Method, device, vehicle and storage medium for detecting vehicle entering and exiting a tunnel

By collecting and analyzing point cloud data in real time, identifying the amount of changes in tunnel areas and non-tunnel areas, the problem of difficulty in adapting to complex tunnel scenarios in the existing technology is solved, and accurate detection of vehicle entry and exit tunnels is achieved.

CN115390035BActive Publication Date: 2024-11-05CHINA FAW CO LTD
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
CN202210910160.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-29
Publication Date
2024-11-05
Estimated Expiration
2042-07-29

AI Technical Summary

Technical Problem

The existing vehicle entry and exit tunnel detection methods are difficult to adapt to complex and changeable actual road tunnel scenarios, and it is impossible to effectively identify the situation of vehicle entry and exit from the tunnel.

Method used

By collecting point cloud data in real time, extracting the roadside point cloud data, and identifying the tunnel area and non-tunnel area based on the stationary point cloud data and the roadside point cloud data, the changes in the area range are used to determine the situation of vehicles entering and leaving the tunnel, avoiding the problem of the problem of the vehicle being in and out of the tunnel Dependence on tunnel scenarios and vehicle distribution.

Benefits of technology

It achieves good adaptability to complex tunnel scenarios, accurately judges the situation of vehicles entering and leaving the tunnel, and improves the scene adaptability and accuracy of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115390035B_ABST
    Figure CN115390035B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, device, vehicle and storage medium for detecting vehicles entering and exiting a tunnel. The method comprises: the vehicle travels along a road, and point cloud data within a first preset range of the vehicle is collected in real time, wherein the point cloud data comprises static point cloud data and dynamic point cloud data; roadside point cloud data is extracted from the static point cloud data; based on the static point cloud data and the roadside point cloud data, tunnel areas and non-tunnel areas are identified from road areas within the first preset range, wherein, during the vehicle's travel along the road, the area ranges of the tunnel area and the non-tunnel area change based on the vehicle's travel dynamics; based on the amount of change in the area ranges of the tunnel area and the non-tunnel area, the situation of the vehicle entering and exiting the tunnel is determined. The present invention solves the technical problem that the existing method for detecting vehicles entering and exiting tunnels is difficult to adapt to the complex and changeable actual road tunnel scenes.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method, device, vehicle and storage medium for detecting a vehicle entering or exiting a tunnel. Background Art

[0002] Tunnels are a typical road scene that is prone to serious clutter. In tunnels, the electromagnetic waves emitted by millimeter-wave radars will be severely scattered, generating a large number of false targets, which seriously affects the detection performance of millimeter-wave radars. Therefore, it is of great significance to distinguish tunnel scenes from other road scenes and perform targeted processing to improve the comprehensive performance of millimeter-wave radars.

[0003] In the existing tunnel scene detection method based on millimeter wave radar, the target area and target quantity threshold are first preset, and then the stationary targets detected by the millimeter wave radar in the preset area are obtained and clustered. Finally, the vehicle is judged whether it enters or exits the tunnel based on the information of the clustered stationary targets and the preset threshold. This method can meet the requirements of tunnel scene judgment to a certain extent. However, when determining the threshold value, a large number of tunnel scene tests are required. At the same time, factors such as the internal structure of the tunnel and the distribution of vehicles will affect the method. It is difficult to cover the complex and changeable actual road tunnel scenes only by using the preset area and threshold value, and it is difficult to fully meet the needs of tunnel scene detection. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, vehicle and storage medium for detecting vehicle entry and exit of a tunnel, so as to at least solve the technical problem that the existing method for detecting vehicle entry and exit of a tunnel is difficult to adapt to the complex and changeable actual road tunnel scenes.

[0005] According to one aspect of an embodiment of the present invention, a method for detecting a vehicle entering or exiting a tunnel is provided, comprising:

[0006] A vehicle travels along a road, and point cloud data within a first preset range of the vehicle is collected in real time, wherein the point cloud data includes static point cloud data and dynamic point cloud data; roadside point cloud data are extracted from the static point cloud data, wherein the roadside point cloud data is used to characterize the point cloud data along both sides of the road collected when the vehicle travels along the road; based on the static point cloud data and the roadside point cloud data, tunnel areas and non-tunnel areas are identified from road areas within the first preset range, wherein, during the vehicle's travel along the road, the area ranges of the tunnel areas and non-tunnel areas change based on the vehicle's travel dynamics; based on the amount of change in the area ranges of the tunnel areas and non-tunnel areas, the situation of the vehicle entering and exiting the tunnel is determined.

[0007] Optionally, based on the static point cloud data and the curb point cloud data, identifying the tunnel area and the non-tunnel area from the road area within the first preset range includes: obtaining a first curve equation and a second curve equation by fitting the curb point cloud data, wherein the first curve equation is the curve equation along the first side of the road, and the second curve equation is the curve equation along the second side of the road; projecting the point cloud data along the first side according to the second curve equation to obtain first projection data, and / or projecting the point cloud data along the second side according to the first curve equation to obtain second projection data, wherein the point cloud data along the first side and the point cloud data along the second side are included in the curb point cloud data; matching the first projection data and the second projection data with the static point cloud data to obtain a matching result; and dividing the road within the first preset range into a tunnel area and a non-tunnel area according to the matching result.

