Method for characterizing the movement of mobile entities and associated computer program product

EP4457682A1Pending Publication Date: 2024-11-06THALES SA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
EP2022839386
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-12-27
Filing Date
2022-12-27
Publication Date
2024-11-06

AI Technical Summary

Technical Problem

Current methods for characterizing the movement of mobile entities in environments are complex and time-consuming, requiring extensive calibration and simulation to generate realistic scenarios, which can be impractical for real-time applications.

Method used

A method that uses a learning phase to train a model with an adjacency matrix and database of movement parameters, allowing for the rapid characterization of mobile entity movements, including anomaly detection and corrective actions, and predicts future scenarios using a supervised learning algorithm and Graph Neural Networks.

Benefits of technology

This approach simplifies and accelerates the characterization of mobile entity movements, enabling more efficient and realistic predictions of crowd behavior in environments, while accounting for temporal and spatial dynamics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1.1
    Figure 1.1
Patent Text Reader

Abstract

The present invention relates to a method (100) for characterizing the movement of mobile entities, such as pedestrians, in areas of an environment. The method (100) comprises a learning phase (110), comprising receiving (121), (122) an adjacency matrix and a database comprising pairs of data for multiple successive times. The learning phase furthermore comprises training a model on the basis of the database and of the adjacency matrix, the model supplying, from a number of one or more entities in each area, a respective set of one or more parameters characterizing the movement of the entities in the environment. The method furthermore comprises a use phase (120) comprising receiving (131) a number of one or more mobile entities for each area, and applying (134) the trained model to the number of one or more mobile entities received for each area, so as to obtain a respective set of one or more parameters characterizing the movement of the mobile entities and associated with said numbers of one or more mobile entities.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] DESCRIPTION

[0002] TITLE: Method for characterizing the movement of mobile entities and associated computer program product

[0003] The present invention relates to a method for characterizing the movement of mobile entities in an environment.

[0004] The present invention also relates to a computer program product comprising software instructions suitable for implementing such a characterization method.

[0005] The present invention relates to the field of movements of mobile entities in a predetermined environment.

[0006] "Mobile entities" are things, or beings, capable of moving in the environment. For example, mobile entities include pedestrians, cyclists, motorcyclists, car drivers, robots, drones, and animals.

[0007] An "environment" is a space, for example a predefined space, in which mobile entities are able to move. For example, the environment is a train station concourse, an airport, a metro concourse, a parking lot, or a forest.

[0008] In the field of characterizing the movement of mobile entities in an environment, it is known to use a simulator to predict a scenario of the evolution of the movements of mobile entities in the environment. To perform such a simulation of the movement of mobile entities in the environment, it is nevertheless required to calibrate the simulator so that the predicted scenario is as realistic as possible. The calibration of the simulator is for example carried out from a set of parameters characterizing the movement of mobile entities in the environment.

[0009] Determining this parameter set is particularly complex since these parameters generally vary over time and depending on the situation. Furthermore, if the parameter set is not well defined, the scenario predicted by the simulator is unrealistic. In such a case, the predicted scenario is unusable.

[0010] The article "Density-based evolutionary framework for crowd model calibration" by J. Zhong, N. Hu, W. Cai, M. Lees, and LB Luo describes a method for determining a set of calibration parameters for a simulator and the use of the simulator to characterize the movement of mobile entities. The method in the article uses evolutionary algorithms in an approach to optimizing the coefficients of a model to approximate the real behavior of a crowd.

[0011] This method, however, requires knowledge of a prior model capable of providing an acceptable set of parameters. In addition, this method requires a significant number of simulations, by the simulator, to converge the evolutionary algorithms towards a satisfactory solution allowing the subsequent generation of a good set of calibration parameters.

[0012] Thus, the art method is sometimes too complex and / or too slow to exploit.

[0013] There is therefore a need to simplify and make faster the characterization of the movement of mobile entities in the environment.

[0014] To this end, the invention proposes a method for characterizing the movement of mobile entities in an environment, which is simpler and faster to use.

