A method, apparatus and equipment for predicting pedestrian movement areas

Abstract

This specification discloses a method, apparatus, and device for predicting pedestrian movement areas. The solution may include: acquiring historical trajectory data of a target pedestrian; obtaining multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment based on the historical trajectory data and the trajectory point information of the target pedestrian at the current moment; determining the density function of the predicted trajectory corresponding to each trajectory point based on the multiple predicted trajectory points; and using each density function, based on a preset confidence interval, obtaining the movement area of ​​the target pedestrian within the preset time period.

Description

Technical Field

[0001] This application relates to the field of pedestrian trajectory prediction, and more particularly to a method, apparatus, and device for predicting pedestrian movement areas. Background Technology

[0002] Pedestrian trajectory prediction refers to predicting a pedestrian's future trajectory based on their historical movement paths. Its applications are wide-ranging, including intelligent driving, mobility services, and service robot navigation. Pedestrian trajectory prediction is indispensable for advanced autonomous driving systems. Connected autonomous driving technology provides a "God's-eye view," allowing for 360-degree observation of the movement of all pedestrians on the road. Combined with pedestrian trajectory prediction, this provides advanced autonomous driving with super-visual information, enabling the planning module to detect hazards in advance and make correct decisions ahead of time.

[0003] Currently, in related technologies, pedestrian trajectory prediction methods involve inputting the historical movement trajectories of pedestrians into a trained model and outputting the predicted trajectory. The model training process involves inputting a large number of pedestrian trajectories into the model for training. However, generating a model from massive amounts of data to predict pedestrian trajectories involves a large computational load, and the output may be uncertain, failing to consider the randomness of pedestrian trajectories.

[0004] Therefore, how to fully consider the randomness of pedestrian trajectories in prediction has become an urgent technical problem to be solved. Summary of the Invention

[0005] This specification provides a method, apparatus, and device for predicting pedestrian movement areas to address the problem that existing technologies cannot adequately consider the randomness of pedestrian trajectories.

[0006] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0007] Firstly, the embodiments of this specification provide a method for predicting pedestrian movement areas, including:

[0008] Obtain the historical trajectory data of the target pedestrian;

[0009] Based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained;

[0010] Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point;

[0011] Using the density functions, the movement area of ​​the target pedestrian within the preset time period is obtained based on the preset information interval.

[0012] Secondly, the pedestrian movement area prediction device provided in the embodiments of this specification includes:

[0013] The historical data acquisition module is used to acquire the historical trajectory data of the target pedestrian.

[0014] The trajectory point prediction module is used to obtain multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment, based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment.

[0015] The function determination module is used to determine the density function of the predicted trajectory corresponding to each trajectory point based on the plurality of predicted trajectory points.

[0016] The motion area determination module is used to obtain the motion area of ​​the target pedestrian within the preset time period by utilizing each of the density functions and based on a preset information interval.

[0017] Thirdly, the pedestrian movement area prediction device provided in the embodiments of this specification includes:

[0018] At least one processor; and,

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0021] Obtain the historical trajectory data of the target pedestrian;

[0022] Based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained;

[0023] Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point;

[0024] Using the density functions, the movement area of ​​the target pedestrian within the preset time period is obtained based on the preset information interval.

[0025] One embodiment of this specification achieves the following beneficial effects: acquiring historical trajectory data of a target pedestrian; obtaining multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment based on the historical trajectory data and the trajectory point information of the target pedestrian at the current moment; determining the density function of the predicted trajectory corresponding to each trajectory point based on the multiple predicted trajectory points; and obtaining the movement area of ​​the target pedestrian within the preset time period using each density function based on a preset confidence interval. Based on this, this application obtains the movement area of ​​the target pedestrian within a preset time period through multiple predicted trajectory points within the preset time period, using the movement area to represent the location where the pedestrian may appear in the future, fully considering the randomness of pedestrian trajectories. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating a method for predicting pedestrian movement areas provided in an embodiment of this specification;

[0028] Figure 2 This is a schematic diagram illustrating an application scenario of a pedestrian movement area prediction method provided in the embodiments of this specification.

[0029] Figure 3 A schematic diagram of the structure of a pedestrian movement area prediction device provided in the embodiments of this specification;

[0030] Figure 4 This is a schematic diagram of the structure of a pedestrian movement area prediction device provided in an embodiment of this specification. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0032] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0033] In existing technologies, methods that predict pedestrian trajectories by generating models from massive amounts of data and by training models require offline collection of large amounts of data and training of models. The training of models involves a large amount of computation, requires differentiation of application scenarios, and the output is uncertain. These methods cannot take into account the physical properties of pedestrians, can produce bizarre trajectories, and cannot fully account for the randomness of pedestrian trajectories.

[0034] To address the shortcomings of existing technologies, this solution provides the following embodiments:

[0035] The method for predicting pedestrian movement areas provided in the embodiments of the specification will be described in detail with reference to the accompanying drawings.

[0036] Figure 1 This is a flowchart illustrating a method for predicting pedestrian movement areas provided in an embodiment of this specification. From a programming perspective, the entity executing the process can be a program or application client mounted on an application server. From a hardware perspective, the entity executing the process can be a mobile terminal, computer terminal, server, or similar computing device; it can be a system or a platform; this embodiment does not impose any particular limitation on this.

[0037] like Figure 1 As shown, the process may include the following steps:

[0038] Step 110: Obtain the historical trajectory data of the target pedestrian.

[0039] Step 120: Based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment, obtain multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment.

[0040] In the embodiments of this specification, pedestrian historical trajectory data may include the pedestrian's identifier, location, speed, time information at that location, etc. Historical trajectory data may refer to data generated before the current moment. Trajectory point information may include the pedestrian's location, speed, orientation, etc. Multiple predicted trajectory points within a preset time period can be obtained from historical trajectory data. To ensure the accuracy of the prediction, the preset time period can be set to 0.1 seconds to 2 seconds, without specific limitation. When the preset time period is 1 second, it means that multiple trajectory points of the target pedestrian within 1 second after the current moment can be obtained, and the pedestrian's movement area within 1 second after the current moment can be predicted.

[0041] Step 130: Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point.

[0042] In the embodiments of this specification, a predicted trajectory point can correspond to a density function, which can represent the probability of a target pedestrian appearing at the predicted trajectory point within a preset time period in the future.

[0043] Step 140: Using each of the density functions, based on a preset information interval, obtain the movement area of ​​the target pedestrian within the preset time period.

[0044] In the embodiments of this specification, the boundary points of the target pedestrian's movement area can be obtained on each density function according to the preset information interval. The boundary lines of the possible movement areas of the target pedestrian can be obtained from the boundary points. The area formed by the boundary lines can represent the movement area of ​​the target pedestrian in the future preset time period. The narrower the width of the movement area, the higher the accuracy of the predicted movement position of the pedestrian. As the preset time period increases, the widest part of the movement area increases, and the prediction accuracy decreases. For example, when the preset time period is 2 seconds, the widest part of the movement area is about 80 centimeters, which can indicate that the maximum width of the movement area that the pedestrian may appear in in the 2nd second of the future is 80 centimeters.

[0045] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification may be interchanged according to actual needs, or some steps may be omitted or deleted.

[0046] Figure 1 The method described in the paper obtains the movement area of ​​the target pedestrian within a preset time period by using multiple predicted trajectory points within the preset time period. The movement area represents the location where the pedestrian may appear in the future, which fully takes into account the randomness of the pedestrian's trajectory.

[0047] At the same time, since it does not use traditional prediction models, it can be applied to more application scenarios. The microsecond-level computing speed allows for high-frequency updates, and the process is simple, saving the inference time of traditional prediction models.

[0048] based on Figure 1 In addition to the method described in the embodiments of this specification, some specific implementation schemes of the method are also provided, which will be described below.

[0049] Optionally, the pedestrian historical trajectory data described in the embodiments of this specification includes multiple trajectory point data of the target pedestrian; the step of obtaining multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment based on the pedestrian historical trajectory data and the trajectory point information of the target pedestrian at the current moment may specifically include:

[0050] Based on the multiple trajectory point data, a historical trajectory fitting curve is obtained;

[0051] Based on the historical trajectory fitting curve, using the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained.

[0052] In the embodiments of this specification, polynomial fitting can be performed based on the trajectory point data to obtain the historical trajectory fitting curve. In order to obtain a smoother boundary line of the motion area, a predicted trajectory point can be predicted every 0.1 seconds on the historical trajectory fitting curve within a preset time period after the current moment. The fitting curve can fully consider the speed of pedestrians and physical constraints.

[0053] To accurately fit all historical trajectory points, optionally, in the embodiments of this specification, based on the historical trajectory fitting curve, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained using the trajectory point information of the target pedestrian at the current moment. Specifically, this may include:

[0054] Based on the historical trajectory fitting curve, regression analysis is performed on the multiple trajectory point data, and the multiple predicted trajectory points are obtained using the trajectory point information of the target pedestrian at the current moment.

[0055] In the embodiments of this specification, an error function can be used for regression analysis. Through regression analysis, the fitting coefficient of the historical trajectory fitting curve can be determined. The historical trajectory fitting curve with a fixed fitting coefficient can be defined as a fitting polynomial so that multiple predicted trajectory points can be obtained on the fitting polynomial in the future.

[0056] Optionally, the historical trajectory fitting curve described in the embodiments of this specification is... Where w represents the fitting coefficient, w j Let x represent the j-th fitting coefficient, and let x represent the x-coordinate of the trajectory point of the target pedestrian. j Let y represent the j-th order of the x-coordinate of the trajectory point of the target pedestrian, y represent the y-coordinate of the trajectory point of the target pedestrian, and M represent the order.

[0057] In the embodiments of this specification, the final value of M can be determined by comparing the calculation results of regression analysis when M takes different values. The value of M generally does not exceed 3. For example, when M takes the values ​​of 0, 1, 2, and 3, regression analysis is performed respectively, and the calculation results are compared. The value of M corresponding to the smallest value of the calculation result can be determined as the final value of M.

[0058] Optionally, the regression analysis processing described in the embodiments of this specification includes calculation according to the regression analysis formula, wherein the regression analysis formula is: Where x can represent the x-coordinate of the trajectory point of the target pedestrian, x iLet represent the x-coordinate of the i-th trajectory point of the target pedestrian, w represent the fitting coefficient, y represent the y-coordinate of the trajectory point of the target pedestrian, and t represent the y-coordinate of the trajectory point of the target pedestrian. i This can be represented as the target pedestrian being located at x. i The vertical coordinate in the pedestrian historical trajectory data corresponding to the time, E can represent the error, and I can represent the number of trajectory points.

[0059] In the embodiments of this specification, in order to obtain a more accurate historical trajectory fitting curve, the error between the historical trajectory fitting curve y(x, w) and the actual historical trajectory points can be minimized. i w) can represent the location of the target pedestrian at x. i The vertical coordinate of the historical trajectory fitting curve corresponding to the time can indicate the location of the target pedestrian on the x-axis. i The vertical coordinate in the historical trajectory data of pedestrians at the time is E(w), which is a quadratic function of w. When the error is minimized, there is a unique solution w*. Therefore, the fitting polynomial y(x, w*) can be obtained. The smaller the error, the higher the fit of the fitting curve. When the error is 0, it means that the fitting curve can perfectly and accurately fit all trajectory points.

[0060] Optionally, the density function of the predicted trajectory described in the embodiments of this specification is: x~N(0,σ) 2 ), σ 2 =c 2 t, where x can represent the x-coordinate of the trajectory point of the target pedestrian, p can represent the probability of the target pedestrian appearing at position x, c can represent the movement speed of the target pedestrian, t can represent the movement time period of the target pedestrian, and N can represent a normal distribution.

[0061] In the embodiments described in this specification, it is assumed that the pedestrian performs Brownian motion within a preset time period after the current moment, and the Brownian motion follows a probability distribution, N(0, σ). 2 In ) , 0 represents the mean, and σ 2 For variance, x~N can represent that the x-coordinate of the target pedestrian's trajectory point follows a normal distribution, and t can be set according to a preset time period. For example, when the preset time period is 2 seconds, the value range of t can be 0.1~2, which means that the movement of the target pedestrian in the next 2 seconds after the current moment meets the probability distribution.

[0062] Optionally, the method described in this specification for obtaining the movement area of ​​the target pedestrian within the preset time period using each of the density functions based on a preset information interval may specifically include:

[0063] Based on the multiple predicted trajectory points, a perpendicular line corresponding to each predicted trajectory point is obtained;

[0064] Using the density function of the predicted trajectory corresponding to each trajectory point, and based on a preset confidence interval, several boundary points are obtained on each of the vertical lines;

[0065] Based on the aforementioned boundary points, the movement area of ​​the target pedestrian within the preset time period is obtained.