[0008] Optionally, the stationary point cloud data includes stationary point cloud data on the first side and stationary point cloud data on the second side; dividing the road within the first preset range into a tunnel area and a non-tunnel area according to the matching results includes: determining a dividing line according to the matching results, wherein the matching results include: first matching data between the first projection data and the stationary point cloud data on the first side, and second matching data between the second projection data and the stationary point cloud data on the second side; dividing the road within the first preset range into a tunnel area and a non-tunnel area using the dividing line.

[0009] Optionally, based on the static point cloud data and the curb point cloud data, identifying the tunnel area and the non-tunnel area from the road area within the first preset range includes: based on the static point cloud data and the curb point cloud data, identifying the potential tunnel area and the non-tunnel area from the road area within the first preset range; dividing the potential tunnel area into multiple sub-areas; calculating the density of the static point cloud data in each sub-area; if the density in the sub-area meets a preset density threshold, marking the sub-area as a tunnel sub-area, and multiple tunnel sub-areas constitute a tunnel area, wherein the preset density threshold is determined based on the dynamic point cloud data.

[0010] Optionally, determining whether a vehicle enters or exits a tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area includes: judging whether the vehicle enters the tunnel according to the amount of change in the area range of the tunnel area or judging whether the vehicle exits the tunnel according to the amount of change in the area range of the non-tunnel area.

[0011] Optionally, judging whether the vehicle has entered the tunnel based on the change in the area range of the tunnel area includes: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a first distribution; if the second preset range only includes non-tunnel areas, obtaining first area range data, wherein the first area range data includes tunnel length data of multiple tunnel areas, and the multiple tunnel length data are arranged according to the acquired time; calculating the average value of the multiple tunnel length data to obtain a first average value; calculating the change in at least two adjacent tunnel length data to obtain a first change; when the first average value is greater than the preset average value and the first change is greater than the preset change, determining that the vehicle is entering the tunnel.

[0012] Optionally, judging whether the vehicle has exited the tunnel based on the change in the area range of the non-tunnel area includes: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a second distribution; if the second preset range only includes the tunnel area, obtaining second area range data, wherein the second area range data includes non-tunnel length data of at least two non-tunnel areas, and the non-tunnel length data are arranged according to the time of acquisition; calculating the change in two adjacent non-tunnel length data to obtain a second change; obtaining the movement distance of the vehicle, wherein the movement distance is used to characterize the distance moved by the vehicle in the process of obtaining the non-tunnel length data; when the second change is equal to the movement distance, it is determined that the vehicle is exiting the tunnel.

[0013] According to one embodiment of the present invention, there is also provided a detection device for a vehicle entering or exiting a tunnel, comprising:

[0014] A collection module, the collection module is used for collecting point cloud data within a first preset range of the vehicle in real time when the vehicle is traveling along the road, wherein the point cloud data includes static point cloud data and dynamic point cloud data; an extraction module, the extraction module is used to extract curb point cloud data from the static point cloud data, wherein the curb point cloud data is used to characterize the point cloud data along both sides of the road collected when the vehicle is traveling along the road; a processing module, the processing module is used to identify tunnel areas and non-tunnel areas from road areas within the first preset range based on the static point cloud data and the curb point cloud data, wherein, during the vehicle's driving along the road, the area range of the tunnel area and the non-tunnel area changes based on the vehicle's driving dynamics; a judgment module, the judgment module is used to determine the situation of the vehicle entering and exiting the tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area.

[0015] Optionally, the processing module is also used to identify tunnel areas and non-tunnel areas from road areas within a first preset range based on static point cloud data and curb point cloud data, including: obtaining a first curve equation and a second curve equation by fitting the curb point cloud data, wherein the first curve equation is a curve equation along a first side of the road, and the second curve equation is a curve equation along a second side of the road; projecting the point cloud data along the first side according to the second curve equation to obtain first projection data, and / or projecting the point cloud data along the second side according to the first curve equation to obtain second projection data, wherein the point cloud data along the first side and the point cloud data along the second side are included in the curb point cloud data; matching the first projection data and the second projection data with the static point cloud data to obtain a matching result; and dividing the road within the first preset range into a tunnel area and a non-tunnel area according to the matching result.

[0016] Optionally, the stationary point cloud data in the acquisition module includes stationary point cloud data on the first side and stationary point cloud data on the second side; the processing module is also used to divide the road within the first preset range into a tunnel area and a non-tunnel area according to the matching results, including: determining a dividing line according to the matching results, wherein the matching results include: first matching data between the first projection data and the stationary point cloud data on the first side, and second matching data between the second projection data and the stationary point cloud data on the second side; using the dividing line to divide the road within the first preset range into a tunnel area and a non-tunnel area.

[0017] Optionally, the processing module is also used to identify tunnel areas and non-tunnel areas from road areas within a first preset range based on static point cloud data and curb point cloud data, including: identifying potential tunnel areas and non-tunnel areas from road areas within the first preset range based on static point cloud data and curb point cloud data; dividing the potential tunnel area into multiple sub-areas; calculating the density of the static point cloud data in each sub-area; if the density in the sub-area meets a preset density threshold, marking the sub-area as a tunnel sub-area, and multiple tunnel sub-areas constitute a tunnel area, wherein the preset density threshold is determined based on the dynamic point cloud data.

