Information processing system, information processing device, information processing method, and information processing program

Abstract

To provide a technique or the like for tracking a target object precisely with a low load.SOLUTION: An information processing system comprises: an acquisition section for acquiring multiple sensor data; a trajectory candidate generation section for generating a trajectory candidate regarding a target object by referring to sensor data acquired in the past; a selection section for selecting sensor data showing a position of a target object from among the acquired sensor data; a trajectory group generation section for generating a trajectory group of target objects on the basis of correlation among trajectory candidates; and an output section for outputting the selected sensor group and trajectory group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system, an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] There are known technologies for tracking a target object. For example, Patent Document 1 discloses a multiple evaluation integration analysis device that detects multiple trajectories from observation signals of multiple acoustic sensors and determines whether the multiple trajectories are identical. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-17240 Summary of the Invention [Problem to be solved by the invention]

[0004] A configuration that references data from many sensors, such as the multiple evaluation integration analysis device described in Patent Document 1, has the problem of a large computational load. On the other hand, a configuration that references trajectories detected by each sensor instead of sensor data reduces the computational load, but if the trajectory detection by each sensor is incorrect, the error cannot be corrected, resulting in low accuracy. Therefore, there is a demand for technology that can track a target object with low load and high accuracy.

[0005] The present disclosure has been made in consideration of the above problems, and one of its objectives is to provide a technique for tracking a target object with low load and high accuracy. [Means for solving the problem]

[0006] An information processing system according to an exemplary aspect of the present disclosure includes: an acquisition means for acquiring a plurality of sensor data from each of a plurality of sensors that detects a position of a target object; a trajectory candidate generation means for generating, for each of the plurality of sensors, one or more trajectory candidates for the target object by referring to sensor data previously acquired from the sensor, the sensor data indicating the position of the target object; a selection means for selecting, by referring to the trajectory candidates of the target object, sensor data indicating the position of the target object from among the sensor data acquired from the sensor; a trajectory group generation means for generating a trajectory group of the target object based on a correlation between the trajectory candidates for each of the plurality of sensors; and an output means for outputting the selected sensor data and the trajectory group.

[0007] An information processing device according to an exemplary aspect of the present disclosure includes: an acquisition means for acquiring, from among a plurality of sensor data acquired from each of a plurality of sensors that detect the position of a target object, sensor data selected as sensor data indicating the position of the target object; and, for each of the plurality of sensors, acquiring a trajectory group of the target object that is generated based on a correlation between the trajectory candidates from among one or more trajectory candidates for the target object that are generated with reference to the sensor data that are previously acquired from the sensors and indicate the position of the target object; an update means for updating the trajectory of the target object with reference to the selected sensor data and the trajectory group of the target object; a prediction means for predicting one or more future trajectories of the target object with reference to the updated trajectories; and an output means for outputting a predicted integrated trajectory group that is the one or more trajectories predicted by the prediction means to a device for selecting the sensor data and a device for generating the trajectory group of the target object.

[0008] An information processing system according to an exemplary aspect of the present disclosure includes: an acquisition means for acquiring a plurality of sensor data from each of a plurality of sensors that detects a position of a target object; a trajectory candidate generation means for generating one or more trajectory candidates for a target object by referring to sensor data previously acquired from the sensor, the sensor data indicating the position of the target object, for each of the plurality of sensors; a selection means for selecting sensor data indicating the position of the target object from the sensor data acquired from the sensor by referring to the trajectory candidates of the target object; a trajectory group generation means for generating a trajectory group of the target object based on a correlation between the trajectory candidates for each of the plurality of sensors; an update means for updating the trajectory of the target object by referring to the selected sensor data and the trajectory group; and a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectories.

[0009] An information processing method according to an exemplary aspect of the present disclosure includes: an acquisition process in which at least one processor acquires a plurality of sensor data from each of a plurality of sensors that detects the position of a target object; a trajectory candidate generation process in which, for each of the plurality of sensors, references sensor data previously acquired from the sensor, the sensor data indicating the position of the target object, to generate one or more trajectory candidates for the target object; a selection process in which, references the trajectory candidates for the target object, selects sensor data indicating the position of the target object from the sensor data acquired from the sensor; a trajectory group generation process in which a trajectory group of the target object is generated based on a correlation between the trajectory candidates for each of the plurality of sensors; and an output process in which the selected sensor data and the trajectory group are output.

