images of the entrance guard detection process to the storage module, finishes the entrance guard detection, and if the audio content data does not contain the information for confirming opening of the door, the processor module sends a play control instruction and voice audio data to the voice module, sends prompt information to the display module, stores the processing information and the video image of the access control detection process to the storage module, and ends the access control detection.
7. The AI-based intelligent gate inhibition detection method according to claim 6, wherein the step S3 comprises the following steps:
s31: the processor module extracts a plurality of video key frames in a preset time interval from the real-time video image;
s32: extracting face information in the plurality of video key frames, if no face information exists, ending the comparison operation, sending prompt information to a display module, executing step S1, and if face information exists, combining the plurality of video key frames into a single-frame image;
s33: extracting the face key point data of the single-frame image, wherein the data comprises position coordinate information of the face key point in the video image;
s34: comparing the confirmed face key point data with preset face key points, if the extracted face key points are complete, the face data is complete face data, ending the comparison operation, and executing the step S5, otherwise executing the step S35;
s35: judging whether the key points of the human face on the y axis of the coordinate axis in the video image are complete, if so, sending a prompting message of the left-right translation of the personnel to a display module, returning to execute the steps S31-S34, and otherwise, executing the step S36;
s36: and judging specific face key points missing on a coordinate axis y axis in the video image, acquiring the positions of the faces in the video image according to the positions of the remaining face key points, finishing the comparison operation, and executing the step S4.
8. The AI intelligent gate inhibition detection method according to claim 7, wherein the step S4 comprises the following steps:
s41: the processor module acquires the position of the human face in the video image obtained in the step S3;
s42: if the face position is in the lower half part of the video image, further judging whether a face key point at the bottommost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, executing step S5, if the face position is in the upper half part of the video image, further judging whether a face key point at the topmost part in the y-axis direction in the coordinate axis is missing, if so, calculating the rotation angle of the image acquisition module, executing step S43, if not, ending the adjustment operation, and executing step S5;
and S43, sending a position adjusting instruction to the image acquisition module.
9. The AI intelligent access control detection method according to claim 8, wherein the step S42 includes the following steps:
s421: the processor module acquires position coordinates of key points of the human face;
s422: selecting one face key point, and calculating the distance between the face key point and other face key points;
s423: selecting preset face key points, and performing position matching of the key points to obtain position coordinates of complete key points corresponding to the current face key points in the video image;
s434: the processor module acquires the current visual angle position of the image acquisition module, and calculates the rotation angle of the image acquisition module from the current position to the missing human face key point position according to the y-axis coordinate in the missing human face key point coordinate axis and the current visual angle position of the image acquisition module.
10. The automatic adjustment AI intelligent gate inhibition detection method of claim 7, wherein the number of face key points is 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110047184.7A CN112907803B (en) | 2021-01-14 | 2021-01-14 | Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110047184.7A CN112907803B (en) | 2021-01-14 | 2021-01-14 | Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112907803A true CN112907803A (en) | 2021-06-04 |
| CN112907803B CN112907803B (en) | 2021-09-28 |
Family
ID=76114074
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110047184.7A Active CN112907803B (en) | 2021-01-14 | 2021-01-14 | Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112907803B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114882630A (en) * | 2022-04-27 | 2022-08-09 | 广东职业技术学院 | Internet of things access control system and control method thereof |
| CN117011964A (en) * | 2023-08-02 | 2023-11-07 | 广州市图威信息技术服务有限公司 | Access control system and access control monitoring method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140010407A1 (en) * | 2012-07-09 | 2014-01-09 | Microsoft Corporation | Image-based localization |
| CN107009962A (en) * | 2017-02-23 | 2017-08-04 | 杭州电子科技大学 | A kind of panorama observation procedure based on gesture recognition |
