CN111856611A

CN111856611A - Trigger detection method, device and system

Info

Publication number: CN111856611A
Application number: CN201910309995.2A
Authority: CN
Inventors: 李扬彦; 单单; 陈颖; 王振华
Original assignee: Alibaba Group Holding Ltd
Current assignee: Wuzhou Online E Commerce Beijing Co ltd
Priority date: 2019-04-17
Filing date: 2019-04-17
Publication date: 2020-10-30
Also published as: WO2020211658A1

Abstract

The embodiment of the application discloses a trigger detection method, a device and a system, wherein the system comprises a road surface detection device and a first sensor, wherein the road surface detection device is used for detecting an event that a vehicle passes through a target detection area through the first sensor buried in the target detection area on the surface of a road; the roadside detection device is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is arranged on roadside equipment and can cover the target detection area; and the fusion algorithm processing device is used for fusing the road surface detection result of the road side detection device with the road side detection result of the road side detection device according to the road surface detection result of the road surface detection device, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to the judgment result. By the embodiment of the application, the false detection rate and the missing detection rate in the trigger detection stage can be reduced, the accuracy of license plate identification can be improved, and the non-inductive payment can be more fully applied in an expressway scene.

Description

Trigger detection method, device and system

Technical Field

The present application relates to the field of trigger detection technologies, and in particular, to a trigger detection method, device and system.

Background

In the face of the increasing traffic pressure of highways, more and more highway operators are aware that the introduction of diversified payment means can make up the defects of the existing payment means of highways, so that the traffic efficiency of vehicles is improved, and the pressure of toll collectors is reduced. The 'non-inductive payment' adopts the internet and electronic payment technology, and by means of the 'license plate payment' concept of the vehicle, the license plate of the vehicle is used as a unique identifier, so that the cash collection mode of a toll station is converted into an on-line mobile payment mode. Before the vehicle is used, a vehicle owner can firstly bind an account number registered in a mobile payment tool with a license plate, in addition, functions of 'secret payment free' and the like can be opened, the license plate number becomes a 'payment code', when a vehicle enters and exits a parking lot or a highway toll station, a high-definition camera installed in the toll station automatically lifts a rod and automatically deducts fees after recognizing the license plate, and the whole process does not need to be stopped. Compare the ETC charge mode, noninductive payment not only opens simply, need not install On-vehicle OBU (On board Unit) equipment moreover, and the payment mode is also very convenient nimble.

However, at present, the non-inductive payment is only relatively fully applied in a parking lot scene, and is limited in an expressway scene. This is because, in an expressway scene, the driving speed of the vehicle is often faster, and the recognition accuracy of the existing license plate recognition technology in the expressway scene has not yet reached the relevant requirements. At present, many suppliers claim that the license plate recognition rate of the suppliers reaches about 99%, however, in severe environments, such as rainstorm, storm, haze, heavy snow and other weather, most license plate recognition rates are reduced by about 3% compared with the ordinary recognition rates, and therefore, in the aspect of risk prevention and control, the pass card auxiliary verification is still required for the non-inductive payment of the expressway.

Therefore, how to improve the accuracy of license plate recognition and enable the non-inductive payment to be more fully applied in the expressway scene becomes a technical problem to be solved by technical personnel in the field.

Disclosure of Invention

The application provides a trigger detection method, a trigger detection device and a trigger detection system, which can reduce the false detection rate and the missed detection rate in the trigger detection stage, are beneficial to improving the accuracy of license plate identification, and enable the non-inductive payment to be more fully applied in the expressway scene.

The application provides the following scheme:

a trigger detection system comprising:

the road surface detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the road surface;

the roadside detection device is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is arranged on roadside equipment and can cover the target detection area;

and the fusion algorithm processing device is used for fusing the road surface detection result of the road side detection device with the road side detection result of the road side detection device according to the road surface detection result of the road surface detection device, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to the judgment result.

A trigger detection method, comprising:

receiving a road surface detection result of a road surface detection device and a road side detection result of the road side detection device, wherein the road surface detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the surface of the road, and the road side detection device is used for detecting the event that the vehicle passes through the target detection area through a second sensor which is installed on road side equipment and can cover the target detection area;

judging whether a vehicle passes through the target detection area or not by fusing the road surface detection result and the roadside detection result;

and generating a trigger signal according to the judgment result.

A trigger detection method, comprising:

and generating a trigger signal according to the judgment result.

A trigger detection system comprising:

the visual detection device is used for detecting an event that a vehicle passes through a target detection area by a visual sensor which is arranged on road side equipment and can cover the target detection area;

the radar detection device is used for detecting an event that a vehicle passes through the target detection area through a radar sensor which is arranged on the road side equipment and can cover the target detection area;

and the fusion algorithm processing device is used for fusing the visual detection result of the visual detection device with the radar detection result of the radar detection device, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to the judgment result.

A trigger detection method, comprising:

receiving a visual detection result of a visual detection device and a radar detection result of a radar detection device, wherein the visual detection device is used for detecting an event that a vehicle passes through a target detection area through a visual sensor which is installed on road side equipment and can cover the target detection area, and the radar detection device is used for detecting the event that the vehicle passes through the target detection area through a radar sensor which is installed on the road side equipment and can cover the target detection area;

Judging whether a vehicle passes through the target detection area or not by fusing the visual detection result and the radar detection result;

and generating a trigger signal according to the judgment result.