[0010] An information processing program according to an exemplary aspect of the present disclosure causes a computer to function as: an acquisition means for acquiring a plurality of sensor data from each of a plurality of sensors that detects the position of a target object; a trajectory candidate generation means for generating, for each of the plurality of sensors, one or more trajectory candidates for the target object by referring to sensor data that has been previously acquired from the sensor and indicates the position of the target object; a selection means for selecting, by referring to the trajectory candidates for the target object, sensor data that indicates the position of the target object from among the sensor data acquired from the sensor; a trajectory group generation means for generating a trajectory group for the target object based on a correlation between the trajectory candidates for each of the plurality of sensors; and an output means for outputting the selected sensor data and the trajectory group. [Effects of the Invention]

[0011] According to one exemplary aspect of the present disclosure, an exemplary effect is achieved in that a technique for tracking a target object with low load and high accuracy can be provided. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing system according to the present disclosure. [Figure 2] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 3] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 4] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 5] 1 is a block diagram illustrating a configuration of an information processing system according to the present disclosure. [Figure 6] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 7] 1 is a diagram illustrating an overview of an information processing system according to the present disclosure. [Figure 8] 1 is a block diagram illustrating a configuration of an information processing system and an information processing device according to the present disclosure. [Figure 9]FIG. 10 is a diagram illustrating an example of a trajectory candidate according to the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of sensor data and selected sensor data according to the present disclosure. [Figure 11] FIG. 10 is a diagram illustrating an example of a trajectory group according to the present disclosure. [Figure 12] FIG. 10 illustrates an example of a predicted integrated trajectory according to the present disclosure. [Figure 13] FIG. 2 is a sequence diagram showing the flow of processing executed in the information processing system according to the present disclosure. [Figure 14] FIG. 1 is a block diagram illustrating a configuration of a computer that functions as an information processing system or an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0013] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technical means employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technical means employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0014] First Exemplary Embodiment A first exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. Note that the scope of application of each technical means employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technical means employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure to the extent that no particular technical obstacles arise. Furthermore, each technical means shown in the drawings referred to in describing this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure to the extent that no particular technical obstacles arise.

[0015] (Configuration of Information Processing System 1) The configuration of the information processing system 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing system 1.

[0016] 1, the information processing system 1 includes an acquisition unit 11, a trajectory candidate generation unit 12, a selection unit 13, a trajectory group generation unit 14, and an output unit 15. In this exemplary embodiment, the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, and the output unit 15 respectively realize an acquisition means, a trajectory candidate generation means, a selection means, a trajectory group generation means, and an output means.

[0017] 1 , the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, and the output unit 15 are connected to a network N so as to be able to communicate with each other, but the configuration of the information processing system 1 is not limited to this configuration. The information processing system 1 may be configured such that one device includes the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, and the output unit 15. Alternatively, the information processing system 1 may be configured such that the plurality of devices are connected via the network N, and each of the plurality of devices includes at least one of the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, and the output unit 15.

[0018] The specific configuration of the network N does not limit this exemplary embodiment, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these networks can be used.

[0019] (Acquisition part 11) The acquisition unit 11 acquires a plurality of pieces of sensor data from a plurality of sensors that detect the position of a target object, and supplies the acquired plurality of pieces of sensor data to the trajectory candidate generation unit 12 and the selection unit 13.

[0020] (Trajectory candidate generation unit 12) The trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data previously acquired from each of the multiple sensors and indicating the position of the target object. The trajectory candidate generation unit 12 supplies the generated one or more trajectory candidates to the selection unit 13 and the trajectory group generation unit 14.

[0021] (Selection section 13) The selection unit 13 refers to the trajectory candidates of the target object for each of the multiple sensors, and selects sensor data indicating the position of the target object from the sensor data acquired from the sensor. The selection unit 13 supplies the selected sensor data to the output unit 15.

[0022] (Trajectory group generation unit 14) The trajectory group generator 14 generates a trajectory group of the target object based on the correlation between the trajectory candidates in each of the multiple sensors. The trajectory group generator 14 supplies the generated trajectory group to the output unit 15.

[0023] (Output section 15) The output unit 15 outputs the selected sensor data and the trajectory group.

[0024] (Effects of Information Processing System 1) As described above, the information processing system 1 employs a configuration including: an acquisition unit 11 that acquires a plurality of sensor data from each of a plurality of sensors that detect the position of a target object; a trajectory candidate generation unit 12 that, for each of the plurality of sensors, references sensor data that has been previously acquired from the sensor and indicates the position of the target object to generate one or more trajectory candidates for the target object; a selection unit 13 that, for each of the plurality of sensors, references the trajectory candidates of the target object and selects sensor data that indicates the position of the target object from the sensor data acquired from the sensor; a trajectory group generation unit 14 that generates a trajectory group of the target object based on the correlation between the trajectory candidates for each of the plurality of sensors; and an output unit 15 that outputs the selected sensor data and trajectory group.

[0025] Therefore, according to the information processing system 1, the selected sensor data and trajectory group are output, and therefore, compared to when only one of them is output, the target object can be tracked with higher accuracy by referring to the selected sensor data and trajectory group. Furthermore, according to the information processing system 1, the selected sensor data and trajectory group are output, rather than all the sensor data and trajectory candidates, and therefore, the target object tracking process can be performed with a low load.

