Navigation method and system
Through the combination of artificial intelligence cameras and beacon positioning technology, high-precision positioning and navigation of vehicles in indoor environments is achieved, solving the problems of delays and interruptions in navigation in indoor environments of traditional navigation systems, and improving navigation accuracy and reliability sex.
Patent Information
- Application Number
- CN202410974491.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
AI Technical Summary
In indoor environments, traditional navigation systems are delayed or interrupted due to factors such as signal occlusion, attenuation and multipath effects, which cannot meet the needs of indoor navigation.
Several artificial intelligence cameras are used to obtain the current position information of the vehicle based on video positioning technology. When the video positioning technology fails, it automatically switches to the beacon positioning technology, and locates through the terminal equipment bound to the vehicle, and according to the current position of the terminal equipment. Navigate information.
It improves the accuracy and reliability of indoor navigation, and solves the problems of large indoor positioning errors and low navigation accuracy in traditional navigation methods.
Smart Images

Figure CN118913302A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of information processing technology, and in particular to a navigation method and system. Background Art
[0002] With the acceleration of urbanization, people's demand for indoor navigation has increased dramatically, especially in complex indoor environments such as shopping malls, hospitals, airports and parking lots. Although the traditional Global Positioning System (GPS) and Beidou navigation system can provide accurate navigation through satellite signals in outdoor environments, greatly facilitating people's travel, these systems face challenges in indoor environments.
[0003] When entering an indoor environment, due to various factors such as obstruction by buildings (such as walls, ceilings, etc.), signal attenuation, and indoor multipath effects, GPS signals and Beidou signals often become weak or even completely unable to be received by terminal devices, resulting in delays or interruptions in indoor navigation services, thus failing to meet people's urgent needs for indoor navigation. Summary of the invention
[0004] Based on the above problems, the present application provides a navigation method and system, which can improve the accuracy and reliability of navigation.
[0005] The embodiments of the present application disclose the following technical solutions:
[0006] In a first aspect, the present application discloses a navigation method, the method comprising:
[0007] Based on several artificial intelligence cameras, the current location information of the vehicle is continuously obtained;
[0008] If the current location information of the vehicle cannot be obtained at the target time, the current location information of the terminal device bound to the vehicle at the target time is obtained according to the beacon positioning technology;
[0009] Navigation is performed according to the current location information of the terminal device.
[0010] Optionally, before executing the step of continuously acquiring the current position information of the vehicle according to the plurality of artificial intelligence cameras, the method further includes:
[0011] When the terminal device is not bound to the vehicle, if the distance between the current location information of the terminal device and the current location information of the vehicle is less than a preset distance threshold, the terminal device is bound to the vehicle.
[0012] Optionally, before executing the step of continuously acquiring the current position information of the vehicle according to the plurality of artificial intelligence cameras, the method further includes:
[0013] When the terminal device is not bound to the vehicle, if the distance between the target point of the location area represented by the current location information of the terminal device and the target point of the location area represented by the current location information of the vehicle is less than a preset distance threshold, the terminal device is bound to the vehicle.
[0014] Optionally, the method further comprises:
[0015] If the current position information of the vehicle can be obtained at the target time, navigation is performed according to the current position information of the vehicle.
[0016] Optionally, the method of continuously acquiring the current position information of the vehicle based on a plurality of artificial intelligence cameras includes:
[0017] Obtaining vehicle characteristic information of the vehicle;
[0018] By continuously identifying the vehicle feature information based on re-identification technology in the vehicle videos provided by several artificial intelligence cameras, the current location information of the vehicle is continuously obtained.
[0019] Optionally, the method of continuously acquiring the current position information of the vehicle based on a plurality of artificial intelligence cameras includes:
[0020] Constructing a three-dimensional scene map based on at least one of a laser radar, an inertial navigation system, and a wheel speed meter and a plurality of artificial intelligence cameras;
[0021] Based on several artificial intelligence cameras, the two-dimensional position coordinates of the vehicle are continuously obtained;
[0022] The two-dimensional position coordinates are mapped to the three-dimensional scene map, and the current position information of the vehicle is continuously acquired, where the current position information is the three-dimensional position coordinates.
[0023] In a second aspect, the present application discloses a navigation system, a terminal device and a server;
[0024] The server is used to continuously obtain the current position information of the vehicle based on a number of artificial intelligence cameras;
[0025] The server is also used to obtain the current location information of the terminal device bound to the vehicle at the target time according to the beacon positioning technology if the current location information of the vehicle cannot be obtained at the target time;
[0026] The server is also used to perform navigation according to the current location information of the terminal device.