A trigger detection apparatus comprising:

the road detection device comprises a first result receiving unit, a second result receiving unit and a control unit, wherein the first result receiving unit is used for receiving a road surface detection result of a road detection device and a road side detection result of the road side detection device, the road detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area of a road surface, and the road side detection device is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is installed on road side equipment and can cover the target detection area;

the first fusion calculation unit is used for judging whether a vehicle passes through the target detection area or not by fusing the road surface detection result and the roadside detection result;

and the first signal generation unit is used for generating a trigger signal according to the judgment result.

A trigger detection apparatus comprising:

a second result receiving unit, configured to receive a visual detection result of a visual detection device and a radar detection result of a radar detection device, where the visual detection device is configured to detect an event that a vehicle passes through a target detection area by using a visual sensor that is mounted on a roadside apparatus and can cover the target detection area, and the radar detection device is configured to detect an event that the vehicle passes through the target detection area by using a radar sensor that is mounted on the roadside apparatus and can cover the target detection area;

The second fusion calculation unit is used for judging whether a vehicle passes through the target detection area or not by fusing the visual detection result and the radar detection result;

and the second signal generating unit is used for generating a trigger signal according to the judgment result.

A roadside apparatus comprising:

the roadside detection device is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is arranged on the roadside equipment and can cover the target detection area;

the fusion algorithm processing device is used for fusing a road surface detection result of the road side detection device with a road side detection result of the road side detection device according to the road surface detection result of the road surface detection device, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to a judgment result; the road surface detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the road surface.

A roadside apparatus comprising:

According to the specific embodiments provided herein, the present application discloses the following technical effects:

according to the embodiment of the application, the detection results of the event that the vehicle passes through the target detection area by the road surface detection device and the road side detection device can be fused, so that whether the vehicle passes through the target detection area or not is judged, and the trigger signal is generated according to the judgment result and is used for triggering the operations such as license plate recognition. The road surface detection device can detect an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the surface of a road, and the roadside detection device can detect the event that the vehicle passes through the target detection area through a second sensor which is installed on roadside equipment and can cover the target detection area. In this way, the detection result of the event that the vehicle enters the target detection area can be triggered and detected by fusing the two systems, so that the false detection rate and the missing detection rate can be reduced. In addition, because the two systems have different working principles and are arranged at large intervals (one is buried under the road surface and the other is arranged on the road side equipment), the two systems have almost completely different failure modes, and the average fault-free running time of the whole trigger detection system is greatly improved. Moreover, the two systems have lower hardware cost, especially for a sensor installed on road side equipment, the system belongs to a hardware device shared by functions such as cooperation with a vehicle and a road, and for a road section provided with the road side equipment, no additional hardware cost needs to be added, so that the overall hardware cost of the trigger detection system in the embodiment of the application is lower, and the system is beneficial to more sufficient application of the non-inductive payment in a highway scene.

In another embodiment, trigger detection may be performed by specifically sensing mutual fusion between different sensors in the base station. In this manner, since there are also different operating principles between different classes of sensors, there will be a significant difference in failure modes, although the mounting locations are relatively close. In this way, since it is not necessary to install hardware equipment on the ground, the requirement for road construction is low, and the sensor equipment used is shared by functions such as cooperation with the vehicle and the road, and therefore, the hardware cost can be reduced as a whole.

Of course, it is not necessary for any product to achieve all of the above-described advantages at the same time for the practice of the present application.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

FIG. 1 is a schematic diagram of a system provided by an embodiment of the present application;

FIG. 2 is a flow chart of a first method provided by an embodiment of the present application;

FIG. 3 is a schematic diagram of another system provided by embodiments of the present application;

FIG. 4 is a flow chart of a second method provided by embodiments of the present application;

fig. 5 is a schematic diagram of an apparatus provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments that can be derived from the embodiments given herein by a person of ordinary skill in the art are intended to be within the scope of the present disclosure.

It should be noted that, in the license plate recognition process, two stages are usually required, one is trigger detection that a vehicle just enters a detection area, and the other is continuous detection that a vehicle travels subsequently until the vehicle leaves the detection area. The license plate recognition equipment can be installed in the detection area, and can perform operations such as photographing and recognition under the triggering of specific instructions. The accuracy of license plate recognition is related to the accuracy of specific trigger detection, in addition to the accuracy of specific recognition algorithm. In other words, one important factor affecting the license plate recognition rate is the exposure timing of the camera that captures the license plate, and the exposure timing is selected according to the result from the vehicle trigger detection. If the vehicle cannot be found when passing by, and the triggering instruction cannot be sent to the identification device in time, the identification device may not acquire the related license plate information in time, and further the identification of the license plate information cannot be mentioned. Therefore, the accuracy of the trigger detection phase is also crucial. In the embodiment of the application, a corresponding solution is mainly provided for the trigger detection phase. Specifically, the so-called trigger detection is to detect an event that a vehicle enters the detection area, and based on the event, a trigger instruction is issued to a specific license plate recognition device or the like.