[0026] (Flow of information processing method S1) The flow of information processing method S1 will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of information processing method S1. As shown in Fig. 2, information processing method S1 includes an acquisition process S11, a trajectory candidate generation process S12, a selection process S13, a trajectory group generation process S14, and an output process S15.

[0027] (Acquisition process S11) In the acquisition process S11, the acquisition unit 11 acquires a plurality of pieces of sensor data from a plurality of sensors that detect the position of a target object. The acquisition unit 11 supplies the acquired plurality of pieces of sensor data to the trajectory candidate generation unit 12 and the selection unit 13.

[0028] (Trajectory candidate generation process S12) In the trajectory candidate generation process S12, the trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data previously acquired from each of the multiple sensors, the sensor data indicating the position of the target object. The trajectory candidate generation unit 12 supplies the generated one or more trajectory candidates to the selection unit 13 and the trajectory group generation unit 14.

[0029] (Selection process S13) In the selection process S13, the selector 13 refers to the trajectory candidates of the target object for each of the multiple sensors, and selects sensor data indicating the position of the target object from the sensor data acquired from the sensor. The selector 13 supplies the selected sensor data to the output unit 15.

[0030] (Trajectory group generation process S14) In trajectory group generation processing S14, the trajectory group generation unit 14 generates a trajectory group of the target object based on the correlation between trajectory candidates in each of the multiple sensors. The trajectory group generation unit 14 supplies the generated trajectory group to the output unit 15.

[0031] (Output process S15) In the output process S15, the output unit 15 outputs the selected sensor data and trajectory group.

[0032] (Effect of information processing method S1) As described above, the information processing method S1 employs a configuration including: an acquisition process S11 in which the acquisition unit 11 acquires a plurality of sensor data from each of a plurality of sensors that detect the position of the target object; a trajectory candidate generation process S12 in which the trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data that has been previously acquired from the sensor and indicates the position of the target object for each of the plurality of sensors; a selection process S13 in which the selection unit 13 refers to the trajectory candidates of the target object for each of the plurality of sensors and selects sensor data that indicates the position of the target object from the sensor data acquired from the sensor; a trajectory group generation process S14 in which the trajectory group generation unit 14 generates a trajectory group of the target object based on the correlation between the trajectory candidates for each of the plurality of sensors; and an output process S15 in which the output unit 15 outputs the selected sensor data and the trajectory group.

[0033] Therefore, according to the information processing method S1, the same effects as those of the information processing system 1 described above can be obtained.

[0034] (Information processing device 2) The configuration of the information processing device 2 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 2.

[0035] 3, the information processing device 2 includes an acquisition unit 21, an update unit 22, a prediction unit 23, and an output unit 24. In this exemplary embodiment, the acquisition unit 21, the update unit 22, the prediction unit 23, and the output unit 24 respectively realize an acquisition means, an update means, a prediction means, and an output means.

[0036] (Acquisition part 21) The acquisition unit 21 acquires, from among a plurality of pieces of sensor data acquired from each of a plurality of sensors that detect the position of the target object, sensor data selected as sensor data indicating the position of the target object, and, for each of the plurality of sensors, from among one or more trajectory candidates for the target object that have been generated with reference to the sensor data that are sensor data previously acquired from the sensor and indicate the position of the target object, a trajectory group of the target object that has been generated based on the correlation between the trajectory candidates. The acquisition unit 21 supplies the acquired sensor data and trajectory group to the update unit 22.

[0037] (Updated part 22) The update unit 22 updates the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object. The update unit 22 supplies the updated trajectory to the prediction unit .

[0038] (Prediction Section 23) The prediction unit 23 refers to the updated trajectory and predicts one or more trajectories of the target object in the future. The prediction unit 23 supplies the predicted trajectories to the output unit 24.

[0039] (output unit 24) The output unit 24 outputs a group of predicted integrated trajectories, which are one or more trajectories predicted by the prediction unit 23, to a device that selects sensor data and a device that generates a group of trajectories of target objects.

[0040] (Effects of information processing device 2) As described above, the information processing device 2 employs a configuration including an acquisition unit 21 that acquires a group of trajectories of a target object generated based on the correlation between trajectory candidates from one or more trajectory candidates for the target object generated with reference to the sensor data that is previously acquired from each of a plurality of sensors that detect the position of the target object, selected as sensor data that indicates the position of the target object, and sensor data that is previously acquired from each of the plurality of sensors and indicates the position of the target object; an update unit 22 that updates the trajectory of the target object with reference to the selected sensor data and the group of trajectories of the target object; a prediction unit 23 that predicts one or more trajectories of the target object in the future with reference to the updated trajectories; and an output unit 24 that outputs a predicted integrated trajectory group, which is the one or more trajectories predicted by the prediction unit 23, to a device that selects sensor data and a device that generates a group of trajectories of the target object.

