Method for detecting a target on a road using roadside equipment and roadside equipment

Abstract

The present invention discloses a method for detecting a target on a road using a roadside device, a roadside device, and a computer-readable medium. The roadside device includes a first sensor and at least one second sensor, the first sensor is based on ultra-wideband technology, and the second sensor includes at least one of a camera, a radar, and a laser radar. The method includes: acquiring target detection data from the first sensor and the second sensor; determining a new detection target list based on the target detection data, the new detection target list includes at least one target and its position; performing target matching based on the new detection target list and a historical detection target list to generate a matched detection target list, the historical detection target list includes at least one previously detected target and its position; fusing the positions of the targets in the matched detection target list to generate a fused detection target list; and outputting the fused detection target list and / or the positions of the targets in the fused detection target list.

Description

Background Art

[0002] Vehicle-to-everything (V2X)-based on-board equipment and roadside equipment can achieve interaction between vehicles and road infrastructure, enabling more efficient and safe travel. At present, the main technical solutions on the roadside are generally multi-sensor fusion solutions based on cameras and millimeter-wave radars, and some are also equipped with laser radars to improve detection accuracy. However, due to issues such as cost, computing power and deployment difficulty, detection solutions including laser radars are only deployed experimentally in a small range.

[0003] The current multi-sensor fusion detection solution based on cameras, radars and lidars can detect most targets, but it is not satisfactory for detecting pedestrians and small targets in the distance. In addition, under extreme weather conditions such as fog and heavy rain, lidars and cameras are basically ineffective, and the detection results rely solely on radars, and the fusion algorithm also fails. The overall detection accuracy will be significantly reduced.

[0004] Therefore, there is a need to improve the existing roadside equipment solutions. Summary of the invention

[0005] The present application proposes a method for detecting a target on a road using a roadside device, a roadside device, and a computer-readable medium.

[0006] According to one aspect of the present application, a method for detecting a target on a road using a roadside device is proposed, wherein the roadside device includes a first sensor and at least one second sensor, wherein the first sensor is based on ultra-wideband (UWB) technology, and the second sensor includes at least one of a camera, a radar, and a laser radar, and the method includes:

[0007] Acquire target detection data from the first sensor and the second sensor;

[0008] Determine a new detection target list based on the target detection data, wherein the new detection target list includes at least one target and its position;

[0009] Performing target matching based on the new detected target list and the historical detected target list to generate a matched detected target list, wherein the historical detected target list includes at least one previously detected target and its position;

[0010] fusing the positions of the targets in the matched detection target list to generate a fused detection target list;

[0011] Output the fused detection target list and / or the positions of the targets in the fused detection target list.

[0012] According to another aspect of the present application, a roadside device is proposed, which includes a first sensor and at least one second sensor, the first sensor is based on ultra-wideband (UWB) technology, the second sensor includes at least one of a camera, a radar and a lidar, and the roadside device is configured to implement the method as described above.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program includes executable instructions. When the executable instructions are executed by a processor, the method described above is implemented.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the executable instructions to implement the method as described above.

[0015] The roadside equipment and corresponding detection scheme proposed in this application can make full use of the strong anti-interference ability and accurate positioning of UWB equipment by referencing the signal source based on UWB technology, and through the reasonable deployment of base station positions, the roads and intersections are fully covered, and the detection accuracy of long-distance objects is improved at a lower cost and the ability to resist extreme weather interference is improved. In the case of camera and lidar failure due to heavy rain and fog, a new detection target list can be established based on the detection results of the UWB device, and the detection results can be merged with the detection results of the radar, which has higher detection accuracy and stronger robustness than the scheme that only uses radar under this condition. In addition, through the method of this application, data from multiple data sources can be optimally merged, and high-precision and highly reliable detection results can be obtained under various conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0017] Figure 1 The present invention is a schematic flowchart of a process of detecting an object on a road using a roadside device according to an embodiment of the present application.

[0018] Figure 2 The present invention is a schematic flowchart of a process of detecting a target on a road using a roadside device according to another embodiment of the present application.

[0019] Figure 3 It is a schematic layout diagram of roadside equipment according to an embodiment of the present application.

[0020] Figure 4 is a schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] The exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided to make the contents of this application comprehensive and complete and to fully convey the concepts of the exemplary embodiments to those skilled in the art. In the drawings, the size of some elements may be exaggerated or deformed for the purpose of clarity. The same reference numerals in the drawings represent the same or similar structures, and their detailed descriptions will be omitted.

[0022] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, elements, etc. can be adopted. In other cases, known structures, methods or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0023] Roadside equipment can overcome some limitations of vehicle-mounted detection equipment. For example, cameras, radars, etc. can be placed at relatively high positions or multiple sensors can be placed on the roadside to achieve wide coverage. Therefore, roadside equipment can obtain environmental information beyond the vehicle's own line of sight for the vehicle. It is an important part of vehicle-road collaboration and is of great significance in supporting autonomous driving. Roadside equipment known in the prior art mainly includes optical sensors (cameras), radars, and laser radars LiDAR. The detection schemes of cameras and LiDARs involve traditional target detection (image recognition) and detection based on deep learning, while radar detection only involves traditional target clustering algorithms. At present, the accuracy and robustness of pedestrian and vehicle detection are improved by fusing multiple sensors of cameras, radars, and LiDARs. Sensor fusion includes data layer fusion (detection data output by sensors), feature layer fusion (extracting features of interest from detection data), and target layer fusion (identifying targets based on features of interest, i.e., vehicles, people, and environment).

[0024] The sensors in current roadside equipment basically meet the requirements for close-range detection, but the effect is not good enough for long-range detection. LiDAR is accurate enough, but the cost is high, the computing power requirement is high, and the deployment is difficult. In addition, under extreme weather conditions such as fog and heavy rain, LiDAR and cameras are basically ineffective. The detection results rely solely on radar, and the fusion algorithm also fails. The overall detection accuracy will be significantly reduced.

[0025] To this end, the present application proposes a method for detecting a target on a road by using a roadside device, wherein the roadside device includes a first sensor and at least one second sensor, wherein the first sensor is based on ultra-wideband (UWB) technology, and the second sensor includes at least one of a camera, a radar, and a laser radar. Figure 1 As shown, the method includes the following steps: S1: acquiring target detection data from the first sensor and the second sensor; S2: determining a new detection target list based on the target detection data, wherein the new detection target list includes at least one target and its position; S3: performing target matching based on the new detection target list and the historical detection target list to generate a matched detection target list, wherein the historical detection target list includes at least one previously detected target and its position; S4: fusing the positions of the targets in the matched detection target list to generate a fused detection target list; S5: outputting the fused detection target list and / or the positions of the targets in the fused detection target list.

[0026] In the solution of the present application, on the one hand, by introducing sensors based on UWB technology, the characteristics of high positioning accuracy and strong anti-interference of UWB technology are fully utilized, and the target can be accurately positioned even in extreme weather and when other sensors fail. In addition, by reasonably arranging UWB base stations, the road sections or intersections to be detected are fully covered, so that even small targets in the distance can be well detected. On the other hand, by fusing the detection data of sensors based on UWB technology with other sensors, the accuracy and robustness of the entire roadside equipment for pedestrian and vehicle detection can be ensured or improved while reducing the dependence on high-performance laser radar (LiDAR). In other words, high accuracy and high robustness of pedestrian and vehicle detection can be achieved at a reasonable cost.

[0027] UWB (Ultra Wide Band) is a wireless carrier communication technology that uses a frequency bandwidth of more than 1GHz. It uses nanosecond non-sinusoidal narrow pulses to transmit data, so it occupies a large spectrum range. Although it uses wireless communication, its data transmission rate can reach more than several hundred megabits per second. UWB technology has the advantages of low system complexity, low power spectrum density of transmitted signals, insensitivity to channel fading, low interception capability, high positioning accuracy, and strong penetration capability.

[0028] The first sensor based on UWB technology includes multiple UWB base stations. Here, the number and / or location of the UWB base stations are determined according to the detection area coverage requirement and positioning error threshold of the first sensor. For example, a UWB base station is deployed at intervals of 50 meters on both sides of the road.

[0029] In this application, the second sensor refers to all possible sensors other than sensors based on UWB technology, such as cameras, radars or lidars and other possible sensors. Each sensor detects targets on the road with its own detection cycle or beat, and collects data on the target. The collected data may include the position coordinates, speed, moving direction, target type, target size, etc. of the target. Although only the position coordinates are mentioned in most places in this application, it is obvious that other collected target parameters, such as speed, moving direction, etc., can also be considered.

[0030] Each time a new set of detection data is obtained, an analysis is performed based on the detected data, and a new detection target list is determined, the new detection target list includes at least one target and its position information. Next, the new detection target list is matched with the historical detection target list. The target matching is performed based on the distance between the position of the target in the new detection target list and the position of the target in the historical detection target list. Here, "distance" can be a preset fixed value, such as not more than 0.1 meters, preferably not more than 0.05 meters, or it can be determined based on the error function of the sensor. The historical detection target list is a collection of targets existing on the road detected by the roadside equipment before the current moment, that is, the historical detection target list includes at least one previously detected target and its position. In view of the fact that the newly detected target may have been detected by the roadside equipment before this and already exists in the historical detection target list, the new detection target list can be matched with the historical detection target list and a matched detection target list can be generated based on the matching result. Afterwards, the positions of the targets in the matched detection target list are fused to generate a fused detection target list; the fused detection target list and / or the positions of the targets in the fused detection target list are output.

[0031] Here, a list generally refers to a collection, and does not necessarily have to be a strict data structure form such as a table, array or linked list. There are many possible forms for "output", for example, it can be sent to vehicles traveling on the road in the form of broadcast or sent to a server in a wired or wireless form, especially a server providing navigation map information, so as to update traffic information on the map, especially obstacle information.

[0032] Figure 2A schematic flow chart of a process of using a roadside device to detect a target in a road according to another embodiment of the present application is shown. In this embodiment, first, target detection data and a corresponding error function are obtained from a sensor of the roadside device. The error function is determined by the characteristics of the sensor itself. For example, the error function of a UWB detection system is a function of periodic increase and decrease related to the location of the target. The errors of sensors such as cameras, radars, and laser radars are symmetrically distributed about the central axis of their detection range, and their error functions are similar to normal distribution functions symmetrical about the aforementioned central axis in the direction perpendicular to the central axis (y direction), while their error functions are increasing functions related to the distance between the target and the sensor in the detection direction parallel to the sensor (x direction). It should be pointed out here that the error functions of each sensor can be known in advance through testing and are determined functions about the position of the detected target. Here, in response to the detection action of the first sensor and / or the second sensor, the target detection data is obtained. That is, each time the first sensor and / or the second sensor performs a detection action, the roadside device obtains target detection data once. A new detection target list is obtained based on these target data, and the list includes at least one target and its position information. But it can also include other information such as target size, speed, direction, etc.

[0033] In the case where the target detection data comes from the first sensor, the position of the target in the new detection target list is determined based on the signal arrival time difference (TDOA) between the UWB base station and the UWB device. At present, the signal arrival time difference is mainly determined by the following method: the signal received by one base station is correlated with the signal received by another base station at the same time to obtain the value of TDOA. This algorithm can estimate the value of TDOA when the base station and the target are not synchronized. When determining the accuracy of TDOA measurement, the first thing to consider is the timing accuracy. The recorded time error will directly convert into the error of the distance measurement. These errors can be divided into two parts: first, the uncertainty of the time recorded by each receiver, which will depend on the clock used by each receiver; second, the synchronization accuracy between receivers. But in any case, the above two methods only require time synchronization between base stations, and do not need to detect signal transmission time. Therefore, the system's requirements for time synchronization are greatly reduced. Because the position of the base station is fixed, synchronization between base stations is much easier to achieve than synchronization between base stations and mobile terminals. In general, compared with other positioning methods, although one more base station is required, TDOA has lower complexity and higher accuracy.

[0034] Preferably, the position of the target in the new detection target list is determined by a hyperbolic positioning algorithm, wherein the target detection data comes from at least 4 of the UWB base stations. The aforementioned hyperbolic positioning algorithm may be, for example, a Chan algorithm. The Chan algorithm is a very useful method for the TDOA positioning method. The Chan algorithm is a non-recursive hyperbolic equation system solution with an analytical expression solution. Its main features are: when the measurement error obeys an ideal Gaussian distribution, its positioning accuracy is high, the amount of calculation is small, and the algorithm accuracy can be improved by increasing the number of determined points.

[0035] Of course, other methods in UWB positioning technology can also be considered, such as the TOA (Time of Arrival) method based on arrival time ranging, the AOA (Angle of Arrival) method based on arrival angle measurement, or the RSSI (Received Signal Strength Indication) method based on received signal strength indication measurement.

[0036] exist Figure 2 In the described embodiment, the historical detection target list is also judged. When the historical detection target list is empty, the historical detection target list is equal to the new detection target list. For example, when the roadside equipment is just put into use or there is no target on the road for a period of time, such as when there are no vehicles or pedestrians at night, the historical detection target list will appear empty. Then, after updating the historical detection target list, the updated historical detection target list is output. Then return to the data acquisition step at the beginning of the method. If the historical detection target list is not empty, target matching is performed based on the new detection target list and the historical detection target list to generate a matched detection target list. Here, for example, the targets in the new detection target list and the targets in the historical detection target list that meet the following target matching conditions can be determined as mutually matching targets:

[0037]

[0038] Among them, xa and ya are the coordinates of the position of target a in the historical detection target list in the x-axis direction and the y-axis direction in the world coordinate system, xb and yb are the coordinates of the position of target b in the new detection target list in the x-axis direction and the y-axis direction in the world coordinate system, ex and ey are the values ​​of the measurement error function of the first sensor or the second sensor providing the target detection data at the position of target b in the new detection target list in the x-axis direction and the y-axis direction. The position of target b in the new detection target list that matches target a in the historical detection target list is added to the historical detection target list to generate the matched detection target list.

[0039] In the case where multiple targets in the historical detection target list and the targets in the new detection target list are determined to be mutually matching targets and / or in the case where multiple targets in the new detection target list and the targets in the historical detection target list are determined to be mutually matching targets, the Hungarian algorithm or a similar algorithm (Hopcroft-Karp algorithm) is used to select the best matching target of the target in the new detection target list from the multiple targets in the historical detection target list as the target in the historical detection target list that matches the target in the new detection target list. The matched detection target list may include multiple groups of data for the same target, and for this purpose, it is necessary to fuse multiple positions corresponding to the same target in the matched detection target list into one position of the same target through fusion processing.

[0040] The fusion process is performed, for example, by using a Kalman filter, wherein the noise variance function of the Kalman filter is determined based on the measurement error function. Kalman filtering is an algorithm that uses a linear system state equation to optimally estimate the system state through system input and output observation data. Since the observation data includes the effects of noise and interference in the system, the optimal estimate can also be regarded as a filtering process. The use of Kalman filtering in continuously changing systems such as roadside equipment is ideal. It has the advantages of small memory usage (no historical data other than the previous state quantity needs to be retained) and high speed, making it very suitable for real-time problems and embedded systems.

[0041] Finally, the fused detection target list and / or the location of the target therein is output. In other words, data in various forms can be output, such as a complete target list including target feature information and current location data, or only location data. The receiver, such as a vehicle, analyzes and evaluates the corresponding location data, and only issues a warning to the driver or the fully automatic / semi-automatic driving system when it finds that the target location conflicts with the current driving route.

[0042] Advantageously, the various sensors and other electronic components of the roadside equipment are time synchronized, for example, the first sensor and the second sensor based on UWB technology are time synchronized and / or the various parts in the UWB detection system are time synchronized. Time synchronization can be performed at fixed intervals, for example, once a day, a week or a month, depending on the performance of the equipment used and the time synchronization requirements. In addition, before acquiring the target detection data, the positions of the first sensor and the second sensor are calibrated in the world coordinate system. Both time synchronization and coordinate calibration can be performed as pre-processing steps when the roadside equipment is started.

[0043] Preferably, in each sensor polling cycle, the historical detection target list is updated by removing the targets in the historical detection target list that do not match the targets in all the new detection target lists from the historical detection target list; and / or the targets in the new detection target list that do not match all the targets in the historical detection target list and are not determined based on the target detection data of the second sensor of the radar type are added to the historical detection target list to update the historical detection target list. This is because the reliability of radar detection results is poor. If the target is only detected by radar, it is very likely to be a false target that does not exist. If it is a target detected by other sensors, it is identified as a newly appeared target and added to the historical detection target list. Here, the sensor polling cycle refers to the longest detection cycle of the detection cycle of the first sensor and the detection cycle of the second sensor. Each sensor in the roadside device continuously detects the target on the road according to the inherent detection cycle. Due to different sensor types, the detection cycle is also different. Here, the detection cycle of the sensor with the longest detection cycle is determined as the sensor polling cycle of the roadside device.