[0015] To this end, the invention relates to a method for characterizing the movement of mobile entities, such as pedestrians, in areas of an environment, the method comprising a learning phase comprising the following steps implemented by a computer:

[0016] - reception of an adjacency matrix indicating the possible movements between two adjacent zones,

[0017] - receiving a database comprising, for each of a plurality of successive instants, a pair of data, each pair of data comprising a number of mobile entity(ies) in each zone and a set of parameter(s) characterizing the movement of the mobile entities in the environment,

[0018] - training a model based on the database and the adjacency matrix, the model being configured to provide, from a number of mobile entity(ies) in each zone, a respective set of parameter(s) characterizing the movement of the mobile entities in the environment, the method further comprising an exploitation phase comprising the following steps:

[0019] - reception, for each zone, of a number of mobile entity(ies), and

[0020] - application, to the number of mobile entity(ies) received for each zone, of the trained model to obtain a respective set of parameter(s) characterizing the movement of the mobile entities in the environment and associated with said number of mobile entity(ies).

[0021] According to particular embodiments, the method comprises one or more of the following characteristics, taken in isolation or in all technically possible combinations: - the method further comprises, during the operating phase, the following steps:

[0022] - detection of an anomaly in the set of parameter(s) obtained, and

[0023] - if the anomaly is detected in the parameter set(s), implementation of a corrective action in the environment;

[0024] - the method comprises, during the operating phase, a step of predicting the movements of the mobile entities in the environment, from the set of parameter(s) obtained, to obtain a predicted scenario;

[0025] - the method further comprises, following the prediction step, the following steps:

[0026] - detection of a predicted anomaly from the predicted scenario, and

[0027] - if the predicted anomaly is detected, implementation of a corrective action in the environment;

[0028] - during the operating phase, the reception stage includes the following sub-stages:

[0029] - obtaining information on mobile entities in the environment from at least one sensor, and

[0030] - for each zone, determination of the number of mobile entity(ies) in the zone by processing the information obtained;

[0031] - the training stage includes the following sub-stages:

[0032] - for each zone, calculation, over a sliding time window of successive instants, of an average number of mobile entity(ies) in the zone,

[0033] - calculation of at least one set of averaged parameter(s), over the sliding time window, from the set of parameter(s) characterizing the movement of the mobile entities in the environment,

[0034] - application, to the model, of a supervised learning algorithm from the average number of mobile entity(ies) in each zone, from at least one set of averaged parameter(s) and from the adjacency matrix;

[0035] - the method further comprises, between the sub-step of calculating at least one set of averaged parameter(s) and the application sub-step, a sub-step of normalizing the average number of mobile entity(ies) of each zone to obtain a normalized vector of number of mobile entity(ies) of which an algebraic norm is preferably equal to one, during the application step, the learning algorithm is applied to the model from the normalized vector, the at least one set of averaged parameter(s) and the adjacency matrix;

[0036] - the respective set of parameter(s) obtained during the exploitation phase includes at least one parameter chosen from a group consisting of: - an average speed of the mobile entities in the environment,

[0037] - a maximum flow rate of mobile entities at one or more points in the environment,

[0038] - an average flow rate of mobile entities at one or more points in the environment,

[0039] - a frequency of arrival near the environment of transport vehicles,

[0040] - for at least a first and a second point in the environment, a proportion of pedestrians at the second point who have previously passed through the first point, and

[0041] - for at least a first point in the environment, a second point in the environment and at least one path between the first and second points, a proportion of pedestrians using said path among the pedestrians going from the first to the second point;

[0042] - The zones are numbered, the adjacency matrix comprising a plurality of rows, a plurality of columns, and a coefficient for each row and each column, each coefficient being equal to a predefined value if a move is possible from the zone whose number is equal to the column of the coefficient, to the zone whose number is equal to the row of the coefficient;

[0043] The present invention also relates to a computer program product comprising software instructions which, when executed by a computer, implement such a characterization method.

[0044] Other characteristics and advantages of the invention will appear on reading the following description of embodiments of the invention, given by way of example only and with reference to the appended drawings in which:

[0045] [FIG. 1], Figure 1 is a schematic view of an environment in which mobile entities are capable of moving,

[0046] [FIG. 2], Figure 2 is a schematic view of a computer suitable for implementing a characterization method according to the invention, and

[0047] [FIG. 3], Figure 3 is a flowchart of the characterization process implemented by the computer of Figure 2.