[0018] Optionally, the judgment module is also used to determine the situation of the vehicle entering or exiting the tunnel based on the change in the area range of the tunnel area and the non-tunnel area, including: judging whether the vehicle enters the tunnel according to the change in the area range of the tunnel area or judging whether the vehicle exits the tunnel according to the change in the area range of the non-tunnel area.

[0019] Optionally, the judgment module is also used to judge whether the vehicle enters the tunnel according to the change in the area range of the tunnel area, including: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a first distribution; if the second preset range only includes non-tunnel areas, obtaining first area range data, wherein the first area range data includes tunnel length data of multiple tunnel areas, and the multiple tunnel length data are arranged according to the acquired time; calculating the average value of multiple tunnel length data to obtain a first average value; calculating the change in at least two adjacent tunnel length data to obtain a first change; when the first average value is greater than the preset average value and the first change is greater than the preset change, it is determined that the vehicle is entering the tunnel.

[0020] Optionally, the judgment module is also used to judge whether the vehicle has exited the tunnel based on the change in the area range of the non-tunnel area, including: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a second distribution; if the second preset range only includes the tunnel area, obtaining second area range data, wherein the second area range data includes non-tunnel length data of at least two non-tunnel areas, and the non-tunnel length data are arranged according to the acquired time; calculating the change in two adjacent non-tunnel length data to obtain a second change; obtaining the vehicle's movement distance, wherein the movement distance is used to characterize the distance the vehicle moves during the process of obtaining the non-tunnel length data; when the second change is equal to the movement distance, it is determined that the vehicle is exiting the lane.

[0021] According to one embodiment of the present invention, a vehicle is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any of the above methods for detecting a vehicle entering or exiting a tunnel.

[0022] According to one embodiment of the present invention, a non-volatile storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute any of the above-mentioned methods for detecting a vehicle entering or exiting a tunnel when the computer program is run on a computer or a processor.

[0023] In an embodiment of the present invention, a vehicle travels along a road, and point cloud data within a first preset range of the vehicle is collected in real time, wherein the point cloud data includes static point cloud data and dynamic point cloud data; roadside point cloud data is extracted from the static point cloud data, wherein the roadside point cloud data is used to characterize the point cloud data along the two sides of the road collected when the vehicle travels along the road; based on the static point cloud data and the roadside point cloud data, a tunnel area and a non-tunnel area are identified from the road area within the first preset range, wherein during the vehicle's travel along the road, the area range of the tunnel area and the non-tunnel area changes based on the vehicle's travel dynamics; based on the amount of change in the area range of the tunnel area and the non-tunnel area, the vehicle's entry and exit of the tunnel is determined. The method determines the vehicle's entry and exit of the tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area, and does not need to determine the threshold value based on a large number of tunnel scenes, and the internal structure of the tunnel and the vehicle situation will not affect the amount of change in the area range of the tunnel area and the non-tunnel area in the present application. Therefore, the above method has good scene adaptability, thereby solving the technical problem that the existing vehicle entry and exit detection method is difficult to adapt to the complex and changeable actual road tunnel scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0025] Figure 1 is a flow chart of a method for detecting a vehicle entering or exiting a tunnel according to one embodiment of the present invention;

[0026] Figure 2 4 is a structural block diagram of a detection device for vehicles entering and exiting a tunnel according to one embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] According to an embodiment of the present invention, an embodiment of a method for detecting a vehicle entering or exiting a tunnel is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0030] The method embodiment can be executed in an electronic device including a memory and a processor, a similar control device or a system. Taking an electronic device as an example, the electronic device may include one or more processors and a memory for storing data. Optionally, the electronic device may also include a communication device and a display device for communication functions. It can be understood by a person of ordinary skill in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0031] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and the like. Among them, different processing units may be independent components or integrated into one or more processors. In some instances, the electronic device may also include one or more processors.

[0032] The memory can be used to store computer programs, for example, to store the computer program corresponding to the method for detecting vehicle entering and exiting a tunnel in the embodiment of the present invention. The processor implements the above-mentioned method for detecting vehicle entering and exiting a tunnel by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0033] The communication device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the communication device includes a network adapter (network interface controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of a mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0035] Figure 1 is a flow chart of a method for detecting a vehicle entering or exiting a tunnel according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0036] Step S101: The vehicle travels along the road and collects point cloud data within a first preset range where the vehicle is located in real time.

[0037] Among them, point cloud data includes static point cloud data and dynamic point cloud data.

[0038] It should be noted that the point cloud data can be collected in real time using millimeter wave radar. The above-mentioned static point cloud data is the point cloud data of static targets collected during driving, and the dynamic point cloud data is the dynamic point cloud data collected during driving. The first preset range is artificially set based on the detection range of the millimeter wave radar.

[0039] Step S102, extracting roadside point cloud data from the static point cloud data.

