Trajectory fusion method, device, electronic device, and storage medium

Abstract

The present application discloses a trajectory fusion method, device, electronic device, and storage medium. The method of the present application includes: obtaining trajectory segments of at least two sensing devices in a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices can respectively sense a section of the motion trajectory of a traffic participant; classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that leave the electronic fence; obtaining driving direction prediction information of each basic trajectory segment, and determining candidate trajectory segments that match each basic trajectory segment from the trajectory segments to be fused based on the driving direction prediction information of each basic trajectory segment; obtaining a fused trajectory based on the basic trajectory segments and the candidate trajectory segments. The technical solution of the present application avoids the trajectory discontinuity problem caused by perception blind spots, and trajectory matching does not rely on vehicle feature information and perception device information, and trajectory matching has high accuracy.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a trajectory fusion method, device, electronic device, and storage medium. Background Art

[0002] Digital twin transportation is part of smart transportation, also known as parallel transportation or virtual transportation. It incorporates real-time collected traffic data into the established traffic model system to achieve virtual digital mapping of the transportation system, and generates traffic optimization and evaluation plans through big data analysis, artificial intelligence and traffic simulation technology.

[0003] Vehicle-road collaboration is a core component of digital twin transportation. Its application in digital twin transportation requires roadside vehicle perception and the formation of complete vehicle trajectories. This requires a large number of sensing devices, including cameras, lidar, and millimeter-wave radar. However, blind spots exist between these devices, preventing seamless coverage and full road-segment perception. Furthermore, it's impossible to form complete vehicle trajectories based on perceived vehicle trajectories. Summary of the Invention

[0004] Based on the above-mentioned problems existing in the prior art, the embodiments of the present application provide a trajectory fusion method, device, electronic device, and storage medium to solve the problem that there are perception blind spots between perception devices and the complete vehicle trajectory cannot be obtained.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a trajectory fusion method, the method comprising:

[0007] Obtaining trajectory segments of at least two sensing devices within a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a motion trajectory of a traffic participant;

[0008] Classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence;

[0009] Acquire driving direction prediction information of each basic trajectory segment, and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment;

[0010] A fused trajectory is obtained according to the basic trajectory segment and the candidate trajectory segment.

[0011] Optionally, the classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused exiting the electronic fence includes:

[0012] determining whether the trajectory segment includes a trajectory point outside the electronic fence;

[0013] If included, determining the trajectory category of the trajectory segment according to the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence;

[0014] If not included, the trajectory segment is determined to be an invalid trajectory segment.

[0015] Optionally, determining the trajectory category of the trajectory segment according to the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence includes:

[0016] If the time of the trajectory point outside the electronic fence is earlier than the trajectory point inside the electronic fence, the trajectory segment is the basic trajectory segment;

[0017] If the time of the trajectory point outside the electronic fence is later than that of the trajectory point inside the electronic fence, the trajectory segment is a trajectory segment to be fused.

[0018] Optionally, determining whether the trajectory segment includes a trajectory point outside the electronic fence includes:

[0019] Constructing a reference ray passing through the electronic fence with a first trajectory point, where the first trajectory point is any trajectory point in the trajectory segment;

[0020] Obtaining the number of intersections between the reference ray and the electronic fence;

[0021] Determine whether the first trajectory point is outside the electronic fence according to the number of intersection points.

[0022] Optionally, obtaining the driving direction prediction information of each basic trajectory segment includes:

[0023] Obtaining all drivable lanes for each basic trajectory segment in an initial period based on the position information of the trajectory points of each basic trajectory segment outside the electronic fence, and obtaining the drivable lanes for the basic trajectory segment in a next period based on the position information of the trajectory points of each basic trajectory segment inside the electronic fence;

[0024] The driving probability corresponding to each drivable lane in the initial time period is obtained according to the driving lane of each basic trajectory segment in the next time period.

[0025] Optionally, determining, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the predicted driving direction information of each basic trajectory segment includes:

[0026] Obtaining the final driving lane of each to-be-fused trajectory segment according to the position information of the trajectory point of each to-be-fused trajectory segment outside the electronic fence;

[0027] Lane consistency matching is performed based on the final driving lane of each trajectory segment to be fused and the drivable lane with the maximum driving probability corresponding to each basic trajectory segment in the initial period;

[0028] The candidate trajectory segments corresponding to each basic trajectory segment are obtained according to the lane consistency matching results.