[0048] With reference to Figure 1, an environment 10 is described comprising a plurality of zones Zi in which mobile entities, such as pedestrians, are likely to move. In the remainder of the description, the mobile entities will be considered to be pedestrians without loss of generality. The elements described below are in fact applicable to other mobile entities such as cyclists, motorcyclists, car drivers, robots, drones, or even animals.

[0049] For example, environment 10 is a train station hall or a metro station.

[0050] In the example illustrated in Figure 1, the environment 10 comprises thirteen zones respectively named Zi to Zi3. The movement of pedestrians in the zones Zi is for example free. In other words, pedestrians are able to move from any first zone Zi to each adjacent second zone Zj.

[0051] For example, in Figure 1, zones Zi, Z3, Z7 correspond to entrances to environment 10. In this same example, zones Z5 and Z6 correspond to train or metro platforms through which pedestrians are forced to pass to enter the train or metro. It is clear that congestion zones are likely to appear.

[0052] The environment 10 further comprises at least one sensor capable of obtaining information on pedestrians in the environment 10, and preferably in the zones Zi. Optionally, the at least one sensor comprises a plurality of cameras, each pointed towards one or more zones Zi and capable of obtaining images of pedestrians in said zone(s) Zi.

[0053] In Figure 2, a calculator 20 is shown.

[0054] The calculator 20 is preferably a computer.

[0055] More generally, the computer 20 is an electronic computer capable of manipulating and / or transforming data represented as electronic or physical quantities in registers of the computer 20 and / or memories, into other similar data corresponding to physical data in memories, registers or other types of display, transmission or storage devices.

[0056] As shown in Figure 2, the computer 20 comprises a display unit 22 and a data processing unit 24.

[0057] The display unit 22 is for example a computer monitor connected to the processing unit 24. The display unit 22 is capable of displaying, to a user, information from the processing unit 24.

[0058] The processing unit 24 is connected to the display unit 22 and comprises a processor 26 and a memory 28. The processing unit 24 is for example connected to the sensor(s) described above. The memory 28 preferably stores a computer program product 30 comprising software instructions which, when executed by the processor 26, implement a method 100 for characterizing the movement of pedestrians in the environment 10. Alternatively, the computer program product is stored on an information medium not shown. The information medium is a medium readable by the computer 20, usually by the processing unit 24. The readable information medium is a medium suitable for storing the electronic instructions and capable of being coupled to a bus of a computer system.

[0059] For example, the information medium is a floppy disk, an optical disk, a CD-ROM, a magneto-optical disk, a ROM memory, a RAM memory, an EPROM memory, an EEPROM memory, a magnetic card, an optical card or a USB key.

[0060] The operation of the calculator 20 will now be described with reference to figure s representing a flowchart of different phases of the method 100 for characterizing the movement of pedestrians.

[0061] The method 100 comprises a learning phase 110 and an operating phase 120.

[0062] The learning phase 110 is for example implemented prior to an implementation of the operating phase 120 in the environment 10.

[0063] The learning phase 1 10 aims to perform machine learning of a model from so-called labeled data which are pairs of data comprising each of the model's input data and the corresponding output data. The purpose of learning is therefore to modify the model so that when it receives the input data of a pair of data, it provides the associated output data in the labeled data.

[0064] The learning phase 110 comprises a first step 121 of receiving an adjacency matrix A indicating the possible movements between two adjacent zones. In the aforementioned example in which the movement between the zones is free, the adjacency matrix A indicates for each zone Zi the other zones Zj which are adjacent to it, that is to say contiguous. Preferably, the zones Zi are numbered and the adjacency matrix A is a square matrix comprising for each zone Zi, a row and a column. In this example, for each row i and for each column j, the adjacency matrix A comprises a coefficient Aj equal to one if the zones Zi and Zj are adjacent, or equal to zero if the zones Zi and Zj are not adjacent.

[0065] In the environment 10 shown in Figure 1, the adjacency matrix A is as follows:

[0066] [MATH1]

[0067] We note that the adjacency matrix A is then a symmetric matrix since, if a first zone Zi is adjacent to a second zone Zj, then the second zone Zj is also adjacent to the first zone Zi.

[0068] According to an alternative embodiment, movements between zones are constrained. In other words, from at least one zone Z i; pedestrians are able to move towards only part of the zones Zj adjacent to said zone Zi.

[0069] Such a case is, for example, observable if environment 10 is an airport. It is no longer possible to go back after passing through customs.