[0040] Among them, the roadside point cloud data is used to represent the point cloud data collected along both sides of the road when the vehicle is driving along the road.

[0041] Specifically, the side of the road is a dividing line between the road and the non-road. Extracting the side point cloud data from the static point cloud data includes setting a length condition and a width deviation, and performing linear fitting on the static point cloud data based on the length condition and the width deviation to obtain the side point cloud data.

[0042] Step S103: identifying tunnel areas and non-tunnel areas from road areas within a first preset range based on the stationary point cloud data and the roadside point cloud data.

[0043] In the process of the vehicle traveling along the road, the area range of the tunnel area and the non-tunnel area changes based on the driving dynamics of the vehicle.

[0044] The identification of the tunnel area and the non-tunnel area from the road area within the first preset range is to distinguish the road according to the features in the stationary point cloud data and the roadside point cloud data. In addition, since the vehicle is in the driving process, the first preset range where the vehicle is located will change continuously. The continuous change of the first preset range will cause the area range of the tunnel area and the non-tunnel area included in the first preset range to change accordingly.

[0045] Step S104, determining the situation of vehicles entering and exiting the tunnel based on the amount of change in the area ranges of the tunnel area and the non-tunnel area.

[0046] Specifically, based on the change in the area range of the tunnel area and the non-tunnel area, the situation of vehicles entering and exiting the tunnel is divided into three stages: the first stage is the tunnel entry stage, in this stage, the area range of the non-tunnel area within the first preset range continues to decrease until it disappears, and the area range of the tunnel area increases from nothing to something; the second stage is the tunnel area stage, in this stage, only the tunnel area is included in the first preset range; the third stage is the tunnel exit stage, in this stage, the area range of the non-tunnel area increases from nothing to something and gradually increases, and the area range of the tunnel area continues to decrease until it disappears.

[0047] Based on the above steps, the vehicle travels along the road, and the point cloud data within the first preset range of the vehicle is collected in real time, wherein the point cloud data includes static point cloud data and dynamic point cloud data; the roadside point cloud data is extracted from the static point cloud data, wherein the roadside point cloud data is used to characterize the point cloud data along the two sides of the road collected when the vehicle travels along the road; based on the static point cloud data and the roadside point cloud data, the tunnel area and the non-tunnel area are identified from the road area within the first preset range, wherein, during the vehicle's travel along the road, the area range of the tunnel area and the non-tunnel area is based on the dynamic changes of the vehicle's travel; based on the change in the area range of the tunnel area and the non-tunnel area, the vehicle's entry and exit of the tunnel is determined. The method determines the vehicle's entry and exit of the tunnel based on the change in the area range of the tunnel area and the non-tunnel area, and does not need to determine the threshold value based on a large number of tunnel scenes, and the internal structure of the tunnel and the vehicle situation will not affect the change in the area range of the tunnel area and the non-tunnel area in the present application. Therefore, the above method has good scene adaptability, thereby solving the technical problem that the existing vehicle entry and exit detection method is difficult to adapt to the complex and changeable actual road tunnel scenes.

[0048] Optionally, step S103, based on the stationary point cloud data and the roadside point cloud data, identifying the tunnel area and the non-tunnel area from the road area within the first preset range may include the following steps:

[0049] Step S1031, obtaining a first curve equation and a second curve equation by fitting according to the curb point cloud data.

[0050] The first curve equation is the curve equation along the first side of the road, and the second curve equation is the curve equation along the second side of the road.

[0051] It should be noted that the roadside point cloud data includes point cloud data along both sides of the road. The point cloud data along the first side is fitted to obtain the first curve equation, and the point cloud data along the second side is fitted to obtain the second curve equation. Both the first curve equation and the second curve equation are equations in the local coordinate system, which is a coordinate system constructed by the vehicle within the current first preset range.

[0052] Step S1032: Projecting the point cloud data along the first side according to the second curve equation to obtain first projection data, and / or projecting the point cloud data along the second side according to the first curve equation to obtain second projection data.

[0053] Among them, the first side line point cloud data and the second side line point cloud data are included in the roadside point cloud data.

[0054] Exemplarily, the above projection is to project each original point in the point cloud data along the first side according to the second curve equation to obtain a projection point, and the projection point corresponds to the original point in the point cloud data along the first side one by one. The line connecting the projection point and the original point passes through the curve corresponding to the second curve equation in the local coordinate system, and the line connecting the projection point and the original point is perpendicular to the tangent at the intersection, wherein the intersection is the intersection of the curve corresponding to the second curve equation in the local coordinate system and the line connecting the projection point and the original point. A collection of multiple projection points constitutes the first projection data.

[0055] Step S1033: Match the first projection data and the second projection data with the stationary point cloud data to obtain a matching result.

[0056] Specifically, the static point cloud data includes the mirror data of the point cloud data along the first side and the point cloud data along the second side. In the tunnel, when the millimeter wave radar acquires the point cloud data along the line, it will also acquire the mirror data due to the reflection effect. For example, when the millimeter wave radar acquires the point cloud data along the first side, it will also acquire the mirror data of the point cloud data along the second side. When the millimeter wave radar acquires the point cloud data along the second side, it will also acquire the mirror data of the point cloud data along the first side.