[0041] Therefore, according to the information processing device 2, the trajectory of the target object is updated by referring to the selected sensor data and trajectory group, so that the target object can be tracked with higher accuracy than when only one of the selected sensor data and trajectory group is referred to. Furthermore, according to the information processing device 2, the trajectory of the target object is updated by referring to the selected sensor data and trajectory group, rather than all sensor data and trajectory candidates, so that the target object tracking process can be performed with low load.

[0042] Furthermore, the information processing device 2 outputs a predicted integrated trajectory group, which is one or more predicted trajectories, to a device that selects sensor data and a device that generates a trajectory group of a target object. Therefore, the information processing device 2 can feed back the highly accurate predicted integrated trajectory group, thereby enabling highly accurate selection of sensor data and generation of a highly accurate trajectory group of a target object.

[0043] (Flow of information processing method S2) The flow of the information processing method S2 will be described with reference to Fig. 4. Fig. 4 is a flow diagram showing the flow of the information processing method S2. As shown in Fig. 4, the information processing method S2 includes an acquisition process S21, an update process S22, a prediction process S23, and an output process S24.

[0044] (Acquisition process S21) In acquisition processing S21, acquisition unit 21 acquires, from among a plurality of pieces of sensor data acquired from each of a plurality of sensors that detect the position of the target object, sensor data selected as sensor data indicating the position of the target object, and, for each of the plurality of sensors, from among one or more trajectory candidates for the target object that have been generated with reference to the sensor data that are sensor data previously acquired from the sensor and indicate the position of the target object, a trajectory group of the target object that has been generated based on the correlation between the trajectory candidates. Acquisition unit 21 supplies the acquired sensor data and trajectory group to update unit 22.

[0045] (Update process S22) In the update process S22, the update unit 22 updates the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object. The update unit 22 supplies the updated trajectory to the prediction unit .

[0046] (Prediction process S23) In the prediction process S23, the prediction unit 23 refers to the updated trajectory and predicts one or more trajectories of the future target object. The prediction unit 23 supplies the predicted trajectories to the output unit 24.

[0047] (Output process S24) In the output process S24, the output unit 24 outputs a group of predicted integrated trajectories, which are one or more trajectories predicted by the prediction unit 23, to a device that selects sensor data and a device that generates a group of trajectories of the target object.

[0048] (Effect of information processing method S2) As described above, the information processing method S2 employs a configuration including an acquisition process S21 in which the acquisition unit 21 acquires sensor data selected as sensor data indicating the position of the target object from among multiple pieces of sensor data acquired from each of multiple sensors that detect the position of the target object, and acquires, for each of the multiple sensors, a group of trajectories of the target object that is generated based on the correlation between the trajectory candidates from among one or more trajectory candidates for the target object that were generated with reference to the sensor data that indicates the position of the target object, which is sensor data previously acquired from the sensor; an update process S22 in which the update unit 22 updates the trajectory of the target object with reference to the selected sensor data and the group of trajectories of the target object; a prediction process S23 in which the prediction unit 23 predicts one or more trajectories of the target object in the future with reference to the updated trajectories; and an output process S24 in which the output unit 24 outputs the predicted integrated trajectory group, which is the one or more trajectories predicted by the prediction unit 23, to a device that selects sensor data and a device that generates the trajectory group of the target object.

[0049] Therefore, according to the information processing method S2, the same effects as those of the information processing device 2 described above can be obtained.

[0050] (Configuration of information processing system 3) The configuration of the information processing system 3 will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the configuration of the information processing system 3.

[0051] 5, the information processing system 3 includes an acquisition unit 11, a trajectory candidate generation unit 12, a selection unit 13, a trajectory group generation unit 14, an update unit 22, and a prediction unit 23. In this exemplary embodiment, the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, the update unit 22, and the prediction unit 23 respectively realize an acquisition means, a trajectory candidate generation means, a selection means, a trajectory group generation means, an update means, and a prediction means.

[0052] As shown in FIG. 5 , the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, the update unit 22, and the prediction unit 23 are connected to a network N so as to be able to transmit and receive data to and from each other, but the configuration of the information processing system 3 is not limited to this configuration. The information processing system 3 may be configured such that a single device includes the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, the update unit 22, and the prediction unit 23. Alternatively, the information processing system 3 may include a plurality of devices connected via the network N, each of which includes at least one of the acquisition unit 11, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, the update unit 22, and the prediction unit 23. The network N is as described above.

[0053] (Acquisition part 11) The acquisition unit 11 acquires a plurality of pieces of sensor data from a plurality of sensors that detect the position of a target object, and supplies the acquired plurality of pieces of sensor data to the trajectory candidate generation unit 12 and the selection unit 13.

[0054] (Trajectory candidate generation unit 12) The trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data previously acquired from each of the multiple sensors and indicating the position of the target object. The trajectory candidate generation unit 12 supplies the generated one or more trajectory candidates to the selection unit 13 and the trajectory group generation unit 14.