[0027] Optionally, the server is further used to navigate according to the current position information of the vehicle if the current position information of the vehicle can be obtained at the target time.
[0028] In a third aspect, the present application discloses a navigation system, the system comprising: a terminal device and a server;
[0029] The server is used to continuously obtain the current position information of the vehicle based on a number of artificial intelligence cameras;
[0030] The server is also used to send the current location information of the vehicle to the terminal device;
[0031] The terminal device is used to obtain the current location information of the terminal device bound to the vehicle at the target time according to the beacon positioning technology if the current location information of the vehicle cannot be obtained at the target time;
[0032] The terminal device is also used to navigate according to the current location information of the terminal device.
[0033] Optionally, the terminal device is also used to navigate according to the current position information of the vehicle if the current position information of the vehicle can be obtained at the target time.
[0034] Compared with the prior art, this application has the following beneficial effects:
[0035] The embodiment of the present application provides a navigation method and system, which utilizes several artificial intelligence cameras to continuously obtain the current position information of the vehicle based on video positioning technology. When the video positioning technology cannot obtain the current position information of the vehicle due to some reasons (such as insufficient light, camera failure, etc.) at the target time, it automatically switches to beacon positioning technology, locates through the terminal device bound to the vehicle, and navigates according to the current position information of the terminal device. Therefore, the navigation method provided by the embodiment of the present application combines video positioning technology and beacon positioning technology, effectively solving the problems of large indoor positioning errors and low navigation accuracy of traditional pure Bluetooth positioning and other navigation methods, and improving the accuracy and reliability of indoor navigation. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0037] Figure 1A flowchart of a navigation method provided in an embodiment of the present application;
[0038] Figure 2 A signaling diagram of a navigation system provided in an embodiment of the present application;
[0039] Figure 3 A flowchart of continuously acquiring the current position information of a vehicle provided in an embodiment of the present application;
[0040] Figure 4 A flowchart of navigating according to the current location information of a terminal device or a vehicle provided in an embodiment of the present application;
[0041] Figure 5 A schematic diagram of binding a terminal device and a vehicle provided in an embodiment of the present application;
[0042] Figure 6 A signaling diagram of another navigation system provided in an embodiment of the present application. DETAILED DESCRIPTION
[0043] As described above, GPS or Beidou navigation systems can be used for navigation in outdoor environments. However, when arriving in indoor environments such as parking lots, there are often delays or interruptions in navigation due to the lack of GPS or Beidou signals, which becomes a navigation problem for the "last mile".
[0044] To solve this problem, various indoor navigation technologies have emerged:
[0045] The first indoor navigation technology is the Angle of Arrival (AoA) positioning technology. AoA positioning technology determines the location of the signal source by measuring the angle at which the radio waves (such as Wi-Fi, Bluetooth or dedicated RF signals) emitted by the signal source (transmitter) reach the receiving antenna array (receiver).
[0046] Although AoA positioning technology can theoretically achieve centimeter-level positioning accuracy, fast signal transmission speed and short response time, it still has the following disadvantages: First, AoA positioning technology has multipath effect in practical applications. In indoor environments, the radio waves emitted by the signal end may be reflected, refracted and scattered multiple times, resulting in the radio waves received by the receiving antenna array being the superposition of multiple radio wave paths, which greatly increases the complexity of angle measurement and reduces the accuracy of angle measurement. Second, AoA positioning technology strongly depends on the layout of the receiving antenna array. If the layout of the receiving antenna array is unreasonable, the accuracy of angle measurement will also be reduced. Third, AoA positioning technology is sensitive to environmental changes. Changes in temperature, humidity, obstacle position, etc. may affect the accuracy of angle measurement, thereby reducing the accuracy of angle measurement. Fourth, AoA positioning technology usually requires the configuration of multiple receiving antenna arrays and the setting of complex signal processing algorithms, which greatly increases the hardware cost and deployment complexity. Fifth, users mainly navigate on terminal devices such as mobile phones and tablets, so the terminal device must be configured with a receiving antenna array and corresponding signal processing chip that supports AoA positioning technology. However, not all terminal devices currently have such hardware conditions and are not widely used.