[0057] The above matching is to match the first projection data with the mirror image data of the first along-line data, and to match the second projection data with the mirror image data of the second along-line data.

[0058] Step S1034: Divide the roads within the first preset range into tunnel areas and non-tunnel areas according to the matching results.

[0059] Specifically, when the mirror data of the first projection data and the first line data have a matching data area, and the mirror data of the second projection data and the second line data in the matching data area also match each other, the road area corresponding to the matching data area is the tunnel area, and the remaining road areas are non-road areas. Similarly, when the mirror data of the second projection data and the second line data have a matching data area, and the mirror data of the first projection data and the first line data in the matching data area also match each other, the road area corresponding to the matching data area is the tunnel area, and the remaining road areas are non-road areas

[0060] It should be noted that the above matching data area is constructed by feature points in a plurality of continuously matched point cloud data. Continuous matching means that the coordinates of a plurality of consecutive feature points in the first projection data are similar to the coordinates of a plurality of consecutive feature points in the mirror image data of a plurality of first line data, or the coordinates of a plurality of consecutive feature points in the second projection data are similar to the coordinates of a plurality of consecutive feature points in the mirror image data of a plurality of second line data.

[0061] Exemplarily, the continuous matching is that the second feature point in the first projection data matches the second feature point in the first along-line data, the third feature point in the first projection data matches the third feature point in the first along-line data, and so on.

[0062] Through steps S1031 to S1034, the tunnel area and the non-tunnel area in the road can be divided only by processing the point cloud data, so that the vehicle entering and exiting the tunnel can be detected based on less basic data.

[0063] Optionally, the stationary point cloud data includes first-side stationary point cloud data and second-side stationary point cloud data. Step S1034, dividing the road within the first preset range into a tunnel area and a non-tunnel area according to the matching result, may include the following steps:

[0064] Step S1034a, determining the dividing line according to the matching result.

[0065] The matching result includes: first matching data between the first projection data and the first side static point cloud data, and second matching data between the second projection data and the second side static point cloud data.

[0066] Specifically, the first matching data and the second matching data are both matching point cloud data, and the matching point cloud data includes a plurality of continuously matched feature points. Determining the boundary line includes: connecting the first matched feature point in the first matching data with the first matched feature point in the second matching data to determine the boundary line, or connecting the last matched feature point in the first matching data with the last matched feature point in the second matching data to determine the boundary line.

[0067] Step S1034b: Divide the road within the first preset range into a tunnel area and a non-tunnel area using a dividing line.

[0068] Using a dividing line to divide the road within the first preset range into a tunnel area and a non-tunnel area can make the boundary between the two areas clearer, thereby making the detection result of vehicles entering and exiting the tunnel more accurate.

[0069] Optionally, step S103, identifying the tunnel area and the non-tunnel area from the road area within the first preset range based on the stationary point cloud data and the roadside point cloud data, may also include the following steps:

[0070] Step S103a: identifying potential tunnel areas and non-tunnel areas from the road area within a first preset range based on the stationary point cloud data and the roadside point cloud data.

[0071] Step S103b: dividing the potential tunnel area into multiple sub-areas.

[0072] Exemplarily, if the tunnel area is a rectangular area, the entire rectangular area is divided into a plurality of sub-areas along the length direction.

[0073] Step S103c, calculating the density of the stationary point cloud data in each sub-region.

[0074] Step S103d: if the density in the sub-region meets the preset density threshold, the sub-region is marked as a tunnel sub-region, and multiple tunnel sub-regions constitute a tunnel region.

[0075] Specifically, the density of the stationary point cloud in each sub-region is compared with a preset density threshold, and the sub-region whose stationary point cloud density meets the preset density threshold is marked as a tunnel sub-region. Multiple tunnel sub-regions together constitute a tunnel region.

[0076] The preset density threshold is determined according to the dynamic point cloud data, and different dynamic point cloud data correspond to different preset density thresholds.

[0077] Through steps S103a, S103b, S103c, and S103d, the tunnel area is first identified as a potential tunnel area, and the potential tunnel area is judged. Only the potential tunnel area that meets the requirements can be marked as a tunnel area, which can effectively avoid misidentification of the tunnel area.

[0078] Optionally, step S104, determining the situation of a vehicle entering or exiting a tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area, may include the following steps: judging whether the vehicle enters the tunnel according to the amount of change in the area range of the tunnel area, or judging whether the vehicle exits the tunnel according to the amount of change in the area range of the non-tunnel area.

[0079] Optionally, judging whether the vehicle has entered the tunnel according to the change in the area range of the tunnel area may include the following steps:

[0080] Step S1041, obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a first distribution situation.

[0081] Specifically, there are three first distribution situations. The first is that the second preset range only includes non-tunnel areas, the second is that the second preset range includes both non-tunnel areas and tunnel areas, and the third is that the second preset range only includes tunnel areas.

[0082] It should be noted that the second preset range is artificially set based on the detection range of the millimeter wave radar, and the second preset range is smaller than the first preset range.

[0083] Step S1042: if the second preset range only includes the non-tunnel area, obtain the first area range data.