[0066] In this embodiment of the specification, a tangent is drawn for each predicted trajectory point. Based on the tangent, a perpendicular line corresponding to each predicted trajectory point can be obtained. The preset confidence interval can be [-2σ, 2σ]. Based on the preset confidence interval, an upper boundary point and a lower boundary point can be obtained on each perpendicular line. The upper boundary points are connected to form an upper boundary line, and the lower boundary points are connected to form a lower boundary line. The area formed by connecting the upper boundary line and the lower boundary line can be determined as the movement area of ​​the target pedestrian within a preset time period.

[0067] Based on the confidence interval [-2σ, 2σ], we can obtain the boundary points with a confidence level of 96% for each density function. Based on the boundary points, we can obtain the boundary lines of the movement areas where the target pedestrian may appear. This can also be understood as the probability that the target pedestrian appears in the movement area formed by the boundary lines of the above areas within a preset time period is 96%.

[0068] Optionally, after obtaining the movement area of ​​the target pedestrian within a preset time using each of the density functions based on a preset information interval in the embodiments of this specification, it may further include:

[0069] Based on the movement area, an avoidance command is generated for the target pedestrian in order to control the target object to avoid the target pedestrian.

[0070] In the embodiments of this specification, the target object may refer to vehicles, robots, etc., and is not specifically limited here. Avoidance instructions or programs for pedestrians can be generated based on the predicted pedestrian movement area to avoid pedestrians, which can serve intelligent driving, mobile travel, and service robot navigation, etc.

[0071] Figure 2 This is a schematic diagram illustrating an application scenario of a pedestrian movement area prediction method provided in the embodiments of this specification.

[0072] like Figure 2As shown, the trajectory of the target pedestrian in the previous six frames can be obtained from a public dataset to create a historical trajectory. The unique ID of the target pedestrian can be obtained, along with the x and y coordinates and velocities in the x and y directions for each frame. The first six frames contain six trajectory points. Using this data, a historical trajectory fitting curve can be obtained. By solving the fitting curve through regression analysis, the fitting coefficients can be determined, resulting in a fitting polynomial. Using the current trajectory point information of the target pedestrian, a predicted trajectory point is predicted every 0.1 seconds after the current moment on the fitting polynomial, resulting in 10 predicted trajectory points within one second after the current moment. A tangent line can be drawn for each predicted trajectory point, and a perpendicular line corresponding to each predicted trajectory point can be obtained from the tangent line. Based on a pre-set confidence interval, an upper boundary point and a lower boundary point can be obtained on each perpendicular line. Subsequently, the movement area of ​​the target pedestrian within the next second can be obtained using these boundary points.

[0073] In the embodiments of this specification, the movement area represents the location where a pedestrian may appear in the future within a certain period of time, which fully considers the randomness of the pedestrian trajectory. At the same time, since no traditional prediction model is used, it can be applied to more application scenarios. The microsecond-level calculation speed can be updated at a very high frequency. The process is simple and saves the inference time of traditional prediction models.

[0074] Figure 3 This is a schematic diagram of the structure of a pedestrian movement area prediction device proposed in an embodiment of this specification.

[0075] The pedestrian movement area prediction device described in the embodiments of this specification may include:

[0076] Historical data acquisition module 302 is used to acquire historical trajectory data of the target pedestrian;

[0077] The trajectory point prediction module 304 is used to obtain multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment.

[0078] The function determination module 306 is used to determine the density function of the predicted trajectory corresponding to each trajectory point based on the plurality of predicted trajectory points;

[0079] The motion area determination module 308 is used to obtain the motion area of ​​the target pedestrian within the preset time period by using each of the density functions and based on a preset information interval.

[0080] Based on the same idea, this specification also provides devices corresponding to the above methods in its embodiments.

[0081] Figure 4This is a schematic diagram of the structure of a pedestrian movement area prediction device provided in an embodiment of this specification. Figure 4 As shown, device 400 may include:

[0082] At least one processor 410; and,

[0083] Memory 430 communicatively connected to the at least one processor; wherein,

[0084] The memory 430 stores instructions 420 that can be executed by the at least one processor 410, the instructions being executed by the at least one processor 410 to enable the at least one processor 410 to:

[0085] Obtain the historical trajectory data of the target pedestrian;

[0086] Based on the pedestrian's historical trajectory data and the target pedestrian's current trajectory point information, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained.

[0087] Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point;

[0088] Using the density functions, the movement area of ​​the target pedestrian within the preset time period is obtained based on the preset information interval.