[0029] Optionally, obtaining a fused trajectory according to the basic trajectory segment and the candidate trajectory segment includes:

[0030] Perform trajectory similarity matching on each basic trajectory segment and its matching candidate trajectory segment to obtain the matching trajectory segment corresponding to each basic trajectory segment;

[0031] Perform trajectory fusion on each basic trajectory segment and its matching trajectory segment to obtain a fused trajectory.

[0032] In a second aspect, an embodiment of the present application further provides a trajectory fusion device, comprising:

[0033] An acquisition unit, configured to acquire trajectory segments of at least two sensing devices in a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a movement trajectory of a traffic participant;

[0034] a classification unit, configured to classify the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence;

[0035] a screening unit, configured to obtain driving direction prediction information of each basic trajectory segment, and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment;

[0036] A fusion unit is configured to obtain a fused trajectory according to the basic trajectory segment and the candidate trajectory segment.

[0037] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0038] processor; and

[0039] A memory is arranged to store computer executable instructions which, when executed, cause the processor to perform a trajectory fusion method.

[0040] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device performs a trajectory fusion method.

[0041] At least one of the above-mentioned technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: when obtaining trajectory segments of the perception device, the embodiments of the present application also obtain the corresponding electronic fence, classify the obtained trajectory segments through the electronic fence, and obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused exiting the electronic fence. Then, based on the basic trajectory segments, the driving direction prediction information of each basic trajectory segment is obtained, and the trajectory segments to be fused are screened based on the driving direction prediction information. In this way, candidate trajectory segments matching each basic trajectory segment can be obtained from the data to be fused, and the complete trajectory of each traffic participant can be obtained through trajectory fusion, avoiding trajectory discontinuity caused by perception blind spots. In addition, the trajectory matching of the embodiments of the present application does not depend on vehicle feature information and perception device information. Through trajectory classification and trajectory screening, highly accurate mutually matching trajectory segments can be obtained, thereby improving matching accuracy and matching efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 This is a flow chart of a trajectory fusion method shown in an embodiment of the present application;

[0044] Figure 2 This is a schematic diagram of an electronic fence at an intersection shown in an embodiment of the present application;

[0045] Figure 3 Schematic diagram of the structure of a trajectory fusion device shown in an embodiment of the present application;

[0046] Figure 4 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0047] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0049] The execution subject of the trajectory fusion method provided in the embodiment of this application can be a roadside edge computing device, a roadside server or a cloud control platform; wherein the execution subject of the embodiment of this application can also be software or hardware. Figure 1 , Figure 1 Taking the execution subject as the roadside edge computing device as an example, a trajectory fusion method provided by the embodiment of this application is introduced. Figure 1 As shown, a trajectory fusion method provided in an embodiment of the present application may include the following steps S110 to S140:

[0050] Step S110 , obtaining trajectory segments of at least two sensing devices in a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices can respectively sense a movement trajectory of a traffic participant.

[0051] Most roadside sensing devices are mounted on roadside poles. Roadside sensing devices on adjacent roadside poles may have perception blind spots. In order to obtain the complete motion trajectory of traffic participants such as motor vehicles and non-motor vehicles, it is necessary to fuse the trajectory fragments of sensing devices mounted on different roadside poles.

[0052] When performing trajectory fusion, the roadside edge computing device first obtains trajectory segments of multiple sensing devices. The trajectory segments may include multiple trajectory segments of multiple traffic participants, so it is necessary to filter out the trajectory segments of the same traffic participant for fusion.

[0053] Most existing technologies require the use of vehicle feature information and / or perception device information for trajectory matching, but the perception device may track multiple targets at the same time, and different perception devices may use different identification IDs for the same target, resulting in poor accuracy of trajectory matching based on vehicle feature information and / or perception device information.