The specific implementation manner of detecting the event that a vehicle enters the detection area may be various, for example, in one implementation manner, the detection may be implemented by using a road surface trigger detection system, for example, the detection may be specifically triggered by using an induction coil or a pressure gauge. The induction coil is a ring-shaped sensor buried in the ground surface. When a large metal object (e.g., a vehicle) passes over the coil, the inductance value of the coil changes greatly, so that the vehicle can be detected. A pressure gauge is a linear sensor array buried in the ground, and when a heavy object (for example, a vehicle) passes over the sensor array, the voltage or resistance of the sensor array changes greatly, so that the vehicle can be detected. However, a disadvantage of such a road surface trigger detection system is that in an expressway scenario, the speed of the vehicle may be relatively high, in which case the vehicle may rapidly pass over a specific induction coil or pressure gauge, in which case the probability of missed detection may be relatively high. In addition, the detection system needs to modify the road surface, the construction difficulty is high, and the positions of the charging points on the expressway which need to be set are too many, for example, the positions comprise an expressway entrance and exit, a provincial boundary position and the like, so that the normal road traffic can be influenced.

In addition, there are also trigger detection schemes that may be considered, for example, by installing an ultrasonic or infrared grating device at a particular toll point, etc., by which an event of a vehicle entering a detection area is detected. Although this method is less affected by vehicle speed, it still needs to involve road construction modification.

Based on the above analysis, the embodiment of the present application provides a new trigger detection method, in which a trigger detection function of a vehicle can be combined with a function of a sensing base station in a vehicle-road cooperative system. In the vehicle-road cooperative system, the sensing base station generally corresponds to roadside equipment, wherein the roadside equipment may be intelligent roadside equipment, and the equipment is infrastructure located in a road subsystem. The system mainly comprises an RSU (road side Unit, V2X equipment deployed on or near a road, and physical units including but not limited to communication (I2V) between the road side Unit and an on-board Unit, communication (I2I) between the road side Unit and the road side Unit, a road side sensor, a calculation storage Unit and the like. The sensing means of the road side sensor mainly comprises the steps of acquiring data of sensors such as a camera, a millimeter wave radar and a laser radar, processing the data in a computing unit through an image or signal processing algorithm, and finally acquiring information of roads and traffic participants, such as lane line coordinates, positions and speeds of vehicles and pedestrians. The vehicle can obtain the information of the surrounding environment by receiving the broadcast message, and further make driving decision or realize auxiliary driving by combining the speed of the vehicle and the like.

Therefore, in the embodiment of the application, specific trigger detection can be realized by combining multiple trigger detection systems based on the road side equipment in the vehicle-road cooperation system, whether a vehicle appears in a specific detection area is judged through mutual verification among different trigger detection systems to detect, and then a trigger instruction is sent to specific license plate recognition equipment. Through the fusion of the multiple trigger detection systems, the false detection rate and the missing detection rate of trigger detection can be reduced, and a foundation is provided for improving the accuracy of license plate identification.

And aiming at different specific scenes, different fusion modes can be adopted. For example, for a target location where a specific vehicle is generally slow in running speed and has an imperceptible billing requirement, for example, an entrance or an exit of an expressway, since the vehicle is usually designed to have a ramp section and the like at such an entrance or exit, the running speed of the vehicle may be slow, which is beneficial for the road surface trigger detection system to perform high-reliability detection. Therefore, for the above situation, the road surface trigger detection system may be combined with the vision or radar (millimeter wave radar or laser radar, etc.) sensor in the roadside device, that is, the sensing results of the vision, radar, etc. sensor in the sensing base station may also be added to the trigger detection, and the detection results of the two sets of systems are subjected to fusion calculation to determine whether a vehicle is passing through the detection area. In this way, when a vehicle is detected by either of the two systems, it can be detected by the hybrid trigger detection system, and therefore the miss rate is greatly reduced. In addition, because the two systems have completely different working principles and larger installation position intervals (one is buried under the road surface and the other is installed on the road side equipment), the two systems have almost completely different failure modes, and the average fault-free running time of the whole trigger detection system is greatly improved. Moreover, the two systems have lower hardware cost (for the sensor installed on the road side equipment, the sensor belongs to the hardware equipment shared by the functions of cooperation with the vehicle and the road and the like, so the hardware cost is lower), and therefore the overall hardware cost of the hybrid trigger detection system is lower.

In addition, there may be a demand for non-sensitive charging on the main road of the highway, for example, when the vehicle crosses the boundary of different jurisdictions, etc., there may be a sectional type of non-sensitive charging, etc. In this scenario, the vehicle belongs to the main road and is not limited by road sections such as ramp roads and the like, so that the running speed of the vehicle may be relatively high, and therefore, the method is not suitable for triggering detection by adopting a road surface triggering detection system. In the sensing base station, since various sensors of different types, such as a vision sensor, a radar sensor, etc., may be included, the trigger detection may also be performed by mutual fusion between different sensors in the specific sensing base station. In this manner, since there are also different operating principles between different classes of sensors, there will be a significant difference in failure modes, although the mounting locations are relatively close. In this way, since it is not necessary to install hardware equipment on the ground, the requirement for road construction is low, and the sensor equipment used is shared by functions such as cooperation with the vehicle and the road, and therefore, the hardware cost can be reduced as a whole.

That is to say, in the embodiment of the present application, a sensor on the roadside device may be used as a part of a data source for trigger detection, and the roadside device and various sensors arranged therein generally belong to hardware devices in a vehicle-road coordination system. In other words, when the design of the vehicle-road cooperative system is normally performed, the above devices need to be installed and deployed, so that when the sensor on the roadside device is used for event perception, on a hardware level, only the same set of hardware device needs to be shared with the vehicle-road cooperative system, and on a software level, an algorithm for event perception, a fusion algorithm, and the like can be additionally implemented. Therefore, the overall hardware cost is controlled, the improvement on the road surface only relates to the entrance or the exit of the expressway, and the construction amount and the difficulty are greatly reduced. In addition, the transformation of the highway entrance and exit does not affect the vehicles normally running in the highway, so the influence on traffic efficiency is small. Certainly, the entrance or the exit of the highway can also be triggered and detected in a way of combining the visual sensor and the radar sensor on the roadside device, and at this time, lower hardware cost can be realized.