[0044] Figure 3 The schematic layout diagram of the roadside equipment according to one embodiment of the present application is shown, specifically the roadside equipment arranged at the intersection. However, it is obvious that the roadside equipment according to the present application can also be arranged in other sections of the road, such as expressways, sharp bends, etc. Figure 3 As shown, multiple first sensors based on UWB technology, specifically multiple UWB base stations 11-19, are arranged at equal intervals n on both sides of the road. For example, it can be stipulated that the determination of the value of n needs to meet two conditions: 1) There are at least 3, preferably 4 UWB base stations that can be connected to vehicles or pedestrians at any position on the road (the required number of base stations is related to the positioning algorithm and is only used as an example here) to ensure the accuracy of UWB positioning. 2) The value of n can ensure that the error of UWB positioning is within the allowable range. Assuming that the maximum design positioning error of the UWB detection system including the first sensor based on UWB technology is Er, the actual maximum positioning error of the UWB detection system is Eal, and the minimum positioning error is Eas, then the selected n value should meet the following conditions:

[0045] Er≥Eal; and

[0046] Eal-Eas≤0.5Er.

[0047] The maximum design positioning error is Er, which can be determined according to the actual project requirements, but the value should not exceed 4 meters. Figure 3After the UWB base station is deployed at the position shown, the error of the UWB detection system along the extension direction of the road is a function of periodic increase and decrease related to the position of the target, where the smaller the value of n, the smaller the error and period. Preferably, for example, a UWB base station can be deployed every 50 meters on both sides of the road, so that at least 3, preferably 4 base stations can detect the target anywhere. Therefore, the positioning detection accuracy will not be affected by the position of vehicles and pedestrians, and the detection success rate of distant pedestrians or small targets can be greatly improved.

[0048] In addition, other sensors 20, 21 are arranged at the intersection as second sensors, such as cameras, radars or lidars. The target vehicle 1 (it can also be a pedestrian holding a mobile phone or other target with a UWB tag) is driving on the road. At this time, the four UWB base stations located on the roadside can be connected to the vehicle and used to locate the vehicle. As mentioned above, the position of the vehicle can be determined based on the signal arrival time difference (TDOA) between the UWB base station and the UWB device. At this time, the other sensors 20, 21 as the second sensors also detect and locate the vehicle in their own ways. Based on the detection data of these sensors, the roadside equipment matches, fuses and finally outputs the fused detection target list or the location information in the list according to the above-mentioned method of the present application.

[0049] In an exemplary embodiment of the present application, a computer-readable storage medium is also provided, on which a computer program is stored, the program including executable instructions, which can implement the steps of the method for detecting a target on a road using a roadside device described in any of the above embodiments when the executable instructions are executed by, for example, a processor. In some possible implementations, various aspects of the present application can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present application described in the method for detecting a target on a road using a roadside device in this specification.

[0050] The program product for implementing the above method according to the embodiment of the present application can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0051] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0052] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0053] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0054] In an exemplary embodiment of the present application, an electronic device is also provided, which may include a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the steps of the method for detecting a target in a road using a roadside device in any of the above embodiments by executing the executable instructions.

[0055] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0056] Refer to the following Figure 4 The electronic device 400 according to this embodiment of the present application is described. Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0057] like Figure 4 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include, but are not limited to: at least one processing unit 410, at least one storage unit 420, a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410), a display unit 440, etc.

[0058] The storage unit stores a program code, which can be executed by the processing unit 410, so that the processing unit 410 performs the steps of various exemplary embodiments of the present application described in the method for detecting a target on a road using a roadside device in this specification. For example, the processing unit 410 can perform the following steps: Figure 1 and Figure 2 Follow the steps shown in .

[0059] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 4201 and / or a cache memory unit 4202 , and may further include a read-only memory unit (ROM) 4203 .

[0060] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0061] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0062] The electronic device 400 may also communicate with one or more external devices 500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 400, and / or communicate with any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 450. Furthermore, the electronic device 400 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 460. The network adapter 460 may communicate with other modules of the electronic device 400 via the bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0063] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the method of using a roadside device to detect a target in a road according to the implementation of the present application.

