BIM (Building Information Modeling)-based intelligent capture system for dangerous goods in defense area
Through the BIM-based intelligent capture system for dangerous items in the zone, combined with three-dimensional model and face recognition algorithm, the problem of existing systems ignoring foreign personnel and unexpected situations is solved, and more efficient security monitoring and management is achieved, which enhances data accuracy and Security.
Patent Information
- Application Number
- CN202411068471.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing intelligent dangerous goods capture system in the defense zone mainly focuses on surface management, neglecting outsiders and accidental conditions, resulting in the loss of dangerous goods and safety risks, causing huge losses.
Adopt a BIM-based intelligent capture system for dangerous items in the zone, combining monitoring module, central processing unit, data output module, BIM modeling module, information import module, data analysis module and risk warning module, and constructing three-dimensional model and facial recognition algorithms. Monitor and manage dangerous items and personnel in real time, provide holographic image display and real-time early warning.
It improves the defense and data accuracy of security equipment, enhances the identification and management of dangerous items and personnel, reduces changes in maps and actual scenarios, reduces operation and maintenance costs, and achieves more efficient safety monitoring and management.
Smart Images

Figure CN119091374A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of security technology, and in particular to a BIM-based intelligent capture system for dangerous objects in a defense zone. Background Art
[0002] BIM is the abbreviation of Building Information Modeling, which is generally translated as Building Information Modeling. Building Information Modeling (BIM) uses the relevant information data of the construction project as the basis of the model to establish the building model. It simulates the real information of the building through digital information simulation. It has the remarkable characteristics of visualization, coordination, simulation, optimization and map-ability. BIM (Building Information Modeling) is not a simple integration of digital information, but an application of digital information, and can be used for digital methods of design, construction and management. This method supports the integrated management environment of construction projects, which can significantly improve the efficiency and reduce risks of construction projects throughout their entire process.
[0003] Through digital means, all devices in the video surveillance, access control system and perimeter alarm system are unified into a network, with 3D fusion rendering as the technical support and 3D information platform as the display basis, providing map display and operation at the entire park level, intuitive interactive experience and performance, integrating various subsystems such as video surveillance, access control system, and perimeter alarm system into a holographic picture. Unified monitoring, early warning, management and space planning provide standardized management processes, and the scene operation and maintenance process has a basis to rely on.
[0004] Cloud Monitoring is the abbreviation of monitoring systems based on cloud computing. Its core is a cloud platform with multimedia data centers as its main components. Its main advantages are: strong storage capacity and high resource utilization, and it can improve the effectiveness of data based on intelligent analysis and data mining, improve the practical value of the monitoring system, and can fully combine the large amount of information interaction and frequent signaling scheduling of multimedia applications for optimized design and improved processing performance. In addition, cloud monitoring can be deeply integrated with the network, making it easy to efficiently, concisely and reliably obtain, share and transmit various multimedia information such as audio and video streams, pictures and message events through standard IP networks, realize end-to-end efficient interactive transmission of multimedia information, simplify the overall architecture, and improve system reliability.
[0005] However, the current intelligent capture system for dangerous goods in defense zones only pays attention to the surface of dangerous goods management, ignoring the loss of dangerous goods caused by outsiders or other unexpected situations, causing huge losses to overall safety and property. Therefore, we propose a BIM-based intelligent capture system for dangerous goods in defense zones. Summary of the invention
[0006] In order to solve the above technical problems, the present invention provides a BIM-based intelligent capture system for dangerous goods in defense areas, which is achieved by the following specific technical means:
[0007] A BIM-based defense zone dangerous goods intelligent capture system includes a monitoring module, a central processing unit, a data output module, a BIM modeling module, an information import module, a data receiving module, a data analysis module and a risk warning module. The monitoring module is electrically connected to the central processing unit through an information optical cable. The monitoring module is used to confirm the specific location and individual characteristics of personnel and dangerous goods entering and leaving the defense zone. The central processing unit is connected to the data output module via an external storage device. The central processing unit is used to process instructions from the external connection module and issue instructions to the lower-level connection module. The data output module is used to import correct internal information. The BIM modeling module is electrically connected to the central processing unit. The BIM modeling module is used to establish a three-dimensional model and display the specific features through a display. The information import module is electrically connected to the central processing unit through the BIM modeling module. The information import module imports external information. The central processing unit is electrically connected to the data receiving module through an information optical fiber. The data analysis module is electrically connected to the data receiving module. The data analysis module processes the received information through a geometric feature face recognition algorithm. The risk warning module is electrically connected to the data analysis module through an information processor. The risk warning module is used to handle external emergencies and display the identity of the prisoner and the specific circumstances of the lost dangerous goods to the staff through the screen.