[0070] Thus, the adjacency matrix A is not symmetrical. In the above example, the coefficient Aij corresponding to the passage from a first zone Zi located before customs, to a second zone Zj located after customs, is equal to one. In this same example, the coefficient Aj corresponding to the reverse passage is equal to zero.

[0071] Then, the learning phase 1 10 comprises a second step 122 of receiving a database. The database comprises, for each of a plurality of successive instants, Tk, a pair of data. Each pair of data comprises on the one hand a number of pedestrian(s) in each zone Zi, and on the other hand a set of parameters characterizing the movement of the pedestrians in the environment 10. The numbers of pedestrian(s) in each zone are for example grouped in the form of a vector. Similarly, the set of parameters forms for example a vector.

[0072] The set of parameters comprises for example one or more parameters chosen from a group consisting of: an average speed of movement of pedestrians in the environment 10, a maximum flow rate of pedestrians at one or more points of the environment 10, an average flow rate of pedestrians at one or more points of the environment 10, a frequency of arrival at the vicinity of the environment 10, of transport vehicle(s), and for at least a first and a second point of the environment, a proportion of pedestrians at the second point who have previously passed through the first point, and for at least a first point of the environment, a second point of the environment and at least one path between the first and second points, a proportion of pedestrians taking said path among the pedestrians going from the first to the second point.

[0073] Then, the learning phase 110 comprises a step 123 of training a model as a function of the database and the adjacency matrix A. The model is configured to provide, from a number of pedestrian(s) in each zone Zi, a respective set of parameters characterizing the movement of the pedestrians in the environment 10.

[0074] The model is for example a neural network. According to this example, the neural network comprises an input layer comprising a neuron for each zone Zi of the environment 10, one or more hidden layers comprising a plurality of neurons each, and an output layer comprising a neuron for each parameter of the parameter set. Furthermore, the neural network comprises connections between each neuron of a layer to a neuron of a following layer and, for each connection, an adjustable weight.

[0075] In particular, the model is preferably a graph neural network or a graph convolutional network. Such networks comprise a plurality of hidden layers, each comprising as many neurons as the input layer. Furthermore, these networks are capable of receiving the adjacency matrix A and of including connections only for the possible movements according to the adjacency matrix A. In other words, with these networks, a connection between a first neuron ni of a hidden layer and a second neuron n, of the following hidden layer, exists only on the condition that a movement between a first respective zone Zi and the second respective zone Zj is possible, according to the adjacency matrix A.Thus, GNN and GCN networks include a smaller number of connections than a classic deep neural network, and consequently fewer adjustable weights, thus making it possible to accelerate the learning of the neural network and to stabilize the learning of the neural network.

[0076] The training step 123 optionally comprises a first calculation sub-step 124, for each zone Zi, of an average number of pedestrian(s) in the zone Zi. For this purpose, during the first calculation sub-step 124, for each zone Z i; the average number of pedestrian(s) is for example calculated over a sliding time window. The sliding window includes for example a predefined number N of successive instants Tk. The sliding window is applied to the numbers of pedestrian(s) of the pairs of data in the database. The predefined number N of successive instants Tk is for example equal to five, ten, fifteen, or twenty.

[0077] For example, for each zone Zi, a first average number is calculated by averaging the number of pedestrian(s) in said zone Z i; for each of the first N moments (T k )k=i N of the database. Then, for each zone Z i; a second average number is calculated by averaging the number of pedestrian(s) in said zone Z i; for N successive instants (Tj)i=2N+I between the second instant T2 and the N+1 -th instant T N+ I of the database. Then, for each zone Zi, the calculation is preferentially iterated until the sliding window reaches the last instant T D for which the database includes a data pair.

[0078] We then understand that for a moment T k any and for each zone Z i; the number of pedestrian(s) in zone Zi contributes to N average number of pedestrian(s) in said zone Zi.

[0079] Similarly, the training step 123 comprises a second sub-step 125 of calculating at least one set of parameters averaged over the sliding time window. The calculation of the or each set of averaged parameters is analogous to that of the average number of pedestrian(s) in each zone Zi.

[0080] Preferably, the same sliding time windows are applied for the calculation of the average number of pedestrian(s) in each zone Zi during the first calculation sub-step 124 and for the calculation of the average parameter sets during the second calculation sub-step 125.