[0047] The second indoor navigation technology currently used is Ultra-Wide Band (UWB) positioning technology. UWB positioning technology is a technology that uses extremely short pulse signals (usually a few nanoseconds) for communication and positioning. By measuring the transmission time difference (Time of Flight, ToF) of these pulse signals from the transmitter to the receiver, the distance between the two can be accurately calculated. When combined with the distance data of multiple receivers (usually a receiving antenna array or network), high-precision positioning in three-dimensional space can be achieved using triangulation or other advanced positioning algorithms.
[0048] Although UWB positioning technology has the advantages of high positioning accuracy (usually centimeter level), strong anti-interference ability, small multipath effect, strong real-time performance, etc., it still has the following disadvantages: First, although the UWB signal itself has strong anti-interference ability, in an environment where wireless devices such as Wi-Fi and Bluetooth are densely deployed, the working frequency bands of these devices may overlap or interfere with the UWB signal, thereby affecting the transmission and reception quality of the UWB signal and reducing the accuracy of positioning. Second, UWB positioning technology requires the deployment of multiple base stations (transmitters and receivers), which involves multiple links such as equipment procurement, installation, debugging and maintenance, so the initial investment is relatively high. At the same time, due to high technical requirements, maintenance costs and technical support requirements are also relatively high. Third, similar to AoA positioning technology, UWB positioning technology also requires terminal devices to have receiving antenna arrays and corresponding signal processing chips that support UWB positioning technology. However, not all terminal devices currently have such hardware conditions, which limits the popularity and application scope of UWB positioning technology.
[0049] The third type of indoor navigation technology is video positioning technology. Video positioning technology analyzes the visual features of indoor scenes (such as corners, edges, textures, etc.) in real-time video streams and matches and calculates them with the indoor scene feature database pre-stored in the terminal device to achieve high-precision indoor positioning. This technology does not rely on GPS signals, so it has unique advantages in indoor environments.
[0050] However, in actual applications, taking the parking lot as an example, although the camera can identify the target vehicle to be located with high accuracy, how to transmit this location information to the user's terminal device in real time and accurately is a key issue. This involves issues such as data transmission delay, packet loss, and data synchronization. In addition, video positioning technology requires rapid processing and analysis of real-time video streams, which consumes a lot of computing resources. Real-time video positioning on resource-constrained terminal devices may face performance bottlenecks.
[0051] After research, the inventor proposed a navigation method and system. The method uses several artificial intelligence cameras to continuously obtain the current location information of the vehicle based on video positioning technology. When the video positioning technology cannot obtain the current location information of the vehicle due to some reasons (such as insufficient light, camera failure, etc.) at the target time, it automatically switches to beacon positioning technology, locates through the terminal device bound to the vehicle, and navigates according to the current location information of the terminal device. Therefore, the navigation method provided by the embodiment of the present application combines video positioning technology and beacon positioning technology, effectively solving the problems of large indoor positioning errors and low navigation accuracy of traditional pure Bluetooth positioning and other navigation methods, and improving the accuracy and reliability of indoor navigation.
[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0053] See also Figure 1 , which is a flowchart of a navigation method provided by an embodiment of the present application. For ease of understanding, the following explanation will be given using a parking lot as an example application scenario. The method includes:
[0054] S101: Continuously obtain the current position information of the vehicle based on a plurality of artificial intelligence cameras.
[0055] Several artificial intelligence (AI) cameras continuously capture real-time video streams of vehicles, pedestrians, obstacles, and the overall parking environment. Understandably, several AI cameras need to be located at key locations throughout the parking lot, such as entrances and exits, intersections of passages, and near parking spaces, to ensure full coverage of the parking lot area and capture high-quality real-time video streams.
[0056] Next, based on the real-time video streams provided by several AI cameras, image recognition technology is used to automatically identify the target vehicle appearing in the real-time video stream, which is usually achieved by detecting vehicle features such as the shape, color, license plate number, etc. Once the vehicle is identified, a unique identifier can be assigned to the vehicle so that it can be continuously tracked in subsequent video frames.
[0057] Subsequently, the target tracking technology is used to continuously obtain the current position information of the vehicle. It is understandable that the current position information of the vehicle can be expressed in a variety of forms: in application scenarios with high precision requirements, the current position information can be an accurate point coordinate (such as longitude and latitude or the coordinate system inside the parking lot), through which the specific position of the vehicle can be directly determined. In application scenarios where the accuracy requirements are not high, the current position information can also be a relative position coordinate relative to a reference point (such as a parking lot entrance and exit, a significant landmark, etc.). This application does not limit this.
[0058] S102: If the current location information of the vehicle cannot be obtained at the target time, the current location information of the terminal device bound to the vehicle at the target time is obtained based on the beacon positioning technology.