[0008] Preferably, the information import module is electrically connected to an external network module, and the external network module divides the information of the dangerous goods into appearance characteristics and specific characteristics, and the appearance characteristics include the length and width of the dangerous goods, the length is L, and the width is d.
[0009] Preferably, after reading in the data, the information import module first determines whether it meets the calculation requirements. If not, it returns to the I / O module to read new data. If it meets the requirements, a comparison operation will be performed. If the calculation result is equal to the setting, it will be saved and transmitted to the central processing unit for further processing. If the setting parameters are not within the range, it will be calculated according to the model, and the difference compensation parameters will be output to the central processing unit. The operation logic function of the central processing unit is used to control the operation of the actuator, and finally it returns to the I / O module to read the latest data, thereby obtaining the specific characteristics of the defense zone and dangerous goods.
[0010] Preferably, the defense zone information import module is electrically connected to the central processing unit, and the defense zone information import module imports the map information of the defense zone into the interior, and selects the aisle path, and sets the weight value of the path unit located on the ground to 0 in the path selection. For each path unit, in addition to the path distance value information, it also includes an identification value indicating whether it is a horizontal ground or a vertical wall, where f represents the horizontal ground and w represents the vertical wall, and the specific data of the site is displayed.
[0011] Preferably, the image acquisition module is electrically connected to the risk warning module, and the image acquisition module is connected to the central processing module; the risk warning module collects face recognition data through the image acquisition module, and issues an alarm when dangerous goods are transported or an audible and visual alarm when face recognition matching is unsuccessful.
[0012] Preferably, the information import module improves the speed of information and data exchange and meets the needs of real-time monitoring; in the early stage of monitoring, the three-dimensional model of each device in the defense zone is completed through the BIM model, and data analysis and abnormal situations are paid attention to through the data analysis module and the risk warning module, which effectively reduces the changes between the map and the actual scene, and cuts the established three-dimensional model to obtain a two-dimensional drawing, thereby improving the accuracy of the monitoring data and the degree of visual management.
[0013] Preferably, the monitoring module later realizes the three-dimensional chart output visualization of the defense zone implementation status through positioning monitoring cameras and the cloud monitoring platform layer. The operation of each LCU in the LCU layer can be monitored and warned in real time, and unexpected intelligent diagnosis can be made, which improves the monitoring level and saves operation and maintenance costs.
[0014] Preferably, the central processing unit realizes the panoramic visualization display of the communication scheduling screen through the NET Framework component, and realizes the development of the visualization system by using Visual Studio 2010, which provides a unified calling interface proxy service.
[0015] Preferably, the BIM modeling module uses a screen to display the three-dimensional building model in a holographic manner, generates and plays a virtual animation monitoring video, and during the monitoring process of the animation display, it synchronously displays the movement of objects and the flow of people. The video can be paused, replayed and fast-forwarded, and the staff can know the unexpected situations that need to be paid attention to at any time and the status of dangerous goods.
[0016] Preferably, the image acquisition module compares the acquisition geometric shape features of the eyes of the entering person with the standard geometric shape features of the eyes to obtain the feature matching results of the eyes, compares the acquisition geometric shape features of the mouth with the standard geometric shape features of the mouth to obtain the feature matching results of the mouth, compares the acquisition geometric shape features of the nose with the standard geometric shape features of the nose to obtain the feature matching results of the nose, and compares the feature matching results of the eyes, the feature matching results of the mouth, and the feature matching results of the nose with the thresholds respectively to obtain the face recognition matching results.
[0017] The present invention has the following beneficial effects:
[0018] This BIM-based intelligent capture system for dangerous goods in defense zones uses a 3D model building tool to automatically convert common model formats into standard formats that can be recognized by the rendering engine. It extracts features from public remote sensing images to automatically generate buildings and roads and store staff information, thereby making up for the lack of 3D visualization expression methods in traditional maps. At the same time, it uses face recognition algorithms to accurately identify strangers and the movement of dangerous goods in 3D scenes, thereby improving the deployment of security equipment and the accuracy of data. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 It is a schematic diagram of the overall process of the present invention;
[0020] Figure 2 It is a schematic diagram of the data simulation process of the present invention;
[0021] Figure 3 It is a schematic diagram of the data import process of the present invention. DETAILED DESCRIPTION
[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0023] See also Figure 1-3A BIM-based defense zone dangerous goods intelligent capture system includes a monitoring module, a central processing unit, a data output module, a BIM modeling module, an information import module, a data receiving module, a data analysis module and a risk warning module. The monitoring module is electrically connected to the central processing unit through an information optical cable. The monitoring module is used to confirm the specific location and individual characteristics of the personnel and dangerous goods entering and leaving the defense zone. The central processing unit is connected to the data output module by telecommunication through an external storage device. The central processing unit is used to process the instructions of the external connection module and issue instructions to the subordinate connection module. The data output module is used to import correct internal information. The BIM modeling module is electrically connected to the central processing unit. The BIM modeling module is used to establish a three-dimensional model and display specific features through a display. The information import module is electrically connected to the central processing unit through the BIM modeling module. The information import module imports external information. The central processing unit is electrically connected to the data receiving module through an information optical fiber. The data analysis module is electrically connected to the data receiving module. The data analysis module processes the received information through a geometric feature face recognition algorithm. The risk warning module is electrically connected to the data analysis module through the information processor.
[0024] See also Figure 1 , risk warning module, used to handle external emergencies, display the identity of the prisoner and the specific situation of the lost dangerous goods on the screen to the staff, the defense zone information import module is electrically connected to the central processor, the defense zone information import module imports the map information of the defense zone into the internal, and selects the aisle path, and sets the weight value of the path unit on the ground to 0 in the path selection. For each path unit, in addition to the path distance value information, it also contains an identification value indicating whether it is a horizontal ground or a vertical wall, where f represents the horizontal ground and w represents the vertical wall, and displays the specific data of the site. The central processor realizes the panoramic visualization of the communication scheduling screen through the NET Framework component, and uses Visual Studio 2010 to realize the development of the visualization system. The component provides a unified call interface proxy service. The BIM modeling module displays the three-dimensional building model through the screen for holographic imaging, generates and plays virtual animation monitoring videos, and in the monitoring process of the animation display, the movement of objects and the flow of people are displayed synchronously. The video can be paused, replayed and fast-forwarded, and the staff can know the unexpected situations and the status of dangerous goods that need to be paid attention to at any time.
[0025] See also Figure 2-3The information import module is electrically connected to the external network module. The external network module divides the information of dangerous goods into appearance features and specific features. The appearance features include the length and width of the dangerous goods, with the length being L and the width being d. After reading the data, the information import module first determines whether it meets the calculation requirements. If not, it returns to the I / O module to read new data. If it meets the requirements, a comparison operation will be performed. If the calculation result is equal to the setting, it will be saved and transmitted to the central processing unit for the next step of processing. If the setting parameters are not within the range, it will be calculated according to the model, and the difference compensation parameters will be output to the central processing unit. The operation logic function of the central processing unit is used to control the operation of the actuator. Finally, it returns to the I / O module to read the latest data, and then obtains the specific characteristics of the defense zone and the dangerous goods. The image acquisition module is electrically connected to the risk warning module, and the image acquisition module is connected to the central processing module; the risk warning module collects face recognition data through the image acquisition module, and sends an audible and visual alarm when the dangerous goods are transported or the face recognition match is unsuccessful. The information import module improves the speed of information and data exchange and meets the needs of real-time monitoring. In the early stage of monitoring, the three-dimensional model of each device in the defense zone is completed through the BIM model. Data analysis and attention are paid to abnormal situations through the data analysis module and the risk warning module, which effectively reduces the changes between the map and the actual scene, and cuts the established three-dimensional model to obtain a two-dimensional drawing, which improves the accuracy of the monitoring data and the degree of visual management. In the later stage of the monitoring module, the three-dimensional chart output visualization of the implementation of the defense zone is realized by positioning the monitoring camera and the cloud monitoring platform layer. The operation of each LCU in the LCU layer can be monitored and warned in real time, and unexpected intelligent diagnosis is made to improve the monitoring level and save operation and maintenance costs. The image acquisition module compares the acquisition geometric shape features of the eyes of the person entering the eye with the standard geometric shape features of the eyes to obtain the feature matching results of the eyes, compares the acquisition geometric shape features of the mouth with the standard geometric shape features of the mouth to obtain the feature matching results of the mouth, compares the acquisition geometric shape features of the nose with the standard geometric shape features of the nose to obtain the feature matching results of the nose, and compares the feature matching results of the eyes, the mouth and the nose with the threshold to obtain the face recognition matching results.
[0026] The BIM-based intelligent capture system for dangerous objects in defense areas of the present application comprises the following steps:
[0027] Step 1: The information import module inputs the patterns of the internal staff's eyes L1, mouth L2, and nose L3 into the central processor through the external network module;
[0028] Step 2: The information import module imports the overall map of the defense zone into the central processor through the defense zone information import module, and the overall map area of the defense zone is set to A;
[0029] Step 3: The central processor imports the map information of the defense zone into the internal system and selects the aisle path. In the path selection, the weight value of the path unit located on the ground is set to 0. For each path unit, in addition to the path distance value information, it also contains an identification value indicating whether it is a horizontal ground or a vertical wall, where f represents the horizontal ground and w represents the vertical wall, and the specific data of the site is displayed.
[0030] Step 4: The central processor compares the built-in map and character information with the data collected by the monitoring module. First, it determines whether it meets the calculation requirements. If not, it returns to the I / O module to read new data. If it meets the requirements, a comparison operation will be performed. If the calculation result is equal to the setting, it will be saved and transmitted to the central processor for further processing. If the setting parameters are not within the range, it will be calculated according to the model, and the difference compensation parameters will be output to the central processor. The operation logic function of the central processor is used to control the operation of the actuator, and finally returns to the I / O module to read the latest data, thereby obtaining the specific characteristics of the defense area and dangerous goods.
[0031] Step 5: The positioning monitoring camera transmits the real-time situation to the monitoring module, and the monitoring module transmits the information to the central processing unit through the data output module.
[0032] Step 6: The CPU transmits the data to the data analysis module through the data receiving module to compare the data:
[0033] Step 2: The zone image is:
[0034] A(i,j)i∈[1,N]j∈[1,N]
[0035] Among them, the defense zone area image A is a grayscale image with N rows and N columns, and A(i, j) is the pixel in the i-th row and i-th column;
[0036] Step 1 The collected shape geometric features of the eye are:
[0037] L 1(a,b)a∈[1,M]b∈[1,M]
[0038] Wherein, M is the number of rows and columns of the feature matrix, the eye acquisition shape geometric feature L1 is a feature matrix with M rows and M columns, and L1(a, b) is the eigenvalue of the eye acquisition shape geometric feature in the ath row and the bth column;
[0039] The geometric features of the collected shape of the mouth in step 1 are:
[0040] L 2(c,d)c∈[1,M]d∈[1,M]
[0041] Wherein, M is the number of rows and columns of the feature matrix, the acquisition shape geometric feature of the mouth L 2 is the feature matrix of M rows and M columns, and L 2(c, d) is the eigenvalue of the acquisition shape geometric feature of the mouth in the cth row and dth column;
[0042] The collected shape geometric features of the nose in step 1 are:
[0043] L 3(e,f)e∈[1,M]f∈[1,M]
[0044] Wherein, M is the number of rows and columns of the feature matrix, the acquisition shape geometric feature of the nose L 3 is a feature matrix with M rows and M columns, and L 3(e, f) is the eigenvalue of the acquisition shape geometric feature of the nose in the e-th row and the f-th column;
[0045] The grayscale image manually imported in step 1 is:
[0046] B(i*,j*)i*∈[1,N]j*∈[1,N]
[0047] The grayscale image B manually imported in advance is a grayscale image with N rows and N columns, and B(i*, j*) is the pixel in the i*th row and the i*th column;
[0048] The standard geometric features of the eye shape in step 1 are:
[0049] L 4(a*, b*)a*∈[1,M]b*∈[1,M]
[0050] Wherein, M is the number of rows and columns of the feature matrix, the standard shape geometric feature of the eye L 4 is a feature matrix with M rows and M columns, and L 4(a*, b*) is the eigenvalue of the standard shape geometric feature of the eye in the a*th row and the b*th column;
[0051] The standard shape geometric features of the mouth in step 1 are:
[0052] L 5(c*,d*)c*∈[1,M]d*∈[1,M]
[0053] Wherein, M is the number of rows and columns of the feature matrix, the standard shape geometric feature of the mouth L 5 is the feature matrix of M rows and M columns, and L 5(c*, d*) is the eigenvalue of the c*th row and d*th column of the standard shape geometric feature of the mouth;
[0054] The standard shape geometric features of the nose in step 1 are:
[0055] L 6(e*, f*)e∈[1,M]f*∈[1,M]
[0056] Wherein, M is the number of rows and columns of the feature matrix, the standard shape geometric feature of the nose L 6 is a feature matrix with M rows and M columns, and L 6(e*, f*) is the eigenvalue of the standard shape geometric feature of the nose in the e*th row and the f*th column;
[0057] The feature matching result of the eye in step 3 is:
[0058] The number of consistent eigenvalues at the same position of the statistical eye acquisition geometric shape feature L1 and the eye standard geometric shape feature L4 matrix is X;
[0059] The feature matching result of the mouth in step 3 is:
[0060] The number of identical eigenvalues at the same position of the matrix of the acquisition geometry feature L 2 of the mouth and the standard geometry feature L 5 of the mouth is Y;
[0061] The feature matching result of the nose in step 3 is:
[0062] The number of consistent eigenvalues at the same position of the matrix of the collected geometric shape feature L 3 of the nose and the standard geometric shape feature L 6 of the nose is Z;
[0063] The face recognition matching result in step 3 is:
[0064] If X>M*M*K and Y>M*M*K and Z>M*M*K, the face recognition match is successful, otherwise the face recognition match is unsuccessful;
[0065] Wherein, M*K is the threshold in step 3, K is the threshold coefficient, and the number of rows of the feature matrix and the number of columns of the feature matrix are both M.
[0066] Step 7: The data analysis module compares the data with the central processor through the geometric face recognition algorithm and concludes that the threshold is exceeded. The risk warning module then issues instructions to the alarm, notifies the staff, and displays the real-time information on the screen.
[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A BIM-based intelligent capture system for dangerous goods in defense areas, comprising a monitoring module, a central processing unit, a data output module, a BIM modeling module, an information import module, a data receiving module, a data analysis module and a risk warning module, characterized in that: The monitoring module is electrically connected to the central processing unit through an information optical cable. The monitoring module is used to confirm the specific location and individual characteristics of the personnel and dangerous goods entering and leaving the defense zone. The central processing unit is telecommunication-connected to the data output module through an external storage device. The central processing unit is used to process the instructions of the external connection module and issue instructions to the subordinate connection module. The data output module is used to import correct internal information. The BIM modeling module is electrically connected to the central processing unit. The BIM modeling module is used to establish a three-dimensional model and display specific characteristics through a display. The information import module is electrically connected to the central processing unit through the BIM modeling module. The information import module imports external information. The central processing unit is electrically connected to the data receiving module through an information optical fiber. The data analysis module is electrically connected to the data receiving module. The data analysis module processes the received information through a geometric feature face recognition algorithm. The risk warning module is electrically connected to the data analysis module through an information processor. The risk warning module is used to handle external emergencies and display the identity of the prisoner and the specific circumstances of the lost dangerous goods to the staff through the screen.