[0084] The first area range data includes tunnel length data of multiple tunnel areas, and the multiple tunnel length data are arranged according to the time when they are acquired.

[0085] It should be noted that the car collects data in real time during the data collection process, and data is collected for each frame. Accordingly, in this method, each frame will generate a different tunnel area, and different tunnel areas correspond to different tunnel length data. Multiple tunnel length data are arranged in the data set according to the time of acquisition.

[0086] Step S1043, calculating an average value of multiple tunnel length data to obtain a first average value.

[0087] Step S1044, calculating the variation of at least two adjacent tunnel length data to obtain a first variation.

[0088] It should be noted that the above-mentioned proximity refers to the acquired time proximity. For example, the variation of the tunnel length data generated by the first frame and the tunnel length data generated by the second frame is calculated to obtain the first variation.

[0089] Step S1045: when the first average value is greater than the preset average value and the first variation is greater than the preset variation, it is determined that the vehicle is entering a tunnel.

[0090] It should be noted that, in some embodiments of the present invention, when the total length of multiple tunnel length data is greater than a preset total length and the first change is greater than a preset change, it can also be determined that the vehicle is entering a tunnel.

[0091] Optionally, judging whether the vehicle has exited the tunnel according to the change in the area range of the non-tunnel area may include the following steps:

[0092] Step S1046, obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located to obtain a second distribution situation.

[0093] Specifically, there are three second distribution situations. The first is that the second preset range only includes non-tunnel areas, the second is that the second preset range includes both non-tunnel areas and tunnel areas, and the third is that the second preset range only includes tunnel areas.

[0094] Step S1047: if the second preset range only includes the tunnel area, obtain the second area range data.

[0095] The second area range data includes non-tunnel length data of at least two non-tunnel areas, and the non-tunnel length data are arranged according to the time when they are acquired.

[0096] It should be noted that no matter how many non-tunnel length data are obtained, the non-tunnel length data of the non-tunnel area obtained should be adjacent data.

[0097] Step S1048, calculating the variation of two adjacent non-tunnel length data to obtain a second variation.

[0098] Step S1049, obtaining the movement distance of the vehicle.

[0099] The moving distance is used to characterize the distance the vehicle moves in the process of obtaining non-tunnel length data.

[0100] Exemplarily, if the acquisition times of two adjacent non-tunnel length data are time t and time t+1 respectively, the movement distance of the vehicle is the distance moved from time t to time t+1.

[0101] Step S1050: When the second change amount is equal to the movement distance, it is determined that the vehicle is exiting the tunnel.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0103] In this embodiment, a detection device for vehicles entering and exiting a tunnel is also provided, and the device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are not repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0104] Figure 2 is a structural block diagram of a detection device 200 for detecting a vehicle entering or exiting a tunnel according to one embodiment of the present invention. Figure 2 As shown, a detection device 200 for vehicles entering and exiting a tunnel is used as an example. The device includes: a collection module 201, the collection module 201 is used for the vehicle to travel along the road, and to collect point cloud data within a first preset range in real time where the vehicle is located, wherein the point cloud data includes static point cloud data and dynamic point cloud data; an extraction module 202, the extraction module 202 is used to extract curb point cloud data from the static point cloud data, wherein the curb point cloud data is used to characterize the point cloud data along both sides of the road collected when the vehicle travels along the road; a processing module 203, the processing module 203 is used to identify tunnel areas and non-tunnel areas from road areas within the first preset range based on the static point cloud data and the curb point cloud data, wherein, during the vehicle's travel along the road, the area ranges of the tunnel area and the non-tunnel area change based on the vehicle's travel dynamics; a judgment module 204, the judgment module 204 is used to determine the situation of the vehicle entering and exiting the tunnel based on the amount of change in the area ranges of the tunnel area and the non-tunnel area.

[0105] Optionally, the processing module 203 is also used to identify the tunnel area and the non-tunnel area from the road area within the first preset range based on the static point cloud data and the curb point cloud data, including: obtaining a first curve equation and a second curve equation by fitting the curb point cloud data, wherein the first curve equation is the curve equation along the first side of the road, and the second curve equation is the curve equation along the second side of the road; projecting the point cloud data along the first side according to the second curve equation to obtain first projection data, and / or projecting the point cloud data along the second side according to the first curve equation to obtain second projection data, wherein the point cloud data along the first side and the point cloud data along the second side are included in the curb point cloud data; matching the first projection data and the second projection data with the static point cloud data to obtain a matching result; and dividing the road within the first preset range into a tunnel area and a non-tunnel area according to the matching result.

[0106] Optionally, the stationary point cloud data in the acquisition module 201 includes stationary point cloud data on the first side and stationary point cloud data on the second side; the processing module 203 is also used to divide the road within the first preset range into a tunnel area and a non-tunnel area according to the matching results, including: determining a dividing line according to the matching results, wherein the matching results include: first matching data between the first projection data and the stationary point cloud data on the first side, and second matching data between the second projection data and the stationary point cloud data on the second side; using the dividing line to divide the road within the first preset range into a tunnel area and a non-tunnel area.