Specific implementations are described in detail below.

Example one

In the first embodiment, a scheme of integrating the road surface trigger detection and the roadside device trigger detection is described first. Specifically, referring to fig. 1, a first embodiment of the present application first provides a trigger detection system, which may include:

a road surface detection device 101 for detecting an event that a vehicle passes through a target detection area on a road surface by a first sensor buried in the target detection area;

the roadside detection device 102 is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is installed on roadside equipment and can cover the target detection area;

and the fusion algorithm processing device 103 is used for fusing the road surface detection result of the road side detection device with the road side detection result of the road side detection device, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to the judgment result.

Among them, the first sensor buried in the road surface is required to have at least one physical quantity of the first sensor rapidly, strongly and predictably changed each time a vehicle passes by the first sensor, so as to overcome the problems of high driving speed of the vehicle, large variation range of the size and weight of the vehicle, bumping during the driving of the vehicle, and the like. In particular implementations, the first sensor may include an induction coil or a pressure gauge. If the induction coil is used, the first sensor only has a vehicle trigger detection function, and the cost is low; if the pressure gauge is used, the vehicle can be triggered to be detected, and additional information such as vehicle speed, wheelbase and the like can be obtained, but the cost is slightly higher. Accordingly, the former may be referred to as a "low distribution system" and, correspondingly, the latter may be referred to as a "high distribution system".

Specifically, the low-distribution system may include an induction coil, a feed line, and a detector. When a massive metal object (such as a vehicle) passes through the coil, the inductance value of the coil is reduced, and the frequency value of an output signal of an oscillating circuit in the detector is increased; when the variation exceeds a threshold value and is found by the frequency detection circuit, the detector considers that the vehicle passes by currently and outputs the detection result, otherwise, the default is no vehicle passes by.

A pressure gauge, a feed line, and a detector may be included in the high-distribution system. As the vehicle passes the detection device, the wheels of each axle sequentially roll the plurality of linear sensors, causing their voltages (or resistance values) to sequentially change. After the changes are adjusted to a proper dynamic range by the multi-channel signal amplifier, the changes are sent to the multi-channel analog-to-digital converter for simultaneous sampling, the sampling result is sent to a signal processing algorithm as a digital signal, and finally, the detection results of whether a vehicle passes through, the movement direction, the vehicle speed, the wheel base and the like are obtained.

The second sensor may specifically comprise a vision sensor or a radar sensor or the like. The visual trigger detection system can detect vehicles on the road surface in real time through an artificial intelligence algorithm and computing power, and can distinguish lanes where the vehicles are located. The visual detection module takes a video image stream as input, checks whether a vehicle exists in a current image frame of the video stream according to a certain fixed frequency, and if the vehicle exists, the system informs related modules and outputs the position of the vehicle to the related modules.

The radar trigger detection system can detect road clearance or the change of electromagnetic wave frequency caused by vehicle passing through by a millimeter wave radar and the like arranged above a road to perform trigger detection on the vehicle. Among them, the millimeter wave radar is an active sensor based on electromagnetic waves. The method transmits electromagnetic waves with modulation bands in different directions and located in a millimeter wave frequency band, receives reflected signals, measures the distance and the speed of objects of the reflected signals, describes the objects into targets and outputs the targets as detection results. The requirements for a millimeter wave radar installed above a road are that at least one physical quantity measured by the radar changes rapidly, strongly and predictably whenever a vehicle passes through a monitoring system, and the problems of high running speed of the vehicle, large size change range of the vehicle, bumping during the running of the vehicle and the like are overcome.

A millimeter wave radar and a signal receiver may be included in the radar trigger detection system. The millimeter wave radar transmits a millimeter wave signal with a narrow wave beam and a known frequency to scan a road surface, and road clearance and Doppler frequency shift are measured in real time. When a vehicle passes through the detection system, road clearance is reduced, Doppler frequency shift is increased, and accordingly the millimeter wave radar can detect the vehicle. The millimeter wave radar can detect a plurality of vehicles at the same time and describe information of their positions, speeds, reflected signal strengths, etc. as a plurality of targets as a result output, which is referred to as multi-target information. And (4) sending the multi-target information to a signal receiver, and generating a final detection result after filtering false targets through algorithm processing.

The signal receiver receives multi-target information output by the millimeter wave radar in real time and filters out false targets through an algorithm. The method mainly comprises the steps of firstly reading map data and calibration parameters, obtaining feasible areas near the radar mounting positions, and filtering out targets outside the feasible areas; secondly, for the targets in the feasible region, the intensity of the reflected signals of the targets can be checked and compared with a pre-stored statistical rule, and the targets which do not accord with the statistical rule are filtered; the remaining targets are output as the final detection result.

After the road surface detection device and the roadside detection device detect the event that the vehicle enters the target detection area, the detection result can be provided to the fusion algorithm processing device, and the system performs fusion processing to obtain the final judgment result. The fusion algorithm processing device may be specifically configured in a processor device on the roadside device, or may also be configured in other devices, and may be respectively connected to the road surface detection device and the roadside detection device, where each of the detection systems and the processor device is in a stationary state, and the distances between the detection systems and the processor device are relatively short, so that data connection may be specifically achieved in various ways such as wired or wireless, and data transmission may be performed between the detection systems and the processor device.