[0089] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for... Figure 4 As the device shown is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0090] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0091] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0092] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0093] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0094] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0096] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0097] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0099] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0100] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0102] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0104] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting pedestrian movement areas, characterized in that, include: Obtain the historical trajectory data of the target pedestrian; Based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained; Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point; Using the density functions, the movement area of ​​the target pedestrian within the preset time period is obtained based on the preset information interval.

2. The method according to claim 1, characterized in that, The pedestrian historical trajectory data includes multiple trajectory point data of the target pedestrian; the step of obtaining multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment based on the pedestrian historical trajectory data and the trajectory point information of the target pedestrian at the current moment specifically includes: Based on the multiple trajectory point data, a historical trajectory fitting curve is obtained; Based on the historical trajectory fitting curve, and using the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained.

3. The method according to claim 2, characterized in that, The step of obtaining multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment, based on the historical trajectory fitting curve and using the trajectory point information of the target pedestrian at the current moment, specifically includes: Based on the historical trajectory fitting curve, regression analysis is performed on the multiple trajectory point data, and the multiple predicted trajectory points are obtained using the trajectory point information of the target pedestrian at the current moment.

4. The method according to claim 2, characterized in that, The historical trajectory fitting curve is: Where w represents the fitting coefficient, w j Let x represent the j-th fitting coefficient, and let x represent the x-coordinate of the trajectory point of the target pedestrian. j Let y represent the j-th order of the x-coordinate of the trajectory point of the target pedestrian, y represent the y-coordinate of the trajectory point of the target pedestrian, and M represent the order.

5. The method according to claim 3, characterized in that, The regression analysis process includes calculations according to the regression analysis formula, wherein the regression analysis formula is: Where x represents the x-coordinate of the trajectory point of the target pedestrian, x i Let w represent the x-coordinate of the i-th trajectory point of the target pedestrian, w represent the fitting coefficient, y represent the y-coordinate of the trajectory point of the target pedestrian, and t represent the y-coordinate of the trajectory point of the target pedestrian. i Indicates that the target pedestrian is located at x i The vertical coordinate in the pedestrian historical trajectory data corresponding to the time, E represents the error, and I represents the number of trajectory points.

6. The method according to claim 1, characterized in that, The density function of the predicted trajectory is x~N(0,σ) 2 ), σ 2 =c 2 t, where x represents the x-coordinate of the trajectory point of the target pedestrian, p represents the probability of the target pedestrian appearing at position x, c represents the movement speed of the target pedestrian, t represents the movement time period of the target pedestrian, and N represents a normal distribution.

7. The method according to claim 1, characterized in that, The step of using each of the density functions, based on a preset information interval, to obtain the movement area of ​​the target pedestrian within the preset time period specifically includes: Based on the multiple predicted trajectory points, a perpendicular line corresponding to each predicted trajectory point is obtained; Using the density function of the predicted trajectory corresponding to each trajectory point, and based on a preset confidence interval, several boundary points are obtained on each of the vertical lines; Based on the aforementioned boundary points, the movement area of ​​the target pedestrian within the preset time period is obtained.

8. The method according to claim 1, characterized in that, After obtaining the movement area of ​​the target pedestrian within a preset time using each of the density functions based on a preset confidence interval, the method further includes: Based on the movement area, an avoidance command is generated for the target pedestrian in order to control the target object to avoid the target pedestrian.

9. A device for predicting pedestrian movement areas, comprising: The historical data acquisition module is used to acquire the historical trajectory data of the target pedestrian. The trajectory point prediction module is used to obtain multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment, based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment. The function determination module is used to determine the density function of the predicted trajectory corresponding to each trajectory point based on the plurality of predicted trajectory points. The motion area determination module is used to obtain the motion area of ​​the target pedestrian within the preset time period by utilizing each of the density functions and based on a preset information interval.

10. A device for predicting pedestrian movement areas, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Obtain the historical trajectory data of the target pedestrian; Based on the pedestrian's historical trajectory data and the trajectory point information of the target pedestrian at the current moment, multiple predicted trajectory points of the target pedestrian within a preset time period after the current moment are obtained; Based on the multiple predicted trajectory points, determine the density function of the predicted trajectory corresponding to each trajectory point; Using the density functions, the movement area of ​​the target pedestrian within the preset time period is obtained based on the preset information interval.

Images