[0059] If at the target time, the current location information of the vehicle cannot be directly obtained from several artificial intelligence cameras due to signal interference, artificial intelligence camera failure, network delay, insufficient light, etc., then it is necessary to determine the terminal device bound to the vehicle (such as a mobile phone, vehicle-mounted navigation device, etc.), and then use the beacon positioning technology to obtain the current location information of the terminal device, and use this to determine the actual location of the vehicle.
[0060] Among them, Beacon positioning technology is a positioning method based on Bluetooth Low Energy (BLE) signals. It transmits BLE signals through multiple beacon devices deployed in indoor environments (i.e. parking lots). The terminal device receives these BLE signals and estimates the distance between the terminal device and the beacon device based on the signal strength (RSSI) or signal arrival time (Time of Arrival, ToA / Time Difference of Arrival, TDoA), thereby determining the current location information of the terminal device.
[0061] Specifically, after the terminal device receives the BLE signal sent by the beacon device, it can estimate the distance between the terminal device and the beacon device based on the signal strength. Generally, the stronger the signal strength, the closer the distance. By comparing the signal strengths of multiple beacon devices, the current location information of the terminal device can be roughly determined. ToA refers to the time it takes for a signal to reach the terminal device from a beacon device. By measuring the propagation time of the signal, the distance between the terminal device and the beacon device can be calculated to determine the current location information of the terminal device. TDoA refers to the time difference between measuring the time it takes for a signal to reach a terminal device from multiple beacon devices. By comparing the arrival time difference of signals from different beacon devices, the current location information of the terminal device can be more accurately located.
[0062] It should be noted that because Beacon signal propagation is affected by many factors (such as obstacles, signal interference, multipath effects, etc.), the accuracy of Beacon positioning technology may be limited, usually between 3-10 meters, which means that it can only provide the approximate location of the terminal device, rather than the precise coordinates. Although the accuracy of Beacon positioning technology is not as high as that of high-precision positioning technologies such as GPS, it can still provide valuable location references indoors or in complex environments.
[0063] It should be noted that if the current position information of the vehicle can be obtained at the target time, navigation can still be performed based on the current position information of the vehicle, that is, navigation is performed through video positioning technology.
[0064] S103: Navigate according to the current location information of the terminal device.
[0065] Once the current location information of the terminal device is determined, it can be used as the rough current location information of the vehicle, and navigation and subsequent processing can be performed based on the current location information of the terminal device, such as updating the vehicle location information, sending notifications to the driver, adjusting the navigation route, etc.
[0066] It should be noted that the navigation method can not only be applied to the navigation of vehicles in the parking lot, so that the vehicle drives to the target parking space or other target location, but also be applied to the navigation of the shopping cart in the shopping mall, so that the shopping cart is moved to the target counter or other target location. For example, a customer may want to move the shopping cart from one place to another in order to better browse the goods or go to the target counter. After the shopping cart is bound to the terminal device (such as a smart phone or a navigation device provided by the shopping mall), the location of the shopping cart can be tracked in real time according to the video positioning technology, and when the current location information of the shopping cart cannot be obtained, the navigation guidance is provided in time through the Beacon positioning technology, thereby improving the accuracy, flexibility and adaptability of the navigation. Alternatively, the navigation method can also be applied to the navigation of the luggage cart in the airport, so that the luggage cart is moved to the target boarding gate or other target location. For example, after the luggage cart is bound to the terminal device (such as a smart phone or a navigation device provided by the airport), the location of the luggage cart can be tracked in real time according to the video positioning technology, and when the current location information of the luggage cart cannot be obtained, the navigation guidance is provided in time through the Beacon positioning technology, thereby improving the accuracy, flexibility and adaptability of the navigation. It should be noted that this application does not limit the specific application scenarios.
[0067] In summary, the embodiment of the present application provides a navigation method, which uses several artificial intelligence cameras to continuously obtain the current position information of the vehicle based on video positioning technology. When the video positioning technology cannot obtain the current position information of the vehicle due to some reasons (such as insufficient light, camera failure, etc.) at the target time, it automatically switches to beacon positioning technology, locates through the terminal device bound to the vehicle, and navigates according to the current position information of the terminal device. Therefore, the navigation method provided by the embodiment of the present application combines video positioning technology and beacon positioning technology, effectively solving the problems of large indoor positioning errors and low navigation accuracy of traditional pure Bluetooth positioning and other navigation methods, and improving the accuracy and reliability of indoor navigation.