| CN107146305A (en) * | 2017-05-02 | 2017-09-08 | 上海灵至科技有限公司 | Unlocking method and door lock based on recognition of face |
| CN107292999A (en) * | 2016-03-30 | 2017-10-24 | 江苏星蓝宇信息技术有限公司 | A kind of environmental suitability face recognition door control system |
| CN109447006A (en) * | 2018-11-01 | 2019-03-08 | 北京旷视科技有限公司 | Image processing method, device, equipment and storage medium |
| CN110175518A (en) * | 2019-04-19 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Camera angle method of adjustment, device, equipment and the system of photographic device |
| CN110276308A (en) * | 2019-06-25 | 2019-09-24 | 上海商汤智能科技有限公司 | Image processing method and device |
| CN112001360A (en) * | 2020-09-09 | 2020-11-27 | 深圳中神电子科技有限公司 | Face recognition monitoring system based on intelligent adjustment |
| CN212160784U (en) * | 2019-12-31 | 2020-12-15 | 深圳阜时科技有限公司 | Identity recognition device and entrance guard equipment |
-
2021
- 2021-01-14 CN CN202110047184.7A patent/CN112907803B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140010407A1 (en) * | 2012-07-09 | 2014-01-09 | Microsoft Corporation | Image-based localization |
| CN107292999A (en) * | 2016-03-30 | 2017-10-24 | 江苏星蓝宇信息技术有限公司 | A kind of environmental suitability face recognition door control system |
| CN107009962A (en) * | 2017-02-23 | 2017-08-04 | 杭州电子科技大学 | A kind of panorama observation procedure based on gesture recognition |
| CN107146305A (en) * | 2017-05-02 | 2017-09-08 | 上海灵至科技有限公司 | Unlocking method and door lock based on recognition of face |
| CN109447006A (en) * | 2018-11-01 | 2019-03-08 | 北京旷视科技有限公司 | Image processing method, device, equipment and storage medium |
| CN110175518A (en) * | 2019-04-19 | 2019-08-27 | 阿里巴巴集团控股有限公司 | Camera angle method of adjustment, device, equipment and the system of photographic device |
| CN110276308A (en) * | 2019-06-25 | 2019-09-24 | 上海商汤智能科技有限公司 | Image processing method and device |
| CN212160784U (en) * | 2019-12-31 | 2020-12-15 | 深圳阜时科技有限公司 | Identity recognition device and entrance guard equipment |
| CN112001360A (en) * | 2020-09-09 | 2020-11-27 | 深圳中神电子科技有限公司 | Face recognition monitoring system based on intelligent adjustment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114882630A (en) * | 2022-04-27 | 2022-08-09 | 广东职业技术学院 | Internet of things access control system and control method thereof |
| CN117011964A (en) * | 2023-08-02 | 2023-11-07 | 广州市图威信息技术服务有限公司 | Access control system and access control monitoring method |
| CN117011964B (en) * | 2023-08-02 | 2024-02-13 | 广州市图威信息技术服务有限公司 | Access control system and access control monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112907803B (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7454041B2 (en) | Person recognition apparatus | |
| CN112907803B (en) | Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method | |
| WO2016112630A1 (en) | Image recognition system and method | |
| CN105700363A (en) | Method and system for waking up smart home equipment voice control device | |
| US11776308B2 (en) | Frictionless access control system embodying satellite cameras for facial recognition | |
| US11064167B2 (en) | Input functionality for audio/video recording and communication doorbells | |
| CN106926252A (en) | A kind of hotel's intelligent robot method of servicing | |
| US11539922B2 (en) | Point-to-point visual communications in a security monitoring system | |
| CN113003330A (en) | Intelligent elevator control method and system based on face recognition | |
| CN110087131A (en) | TV control method and main control terminal in television system | |
| CN111429638B (en) | Access control method based on voice recognition and face recognition | |
| CN111223219A (en) | Identity recognition method and storage medium | |
| CN112565396B (en) | Information pushing method and device, robot and storage medium | |
| JP2005084824A (en) | Face image collation apparatus and face image collation method and passage controller | |
| CN212160784U (en) | Identity recognition device and entrance guard equipment | |
| CN111063085A (en) | Identity recognition device and entrance guard equipment | |
| JP2005199373A (en) | Communication device and communication method | |
| CN208873201U (en) | A kind of wireless access control system | |
| KR102249123B1 (en) | Eyelid detection device, Display device auto-off system for silver generation, and control method thereof | |
| CN113012325A (en) | Control method, system, terminal and storage medium of ultrasonic access control | |
| CN207373180U (en) | A kind of hotel's intelligent robot service system | |
| CN113192251B (en) | Method for realizing identity recognition of multiple biological characteristics capable of being configured on line | |
| CN113269916B (en) | Guest prejudging analysis method and system based on face recognition | |
| CN203350982U (en) | Video-based gender identification warning device | |
| CN210038916U (en) | Access control terminal and system with face recognition function |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |