Precise passenger identification system and method based on multi-source data

Abstract

The invention belongs to the technical field of personnel identification, and particularly discloses a passenger accurate identification system and method based on multi-source data, and the system comprises a UWB label positioning monitoring module, a video monitoring module, an omnidirectional distance measurement base station monitoring module, a first data processing module, and a second data processing module. The UWB label positioning monitoring module is used for collecting first label information around the mining manned vehicle, the video monitoring module is used for collecting image information around the mining manned vehicle, and the omnidirectional distance measurement base station monitoring module is used for collecting second label information around the mining manned vehicle. The first data processing module is used for receiving the first label information, the image information and the second label information and identifying the number of personnel, and the second data processing module is used for receiving data processed by the first data processing module. According to the identification method, accurate identification is carried out by using the identification system. According to the invention, accurate identification of passengers in the compartment of the mining manned vehicle can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of personnel identification, and in particular relates to a system and method for accurately identifying passengers based on multi-source data. Background Art

[0002] The precise positioning system for coal mine personnel carried by mining manned vehicles provides a basis for the identification of passengers underground. The precise positioning system for coal mine personnel in the existing technology is mainly based on UWB precise positioning technology or AI recognition technology. UWB precise positioning technology is mainly divided into two ways to realize the identification of passengers: one is based on the one-dimensional positioning data of the precise positioning substation in the tunnel, with the vehicle positioning card as the origin, setting the judgment threshold, and then adsorbing and positioning the personnel within this range, so as to identify the passengers. The other is to install a card reader in the car, and the card reader in the car locates the tags carried by the passengers inside the vehicle, and links with the system platform through the positioning card outside the car, so as to realize the precise identification of the people in the car. AI recognition technology is to install an AI recognition camera in the car and judge the passengers through face recognition technology.

[0003] However, both personnel identification based on UWB precise positioning technology and AI recognition technology have the problem of inaccurate recognition, specifically:

[0004] The recognition based on UWB positioning technology has the following defects:

[0005] The vehicle positioning card is used as the origin for identification. Since the precise positioning in the lane is one-dimensional, when the vehicle is parked, people walking in the lane within the threshold range will also be attracted to the identification range, resulting in incorrect identification of the number of passengers and even overload alarms. Because this mode completely relies on base station positioning in the lane, its reliability is low and the recognition error rate is high.

[0006] By installing a card reader in the car, the card reader inside the car can locate the tags carried by the passengers inside the vehicle. Based on the non-line-of-sight transmission of UWB, people walking in the lane can be basically excluded during the movement of the vehicle, which can ensure a high recognition accuracy. However, when the vehicle stops at the waiting point, the distance between the vehicle and the surrounding people is relatively close. Due to the influence of the metal of the vehicle, the multipath effect of UWB positioning will cause positioning deviation, and the threshold setting of the on-board card reader is not particularly critical, which will make it impossible to distinguish between people getting on and off the vehicle, resulting in recognition errors.

[0007] The following defects exist based on face recognition technology: When using AI face recognition technology to identify people, because underground workers wear helmets when riding in vehicles, there is a situation where faces cannot be automatically captured and accurately identified. If accurate identification is required, face verification is required when getting on and off the vehicle, which greatly reduces the efficiency of getting on and off the vehicle and increases time costs. In addition, after the workers have been working, their faces are dirty and the recognition accuracy is not high. This method has a high reliability for identifying the number of people, but a low accuracy for identifying people. Summary of the invention

[0008] In view of the above-mentioned problems, the purpose of the present invention is to provide a system and method for accurately identifying passengers in a mining vehicle based on multi-source data, which can realize accurate identification of passengers in the vehicle compartment.

[0009] The technical solution of the present invention is: a passenger accurate identification system based on multi-source data, comprising:

[0010] The UWB tag positioning monitoring module is used to collect the first tag information around the mining manned vehicle in real time. The first tag information is used to be worn by the personnel in the mine;

[0011] Video monitoring module, used to collect image information around mining vehicles in real time;

[0012] The omnidirectional ranging base station monitoring module is used to collect the second tag information around it in real time. The second tag information is used to be worn by the personnel in the mine;

[0013] The first data processing module is connected to the UWB tag positioning monitoring module, the video monitoring module, and the omnidirectional ranging base station monitoring module, respectively, and is used to receive the first tag information and identify the number of people according to the first tag information, receive the image information and identify the number of people according to the image information, and receive the second tag information and identify the number of people according to the second tag information;

[0014] The second data processing module is used to receive the data processed by the first data processing module and the UWB positioning data of the platform and reprocess them. When MX=Y, the actual number of people in the mining manned vehicle is Y; when MX≠Y, an early warning prompt is issued and the difference in the number of people is displayed; wherein M represents the number of people identified by the first tag information, X represents the number of people identified by the image information, and Y represents the number of people identified by the second tag information.

[0015] Furthermore, the UWB tag positioning monitoring module is used to collect first tag information within a range of N1 meters around the mining manned vehicle in real time, wherein 5≥N1>0.

[0016] Furthermore, the video monitoring module is used to collect image information within a range of N2 meters around the mining manned vehicle in real time, wherein N2=N1.

[0017] Furthermore, the omnidirectional ranging base station monitoring module is used to collect second tag information within a range of N3 meters around the omnidirectional ranging base station monitoring module in real time, wherein N3 is the distance between the omnidirectional ranging base station monitoring module and the farthest end of the mining manned vehicle.

[0018] Furthermore, the second data processing module is connected to the first data processing module through the switching module to receive data processed by the first data processing module.

[0019] Furthermore, the second data processing module is used to connect to the external UWB platform through the wireless communication module to achieve data exchange with the external UWB platform.

[0020] Furthermore, the personnel tag is used to correspond to the identity information of the personnel in the mine.

[0021] Furthermore, the second data processing module is also used to display the identity information of the passengers.

[0022] A method for accurately identifying passengers based on multi-source data, using the above-mentioned recognition system for accurate identification, specifically includes the following steps:

[0023] The UWB tag positioning monitoring module is used to collect the first tag information around the mining manned vehicle in real time, and the first data processing module receives and identifies the first tag information to monitor the number of personnel in real time, which is recorded as M;

[0024] The video monitoring module is used to collect image information around the mining manned vehicle in real time, and the first data processing module receives and identifies the image information to monitor the number of people around the vehicle in real time, which is recorded as X;

[0025] The omnidirectional ranging base station monitoring module is used to collect the second tag information around it, and the first data processing module receives and identifies the second tag information personnel and monitors the number of personnel in real time, which is recorded as Y, and monitors the distance change corresponding to the number of personnel in and around the vehicle in real time;

[0026] The second data processing module receives the data processed by the first data processing module and processes it, specifically:

[0027] When MX=Y, the actual number of people in the car is Y; when MX≠Y, it proves that there is a deviation in personnel identification. At this time, the second data processing module displays the difference in the number of people and issues an early warning.

[0028] Compared with the prior art, the beneficial effect of the present invention lies in: the present invention is based on a two-way data source, with a UWB tag positioning monitoring module and a video monitoring module as one of the data sources for identifying the occupants of a mining manned vehicle, and an omnidirectional ranging base station monitoring module as another data source for identifying the occupants of a mining manned vehicle. After real-time information collection, the number of people in the vehicle is identified and compared, and the result after comparison is the actual number of people in the vehicle. This method can not only perform high-reliability identification, but also accurately judge the actual number of people in the vehicle, thereby realizing accurate identification of passengers in the compartment of a mining manned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a structural module diagram of the recognition system of the present invention;

[0030] Figure 2 It is a flow chart of the identification method of the present invention. DETAILED DESCRIPTION

[0031] The following is combined with Figure 1 To the attached Figure 2 , the specific embodiments of the present invention are described in detail. In the description of the present invention, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0032] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features; in the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0033] It should be noted that the circuit connections involved in the present invention all adopt conventional circuit connection methods and do not involve any innovation.

[0034] Among them, UWB refers to ultra-wideband, which is a wireless carrier communication technology. It does not use a sinusoidal carrier, but uses nanosecond non-sinusoidal narrow pulses to transmit data, so it occupies a wide spectrum range. UWB technology has the advantages of low system complexity, low power spectrum density of transmitted signals, insensitivity to channel fading, low interception capability, and high positioning accuracy. It is especially suitable for high-speed wireless access in dense multipath places such as indoors.

[0035] Example

[0036] like Figure 1 A passenger accurate identification system based on multi-source data is shown, including a UWB tag positioning monitoring module, a video monitoring module, an omnidirectional ranging base station monitoring module, a first data processing module and a second data processing module.

[0037] The UWB tag positioning monitoring module is installed in the mining manned vehicle and is used to collect the first tag information around the mining manned vehicle in real time. The UWB tag positioning monitoring module is fixed above or below the center console by a sinking or floating installation method.

[0038] The video monitoring module is installed around the mining manned vehicle to collect image information around the mining manned vehicle in real time. The video monitoring module of this embodiment includes 4 commercially available cameras, which are respectively installed at the front, rear, left and right of the mining manned vehicle by drilling holes in the vehicle skin and constitute a 360-degree surround image recognition imaging device for the vehicle. In actual use, the universal adjustment bracket provided by the camera is used for fixing and calibration.

[0039] The omnidirectional ranging base station monitoring module is installed in the mining manned vehicle and is used to collect the second tag information around it in real time; the omnidirectional ranging base station monitoring module of this embodiment adopts a commercially available omnidirectional ranging base station, which is installed in the manned compartment of the mining manned vehicle by an inverted installation method.

[0040] The first data processing module is connected to the UWB tag positioning monitoring module, the video monitoring module, and the omnidirectional ranging base station monitoring module respectively, and is used to receive the first tag information and identify the number of people according to the first tag information, receive the image information and identify the number of people according to the image information, and receive the second tag information and identify the number of people according to the second tag information; the first data processing module is also used to monitor the distance change of the second tag corresponding to the mining manned vehicle in real time; the first tag information and the second tag information are both personnel tags, and the personnel tags are used to be worn on the bodies of personnel underground in the mine; the first data processing module of this embodiment adopts a commercially available multi-protocol gateway, which is fixed to the connection between the vehicle body and the front of the vehicle by hanging installation, or placed under the seat in the passenger compartment.

[0041] The second data processing module is installed in the mining manned vehicle, and is used to receive the data processed by the first data processing module and the UWB positioning data of the platform and reprocess them. When MX=Y, the actual number of people in the mining manned vehicle is Y; when MX≠Y, an early warning prompt is issued and the difference in number is displayed; where M represents the number of people identified by the first tag information, X represents the number of people identified by the image information, and Y represents the number of people identified by the second tag information. In this embodiment, the second data processing module uses a commercially available tablet computer.

[0042] In this embodiment, the second data processing module is connected to the first data processing module in communication, the second data processing module base is connected to the multi-protocol gateway in communication, the multi-protocol network management is electrically connected to the 360-degree panoramic camera, and the multi-protocol gateway is electrically connected to the omnidirectional ranging base station. In addition, this embodiment also includes a multi-channel power supply, which is electrically connected to the second data processing module base and the multi-protocol gateway, and the multi-channel power supply is used to supply power to the second data processing module base and the multi-protocol gateway.

[0043] It should be noted that the mining manned vehicle proposed in this embodiment is a mining trackless rubber-wheeled vehicle, which mainly includes a man-car. With the precise positioning system, wireless communication system and 10G ring network and other coal mine infrastructure, it can realize the integrated coordination of man, vehicle, road and platform.

[0044] Preferably, the UWB tag positioning monitoring module is used to collect first tag information within a range of N1 meters around the mining manned vehicle in real time, wherein 5≥N1>0.