[0054] Unlike the prior art, the embodiment of the present application, when obtaining the trajectory segments of the sensing device in the target area, also obtains the electronic fence corresponding to the target area. The electronic fence can distinguish all trajectory segments entering and exiting the electronic fence. The two types of trajectory segments are used as the basis for trajectory fusion, so that the trajectory matching of the embodiment of the present application does not rely on vehicle features and sensing device information, and can improve matching accuracy.

[0055] The target area can be an intersection, a T-junction, or any other road section. The geo-fence corresponding to the target area can be drawn in advance. For example, the target area where the geo-fence needs to be drawn can be determined based on information such as the location of the sensing device and its blind spots with other sensing devices. The geo-fence information for this target area can then be drawn on the high-precision map. This allows the corresponding geo-fence to be retrieved when a trajectory segment provided by a sensing device within the target area is obtained.

[0056] During the electronic fence drawing process, the trajectory segments of the sensing device should be made to intersect with the electronic fence as much as possible so that the trajectory segments can be classified by the electronic fence. For example, the area where the electronic fence is located covers the perception blind area of ​​the at least two sensing devices and overlaps with the perception area of ​​each sensing device. When the position or perception direction of the sensing device changes, the electronic fence should be updated. The electronic fence can also be drawn dynamically, for example, the electronic fence can be redrawn at regular intervals. The embodiment of the present application does not limit the drawing method of the electronic fence, and those skilled in the art can make a reasonable choice as long as the trajectory segments can be classified by type through the electronic fence.

[0057] Step S120 : Classify the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused exiting the electronic fence.

[0058] The roadside edge computing device can classify the trajectory segments acquired in real time according to the electronic fence, namely the basic trajectory segments entering the electronic fence and the trajectory segments to be fused when leaving the electronic fence.

[0059] When a traffic participant passes through the area where the electronic fence is located, each basic trajectory segment has at least one trajectory segment to be fused. Therefore, the fusion of basic trajectory segments and trajectory segments to be fused can avoid the trajectory discontinuity problem caused by perception blind spots.

[0060] Step S130 : obtaining driving direction prediction information of each basic trajectory segment, and determining a candidate trajectory segment matching each basic trajectory segment from the trajectory segments to be fused based on the driving direction prediction information of each basic trajectory segment.

[0061] Step S140 : obtaining a fused trajectory according to the basic trajectory segment and the candidate trajectory segment.

[0062] After initially classifying the trajectory segments and determining the base trajectory segments and the trajectory segments to be fused, the present embodiment further analyzes the driving intent of the base trajectory segments and predicts the most likely driving direction for each base trajectory segment. This allows the trajectory segments to be fused to be screened based on the most likely driving directions of the base trajectory segments, and a fused trajectory is obtained based on the selected candidate trajectory segments that match the base trajectory segments. This driving intent-based trajectory segment screening not only improves computational efficiency but also enhances matching accuracy.

[0063] like Figure 1 As can be seen from the trajectory fusion method shown, this embodiment, when acquiring trajectory segments of the sensing device, also acquires the corresponding electronic fence. The acquired trajectory segments are classified using the electronic fence to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence. Then, using the basic trajectory segments as the basis for matching, driving direction prediction information is obtained for each basic trajectory segment. Based on the driving direction prediction information, the trajectory segments to be fused are screened. In this way, candidate trajectory segments that match each basic trajectory segment can be obtained from the data to be fused. Through trajectory fusion, the complete trajectory of each traffic participant is obtained, avoiding trajectory discontinuities caused by perception blind spots. In addition, the trajectory matching of this embodiment does not rely on vehicle feature information or sensing device information. Through trajectory classification and trajectory screening, highly accurate mutually matching trajectory segments can be obtained, improving matching accuracy and efficiency.

[0064] In some embodiments of the present application, the above step S120 of classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused when exiting the electronic fence includes:

[0065] determining whether the trajectory segment includes a trajectory point outside the geo-fence;

[0066] If included, the trajectory category of the trajectory segment is determined according to the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence. If the time of the trajectory point outside the electronic fence is earlier than that of the trajectory point inside the electronic fence, the trajectory segment is the basic trajectory segment; if the time of the trajectory point outside the electronic fence is later than that of the trajectory point inside the electronic fence, the trajectory segment is the trajectory segment to be fused, such as Figure 2 The track segment on the upper left of the middle electronic fence is the basic track segment for entering the electronic fence. Figure 2 The trajectory segment on the right side of the electronic fence is the trajectory segment to be fused after leaving the electronic fence.