[0107] Optionally, the processing module 203 is also used to identify tunnel areas and non-tunnel areas from road areas within a first preset range based on the static point cloud data and the curb point cloud data, including: identifying potential tunnel areas and non-tunnel areas from road areas within the first preset range based on the static point cloud data and the curb point cloud data; dividing the potential tunnel area into multiple sub-areas; calculating the density of the static point cloud data in each sub-area; if the density in the sub-area meets a preset density threshold, marking the sub-area as a tunnel sub-area, and multiple tunnel sub-areas constitute a tunnel area, wherein the preset density threshold is determined based on the dynamic point cloud data.

[0108] Optionally, the judgment module 204 is also used to determine the situation of the vehicle entering or exiting the tunnel based on the change in the area range of the tunnel area and the non-tunnel area, including: judging whether the vehicle enters the tunnel according to the change in the area range of the tunnel area or judging whether the vehicle exits the tunnel according to the change in the area range of the non-tunnel area.

[0109] Optionally, the judgment module 204 is also used to judge whether the vehicle enters the tunnel according to the change in the area range of the tunnel area, including: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located; if the second preset range only includes non-tunnel areas, obtaining first area range data, wherein the first area range data includes tunnel length data of multiple tunnel areas, and the multiple tunnel length data are arranged according to the acquired time; calculating the average value of the multiple tunnel length data to obtain a first average value; calculating the change in at least two adjacent tunnel length data to obtain a first change; when the first average value is greater than the preset average value and the first change is greater than the preset change, it is determined that the vehicle is entering the tunnel.

[0110] Optionally, the judgment module 204 is also used to judge whether the vehicle has exited the tunnel based on the change in the area range of the non-tunnel area, including: obtaining the distribution of tunnel areas and non-tunnel areas within a second preset range where the vehicle is located; if the second preset range only includes the tunnel area, obtaining second area range data, wherein the second area range data includes non-tunnel length data of at least two non-tunnel areas, and the non-tunnel length data are arranged according to the acquired time; calculating the change in two adjacent non-tunnel length data to obtain a second change; obtaining the vehicle's movement distance, wherein the movement distance is used to characterize the distance the vehicle moves during the process of obtaining the non-tunnel length data; when the second change is equal to the movement distance, it is determined that the vehicle is exiting the lane.

[0111] An embodiment of the present invention further provides a vehicle, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in the embodiment of the above-mentioned method for detecting vehicle entering and exiting a tunnel.

[0112] Optionally, in this embodiment, the processor in the vehicle may be configured to run a computer program to perform the following steps:

[0113] Step S101: The vehicle travels along the road and collects point cloud data within a first preset range where the vehicle is located in real time.

[0114] Step S102, extracting roadside point cloud data from the static point cloud data.

[0115] Step S103: identifying tunnel areas and non-tunnel areas from road areas within a first preset range based on the stationary point cloud data and the roadside point cloud data.

[0116] Step S104, determining the situation of vehicles entering and exiting the tunnel based on the amount of change in the area ranges of the tunnel area and the non-tunnel area.

[0117] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0118] An embodiment of the present invention further provides a non-volatile storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps in the embodiment of the above-mentioned method for detecting vehicle entry and exit of a tunnel when running on a computer or a processor.

[0119] Optionally, in this embodiment, the non-volatile storage medium may be configured to store a computer program for performing the following steps:

[0120] Step S101: The vehicle travels along the road and collects point cloud data within a first preset range where the vehicle is located in real time.

[0121] Step S102, extracting roadside point cloud data from the static point cloud data.

[0122] Step S103: identifying tunnel areas and non-tunnel areas from road areas within a first preset range based on the stationary point cloud data and the roadside point cloud data.

[0123] Step S104, determining the situation of vehicles entering and exiting the tunnel based on the amount of change in the area ranges of the tunnel area and the non-tunnel area.

[0124] Optionally, in this embodiment, the above-mentioned non-volatile storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0125] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0126] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0131] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting a vehicle entering or exiting a tunnel, characterized in that: include: The vehicle travels along the road, and point cloud data within a first preset range where the vehicle is located is collected in real time, wherein the point cloud data includes static point cloud data and dynamic point cloud data; Extracting roadside point cloud data from the stationary point cloud data, wherein the roadside point cloud data is used to represent point cloud data along both sides of the road collected when the vehicle is traveling along the road; Based on the stationary point cloud data and the roadside point cloud data, identifying a tunnel area and a non-tunnel area from a road area within the first preset range, wherein during the driving of the vehicle along the road, the area ranges of the tunnel area and the non-tunnel area change based on the driving dynamics of the vehicle; Based on the amount of change in the area ranges of the tunnel area and the non-tunnel area, the situation of the vehicle entering or exiting the tunnel is determined.

2. The method for detecting a vehicle entering or exiting a tunnel according to claim 1, characterized in that: The identifying, based on the stationary point cloud data and the roadside point cloud data, a tunnel area and a non-tunnel area from a road area within the first preset range comprises: A first curve equation and a second curve equation are obtained by fitting the roadside point cloud data, wherein the first curve equation is a curve equation along a first side of the road, and the second curve equation is a curve equation along a second side of the road; Projecting the first side line point cloud data according to the second curve equation to obtain first projection data, and / or projecting the second side line point cloud data according to the first curve equation to obtain second projection data, wherein the first side line point cloud data and the second side line point cloud data are included in the roadside point cloud data; Matching the first projection data and the second projection data with the stationary point cloud data to obtain a matching result; The roads within the first preset range are divided into a tunnel area and a non-tunnel area according to the matching result.