[0068] See also Figure 2 , which is a signaling diagram of a navigation system provided in an embodiment of the present application. The navigation system 20 includes a terminal device 21 and a server 22.
[0069] The terminal device 21 is the direct interface for the user to interact with the navigation system 20. It can be any device with network communication and positioning functions, such as a smart phone, a smart watch, and a car navigation system. The server 22 is the core processing unit of the navigation system 20. It is responsible for processing navigation requests from the terminal device 21 and generating corresponding navigation information. The design of this architecture aims to achieve efficient and accurate navigation services through the collaboration between the two.
[0070] S201: The server continuously obtains the current location information of the vehicle based on a number of artificial intelligence cameras.
[0071] Several AI cameras installed in the parking lot will continuously capture real-time video streams (i.e., vehicle videos) containing vehicles, pedestrians, obstacles, and the overall environment of the parking lot, and send the real-time video streams to the server 22 for processing.
[0072] After receiving these real-time video streams, the server 22 can use image recognition technology and AI algorithms to perform real-time analysis on the acquired real-time video streams, thereby automatically identifying the target vehicle appearing in the real-time video stream. Once the vehicle is identified in the real-time video stream, the AI camera can continuously track the vehicle, so that the server 22 can continuously obtain the current position information of the vehicle. The current position information is the two-dimensional (2D) position coordinates of the vehicle. It can be understood that by connecting multiple 2D position coordinates, the server 22 can obtain the driving trajectory of the vehicle.
[0073] It should be noted that, in actual applications, the process of the server 22 continuously acquiring the current position information of the vehicle based on several AI cameras takes about 200 milliseconds (ms). This delay rate is very low in actual applications and can be almost ignored.
[0074] In some specific implementations, in order to achieve continuous tracking of the vehicle throughout the parking lot, the server 22 may first obtain the vehicle feature information of the vehicle (such as the type, color, license plate number, and other features of the vehicle). Subsequently, the server 22 continuously identifies the vehicle feature information based on the re-identification (ReID) technology in the real-time video stream provided by several AI cameras, and tracks the movement trajectory of the vehicle under multiple different AI cameras through the spatiotemporal trajectory association algorithm, thereby continuously obtaining the current location information of the vehicle. As a result, even if the vehicle disappears from the field of view of one AI camera and reappears in the field of view of another AI camera, the server 22 can maintain continuous tracking of the vehicle.
[0075] See also Figure 3, which is a flow chart of continuously acquiring the current position information of a vehicle provided in an embodiment of the present application. If at least one of a laser radar (LiDAR), an inertial navigation system (INS) and a wheel speed meter is also provided in the parking lot, the server 22 can first construct a three-dimensional (3D) scene map of the parking lot based on the data detected by the above sensors and the real-time video stream captured by the AI camera. Subsequently, the current position information of the vehicle (i.e., the 2D position coordinates) obtained through the above steps is projected into the 3D scene map, and more accurate and comprehensive current position information of the vehicle can be obtained, and the current position information is the 3D position coordinates. Thus, not only the specific position of the vehicle can be known, but also the 3D position coordinates and orientation of the vehicle in the entire 3D scene map can be known.
[0076] S202: If the current location information of the vehicle cannot be obtained at the target time, the server obtains the current location information of the terminal device bound to the vehicle at the target time based on the beacon positioning technology.
[0077] See also Figure 4 , which is a flowchart of navigating according to the current location information of the terminal device or the current location information of the vehicle provided by the embodiment of the present application. At the target time, the server 22 first needs to determine whether the current location information of the vehicle can be obtained.
[0078] If the server 22 can obtain the current location information of the vehicle at the target time, the server 22 can continue to navigate directly based on the current location information of the vehicle at the target time based on the video positioning technology. If the server 22 cannot obtain the current location information of the vehicle at the target time, the server 22 can obtain the current location information of the terminal device 21 bound to the vehicle based on the Beacon positioning technology, and use it to determine the actual location of the vehicle.
[0079] It should be noted that since the server 22 cannot obtain the current location information of the vehicle when confirming the target time, it will directly obtain the current location information of the terminal device 21 bound to the vehicle. Therefore, the server 22 needs to bind the terminal device 21 to the vehicle in advance before executing the above-mentioned S201 step.