It should be noted that, the roadside device described in the embodiment of the present application may be collectively referred to as an intelligent roadside device, and the device is an infrastructure located in a road subsystem. The system mainly comprises physical units such as RSU (road side unit), road side sensor, calculation storage unit and the like; the computing storage unit can be composed of two subunits of intelligent computing and storage. Different physical units may be deployed on different physical devices, or may be deployed in the same physical device. Therefore, in specific implementation, a specific fusion computing system can be deployed in the road side equipment by means of the characteristics of the road side equipment, and only a special intelligent computing and storing subunit is expanded for the embodiment of the application on the original basis. In this way, the original intelligent computing and storing subunit can still be used for performing related computing in the vehicle-road cooperative system, and the expanded intelligent computing and storing subunit is used for the fusion computing processing related to trigger detection in the embodiment of the present application.

Specifically, when the fusion process is performed, the same corresponding vehicle in the road surface detection result and the roadside detection result may be identified first. In a specific implementation, the first sensor is just below the ground of the target detection area, so that the detection result naturally has a position information attribute, and the second sensor is installed on roadside equipment, but has the position sensing capability, so that the sensed position information can be carried in the roadside detection result. In this way, the fusion algorithm processing device may determine, after receiving the detection results of the two, that the vehicle included in the road surface detection result and the vehicle in the roadside detection result are determined to be the same vehicle and determine that the vehicle is passing through the target detection area if the road surface detection result indicates that the vehicle passes through the target detection area and the roadside detection result indicates that the position information of the vehicle is located in the target detection area.

In concrete implementation, the road surface detection result and the roadside detection result may be directly present in two states of yes and no, and if both the detection results are yes at a certain time, yes is output after fusion, and if both are no, no is output after fusion. However, if one is yes and the other is no, it means that the detection results of the two are contradictory, and therefore, a situation that the fusion cannot be performed may occur, which does not meet the original design purpose of the fusion algorithm. Therefore, in an optional implementation manner, in order to further improve the reliability of the trigger detection, a compromise scheme may be further adopted to fuse the two detection results. Specifically, after receiving the detection results of the two detection systems, in the fusion calculation process, probability calculation may be performed first, and then fusion may be performed, so as to obtain the result of the fusion calculation. That is, after receiving the detection results of the two detection systems, the respective "confidence" of the two detection systems is determined, then the two detection systems are added, and the obtained result is compared with the decision threshold, so as to improve the reliability of the specific fusion result.

Specifically, when calculating the probability, the probability calculation can be performed in real time by the two detection systems according to the detection algorithm, specifically, the probability is called a posterior probability, and mathematically, the probability can be determined by the matching degree between the detection result and the template signal or the training model. Thus, when performing the fusion calculation, it can be performed as follows:

y＝p1*r1+p2*r2

wherein p1 and p2 are weights derived by a posterior probability; r1 and r2 are the initial detection results, 1 indicates the presence of a car in the designated area, and 0 indicates the absence of a car.

And then, the fusion algorithm compares the y with a judgment threshold to obtain a final result of whether a vehicle passes through.

In a specific implementation, the calculation of the posterior probability may be performed separately in each detection system. Specifically, the road surface detection device can determine a first posterior probability according to the matching degree between the initial detection result and the template signal/training model; the roadside detection device may determine the second posterior probability according to a matching degree between the initial detection result and the template signal/training model. In this way, the first initial detection result may be multiplied by the first posterior probability to obtain a first probability; and multiplying the second initial detection result by the second posterior probability to obtain a second probability. Therefore, after the two probabilities received by the fusion calculation system are fused, the two probabilities are added to be used as a result of the fusion calculation, and the result is compared with the judgment threshold to obtain the final result of whether the vehicle passes through or not. That is, for each detection system, the initial detection result is a result of 0 or 1, and after obtaining the initial detection result, the initial detection result is not directly sent to the fusion calculation system for fusion calculation, but the posterior probability is calculated according to the matching degree with the template signal/training model, and then the posterior probability is multiplied by the initial detection result, and the calculated probability value is used as the actual output value of the detection system. In this way, the probability value of the data received by the computing system is fused and is no longer the initial detection result of 0 or 1.

Alternatively, in order to obtain the fusion detection result more accurately, a priori probability component can be introduced. Specifically, the confidence of the detection result obtained by a specific detection system may also be affected by factors such as weather, vehicle speed, and the like, and such an effect may be obtained through analysis of some historical data or machine learning. Therefore, the prior probability can be obtained by providing different detection probabilities corresponding to different weather and vehicle speeds according to the statistical results stored in advance. Since the respective working principles and the like are different for different detection systems, the confidence degrees of the detection results may be different even under the same weather, vehicle speed and other conditions, and therefore, the prior probabilities in the respective detection systems can be obtained respectively. Thus, by combining these two probabilities, the problem of accuracy of the fusion detection result can be solved more accurately. For example, in one implementation, the mathematical description of a particular algorithm may be as follows:

y＝c1*x1+c2*x2,

where c1 and c2 are weights derived by a priori probability, x1 and x2 are the outputs of the two detection systems, and y is the output of the fusion algorithm. For x1 and x2, their calculation methods are as follows:

x1＝p1*r1，x2＝p2*r2

And finally, the fusion algorithm compares y with a judgment threshold to obtain the final result of whether a vehicle passes through.