[0081] Optionally, the first 124 and second 125 calculation sub-steps are performed simultaneously by the processing unit 24.

[0082] The training step 123 advantageously comprises a sub-step 126 of normalizing the average number of pedestrian(s) in each zone Z i;to obtain a normalized vector VN whose algebraic norm is preferably equal to one. The normalization substep 126 is also called the standardization substep.

[0083] The algebraic norm ||7|| of a vector V comprising K components is for example defined by the following equation:

[0084] [Math 2] Or T is the transpose operator, is the square root function, Vi is the i-th component of the vector V.

[0085] To this end, for each sliding window, the average numbers of pedestrian(s) are, for example, grouped into an average vector VM. The average vector VM is then normalized, to obtain a normalized vector VN, for example, according to the following equation:

[0086] [Math 3]

[0087] 1

[0088] VN = - VM iim

[0089] The training step optionally further comprises a sub-step 127 of applying, to the model, a supervised learning algorithm from the or each normalized vector VN, from the or each averaged set of parameters and from the adjacency matrix A.

[0090] The supervised learning algorithm is for example a stochastic gradient descent algorithm.

[0091] During the application sub-step 127, the supervised learning algorithm modifies the weights of the model so that, when a normalized vector VN is provided as input to the model, the model provides at its output a set of parameters as close as possible to the averaged set of parameters corresponding to said normalized vector VN. The adjacency matrix A makes it possible to limit the number of weights to be modified by the supervised learning algorithm.

[0092] After the training step 123, the model is said to be trained and the learning phase 110 ends.

[0093] The operating phase 120 is for example implemented following the learning phase 110, or several hours, days, or months after the learning phase 110.

[0094] The operating phase 120 includes a third reception step 131 during which, for each zone Z i; a number of pedestrian(s) in the Zi zone is received.

[0095] Optionally, the third reception step 131 comprises a sub-step 132 of obtaining information(s) from the at least one sensor present in the environment 10.

[0096] When the at least one sensor comprises cameras, during the obtaining sub-step 132, the images captured by the cameras are obtained by the processing unit 24.

[0097] Then, the third reception step 131 optionally comprises a sub-step 133 of determining a number of pedestrian(s) in each zone Zi by processing the information obtained during the obtaining sub-step 132.

[0098] When the information is images, the determination of the number of pedestrians in each zone Zi is, for example, carried out by applying a known image processing algorithm. Such an algorithm is based, for example, on artificial intelligence tools such as models derived from machine learning. The images are then VGA data (from the English, Video Content Analysis).

[0099] Then the exploitation phase 120 comprises a step 134 of application, to the number of pedestrian(s) received for each zone Zi, of the model trained during the learning phase 110, to obtain a respective set of parameters characterizing the movement of the pedestrians in the environment 10.

[0100] The set of parameters obtained during application step 134 then depends on the number of pedestrian(s) received.

[0101] Optionally, the operating phase 120 comprises a first step 135 of detecting an anomaly in the parameter set. The anomaly is, for example, the fact that one of the parameters in the parameter set exceeds a predefined threshold.

[0102] For example, when the parameter set includes the average speed of pedestrians in environment 10, if the average speed is greater than a first predefined value such as 10km / h, then an anomaly is detected indicating that pedestrians are running instead of walking. Such an anomaly is for example characteristic of an abnormal crowd movement.

[0103] In the same example, if the average speed is lower than a second predefined value such as 2km / h, then an anomaly is detected indicating overall congestion of the environment 10 preventing the peaceful movement of pedestrians.

[0104] According to another example, when the set of parameters includes the maximum flow rate of pedestrians at a point in the environment 10, if this flow rate is less than a third predefined value such as 100 pedestrians per minute, then an anomaly is detected indicating that an element is blocking the aforementioned point in the environment 10.

[0105] According to yet another example, when the set of parameters comprises the frequency of arrival at the vicinity of the environment 10 of transport vehicles, if this frequency is less than a fourth predefined value, then an anomaly is detected indicating a problem with the circulation of the transport vehicles. Such a problem is for example likely to create congestion in the environment 10 because the pedestrians risk not being extracted from the environment 10 quickly enough by the transport vehicles.