[0055] (Selection section 13) The selection unit 13 refers to the trajectory candidates of the target object for each of the multiple sensors, and selects sensor data indicating the position of the target object from the sensor data acquired from the sensor. The selection unit 13 supplies the selected sensor data to the update unit 22.

[0056] (Trajectory group generation unit 14) The trajectory group generating unit 14 generates a trajectory group of the target object based on the correlation between the trajectory candidates in each of the multiple sensors. The trajectory group generating unit 14 supplies the generated trajectory group to the updating unit 22.

[0057] (Updated part 22) The update unit 22 updates the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object. The update unit 22 supplies the updated trajectory to the prediction unit .

[0058] (Prediction Section 23) The prediction unit 23 refers to the updated trajectory and predicts one or more trajectories of the target object in the future.

[0059] (Effects of Information Processing System 3) As described above, the information processing system 3 employs a configuration including an acquisition unit 11 that acquires multiple pieces of sensor data from multiple sensors that detect the position of a target object, a trajectory candidate generation unit 12 that, for each of the multiple sensors, references sensor data that has been previously acquired from the sensor and indicates the position of the target object to generate one or more trajectory candidates for the target object, a selection unit 13 that, for each of the multiple sensors, references the trajectory candidates of the target object and selects sensor data that indicates the position of the target object from the sensor data acquired from the sensor, a trajectory group generation unit 14 that generates a trajectory group of the target object based on the correlation between the trajectory candidates for each of the multiple sensors, an update unit 22 that updates the trajectory of the target object by reference to the selected sensor data and the trajectory group of the target object, and a prediction unit 23 that predicts one or more future trajectories of the target object by reference to the updated trajectories.

[0060] Therefore, according to the information processing system 3, the same effects as those of the information processing system 1 or the information processing device 2 described above can be obtained.

[0061] (Flow of information processing method S3) The flow of information processing method S3 will be described with reference to Fig. 6. Fig. 6 is a flow diagram showing the flow of information processing method S3. As shown in Fig. 6, information processing method S3 includes an acquisition process S11, a trajectory candidate generation process S12, a selection process S13, a trajectory group generation process S14, an update process S22, and a prediction process S23.

[0062] (Acquisition process S11) In the acquisition process S11, the acquisition unit 11 acquires a plurality of pieces of sensor data from a plurality of sensors that detect the position of a target object. The acquisition unit 11 supplies the acquired plurality of pieces of sensor data to the trajectory candidate generation unit 12 and the selection unit 13.

[0063] (Trajectory candidate generation process S12) In the trajectory candidate generation process S12, the trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data previously acquired from each of the multiple sensors and indicating the position of the target object. The trajectory candidate generation unit 12 supplies the generated one or more trajectory candidates to the selection unit 13 and the trajectory group generation unit 14.

[0064] (Selection process S13) In the selection process S13, the selection unit 13 refers to the trajectory candidates of the target object for each of the multiple sensors, and selects sensor data indicating the position of the target object from the sensor data acquired from the sensor. The selection unit 13 supplies the selected sensor data to the update unit 22.

[0065] (Trajectory group generation process S14) In the trajectory group generation process S14, the trajectory group generation unit 14 generates a trajectory group of the target object based on the correlation between the trajectory candidates in each of the multiple sensors. The trajectory group generation unit 14 supplies the generated trajectory group to the update unit 22.

[0066] (Update process S22) In the update process S22, the update unit 22 updates the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object. The update unit 22 supplies the updated trajectory to the prediction unit .

[0067] (Prediction process S23) In the prediction process S23, the prediction unit 23 refers to the updated trajectories and predicts one or more trajectories of the target object in the future.

[0068] (Effect of information processing method S3) As described above, the information processing method S3 employs a configuration including an acquisition process S11 in which the acquisition unit 11 acquires multiple pieces of sensor data from each of multiple sensors that detect the position of the target object; a trajectory candidate generation process S12 in which the trajectory candidate generation unit 12 generates one or more trajectory candidates for the target object by referring to sensor data that has been previously acquired from the sensor and indicates the position of the target object for each of the multiple sensors; a selection process S13 in which the selection unit 13 refers to the trajectory candidates of the target object for each of the multiple sensors and selects sensor data that indicates the position of the target object from the sensor data acquired from the sensor; a trajectory group generation process S14 in which the trajectory group generation unit 14 generates a trajectory group of the target object based on the correlation between the trajectory candidates for each of the multiple sensors; an update process S22 in which the update unit 22 updates the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object; and a prediction process S23 in which the prediction unit 23 predicts one or more trajectories of the target object in the future by referring to the updated trajectories.

[0069] Therefore, according to the information processing method S3, the same effects as those of the information processing system 3 described above can be obtained.

[0070] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technical means employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technical means employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technical means shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0071] (Outline of Information Processing System 3A) An overview of the information processing system 3A will be described with reference to Fig. 7. Fig. 7 is a diagram showing an overview of the information processing system 3A.