[0067] If not, the trajectory segment is determined to be an invalid trajectory segment. In this embodiment of the present application, the invalid trajectory segment is deleted to avoid the final trajectory being not smooth due to the fusion of invalid trajectory segments.

[0068] In some possible implementations of this embodiment, the electronic fence is as follows Figure 2 The convex polygon shown in FIG. 1 is used to determine whether the trajectory segment includes a trajectory point outside the electronic fence, including:

[0069] A reference ray passing through the electronic fence is constructed using a first trajectory point, where the first trajectory point is any trajectory point in the trajectory segment. For ease of calculation, the reference ray can optionally be a horizontal ray. Of course, the direction of the reference ray can also be a vertical direction or other directions, as long as the reference ray passes through the electronic fence.

[0070] Obtain the number of intersections between the reference ray and the electronic fence, and determine whether the first trajectory point is outside the electronic fence based on the number of intersections. If the number of intersections is an odd number, the first trajectory point is inside the electronic fence; if the number of intersections is an even number, the first trajectory point is outside the electronic fence.

[0071] Assume that the first track point is P0 (x0, y0), and the vertices of each edge of the electronic fence are P1, P2, P3, etc. The equation of the line of each edge can be determined by the two vertices corresponding to the edge. Taking the edge where the line P1P2 is located as an example, its line equation is as follows:

[0072] x=(y0-p1.y)*(p2.x-p1.x) / (p2.y-p1.y)+x0;

[0073] Substitute the ordinate of point P0 into the above straight line equation. If the calculated horizontal coordinate x is greater than x0, then point P0 intersects with the edge; if the calculated horizontal coordinate x is equal to x0, then point P0 is on the edge and also intersects with the edge; if the calculated horizontal coordinate x is less than x0, then point P0 does not intersect with this edge.

[0074] In this way, it is possible to calculate whether the first track point intersects with each edge of the electronic fence, and calculate the number of intersections between the first track point and the electronic fence based on the intersection with each edge.

[0075] It should be noted that in other embodiments of the present application, other methods may also be used to determine whether a trajectory segment includes a trajectory point outside the electronic fence, such as area method, vector product method, etc.

[0076] In some embodiments of the present application, the above step S130 of obtaining the driving direction prediction information of each basic trajectory segment includes:

[0077] Obtaining all drivable lanes for each basic trajectory segment in an initial period based on the position information of the trajectory points of each basic trajectory segment outside the electronic fence, and obtaining the drivable lanes for the basic trajectory segment in a next period based on the position information of the trajectory points of each basic trajectory segment inside the electronic fence;

[0078] The driving probability corresponding to each drivable lane in the initial time period is obtained according to the driving lane of each basic trajectory segment in the next time period.

[0079] This embodiment can accurately determine the driving intention of the traffic participant by combining the lane information of the basic trajectory segment in the initial period and the lane information in the next period. Figure 2 Taking the intersection shown as an example, the basic trajectory segment can be used to determine the target vehicle's driving lane before entering the electronic fence. For example, all the vehicle's drivable lanes in the initial period can be determined by the trajectory points before the lane stop line. For example, based on the trajectory points of a certain basic trajectory segment at the initial moment, it can be determined that the lane at the initial moment corresponds to a drivable lane, including a straight lane, a left turn lane, and a left turn lane. Then, combined with the trajectory points of the basic trajectory segment at the next moment after entering the electronic fence, the probability of the vehicle traveling in each drivable lane can be given, thereby realizing driving intention prediction.

[0080] After achieving driving intention prediction for each basic trajectory segment, the final driving lane of each trajectory segment to be fused is obtained based on the position information of the trajectory points of each trajectory segment to be fused that are outside the electronic fence. Lane consistency matching is performed between the final driving lane of each trajectory segment to be fused and the drivable lane with the highest driving probability corresponding to each basic trajectory segment in the initial time period. Based on the lane consistency matching results, candidate trajectory segments corresponding to each basic trajectory segment are obtained.