[0106] It is clear that the predefined threshold(s) are likely to change over time, particularly over the course of the day or year.

[0107] Optionally, the operating phase 120 comprises, if an anomaly is detected during the first determination step 135, a first step 136 of implementing a corrective action in the environment 10. It is clear that the corrective action is an action carried out automatically or an action recommended for its implementation by a user, in order to overcome the detected anomaly.

[0108] The corrective action is, for example, an opening of a new Zi zone in environment 10, an extension of an already existing Zi zone or an opening of a passage between two Zi zones not yet adjacent.

[0109] The first implementation step 136 comprises, for example, the transmission of an alert to an operator, via the display unit 22. The operator is then able to implement one of the aforementioned corrective actions.

[0110] Alternatively, the first implementation step 136 comprises, for example, sending an actuation command in the environment 10 to carry out one of the aforementioned correction actions, autonomously.

[0111] Alternatively or as an optional addition, following the application step 134, the operating phase 120 comprises a step 137 of predicting the movement of pedestrians in the environment 10. The prediction step 137 comprises, for example, the simulation of the movement of pedestrians in the environment 10, by a simulator included in the memory 28 of the processing unit 24, from the set of parameters obtained by applying the trained model to the number of pedestrian(s) in each zone Zi.

[0112] We then understand that the parameters of the parameter set are input quantities of the simulator allowing to predict, as faithfully as possible, the evolution of the movement of pedestrians in the environment 10. In other words, these parameters are calibration parameters of the simulator.

[0113] During the prediction step 137, a predicted scenario is determined. The predicted scenario describes the evolution of the movement of pedestrians in the environment 10 during a predefined duration.

[0114] The preset duration is, for example, five minutes, ten minutes, thirty minutes, one hour, two hours, or five hours.

[0115] It is clear that the longer the predefined duration, the less realistic the predicted scenario is. Indeed, after a long duration, the situation in the environment 10 has evolved such that the parameters of the parameter set have become obsolete.

[0116] The predicted scenario includes an evolution of quantities simulated by the simulator.

[0117] The simulated quantities are for example the position of each pedestrian in the environment 10, or the density of pedestrians in each zone Zi

[0118] Following the prediction step 137, the exploitation phase 120 advantageously comprises a second step 138 of detecting a predicted anomaly from the predicted scenario. The second detection step 138 is analogous to the first detection step 135 except that the predicted anomaly is detected in the simulated quantities rather than in the parameters of the parameter set.

[0119] If a predicted anomaly is detected during the second detection step 138, then the exploitation phase 120 advantageously comprises a second implementation step 139 analogous to the first implementation step 136.

[0120] During the second implementation step 139, the corrective action is implemented in the environment 10 in a preventive manner. In other words, the corrective action(s) implemented during the second implementation step 139 are intended to prevent the predicted anomaly(ies) detected from occurring in the environment 10.

[0121] Then, the operating phase 120 is for example repeated with the reception 131 of new numbers of pedestrian(s) in the Zi zones.

[0122] Thus, the method according to the invention makes it possible to characterize the movement of pedestrians in the environment 10 in a simple and realistic manner.

[0123] With the first 124 and second 125 optional sub-steps of calculation, a temporal dynamics of pedestrians is taken into account. In other words, taking into account several pairs of data for each input of the model training makes it possible to account for a temporal evolution of the movement of pedestrians.

[0124] With the optional normalization step 126, or standardization, training is accelerated since all vectors used for model training are comparable.

[0125] With the optional training sub-step 127 taking into account the adjacency matrix A, the training of the model is accelerated. In addition, for a fixed number of data pairs, the training of the model from the adjacency matrix A is of better quality than without the use of the adjacency matrix A.

[0126] Furthermore, the use of the adjacency matrix A makes it possible to account for the spatiality of the environment 10 and takes advantage of knowledge of the distribution of zones Zi in the environment 10.

[0127] The optional sub-steps of obtaining 132 and determining 133 make it possible to receive the number of pedestrian(s) in each zone Zi in a simple and substantially inexpensive manner.

[0128] The optional prediction step 137 in combination with the application step 134 makes it possible to faithfully account for a change in the movement of pedestrians in the environment 10 and therefore to predict potential future anomalies.

[0129] The optional detection steps 135, 138 and implementation steps 136, 139 ensure the proper movement of pedestrians in the environment 10.