[0072] The information processing system 3A is a system that tracks a target object TO. "Tracking the target object TO" can also be expressed as detecting an integrated trajectory clc, which is the trajectory of the target object TO. The information processing system 3A also predicts a predicted integrated trajectory pclc, which is the trajectory of the target object TO in the future. In this exemplary embodiment, an example will be described in which the integrated trajectory clc of the target object TO at time t is detected and the predicted integrated trajectory pclc of the target object TO at time t+1 is predicted.

[0073] The target object TO is not particularly limited as long as it is a moving object (including a living thing), but one example is an object moving in the air (for example, an aircraft (manned aircraft and unmanned aircraft)). Another example is an object moving on the ground (for example, a car) or a person. Yet another example is an object moving on water (sea) (for example, a ship). With this configuration, the information processing system 3A can track objects moving in the air, objects and people moving on the ground, and objects moving on water.

[0074] As shown in FIG. 7, the information processing system 3A includes a plurality of sensors SN, an information processing system 1A, and an information processing device 2A.

[0075] In Fig. 7, the multiple sensors SN include two sensors SN1 and SN2, but the number of sensors SN is not limited and may be three or more. Furthermore, the multiple sensors SN may be multiple sensors SN as shown in Fig. 7, or may be sensors SN whose sensing ranges are changeable (for example, movable sensors SN). Examples of sensors include, but are not limited to, cameras that capture images, radars, and lidars.

[0076] The sensor SN and the information processing system 1A are communicatively connected. The information processing system 1A and the information processing device 2A are also communicatively connected. The sensor SN and the information processing system 1A, and the information processing system 1A and the information processing device 2A may be communicatively connected via the above-mentioned network N, or may be communicatively connected directly.

[0077] The information processing system 1A also includes an information processing device 1_1A and an information processing device 1_2A. The information processing device 1_1A and the information processing device 1_2A are also connected to each other so as to be able to communicate with each other.

[0078] Each of the sensors SN1 and SN2 detects the position of one or more objects present in a detection range and outputs sensor data sd indicating the positions to the information processing system 1A. More specifically, the sensor SN1 outputs the sensor data sd to the information processing device 1_1A, and the sensor SN2 outputs the sensor data sd to the information processing device 1_2A.

[0079] The information processing system 1A selects sensor data SSD indicating the position of the target object TO from the sensor data sd. The information processing system 1A also generates a trajectory group lcg of the target object TO. The information processing system 1A outputs the selected sensor data SSD and trajectory group lcg to the information processing device 2A. The selected sensor data SSD and trajectory group lcg will be described later.

[0080] The information processing device 2A detects an integrated trajectory clc of the target object TO by referring to the selected sensor data SSD and the trajectory group LCg and updating the trajectory of the target object TO. In addition, the information processing device 2A predicts a predicted integrated trajectory pclc of the target object TO, which is the future trajectory of the target object TO.

[0081] Furthermore, the information processing device 2A outputs one or more predicted integrated trajectory groups pclcg of the predicted target object TO to the information processing system 1A. The information processing system 1A further refers to the predicted integrated trajectory group pclcg and selects sensor data ssd indicating the position of the target object TO. In this way, the information processing system 3A is a feedback system.

[0082] (Configuration of information processing system 1A) The configuration of the information processing system 1A will be described with reference to Fig. 8. Fig. 8 is a block diagram showing the configurations of the information processing system 1A and an information processing device 2A.

[0083] As described above, the information processing system 1A includes the information processing device 1_1A and the information processing device 1_2A that can communicate with each other. As shown in Fig. 8, the information processing device 1_1A and the information processing device 1_2A may have the same functions. Alternatively, the information processing system 1A may be realized by a single information processing device.

[0084] 8 may be provided in another information processing device 1_3A that can communicate with the information processing device 1_1A and the information processing device 1_2A. As an example, the information processing device 1_1A and the information processing device 1_2A may not include a trajectory group generation unit 14, an output unit 15, and a sensor data group generation unit 16, which will be described later, but may include them in the other information processing device 1_3A.

[0085] Alternatively, the information processing device 1_1A and the information processing device 1_2A may have different functions. As an example, the information processing device 1_1A may include a trajectory group generation unit 14, an output unit 15, and a sensor data group generation unit 16, which will be described later, and the information processing device 1_2A may not include the trajectory group generation unit 14, the output unit 15, and the sensor data group generation unit 16.

[0086] The components included in the information processing device 1_1A will be described below, but in this exemplary embodiment, the case will be described where the information processing device 1_1A and the information processing device 1_2A have the same functions.

[0087] As shown in FIG. 8, the information processing device 1_1A includes a control unit 10_1A, a storage unit 11_1A, an input / output unit 12_1A, and a communication unit 13_1A.