[0080] See also Figure 5 , which is a schematic diagram of a terminal device and a vehicle binding provided by an embodiment of the present application. In some specific implementations, such as Figure 5In A, when the terminal device 21 has not established a binding relationship with the vehicle, if the current location information of the terminal device 21 (i.e., the terminal location information) is a location area, then when the distance between the target point (e.g., the center point) of the location area represented by the current location information of the terminal device 21 and the target point of the location area represented by the current location information of the vehicle (i.e., the vehicle location information) is less than a preset distance threshold, the terminal device 21 is bound to the vehicle.
[0081] If the current location information of the terminal device 21 is a 2D coordinate or a 3D coordinate, then when the distance between the current location information of the terminal device 21 and the current location information of the vehicle is less than a preset distance threshold, the terminal device 21 is bound to the vehicle.
[0082] It should be noted that the preset distance threshold may be 0.3 meters, 0.5 meters, etc., and this application does not limit this. This binding method is suitable for scenes with low vehicle density, such as private parking lots, small garages, etc.
[0083] It should be noted that in order to improve the accuracy and stability of binding, the terminal device 21 can also first pre-bind the terminal device 21 with the detected vehicle to be bound, and no information is transmitted at this time. Subsequently, a preset time threshold is introduced as a judgment condition. When within the preset time threshold, the straight-line distance between the terminal device 21 and the vehicle to be bound is always less than the preset distance threshold, then the terminal device 21 and the vehicle to be bound are finally bound, and information can be transmitted between the terminal device 21 and the vehicle. As a result, this pre-binding and final binding mechanism helps to reduce the possibility of misjudgment and misoperation. It should be noted that the preset time threshold can be 30 seconds, 60 seconds, etc., and this application does not limit this.
[0084] In some other specific implementations, such as Figure 4 In B, when the terminal device 21 has not established a binding relationship with the vehicle, if the current location information of the terminal device 21 is a location area, and there is no current location information of the vehicle in the location area, then binding cannot be performed. If the current location information of the terminal device 21 is a 2D coordinate or a 3D coordinate, and there is no current location information of the vehicle within the error range of the 2D coordinate or the 3D coordinate, then binding cannot be performed. This may be because the target vehicle is not at the current location, or the current location information of the vehicle has not been updated.
[0085] In some other specific implementations, such as Figure 4In C, when the terminal device 21 has not established a binding relationship with a vehicle, if the current location information of the terminal device 21 is a location area, and there is current location information of multiple vehicles in the location area, further analysis is required. Specifically, the terminal device 21 needs to continuously track the current location information of these vehicles, and select a target vehicle from multiple vehicles through the distance relationship and time relationship between the current location information of the terminal device 21 and the current location information of multiple vehicles, and bind the terminal device 21 and the target vehicle.
[0086] In one example, a vehicle whose distance between a target point (e.g., a center point) of a location area represented by the current location information of the terminal device 21 and a target point of a location area represented by the current location information of multiple vehicles is always the smallest within a preset time threshold can be selected as the target vehicle.
[0087] In another example, within a preset time threshold, if the distance between the target point of the location area represented by the current location information of a certain vehicle and the target point of the location area represented by the current location information of the terminal device 21 is always less than the preset distance threshold, while the distance between the target point of the location area represented by the current location information of other vehicles and the target point of the location area represented by the current location information of the terminal device 21 is getting larger and larger, then the vehicle can be set as a target vehicle, and the terminal device 21 and the target vehicle can be bound.
[0088] It should be noted that if the current location information of the terminal device 21 is a 2D coordinate or a 3D coordinate, and there is current location information of multiple vehicles within the error range of the 2D coordinate or the 3D coordinate, the target vehicle can also be identified by the above method and the target vehicle can be bound to the terminal device 21.
[0089] It should be noted that, in addition to the above-mentioned method of binding the target vehicle to the terminal device 21, deep learning technology can also be introduced to construct a pairing model. Specifically, it is first necessary to collect a large amount of current location information of the terminal device 21 and the current location information of the vehicle, as well as the pairing results between the current location information of the terminal device 21 and the current location information of the vehicle, including normal pairing (i.e., the terminal device 21 is indeed bound to the target vehicle), wrong pairing (i.e., there is no actual association between the terminal device 21 and the vehicle), etc. Subsequently, the current location information of the terminal device 21 and the current location information of the vehicle are used as input, and the pairing result between the current location information of the terminal device 21 and the current location information of the vehicle is used as output to train the deep learning model and obtain the pairing model. The advantage of deep learning technology is that it can automatically learn the complex pairing results in the current location information of the terminal device 21 and the current location information of the vehicle, thereby improving the accuracy and robustness of the pairing. At the same time, the deep learning model also has a good generalization ability and can adapt to new and abnormal situations.