3. The method for detecting a vehicle entering or exiting a tunnel according to claim 2, characterized in that: The stationary point cloud data includes first-side stationary point cloud data and second-side stationary point cloud data; The dividing the road within the first preset range into tunnel areas and non-tunnel areas according to the matching result includes: Determine a dividing line according to the matching result, wherein the matching result includes: first matching data between the first projection data and the first side static point cloud data, and second matching data between the second projection data and the second side static point cloud data; The road within the first preset range is divided into a tunnel area and a non-tunnel area by using the dividing line.

4. The method for detecting a vehicle entering or exiting a tunnel according to claim 1, characterized in that: The identifying, based on the stationary point cloud data and the roadside point cloud data, a tunnel area and a non-tunnel area from a road area within the first preset range comprises: Based on the stationary point cloud data and the roadside point cloud data, identifying potential tunnel areas and non-tunnel areas from the road area within the first preset range; dividing the potential tunnel area into a plurality of sub-areas; Calculating the density of the stationary point cloud data in each of the sub-regions; If the density in the sub-region meets a preset density threshold, the sub-region is marked as a tunnel sub-region, and a plurality of the tunnel sub-regions constitute the tunnel region, wherein the preset density threshold is determined according to the dynamic point cloud data.

5. The method for detecting a vehicle entering or exiting a tunnel according to claim 1, characterized in that: The determining of the vehicle entering or exiting the tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area includes: It is determined whether the vehicle enters the tunnel according to the amount of change in the area range of the tunnel area, or it is determined whether the vehicle exits the tunnel according to the amount of change in the area range of the non-tunnel area.

6. The method for detecting a vehicle entering or exiting a tunnel according to claim 5, characterized in that: The step of judging whether the vehicle has entered the tunnel according to the change in the area range of the tunnel area comprises: Acquiring distribution conditions of the tunnel area and the non-tunnel area within a second preset range where the vehicle is located to obtain a first distribution condition; If the second preset range only includes non-tunnel areas, obtaining first area range data, wherein the first area range data includes tunnel length data of a plurality of the tunnel areas, and the plurality of tunnel length data are arranged according to the time when they are obtained; Calculating an average value of a plurality of tunnel length data to obtain a first average value; Calculating the variation of at least two adjacent tunnel length data to obtain a first variation; When the first average value is greater than a preset average value and the first variation is greater than a preset variation, it is determined that the vehicle is entering a tunnel.

7. The method for detecting a vehicle entering or exiting a tunnel according to claim 5, characterized in that: The step of judging whether the vehicle has exited the tunnel according to the change in the area range of the non-tunnel area comprises: Acquiring distribution conditions of the tunnel area and the non-tunnel area within a second preset range where the vehicle is located to obtain a second distribution condition; If the second preset range only includes the tunnel area, obtaining second area range data, wherein the second area range data includes non-tunnel length data of at least two of the non-tunnel areas, and the non-tunnel length data are arranged according to the time when they are obtained; Calculating the variation of two adjacent non-tunnel length data to obtain a second variation; Acquiring a movement distance of the vehicle, wherein the movement distance is used to characterize a distance moved by the vehicle during the process of acquiring the non-tunnel length data; When the second change amount is equal to the movement distance, it is determined that the vehicle is exiting the tunnel.

8. A detection device for vehicles entering and exiting a tunnel, characterized in that: include: A collection module, the collection module is used for collecting point cloud data within a first preset range where the vehicle is located in real time when the vehicle is traveling along the road, wherein the point cloud data includes static point cloud data and dynamic point cloud data; An extraction module, the extraction module is used to extract roadside point cloud data from the static point cloud data, wherein the roadside point cloud data is used to represent the point cloud data along both sides of the road collected when the vehicle is traveling along the road; a processing module, the processing module being configured to identify a tunnel area and a non-tunnel area from a road area within the first preset range based on the stationary point cloud data and the roadside point cloud data, wherein during the driving of the vehicle along the road, the area ranges of the tunnel area and the non-tunnel area change based on the driving dynamics of the vehicle; A judgment module is used to determine the situation of the vehicle entering or exiting the tunnel based on the amount of change in the area range of the tunnel area and the non-tunnel area.

9. A vehicle comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for detecting a vehicle entering or exiting a tunnel as claimed in any one of claims 1 to 7.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the computer program is configured to execute the method for detecting a vehicle entering or exiting a tunnel as claimed in any one of claims 1 to 7 when running on a computer or a processor.

Citation Information

Patent Citations

  • Mobile tunnel laser detection data processing method

    CN110411361A

  • Auxiliary navigation method, vehicle unit and vehicle

    CN110411461A

  • A tunnel scene detection method and a millimeter wave radar

    CN111699408A

  • Vehicle tracking method and system

    CN112099042A

  • High-speed railway side slope deformation detection method and device

    CN112731440A