[0088] (Storage unit 11_1A) The storage unit 11_1A stores data referenced by the control unit 10_1A. Examples of the storage unit 11_1A include, but are not limited to, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0089] Examples of data stored in the storage unit 11_1A include, but are not limited to, a plurality of sensor data sd output from the sensor SN1 up to time t, and one or a plurality of trajectory candidates lc of the target object TO.

[0090] (I / O section 12_1A) The input / output unit 12_1A is an interface that receives input of data and outputs data. Examples of the input / output unit 12_1A include, but are not limited to, a microphone, a camera, an eye-gaze input device, a keyboard, a touchpad, a speaker, and a liquid crystal display.

[0091] (Communication section 13_1A) The communication unit 13_1A is an interface that transmits and receives data via the network N, or transmits and receives data directly to a device that can communicate with the information processing device 1_1A. Examples of the communication unit 13_1A include, but are not limited to, communication chips for various communication standards such as Ethernet (registered trademark), Wi-Fi (Wireless Fidelity, registered trademark), and wireless communication standards for mobile data communication networks, and USB-compliant connectors.

[0092] As one example, the communication unit 13_1A receives sensor data sd from the sensor SN1. As another example, the communication unit 13_1A receives a predicted integrated trajectory group plclg from the information processing device 2A. As yet another example, the communication unit 13_1A transmits the selected sensor data SSD and trajectory group lcg to the information processing device 2A.

[0093] (control unit 10_1A) The control unit 10_1A controls each component included in the information processing device 1_1A. As shown in FIG. 8 , the control unit 10_1A also includes an acquisition unit 11, a trajectory candidate generation unit 12, a selection unit 13, a trajectory group generation unit 14, an output unit 15, and a sensor data group generation unit 16. In this exemplary embodiment, the acquisition unit 11 realizes an acquisition means and an integrated trajectory group acquisition means. In this exemplary embodiment, the trajectory candidate generation unit 12, the selection unit 13, the trajectory group generation unit 14, the output unit 15, and the sensor data group generation unit 16 realize a trajectory candidate generation means, a selection means, a trajectory group generation means, an output means, and a sensor data group generation means, respectively.

[0094] (Acquisition part 11) The acquisition unit 11 acquires data via the input / output unit 12_1A or the communication unit 13_1A. The acquisition unit 11 stores the acquired data in the storage unit 11_1A. As an example, the acquisition unit 11 acquires sensor data sd. As another example, the acquisition unit 11 acquires a predicted integrated trajectory set plclg.

[0095] (Trajectory candidate generation unit 12) The trajectory candidate generation unit 12 generates one or more trajectory candidates lc for the target object TO. As an example, the trajectory candidate generation unit 12 generates one or more trajectory candidates lc for the target object TO at time t by referring to sensor data sd previously acquired from the sensor SN1 (i.e., sensor data sd up to time t-1) that indicates the position of the target object TO. The trajectory candidate generation unit 12 stores the generated one or more trajectory candidates lc in the storage unit 11_1A.

[0096] An example of a method by which the trajectory candidate generation unit 12 generates the trajectory candidate lc is a method using a tracking method in a random finite set (e.g., MHT (Multiple Hypothesis Tracking), JPDA (Joint Probabilistic Data Association), PHD (Probability Hypothesis Density), or GLMB (Generalized label multi-Bernoulli). Another example of a method by which the trajectory candidate generation unit 12 generates the trajectory candidate lc is a method using ByteTrack in addition to the above-mentioned method when the sensor data sd is a camera image.

[0097] In the information processing system 1A, a process of generating one or more trajectory candidates lc by referring to the sensor data sd is performed in both the information processing device 1_1A and the information processing device 1_2A. That is, in the information processing system 1A, a process of generating one or more trajectory candidates lc by referring to the sensor data sd is performed for each of the multiple sensors SN.

[0098] An example of the process executed by the trajectory candidate generating unit 12 will be described with reference to Fig. 9. Fig. 9 is a diagram showing an example of a trajectory candidate lc.

[0099] The trajectory candidate generating unit 12 of the information processing device 1_1A refers to the sensor data sd up to time t-1, and predicts the position (positions pp1_1 and pp1_2) of the target object TO at time t, thereby generating trajectory candidates lc1_1 and lc1_2 shown in FIG. 9.

[0100] Similarly, the trajectory candidate generating unit 12 of the information processing device 1_2A generates the trajectory candidate lc2_1 and the trajectory candidate lc1_2 shown in FIG.

[0101] 9 are trajectory candidates lc included in the predicted integrated trajectory group plclg generated by the information processing device 2 A. The trajectory candidates lc3_1 and lc3_2 will be described later.

[0102] (Selection section 13) The selection unit 13 selects sensor data ssd indicating the position of the target object TO from the sensor data sd. As an example, the selection unit 13 refers to the trajectory candidate lc of the target object TO at time t generated by the trajectory candidate generation unit 12, and selects sensor data ssd indicating the position of the target object TO from the sensor data sd acquired from the sensor SN1 at time t. The selection unit 13 stores the selected sensor data ssd in the storage unit 11_1A.