[0064] Those skilled in the art will readily appreciate other embodiments of the present application after considering the description and practicing the contents disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The description and embodiments are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for detecting a target on a road using a roadside device, the roadside device comprising a first sensor and at least one second sensor, the first sensor being based on ultra-wideband (UWB) technology, the second sensor comprising at least one of a camera, a radar, and a laser radar, the method comprising: In response to a detection action of the first sensor and / or the second sensor, acquiring target detection data from the first sensor and the second sensor; Determine a new detection target list based on the target detection data, wherein the new detection target list includes at least one target and its position; Target matching is performed based on the distance between the position of the target in the new detection target list and the position of the target in the historical detection target list to generate a matched detection target list, wherein the historical detection target list includes at least one previously detected target and its position; wherein, in each sensor polling cycle, the historical detection target list is updated by removing from the historical detection target list the targets in the historical detection target list that do not match with all the targets in the new detection target list, wherein the sensor polling cycle is the longest detection cycle of the detection cycle of the first sensor and the detection cycle of the second sensor; and the targets in the new detection target list that do not match with all the targets in the historical detection target list and are not determined based on the target detection data from the second radar type sensor are added to the historical detection target list to update the historical detection target list; fusing the positions of the targets in the matched detection target list to generate a fused detection target list; Update the historical detection target list based on the fused detection target list; if there is no target position in the historical detection target list, update the historical detection target list based on the new detection target list; Output the fused detection target list and / or the positions of the targets in the fused detection target list.

2. The method according to claim 1, characterized in that The target matching includes: The targets in the new detection target list and the targets in the historical detection target list that meet the following target matching conditions are determined as mutually matching targets: Wherein, xa and ya are respectively the coordinates of the position of target a in the historical detection target list in the x-axis direction and the y-axis direction in the world coordinate system, xb and yb are respectively the coordinates of the position of target b in the new detection target list in the x-axis direction and the y-axis direction in the world coordinate system, ex and ey are respectively the values ​​of the measurement error function of the first sensor or the second sensor providing the target detection data at the position of target b in the new detection target list in the x-axis direction and the y-axis direction; and The position of the target b in the new detected target list that matches the target a in the historical detected target list is added to the historical detected target list to generate the matched detected target list.

3. The method according to claim 1, characterized in that The first sensor includes a plurality of UWB base stations disposed on both sides of the road, the target has a UWB device, and determining a new detection target list based on the target detection data includes: In a case where the target detection data comes from the first sensor, the position of the target in the new detected target list is determined based on a signal arrival time difference between the UWB base station and the UWB device.

4. The method according to claim 3, characterized in that Determining the position of the target in the new detection target list based on the signal arrival time difference between the UWB base station and the UWB device includes: The position of the target in the new detected target list is determined by a hyperbolic positioning algorithm, wherein the target detection data comes from at least four of the UWB base stations.

5. The method according to claim 4, characterized in that The hyperbolic positioning algorithm is the Chan algorithm.

6. The method according to any one of claims 3 to 5, characterized in that The number and / or location of the UWB base stations are determined based on the detection area coverage requirement of the first sensor and a positioning error threshold.

7. The method according to claim 2, characterized in that In the case where multiple targets in the historical detection target list and the targets in the new detection target list are determined to be mutually matching targets and in the case where multiple targets in the new detection target list and the targets in the historical detection target list are determined to be mutually matching targets, the Hungarian algorithm is used to select the best matching target with the target in the new detection target list from the targets in the historical detection target list as the target in the historical detection target list that matches the target in the new detection target list.

8. The method according to claim 2 or 7, characterized in that: Fusing the positions of the objects in the matched detection target list to generate a fused detection target list includes: Multiple positions corresponding to the same target in the matched detection target list are merged into one position of the same target.

9. The method according to claim 8, characterized in that Fusing the targets in the matched detection target list to generate a fused detection target list further includes: The fusion is performed using a Kalman filter, wherein a noise variance function of the Kalman filter is determined based on the measurement error function.

10. The method according to claim 1, characterized in that Before acquiring the target detection data, time synchronization is performed on the first sensor and the second sensor.

11. The method according to claim 1, characterized in that: Before acquiring the target detection data, positions of the first sensor and the second sensor are calibrated in a world coordinate system.

12. The method according to claim 1, characterized in that The fused detection target list and / or the positions of the targets in the fused detection target list are output in a broadcast form.

13. A roadside device, comprising a first sensor and at least one second sensor, wherein the first sensor is based on ultra-wideband (UWB) technology, and the second sensor comprises at least one of a camera, a radar, and a lidar, and the roadside device is configured to implement a method according to any one of claims 1 to 12.

14. The roadside equipment according to claim 13, characterized in that: The first sensor includes a plurality of UWB base stations arranged on both sides of the road, and the number and / or positions of the UWB base stations are determined based on a detection area coverage requirement and a positioning error threshold of the first sensor.

15. A computer-readable storage medium having a computer program stored thereon, the computer program comprising executable instructions, and when the executable instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

16. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 12.

Images