[0081] In practical applications, the driving lanes corresponding to each trajectory segment to be fused may be different in the initial and final periods. To improve the accuracy of screening candidate trajectory segments, a consistency match should be performed based on the final driving lane of each trajectory segment to be fused in the next period and the drivable lane with the highest driving probability of the basic trajectory in the initial period. If the driving lanes of the two segments meet the consistency matching condition, the two trajectory segments may be two trajectory segments of the same traffic participant. Conversely, if the driving lanes of the two segments do not meet the consistency matching condition, the two trajectory segments cannot be two trajectory segments of the same traffic participant.

[0082] For example, if the drivable lane with the highest driving probability corresponding to the basic trajectory segment in the initial period is the first straight lane, then the final driving lane of the candidate trajectory segment that meets the consistency matching conditions should be the first straight lane; for another example, if the drivable lane with the highest driving probability corresponding to the basic trajectory segment in the initial period is the left turn lane, then the final driving lane of the candidate trajectory segment that meets the consistency matching conditions should be the left turn lane.

[0083] It should be noted that a trajectory segment refers to an ordered set of trajectory points within a period of time. In the embodiment of the present application, the entire time period of the trajectory segment can be divided into time periods according to the time information of the trajectory points intersecting with the electronic fence, and two time periods are obtained. The initial time period and the next time period can be subsets of these two time periods respectively.

[0084] As mentioned above, the candidate trajectory segments that match each basic trajectory segment obtained by lane consistency matching may be two trajectory segments of the same traffic participant or two trajectory segments of different traffic participants. Therefore, it is necessary to perform trajectory similarity matching on each basic trajectory segment and its matching candidate trajectory segments to determine the basic trajectory segments and matching trajectory segments that belong to the same traffic participant.

[0085] Thus, in some embodiments of the present application, obtaining a fused trajectory according to the basic trajectory segment and the candidate trajectory segment includes:

[0086] Perform trajectory similarity matching on each basic trajectory segment and its matching candidate trajectory segment to obtain the matching trajectory segment corresponding to each basic trajectory segment; perform trajectory fusion on each basic trajectory segment and its matching trajectory segment to obtain the fused trajectory.

[0087] In some possible implementations of this embodiment, each base trajectory segment and its candidate trajectory segments can be matched using a variety of similarity matching algorithms to obtain a similarity score for each candidate trajectory segment. For example, the candidate trajectory segments can be scored using a similarity matching algorithm such as Euclidean distance and azimuth angle. The candidate trajectory segment with the highest similarity score is determined as the matching trajectory segment corresponding to the base trajectory segment. Trajectory fusion is then performed based on the base trajectory segment and its matching trajectory segments. The fused trajectory can then be subjected to frame insertion, smoothing, and other processing to obtain a complete and continuous motion trajectory.

[0088] The trajectory fusion method described in the embodiment of the present application can fuse multiple pole trajectory segments at an intersection, and can also fuse two pole trajectory segments at the intersection of two poles in scenarios such as highways.

[0089] The embodiment of the present application also provides a trajectory fusion device 300, such as Figure 3, a schematic structural diagram of a trajectory fusion device in an embodiment of the present application is provided. The device 300 includes: an acquisition unit 310, a classification unit 320, a screening unit 330, and a fusion unit 340, wherein:

[0090] An acquisition unit 310 is configured to acquire trajectory segments of at least two sensing devices within a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a movement trajectory of a traffic participant;

[0091] A classification unit 320 is configured to classify the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence;

[0092] a screening unit 330 configured to obtain driving direction prediction information of each basic trajectory segment, and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment;

[0093] The fusion unit 340 is configured to obtain a fused trajectory according to the basic trajectory segment and the candidate trajectory segment.

[0094] In one embodiment of the present application, the classification unit 320 is used to determine whether the trajectory segment includes a trajectory point outside the electronic fence; if so, determine the trajectory category of the trajectory segment based on the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence; if not, determine that the trajectory segment is an invalid trajectory segment.

[0095] In one embodiment of the present application, the classification unit 320 is specifically configured to: if the time of the trajectory point outside the electronic fence is earlier than the time of the trajectory point inside the electronic fence, then the trajectory segment is a basic trajectory segment; if the time of the trajectory point outside the electronic fence is later than the time of the trajectory point inside the electronic fence, then the trajectory segment is a trajectory segment to be fused.