[0045] Preferably, the video monitoring module is used to collect image information within a range of N2 meters around the mining manned vehicle in real time, wherein N2=N1.

[0046] Among them, the monitoring range of the UWB tag positioning monitoring module should be consistent with the monitoring range of the video monitoring module to ensure the accuracy of data judgment when the collected data is identified later.

[0047] Preferably, the omnidirectional ranging base station monitoring module is used to collect the second tag information within a range of N3 meters around the omnidirectional ranging base station monitoring module in real time, wherein N3 is the distance between the omnidirectional ranging base station monitoring module and the farthest end of the mining manned vehicle.

[0048] Preferably, the second data processing module is connected to the first data processing module via the switching module for receiving the data processed by the first data processing module.

[0049] Preferably, the second data processing module is used to connect to the external UWB platform through the wireless communication module to achieve data exchange with the external UWB platform.

[0050] Preferably, the personnel tag is used to correspond to the identity information of the personnel in the mine.

[0051] Preferably, the second data processing module is also used to display the identity information of the passengers.

[0052] like Figure 2 A method for accurately identifying passengers based on multi-source data is shown, which uses the recognition system proposed in this embodiment to perform accurate recognition, and specifically includes the following steps:

[0053] Taking the UWB tag positioning monitoring module as the center, the UWB tag positioning monitoring module is used to collect the tag information of the personnel tags within the range of N1 meters around the mining manned vehicle in real time, and the corresponding system matches the identity information of the personnel in the mine, and the identity information is specifically the name, department, etc. of the personnel. The first data processing module receives and identifies the first tag information to monitor the number of personnel in real time, which is recorded as M; where N1 is 4m.

[0054] The video monitoring module is used to collect image information within a range of N2 meters around the mining manned vehicle in real time. The first data processing module receives and identifies the image information to monitor the number of people around the vehicle in real time, denoted as X; wherein N2=N1 is 4m.

[0055] The omnidirectional ranging base station monitoring module is used to collect the second tag information within the range of N3 meters around it in real time, where N3 is the distance between the omnidirectional ranging base station monitoring module and the farthest end of the mining manned vehicle. The first data processing module receives and identifies the second tag information personnel and monitors the number of personnel in real time, recorded as Y, and monitors the distance change corresponding to the number of personnel in and around the vehicle in real time;

[0056] The second data processing module receives the data processed by the first data processing module and processes it, specifically:

[0057] Set the judgment parameters in the second data processing module:

[0058] ① The distance from the omnidirectional ranging base station to the farthest end of the mining vehicle is A meters. ② The judgment algorithm considers that B consecutive points meet the distance threshold inside the mining vehicle, which means that the vehicle is boarding. ③ The judgment algorithm considers that B consecutive points meet the distance threshold for getting off the vehicle, which means that the vehicle is getting off. ④ The judgment algorithm considers that if there is no distance data after C seconds, the vehicle is getting off.

[0059] The above parameters are combined with the data processed by the first data processing module to display the passenger information and quantity, and connect with the external UWB platform for data exchange.

[0060] When MX=Y, the actual number of people in the car is Y, and the corresponding system matches the identity information of the people in the mine.

[0061] When MX≠Y, it proves that there is a deviation in personnel identification. At this time, the second data processing module displays the difference in the number of people, matches the personnel, and alarms to remind, displaying the difference in the number of people and the closest personnel information. Among them, when MX>Y, it can be basically judged that the number of people identified by the first tag information in conjunction with the image information is larger than the number of people identified by the second tag information. This is because the omnidirectional ranging base station monitoring module has not accurately collected the second tag information of all the people in the car, resulting in personnel identification errors. At this time, there may be people getting on and off the car, so an early warning is issued to remind people to pay attention to getting on and off the vehicle. When MX<Y, it can be basically judged that the number of people identified by the first tag information in conjunction with the image information is smaller than the number of people identified by the second tag information, or the omnidirectional ranging base station monitoring module collects the second tag information of people outside the car and misreads it into the car, resulting in personnel identification errors. At this time, there are people around the car, so an early warning is issued to remind people to pay attention to pedestrians around the car.