[0090] In some specific implementations, the terminal device 21 can directly bind the vehicle's license plate number, VIN code or other unique identifier on a specific application (such as navigation software, vehicle management application, etc.), thereby binding to the vehicle.
[0091] It is understandable that when the server 22 obtains the current location information of the vehicle, there may be a certain delay due to reasons such as slow network connection speed. Therefore, if the server 22 wants to obtain the current location information of the vehicle at the target time T, it can first obtain the current location information of the vehicle at time T-1, and obtain the destination information of the vehicle.
[0092] Next, the vehicle's planned path is determined by the path planning algorithm based on the vehicle's current location information and destination information at time T-1. The goal of the path planning algorithm is to find an optimal path from the vehicle's current location at time T-1 to the destination. This optimal path is generated by combining factors such as road network, traffic rules (such as one-way streets, no left turns, etc.), road grades (such as highways, ordinary roads), traffic congestion, construction areas, etc., to ensure rationality and safety.
[0093] Subsequently, the vehicle's travel speed is determined based on the vehicle's current position information at different time points. Specifically, the travel speed can be obtained by calculating the change in the vehicle's current position information at two known time points (the first moment and the second moment). If the current moment is 7:55, the vehicle's current position information at the first moment 7:52 is (100m, 500m), and the vehicle's current position information at the second moment 7:54 is (100m, 800m), then the vehicle traveled 300m in two minutes, that is, the vehicle's travel speed is 150m / min.
[0094] It should be noted that the above driving speed is an average value calculated based on the actual driving situation, and in actual applications, the instantaneous value of the vehicle's driving speed at 7:54 can also be directly selected based on the actual driving situation for subsequent calculation. This application does not limit this.
[0095] Finally, combined with the planned path information and driving speed of the vehicle, the predicted position information of the vehicle at the target time T can be predicted, and the predicted position information can be used as the current position information of the vehicle at the target time T.
[0096] It is understandable that the above embodiment combines the planned path information and driving speed of the vehicle to obtain the predicted position information of the vehicle at the target time. In practical applications, in order to improve the prediction accuracy, in addition to considering the planned path information and driving speed of the vehicle, other factors that may affect the vehicle position can also be combined. For example, driving acceleration (reflecting the trend of speed change), steering angle (reflecting the change in driving direction), road conditions (such as the impact of wetness and potholes on driving speed), traffic flow (affecting driving speed and path selection), etc. By comprehensively considering these factors, the motion compensation method is used to further reduce the error between the predicted position information and the current position information. This application is not limited to this.
[0097] S203: The server performs navigation according to the current location information of the terminal device.
[0098] It is understandable that step S203 is similar to step S103 and will not be described in detail here.
[0099] In summary, the embodiment of the present application provides a navigation system, which uses several artificial intelligence cameras to continuously obtain the current position information of the vehicle based on video positioning technology. When the video positioning technology cannot obtain the current position information of the vehicle due to some reasons (such as insufficient light, camera failure, etc.) at the target time, it automatically switches to beacon positioning technology, locates through the terminal device bound to the vehicle, and navigates according to the current position information of the terminal device. Therefore, the navigation system provided by the embodiment of the present application combines video positioning technology and beacon positioning technology, effectively solving the problem of low navigation accuracy of the navigation systems of traditional GPS and Beidou navigation systems in indoor environments, and improving the accuracy and reliability of navigation.
[0100] See also Figure 6 , which is a signaling diagram of another navigation system provided in an embodiment of the present application. The navigation system 20 includes a terminal device 21 and a server 22.
[0101] S601: The server continuously obtains the current location information of the vehicle based on several artificial intelligence cameras.
[0102] S602: The server sends the current location information of the vehicle to the terminal device.
[0103] S603: If the current location information of the vehicle cannot be obtained at the target time, the terminal device obtains the current location information of the terminal device bound to the vehicle at the target time based on the beacon positioning technology.
[0104] S604: The terminal device performs navigation according to the current location information of the terminal device.
[0105] In some specific implementations, the terminal device 21 is also used to navigate according to the current position information of the vehicle if the current position information of the vehicle can be obtained at the target time.