In specific implementation, the introduction of the prior probability may be completed by a fusion computing system, that is, after receiving the road surface detection result and the roadside detection result (which has been calculated according to the posterior probability), first, a first prior probability corresponding to the road surface detection device and a second prior probability corresponding to the roadside detection result may be determined according to the pre-stored historical statistical results corresponding to the respective detection systems. Then, the road surface detection result may be multiplied by the first prior probability, the roadside detection result may be multiplied by the second prior probability, and the products of the two may be added to obtain a final fusion calculation result. And then, comparing the fusion calculation result with a judgment threshold to determine a fusion judgment result, namely whether a vehicle passes through the target area.

During specific implementation, after generating a specific trigger signal according to a specific fusion estimation result, the fusion algorithm processing device may further send the trigger signal to a license plate recognition device, where the license plate recognition device is configured to recognize a license plate of a vehicle, so as to perform charging processing on the vehicle.

According to the scheme provided by the first embodiment of the application, the specific license plate recognition device, the first sensor and the roadside device can be arranged at a target position on a highway, wherein the target position has the characteristic of slow running of vehicles and has a non-inductive charging requirement. For example, it may be specifically provided at an entrance/exit of a highway for a non-sensitive billing process for a vehicle entering or leaving the highway, or the like.

It should be noted that, in a specific implementation, the fusion estimation result provided in the embodiment of the present application may also be provided to a processing module for performing traffic flow monitoring, and the like.

In short, according to the embodiment of the application, the detection results of the event that the vehicle passes through the target detection area by the road surface detection device and the road side detection device can be fused, so that whether the vehicle passes through the target detection area or not is judged, and the trigger signal is generated according to the judgment result and is used for triggering the operations such as the identification of the license plate. The road surface detection device can detect an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the surface of a road, and the roadside detection device can detect the event that the vehicle passes through the target detection area through a second sensor which is installed on roadside equipment and can cover the target detection area. In this way, the detection result of the event that the vehicle enters the target detection area can be triggered and detected by fusing the two systems, so that the false detection rate and the missing detection rate can be reduced. In addition, because the two systems have different working principles and larger distance between installation positions (one is buried under the road surface and the other is hung on road side equipment), the two systems have almost completely different failure modes, and the average fault-free running time of the whole trigger detection system is greatly improved. Moreover, both sets of systems have lower hardware cost, especially for the sensor installed on the roadside device, belong to the hardware device that shares with functions such as vehicle and road cooperation, to the highway section that has set up the roadside device, more need not newly increase the hardware cost, consequently for the whole hardware cost of the trigger detection system in this application embodiment is lower.

Example two

The second embodiment corresponds to the first embodiment, and provides a trigger detection method from the perspective of a specific fusion algorithm processing device, referring to fig. 2, where the method specifically includes:

s201: receiving a road surface detection result of a road surface detection device and a road side detection result of the road side detection device, wherein the road surface detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the surface of the road, and the road side detection device is used for detecting the event that the vehicle passes through the target detection area through a second sensor which is installed on road side equipment and can cover the target detection area;

s202: judging whether a vehicle passes through the target detection area or not by fusing the road surface detection result and the roadside detection result;

s203: and generating a trigger detection signal according to the judgment result.

The roadside detection result also comprises the perceived position information of the vehicle; at this time, specifically, when it is determined whether a vehicle passes through the target detection area, the following may be performed: and if the road surface detection result indicates that a vehicle passes through the target detection area and the roadside detection result indicates that the position information of the vehicle is located in the target detection area, determining the vehicle included in the road surface detection result and the vehicle in the roadside detection result as the same vehicle and determining that the vehicle passes through the target detection area.

In addition, in a specific implementation, the road surface detection result may include: a first probability that a vehicle passes through the target detection zone; the roadside detection result may include: a second probability that a vehicle passes through the target detection zone; at this time, when it is determined whether a vehicle passes through the target detection region, it may be determined whether the vehicle passes through the target detection region according to the first probability, the second probability, and determination threshold information in a preset estimation algorithm.

Specifically, the first probability is determined by the road surface detection device according to an initial detection result and a posterior probability corresponding to the road surface detection device;

the second probability is determined by the roadside detection device according to an initial detection result and a posterior probability corresponding to the roadside detection device;

wherein the posterior probability is determined according to the matching degree between the initial detection result and a template signal and/or a pre-trained model;

the initial detection result is as follows: and the respective detection systems detect whether the vehicle passes through the target detection area or not.

Or, further, during the fusion calculation, a first prior probability corresponding to the road surface detection device and a second prior probability corresponding to the roadside detection device may be determined according to current weather and/or vehicle speed factors and pre-stored historical statistical results corresponding to respective detection systems; the historical statistics include: the confidence of the initial detection result of each detection system under the condition of corresponding weather and/or vehicle speed;

And then, adding the product of the first probability and the first prior probability and the product of the second probability and the second prior probability, and judging whether a vehicle passes through the target detection area or not by comparing the added result with preset threshold information.