[0096] In one embodiment of the present application, the classification unit 320 is further used to construct a reference ray passing through the electronic fence with a first trajectory point, where the first trajectory point is any trajectory point in the trajectory segment; obtain the number of intersections between the reference ray and the electronic fence; and determine whether the first trajectory point is outside the electronic fence based on the number of intersections.

[0097] In one embodiment of the present application, the first screening unit 330 is configured to obtain all drivable lanes for each basic trajectory segment in an initial period based on the position information of the trajectory points of each basic trajectory segment outside the electronic fence, and to obtain the driving lanes for the basic trajectory segment in a next period based on the position information of the trajectory points of each basic trajectory segment within the electronic fence; and to obtain the driving probability corresponding to each drivable lane in the initial period based on the driving lanes of each basic trajectory segment in the next period.

[0098] In one embodiment of the present application, the screening unit 330 is configured to obtain a final driving lane for each trajectory segment to be fused based on the location information of the trajectory point outside the electronic fence of each trajectory segment to be fused; perform lane consistency matching between the final driving lane of each trajectory segment to be fused and the drivable lane with the highest driving probability corresponding to each basic trajectory segment in the initial time period; and obtain a candidate trajectory segment corresponding to each basic trajectory segment based on the lane consistency matching result.

[0099] In one embodiment of the present application, the fusion unit 340 is configured to perform trajectory similarity matching on each basic trajectory segment and its matching candidate trajectory segment to obtain a matching trajectory segment corresponding to each basic trajectory segment; and perform trajectory fusion on each basic trajectory segment and its matching trajectory segment to obtain a fused trajectory.

[0100] It can be understood that the above-mentioned trajectory fusion device can implement each step of the trajectory fusion method provided in the above-mentioned embodiment. The relevant explanations about the trajectory fusion method are applicable to the trajectory fusion device and will not be repeated here.

[0101] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor and, optionally, an internal bus, a network interface, and memory. The memory may include internal memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for its services.

[0102] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0103] The memory is used to store programs. Specifically, the program may include program code, which includes computer operating instructions. The memory may include internal memory and non-volatile memory, and provides instructions and data to the processor.

[0104] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs it, forming a trajectory fusion device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0105] Obtaining trajectory segments of at least two sensing devices within a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a motion trajectory of a traffic participant;

[0106] Classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence;

[0107] Acquire driving direction prediction information of each basic trajectory segment, and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment;

[0108] A fused trajectory is obtained according to the basic trajectory segment and the candidate trajectory segment.

[0109] The above application Figure 1The methods performed by the trajectory fusion device disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor or by software instructions. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-established in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the trajectory fusion method described above.

[0110] The electronic device may also perform Figure 1 The method of executing the trajectory fusion device in Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0111] The embodiment of the present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, can enable the electronic device to execute Figure 1 The method performed by the trajectory fusion device in the embodiment shown specifically performs the following operations:

[0112] Obtaining trajectory segments of at least two sensing devices within a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a motion trajectory of a traffic participant;

[0113] Classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence;

[0114] Acquire driving direction prediction information of each basic trajectory segment, and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment;

[0115] A fused trajectory is obtained according to the basic trajectory segment and the candidate trajectory segment.

[0116] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0117] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0118] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0121] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0122] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A trajectory fusion method, characterized in that: The method comprises: Obtaining trajectory segments of at least two sensing devices within a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a motion trajectory of a traffic participant; Classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence; Acquire driving direction prediction information for each basic trajectory segment based on lane information in an initial period and lane information in a subsequent period, wherein the driving direction prediction information indicates a driving probability corresponding to each drivable lane of the traffic participant in the initial period; and determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment; Obtaining a fused trajectory according to the basic trajectory segment and the candidate trajectory segment; The step of determining, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the predicted driving direction information of each basic trajectory segment comprises: Obtaining the final driving lane of each trajectory segment to be fused based on the position information of the trajectory point outside the electronic fence of each trajectory segment to be fused; performing lane consistency matching between the final driving lane of each trajectory segment to be fused and the drivable lane with the maximum driving probability corresponding to each basic trajectory segment in the initial period; and obtaining a candidate trajectory segment corresponding to each basic trajectory segment based on the lane consistency matching result; The area where the electronic fence is located covers the perception blind areas of the at least two perception devices and has an overlapping area with the perception area of ​​each perception device.