[0062] The specific models of the above electronic components are not specially specified, and ordinary products available on the market can be selected as long as they can meet the use requirements of the present invention.

[0063] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and does not limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the protection scope of the present invention.

Claims

1. A passenger identification system based on multi-source data, characterized in that: include: The UWB tag positioning monitoring module is used to collect the first tag information around the mining manned vehicle in real time. The first tag information is used to be worn by the personnel in the mine; Video monitoring module, used to collect image information around mining vehicles in real time; The omnidirectional ranging base station monitoring module is used to collect the second tag information around it in real time. The second tag information is used to be worn by the personnel in the mine; The first data processing module is connected to the UWB tag positioning monitoring module, the video monitoring module, and the omnidirectional ranging base station monitoring module, respectively, and is used to receive the first tag information and identify the number of people according to the first tag information, receive the image information and identify the number of people according to the image information, and receive the second tag information and identify the number of people according to the second tag information; The second data processing module is used to receive the data processed by the first data processing module and the UWB positioning data of the platform and reprocess them. When MX=Y, the actual number of people in the mining manned vehicle is Y; when MX≠Y, an early warning prompt is issued and the difference in the number of people is displayed; wherein M represents the number of people identified by the first tag information, X represents the number of people identified by the image information, and Y represents the number of people identified by the second tag information.

2. The passenger identification system based on multi-source data as claimed in claim 1, characterized in that: The UWB tag positioning monitoring module is used to collect first tag information within a range of N1 meters around the mining manned vehicle in real time, where 5≥N1>0.

3. The passenger identification system based on multi-source data as claimed in claim 2, characterized in that: The video monitoring module is used to collect image information within a range of N2 meters around the mining manned vehicle in real time, wherein N2=N1.

4. The passenger identification system based on multi-source data as claimed in claim 1, characterized in that: The omnidirectional ranging base station monitoring module is used to collect the second tag information within a range of N3 meters around the omnidirectional ranging base station monitoring module in real time, wherein N3 is the distance between the omnidirectional ranging base station monitoring module and the farthest end of the mining manned vehicle.

5. The passenger identification system based on multi-source data as claimed in claim 1, characterized in that: The second data processing module is connected to the first data processing module through the switching module to receive the data processed by the first data processing module.

6. The passenger identification system based on multi-source data as claimed in claim 1, characterized in that: The second data processing module is used to connect to an external UWB platform through a wireless communication module to achieve data intercommunication with the external UWB platform.

7. The passenger identification system based on multi-source data as claimed in claim 1, characterized in that: The personnel tag is used to correspond to the identity information of the personnel in the mine.

8. The passenger identification system based on multi-source data as claimed in claim 7, characterized in that: The second data processing module is also used to display the identity information of passengers.

9. A method for accurately identifying passengers based on multi-source data, characterized in that: Using the recognition system described in any one of claims 1 to 8 to perform accurate recognition specifically comprises the following steps: The UWB tag positioning monitoring module is used to collect the first tag information around the mining manned vehicle in real time, and the first data processing module receives and identifies the first tag information to monitor the number of personnel in real time, which is recorded as M; The video monitoring module is used to collect image information around the mining manned vehicle in real time, and the first data processing module receives and identifies the image information to monitor the number of people around the vehicle in real time, which is recorded as X; The omnidirectional ranging base station monitoring module is used to collect the second tag information around it, and the first data processing module receives and identifies the second tag information personnel and monitors the number of personnel in real time, which is recorded as Y, and monitors the distance change corresponding to the number of personnel in and around the vehicle in real time; The second data processing module receives the data processed by the first data processing module and processes it, specifically: When MX=Y, the actual number of people in the car is Y; when MX≠Y, it proves that there is a deviation in personnel identification. At this time, the second data processing module displays the difference in the number of people and issues an early warning.

Images