Claims

DEMANDS 1. A method (100) for characterizing the movement of mobile entities, such as pedestrians, in zones (Zi) of an environment (10), the method (100) comprising a learning phase (110) including the following steps implemented by a computer (20): receiving (121) an adjacency matrix (A) indicating the possible movements between two adjacent zones (Zi), receiving (122) a database comprising, for each of a plurality of successive instants (Tk), a pair of data, each pair of data comprising a number of mobile entity(ies) in each zone (Zi) and a set of parameters characterizing the movement of the mobile entities in the environment (10), training a model based on the database and the adjacency matrix (A), the model being configured to provide, from a number of mobile entity(ies) in each zone (Zi),a respective set of parameter(s) characterizing the movement of mobile entities in the environment (10), the process further comprising an operation phase (120) comprising the following steps:, - reception (131), for each zone (Zi), of a number of mobile entity(ies), and - application (134), to the number of mobile entity(ies) received for each zone (Zi), of the model trained to obtain a respective set of parameter(s) characterizing the movement of mobile entities in the environment (10) and associated with said number of mobile entity(ies), during the exploitation phase (120), the reception step (131) comprising the following sub-steps: obtaining information on the mobile entities in the environment (10) from at least one sensor, and for each zone (Zi), determining the number of mobile entity(ies) in the zone (Zi) by processing the information obtained.

2. A method (100) according to claim 1, wherein the method further comprises, during the operating phase (120), the following steps: detection (135) of an anomaly in the obtained parameter set(s), and - if the anomaly is detected in the parameter set(s), implementation (136) of a corrective action in the environment (10).

3. Method (100) according to claim 1 or 2, further comprising, during the operating phase (120), a step (137) of predicting the movements of mobile entities in the environment (10), from the set of parameter(s) obtained, to obtain a predicted scenario.

4. Method (100) according to claim 3, further comprising, following the prediction step (137), the following steps: detection (138) of a predicted anomaly from the predicted scenario, and if the predicted anomaly is detected, implementation (139) of a corrective action in the environment (10).

5. A method (100) according to any one of the preceding claims, wherein the training step (123) comprises the following substeps: - for each zone (Zi), calculation (124), over a sliding time window of successive instants (Tk), of an average number of mobile entity(ies) of the zone (Zi), - calculation (125) of at least one averaged parameter set(s), over the sliding time window, from the parameter set(s) characterizing the movement of mobile entities in the environment (10), application (127), to the model, of a supervised learning algorithm from the average number of mobile entity(ies) in each zone (Zi), of the at least one averaged parameter set(s) and of the adjacency matrix (A).

6. Method (100) according to the preceding claim, further comprising, between the calculation substep (125) of at least one set of averaged parameter(s) and the application substep (127), a normalization substep (126) of the average number of moving entity(ies) of each zone (Zi) to obtain a normalized vector (VN) of number of moving entity(ies) whose algebraic norm is preferably equal to one, during the application step (127), the learning algorithm is applied to the model from the normalized vector (VN), the at least one set of averaged parameter(s) and the adjacency matrix (A).

7. A method (100) according to any one of the preceding claims, wherein the respective set of parameter(s) obtained during the operating phase (120) comprises at least one parameter selected from a group consisting of: 16 an average speed of mobile entities in the environment (10), a maximum flow rate of mobile entities at one or more points in the environment (10), an average flow rate of mobile entities at one or more points in the environment (10), a frequency of arrival at the edges of the environment (10), of transport vehicles, for at least a first and a second point in the environment, a proportion of pedestrians at the second point who have previously passed through the first point, and for at least a first point in the environment, a second point in the environment and at least one path between the first and second points, a proportion of pedestrians using said path among the pedestrians going from the first to the second point.

8. Method (100) according to any one of the preceding claims, wherein the zones (Zi) are numbered, the adjacency matrix (A) comprising a plurality of rows, a plurality of columns, and a coefficient (Aij) for each row and each column, each coefficient (AJ) being equal to a predefined value if a displacement is possible from the zone (Zj) whose number is equal to the column of the coefficient (A, to the zone (Zi) whose number is equal to the row of the coefficient (Ai.

9. Product computer program comprising software instructions which, when executed by a computer, implement the characterization method (100) according to any one of claims 1 to 8.