EXAMPLE III

The third embodiment provides another trigger detection system, in which two sets of trigger detection systems may be included as well, detection may be performed by two different sensor devices that are installed on the roadside device and may cover the target detection area, and detection results are fused together, so as to improve reliability of specific trigger detection. Specifically, referring to fig. 3, the system may include:

the vision detection device 301 is used for detecting an event that the vehicle passes through a target detection area by a vision sensor which is installed on road side equipment and can cover the target detection area;

a radar detection device 302, configured to detect an event that a vehicle passes through the target detection area through a radar sensor that is mounted on the roadside apparatus and can cover the target detection area;

and the fusion algorithm processing device 303 is configured to fuse the visual detection result of the visual detection device with the radar detection result of the radar detection device, determine whether a vehicle passes through the target detection area, and generate a trigger detection signal according to the determination result.

The fusion algorithm processing device can be further used for sending the trigger detection signal to a license plate recognition device, and the license plate recognition device is used for recognizing a license plate of a vehicle so as to charge the vehicle.

In the third embodiment, the license plate recognition device and the road side device are more suitable for being arranged at a target position on a highway, wherein the target position has the characteristic of rapid vehicle driving and has an insensitive charging demand. For example, it may be specifically the jurisdiction boundary on the expressway, where the jurisdiction boundary is usually located on the main road of the expressway, and the driving speed of the vehicle will usually be relatively fast, so that the solution provided in the third embodiment may be used to implement the non-inductive charging process for the vehicles entering different jurisdictions. Of course, it is also possible if it is provided at the entrance or exit of a highway.

The specific visual trigger detection system and radar trigger detection system in the third embodiment may be the same as those in the first embodiment, and are not described in detail here.

Through the third embodiment, the trigger detection can be performed through mutual fusion between different sensors in the specific sensing base station. In this manner, since there are also different operating principles between different classes of sensors, there will be a significant difference in failure modes, although the mounting locations are relatively close. In this way, since it is not necessary to install hardware equipment on the ground, the requirement for road construction is low, and the sensor equipment used is shared by functions such as cooperation with the vehicle and the road, and therefore, the hardware cost can be reduced as a whole.

Example four

The fourth embodiment corresponds to the first embodiment, and from the perspective of a specific fusion algorithm processing device, a trigger detection method is provided, and referring to fig. 4, the method may specifically include:

s401: receiving a visual detection result of a visual detection device and a radar detection result of a radar detection device, wherein the visual detection device is used for detecting an event that a vehicle passes through a target detection area through a visual sensor which is installed on road side equipment and can cover the target detection area, and the radar detection device is used for detecting the event that the vehicle passes through the target detection area through a radar sensor which is installed on the road side equipment and can cover the target detection area;

s402: judging whether a vehicle passes through the target detection area or not by fusing the visual detection result and the radar detection result;

s403: and generating a trigger detection signal according to the judgment result.

In a specific implementation, the visual inspection result may include: a third probability that a vehicle passes through the target detection zone; the radar detection result may include: a fourth probability that a vehicle passes through the target detection zone; at this time, whether a vehicle passes through the target detection area may be determined according to the third probability, the fourth probability and determination threshold information in a preset estimation algorithm.

For the parts of the second to fourth embodiments that are not described in detail, reference may be made to the description of the first embodiment, and details are not repeated here.

Corresponding to the second embodiment, the embodiment of the present application further provides a trigger detection device, referring to fig. 5, where the device may specifically include:

a result receiving unit 501, configured to receive a road surface detection result of a road surface detection device and a roadside detection result of a roadside detection device, where the road surface detection device is configured to detect an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on a road surface, and the roadside detection device is configured to detect an event that a vehicle passes through the target detection area through a second sensor that is mounted on a roadside apparatus and can cover the target detection area;

a fusion calculation unit 502, configured to determine whether a vehicle passes through the target detection area by fusing the road surface detection result and the roadside detection result;

a signal generating unit 503, configured to generate a trigger signal according to the determination result.

The roadside detection result also comprises the perceived position information of the vehicle;

The fusion calculation unit may be specifically configured to:

and if the road surface detection result indicates that a vehicle passes through the target detection area and the roadside detection result indicates that the position information of the vehicle is located in the target detection area, determining the vehicle included in the road surface detection result and the vehicle in the roadside detection result as the same vehicle and determining that the vehicle passes through the target detection area.

In specific implementation, the road surface detection result includes: a first probability that a vehicle passes through the target detection zone;

the roadside detection result includes: a second probability that a vehicle passes through the target detection zone;

the fusion calculation unit may be specifically configured to:

and judging whether the vehicle passes through the target detection area or not according to the first probability, the second probability and judgment threshold information in a preset estimation algorithm.

The first probability is determined by the road surface detection device according to an initial detection result and a posterior probability corresponding to the road surface detection device;

Wherein the posterior probability is determined according to the matching degree between the initial detection result and the template signal/training model;

In a specific implementation, the first fusion computing unit may specifically include:

the prior probability determining subunit is used for determining a first prior probability corresponding to the road surface detection device and a second prior probability corresponding to the roadside detection device according to current weather and/or vehicle speed factors and pre-stored historical statistical results corresponding to respective detection systems; the historical statistics include: the confidence of the initial detection result of each detection system under the condition of corresponding weather and/or vehicle speed;

and the judging subunit is used for adding the product of the first probability and the first prior probability and the product of the second probability and the second prior probability, and judging whether a vehicle passes through the target detection area or not by comparing the added result with preset threshold information.