2. According to claim 1, a BIM-based intelligent capture system for dangerous goods in defense areas is characterized by: The information import module is electrically connected to the external network module, and the external network module divides the information of the dangerous goods into appearance characteristics and specific characteristics, and the appearance characteristics include the length and width of the dangerous goods, the length is L, and the width is d.
3. According to the BIM-based intelligent capture system for dangerous goods in defense areas according to claim 1, it is characterized by: After reading the data, the information import module first determines whether it meets the calculation requirements. If not, it returns to the I / O module to read new data. If it meets the requirements, it will perform a comparison operation. If the calculation result is equal to the setting, it will be saved and transmitted to the central processing unit for the next step of processing. If the setting parameters are not within the range, it will be calculated according to the model, and the difference compensation parameters will be output to the central processing unit. The operation logic function of the central processing unit is used to control the operation of the actuator, and finally return to the I / O module to read the latest data, thereby obtaining the specific characteristics of the defense zone and dangerous goods.
4. According to claim 2, a BIM-based intelligent capture system for dangerous objects in defense areas is characterized by: The defense zone information import module is electrically connected to the central processing unit. The defense zone information import module imports the map information of the defense zone into the internal part and selects the aisle path. In the path selection, the weight value of the path unit located on the ground is set to 0. For each path unit, in addition to the path distance value information, it also includes an identification value indicating whether it is a horizontal ground or a vertical wall, where f represents the horizontal ground and w represents the vertical wall, and the specific data of the site is displayed.
5. According to the BIM-based intelligent capture system for dangerous objects in defense areas according to claim 1, it is characterized by: The image acquisition module is electrically connected to the risk warning module, and the image acquisition module is connected to the central processing module; the risk warning module collects face recognition data through the image acquisition module, and issues an alarm when dangerous goods are transported or an audible and visual alarm when face recognition matching is unsuccessful.
6. The BIM-based intelligent capture system for dangerous objects in defense areas according to claim 1 is characterized by: The information import module improves the speed of information and data exchange and meets the needs of real-time monitoring. In the early stage of monitoring, the three-dimensional model of each device in the defense zone is completed through the BIM model, and data analysis and abnormal situations are paid attention to through the data analysis module and the risk warning module, which effectively reduces the changes between the map and the actual scene, and cuts the established three-dimensional model to obtain a two-dimensional drawing, thereby improving the accuracy of the monitoring data and the degree of visual management.
7. The BIM-based intelligent capture system for dangerous objects in defense areas according to claim 1 is characterized by: The monitoring module can later realize the visualization of the three-dimensional chart output of the defense zone implementation status through the positioning monitoring camera and the cloud monitoring platform layer. The operation of each LCU in the LCU layer can be monitored and warned in real time, and unexpected intelligent diagnosis can be carried out to improve the monitoring level and save operation and maintenance costs.
8. The BIM-based intelligent capture system for dangerous objects in defense areas according to claim 4 is characterized by: The central processing unit realizes the panoramic visualization display of the communication scheduling screen through the NET Framework component, and realizes the development of the visualization system by using Visual Studio 2010. The component provides a unified calling interface proxy service.
9. The BIM-based intelligent capture system for dangerous objects in defense areas according to claim 1 is characterized by: The BIM modeling module uses the screen to display the three-dimensional building model in a holographic manner, generates and plays virtual animation monitoring videos, and synchronously displays the movement of objects and the flow of people during the monitoring process of the animation display. The video can be paused, replayed and fast-forwarded, and the staff can know the unexpected situations that need to be paid attention to at any time and the status of dangerous goods.
10. The BIM-based intelligent capture system for dangerous objects in defense areas according to claim 5 is characterized by: The image acquisition module compares the acquisition geometric shape features of the eyes of the person entering the image with the standard geometric shape features of the eyes to obtain the feature matching results of the eyes, compares the acquisition geometric shape features of the mouth with the standard geometric shape features of the mouth to obtain the feature matching results of the mouth, compares the acquisition geometric shape features of the nose with the standard geometric shape features of the nose to obtain the feature matching results of the nose, and compares the feature matching results of the eyes, the mouth and the nose with the thresholds respectively to obtain the face recognition matching results.
Citation Information
Cited By
Dynamic face recognition device for intelligent construction site based on BIM model
CN120976993A