[0106] It is understandable that in steps S201 to S203, data processing (such as prediction of predicted position information, judgment on whether the current position information of the vehicle can be obtained at the target time, etc.) is completed by the server 22. When the server 22 finds that the current position information of the vehicle cannot be obtained at the target time, it will actively use the Beacon positioning technology to obtain the current position information of the terminal device 21 and navigate accordingly. In steps S601 to S604, the server 22 is responsible for data collection and preliminary processing (such as obtaining the current position information of the vehicle), but more decision-making power (such as judgment on whether the current position information of the vehicle can be obtained at the target time, etc.) is handed over to the terminal device 21, and the terminal device 21 determines whether the Beacon positioning technology needs to be used, and how to navigate based on the current position information.
[0107] In summary, the embodiment of the present application provides a navigation system, which uses several artificial intelligence cameras to continuously obtain the current position information of the vehicle based on video positioning technology. When the video positioning technology cannot obtain the current position information of the vehicle due to some reasons (such as insufficient light, camera failure, etc.) at the target time, it automatically switches to beacon positioning technology, locates through the terminal device bound to the vehicle, and navigates according to the current position information of the terminal device. Therefore, the navigation system provided by the embodiment of the present application combines video positioning technology and beacon positioning technology, effectively solving the problem of low navigation accuracy of the navigation systems of traditional GPS and Beidou navigation systems in indoor environments, and improving the accuracy and reliability of navigation.
[0108] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0109] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A navigation method, characterized in that: The method comprises: Based on several artificial intelligence cameras, the current location information of the vehicle is continuously obtained; If the current location information of the vehicle cannot be obtained at the target time, the current location information of the terminal device bound to the vehicle at the target time is obtained according to the beacon positioning technology; Navigation is performed according to the current location information of the terminal device.
2. The method according to claim 1, characterized in that Before executing the step of continuously acquiring the current position information of the vehicle according to the plurality of artificial intelligence cameras, the method further includes: When the terminal device is not bound to the vehicle, if the distance between the current location information of the terminal device and the current location information of the vehicle is less than a preset distance threshold, the terminal device is bound to the vehicle.
3. The method according to claim 1, characterized in that Before executing the step of continuously acquiring the current position information of the vehicle according to the plurality of artificial intelligence cameras, the method further includes: When the terminal device is not bound to the vehicle, if the distance between the target point of the location area represented by the current location information of the terminal device and the target point of the location area represented by the current location information of the vehicle is less than a preset distance threshold, the terminal device is bound to the vehicle.
4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: If the current position information of the vehicle can be obtained at the target time, navigation is performed according to the current position information of the vehicle.
5. The method according to claim 1, characterized in that The method of continuously acquiring the current position information of the vehicle based on a plurality of artificial intelligence cameras includes: Obtaining vehicle characteristic information of the vehicle; By continuously identifying the vehicle feature information based on re-identification technology in the vehicle videos provided by several artificial intelligence cameras, the current location information of the vehicle is continuously obtained.
6. The method according to claim 1, characterized in that The method of continuously acquiring the current position information of the vehicle based on a plurality of artificial intelligence cameras includes: Constructing a three-dimensional scene map based on at least one of a laser radar, an inertial navigation system, and a wheel speed meter and a plurality of artificial intelligence cameras; Based on several artificial intelligence cameras, the two-dimensional position coordinates of the vehicle are continuously obtained; The two-dimensional position coordinates are mapped to the three-dimensional scene map, and the current position information of the vehicle is continuously acquired, where the current position information is the three-dimensional position coordinates.
7. A navigation system, characterized in that: The system comprises: a terminal device and a server; The server is used to continuously obtain the current position information of the vehicle based on a number of artificial intelligence cameras; The server is further configured to obtain the current location information of the terminal device bound to the vehicle at the target time according to the beacon positioning technology if the current location information of the vehicle cannot be obtained at the target time; The server is also used to perform navigation according to the current location information of the terminal device.
8. The system according to claim 7, characterized in that The server is also used to perform navigation according to the current position information of the vehicle if the current position information of the vehicle can be obtained at the target time.
9. A navigation system, characterized in that: The system comprises: a terminal device and a server; The server is used to continuously obtain the current position information of the vehicle based on a number of artificial intelligence cameras; The server is also used to send the current location information of the vehicle to the terminal device; The terminal device is used to obtain the current location information of the terminal device bound to the vehicle at the target time according to the beacon positioning technology if the current location information of the vehicle cannot be obtained at the target time; The terminal device is also used to navigate according to the current location information of the terminal device.
10. The system according to claim 7, characterized in that The terminal device is also used to navigate according to the current position information of the vehicle if the current position information of the vehicle can be obtained at the target time.
Citation Information
Cited By
Apparatus and Method for Determining Location Based on Image and Hybrid Positioning Information Using On-Device AI
KR1020260130105A