Corresponding to the fourth embodiment, the embodiment of the present application further provides a trigger detection device, referring to fig. 5, where the device may specifically include:

A result receiving unit, configured to receive a visual detection result of a visual detection device and a radar detection result of a radar detection device, where the visual detection device is configured to detect an event that a vehicle passes through a target detection area by using a visual sensor that is mounted on a roadside apparatus and can cover the target detection area, and the radar detection device is configured to detect an event that the vehicle passes through the target detection area by using a radar sensor that is mounted on the roadside apparatus and can cover the target detection area;

the fusion calculation unit is used for judging whether a vehicle passes through the target detection area or not by fusing the visual detection result and the radar detection result;

and the signal generating unit is used for generating a trigger signal according to the judgment result.

In a specific implementation, the visual inspection result includes: a third probability that a vehicle passes through the target detection zone;

the radar detection result comprises: a fourth probability that a vehicle passes through the target detection zone;

the fusion calculation unit may be specifically configured to:

and judging whether the vehicle passes through the target detection area or not according to the third probability, the fourth probability and judgment threshold information in a preset estimation algorithm.

EXAMPLE five

As described above, in the embodiment of the present application, a specific fusion algorithm processing device may be deployed in a plurality of specific devices, and in one scheme, since the roadside device itself has a computing capability and a data storage capability, the fusion algorithm processing device may also be directly implemented in the roadside device. Specifically, an embodiment of the present application further provides a roadside device, which may specifically include:

EXAMPLE six

The fifth embodiment corresponds to the first and second embodiments, and in the third and fourth embodiments, the embodiment of the present application further provides another roadside apparatus, including:

For details in the fifth and sixth embodiments, reference may be made to the descriptions in the foregoing embodiments, which are not repeated herein.

From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments of the present application.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

The trigger detection method, device and system provided by the present application are introduced in detail, and a specific example is applied in the present application to explain the principle and implementation manner of the present application, and the description of the above embodiment is only used to help understanding the method and core ideas of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, the specific embodiments and the application range may be changed. In view of the above, the description should not be taken as limiting the application.

Claims

1. A trigger detection system, comprising:

2. The system of claim 1,

the fusion algorithm processing device is further used for sending the trigger signal to license plate recognition equipment, and the license plate recognition equipment is used for recognizing the license plate of the vehicle.

3. The system of claim 2,

the license plate recognition device, the first sensor and the road side device are arranged at a target position which has the characteristic of slow running of a vehicle and has a non-inductive charging requirement.

4. A method of trigger detection, comprising:

and generating a trigger signal according to the judgment result.

5. The method of claim 4,

the roadside detection result also comprises the position information of the detected vehicle;

the judging whether the vehicle passes through the target detection area comprises the following steps:

6. The method of claim 4,

the road surface detection result includes: a first probability that a vehicle passes through the target detection zone;

7. The method of claim 6,

wherein the posterior probability is determined according to the matching degree between the initial detection result and the template signal and/or the trained mathematical model;

8. The method of claim 7,

the judging whether a vehicle passes through the target detection area according to the first probability, the second probability and judgment threshold information in a preset estimation algorithm comprises the following steps:

determining a first prior probability corresponding to the road surface detection device and a second prior probability corresponding to the roadside detection device according to current weather and/or vehicle speed factors and pre-stored historical statistical results corresponding to respective detection systems; the historical statistics include: the confidence of the initial detection result of each detection system under the condition of corresponding weather and/or vehicle speed;

and adding the product of the first probability and the first prior probability and the product of the second probability and the second prior probability, and judging whether a vehicle passes through the target detection area or not by comparing the added result with preset threshold information.

9. A trigger detection system, comprising:

the visual detection device is used for detecting an event that a vehicle passes through a target detection area through a visual sensor which is arranged on roadside equipment and can cover the target detection area;

10. The system of claim 9,

11. The system of claim 10,

the license plate recognition equipment and the road side equipment are arranged at a target position which has the characteristic of rapid vehicle running and has a non-inductive charging demand.

12. The system of claim 9,

the vision sensor is used for being installed on the roadside equipment in a hanging mode;

the radar sensor is used for being installed on the roadside equipment in a hanging or side-mounted mode.

13. A method of trigger detection, comprising:

and generating a trigger signal according to the judgment result.

14. A trigger detection apparatus, comprising:

the system comprises a result receiving unit, a road detection unit and a roadside detection unit, wherein the result receiving unit is used for receiving a road surface detection result of the road detection device and a roadside detection result of the roadside detection device, the road detection device is used for detecting an event that a vehicle passes through a target detection area through a first sensor buried in the target detection area on the surface of the road, and the roadside detection device is used for detecting an event that the vehicle passes through the target detection area through a second sensor which is installed on roadside equipment and can cover the target detection area;

The fusion calculation unit is used for judging whether a vehicle passes through the target detection area or not by fusing the road surface detection result and the roadside detection result;

15. A trigger detection apparatus, comprising:

16. A roadside apparatus characterized by comprising:

17. A roadside apparatus characterized by comprising:

the visual detection system is used for detecting an event that a vehicle passes through a target detection area by a visual sensor which is arranged on roadside equipment and can cover the target detection area;

the radar detection system is used for detecting an event that a vehicle passes through the target detection area through a radar sensor which is arranged on the road side equipment and can cover the target detection area;

and the fusion algorithm processing device is used for fusing the visual detection result of the visual detection system with the radar detection result of the radar detection system, judging whether a vehicle passes through the target detection area or not, and generating a trigger signal according to the judgment result.