2. The trajectory fusion method according to claim 1, wherein: The classifying the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence includes: determining whether the trajectory segment includes a trajectory point outside the electronic fence; If included, determining the trajectory category of the trajectory segment according to the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence; If not included, the trajectory segment is determined to be an invalid trajectory segment.

3. The trajectory fusion method according to claim 2, wherein: The determining the trajectory category of the trajectory segment according to the temporal relationship between the trajectory points outside the electronic fence and the trajectory points inside the electronic fence includes: If the time of the trajectory point outside the electronic fence is earlier than the trajectory point inside the electronic fence, the trajectory segment is the basic trajectory segment; If the time of the trajectory point outside the electronic fence is later than that of the trajectory point inside the electronic fence, the trajectory segment is a trajectory segment to be fused.

4. The trajectory fusion method according to claim 2, wherein: Determining whether the trajectory segment includes a trajectory point outside the electronic fence includes: Constructing a reference ray passing through the electronic fence with a first trajectory point, where the first trajectory point is any trajectory point in the trajectory segment; Obtaining the number of intersections between the reference ray and the electronic fence; Determine whether the first trajectory point is outside the electronic fence according to the number of intersection points.

5. The trajectory fusion method according to claim 2, wherein: The step of obtaining the predicted driving direction information of each basic trajectory segment includes: Obtaining all drivable lanes for each basic trajectory segment in an initial period based on the position information of the trajectory points of each basic trajectory segment outside the electronic fence, and obtaining the drivable lanes for the basic trajectory segment in a next period based on the position information of the trajectory points of each basic trajectory segment inside the electronic fence; The driving probability corresponding to each drivable lane in the initial time period is obtained according to the driving lane of each basic trajectory segment in the next time period.

6. The trajectory fusion method according to claim 1, wherein: The obtaining of a fused trajectory according to the basic trajectory segment and the candidate trajectory segment includes: Perform trajectory similarity matching on each basic trajectory segment and its matching candidate trajectory segment to obtain the matching trajectory segment corresponding to each basic trajectory segment; Perform trajectory fusion on each basic trajectory segment and its matching trajectory segment to obtain a fused trajectory.

7. A trajectory fusion device, characterized in that: The device comprises: An acquisition unit, configured to acquire trajectory segments of at least two sensing devices in a target area and an electronic fence corresponding to the target area, wherein the at least two sensing devices are capable of respectively sensing a segment of a movement trajectory of a traffic participant; a classification unit, configured to classify the trajectory segments to obtain basic trajectory segments entering the electronic fence and trajectory segments to be fused that exit the electronic fence; a screening unit configured to obtain driving direction prediction information for each basic trajectory segment based on lane information of each basic trajectory segment in an initial time period and lane information in a subsequent time period, the driving direction prediction information indicating the driving probability of a traffic participant corresponding to each drivable lane in the initial time period; and to determine, from the trajectory segments to be fused, a candidate trajectory segment that matches each basic trajectory segment based on the driving direction prediction information of each basic trajectory segment; the screening unit further configured to obtain a final driving lane for each trajectory segment to be fused based on position information of a trajectory point outside the electronic fence of each trajectory segment to be fused; perform lane consistency matching between the final driving lane of each trajectory segment to be fused and the drivable lane with the greatest driving probability corresponding to each basic trajectory segment in the initial time period; and obtain a candidate trajectory segment corresponding to each basic trajectory segment based on the lane consistency matching result; a fusion unit, configured to obtain a fused trajectory according to the basic trajectory segment and the candidate trajectory segment; The area where the electronic fence is located covers the perception blind areas of the at least two perception devices and has an overlapping area with the perception area of ​​each perception device.

8. An electronic device comprising: processor; as well as A memory arranged to store computer-executable instructions, wherein when the instructions are executed, the processor executes the trajectory fusion method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing one or more programs, wherein when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device executes the trajectory fusion method according to any one of claims 1 to 6.

Images