[0103] In the information processing system 1A, a process of selecting sensor data SSD indicating the position of the target object TO is performed in both the information processing device 1_1A and the information processing device 1_2A. That is, in the information processing system 1A, a process of selecting sensor data SSD indicating the position of the target object TO is performed for each of the multiple sensors SN.

[0104] An example of the process executed by the selection unit 13 will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example of the sensor data sd and the selected sensor data ssd.

[0105] 10, the sensor data sd acquired from the sensor SN1 at time t includes not only the position of the target object TO but also sensor data sd indicating the positions of other objects. Hereinafter, the sensor data sd indicating the positions of other objects will also be referred to as noise.

[0106] First, as shown in the upper part of Figure 10, the selection unit 13 compares the sensor data sd acquired from the sensor SN1 at time t with the position pp of the target object TO at time t identified by referring to the trajectory candidate lc of the target object TO at time t generated by the trajectory candidate generation unit 12.

[0107] Next, the selection unit 13 selects, from the sensor data sd, sensor data ssd in the vicinity of the position pp of the target object TO at time t, as shown in the lower side of Fig. 10. In other words, from the sensor data sd, the selection unit 13 selects one or more sensor data ssd indicating a position that is estimated to be the position of the target object TO at time t.

[0108] Here, the selection unit 13 of the information processing device 1_1A may be configured to refer only to the trajectory candidate lc1_1 and the trajectory candidate lc1_2 generated by the trajectory candidate generation unit 12 of the information processing device 1_1A. Alternatively, the selection unit 13 of the information processing device 1_1A may be configured to acquire the trajectory candidate lc2_1 and the trajectory candidate lc2_2 generated by the trajectory candidate generation unit 12 of the information processing device 1_2A, and refer to the trajectory candidate lc2_1 and the trajectory candidate lc2_2 in addition to the trajectory candidate lc1_1 and the trajectory candidate lc1_2.

[0109] For example, in the diagram shown in the upper part of Fig. 10, the selection unit 13 refers to the trajectory candidate lc1_1 and the trajectory candidate lc1_2 generated by the trajectory candidate generation unit 12 of the information processing device 1_1A, and identifies the positions pp1_1 and pp1_2 of the target object TO at the time t. Then, in the diagram shown in the lower part of Fig. 10, the selection unit 13 selects the sensor data SSD in the vicinity of each of the positions pp1_1 and pp1_2.

[0110] Alternatively, the selection unit 13 refers to the trajectory candidates lc2_1 and lc2_2 generated by the trajectory candidate generation unit 12 of the information processing device 1_2A in addition to the positions pp1_1 and pp1_2 in the diagram shown in the upper part of Fig. 10, and identifies the positions pp2_1 and pp2_2 of the target object TO at time t. Then, the selection unit 13 selects the sensor data SSD in the vicinity of each of the positions pp1_1, pp1_2, pp2_1, and pp2_2 in the diagram shown in the lower part of Fig. 10.

[0111] 10, positions pp3_1 and pp3_2 are positions specified by the trajectory candidate lc included in the predicted integrated trajectory group pclcg. The positions pp3_1 and pp3_2 will be described later.

[0112] As for the range for selecting the sensor data SSD, the selector 13 may select the sensor data SSD within a predetermined range from the position pp of the target object TO at the time t, for example.

[0113] As another example, the selection unit 13 may select the sensor data ssd indicating the position of the target object TO based on the degree of dispersion of the sensor data sd present around the position pp of the target object TO. In other words, the selection unit 13 sets a range for selecting the sensor data ssd according to the position pp of the target object TO, the number of sensor data sd present around the position pp, and the distance between the sensor data sd and the position pp.

[0114] For example, in the diagram shown in the upper part of Fig. 10, around the position pp1_1 of the target object TO at time t, there is only one piece of sensor data sd at a short distance from the position pp1_1. Therefore, the selection unit 13 narrows the range from which the sensor data ssd is selected for the position pp1_1 of the target object TO at time t. On the other hand, in the diagram shown in the upper part of Fig. 10, around the position pp2_1 of the target object TO at time t, there are four pieces of sensor data sd at a slightly shorter distance from the position pp2_1. Therefore, the selection unit 13 widens the range from which the sensor data ssd is selected for the position pp2_1 of the target object TO at time t.

[0115] With this configuration, when the reliability of the sensor data SSD indicating the position of the target object TO is low, the selector 13 can select many pieces of sensor data SSD as candidates.

[0116] As yet another example, the selection unit 13 may change the range in which the sensor data ssd is selected based on the position pp of the target object TO. For example, if the position pp is a noisy location, the selection unit 13 sets a wide range in which the sensor data ssd is selected. As yet another example, the range in which the sensor data ssd is selected may be changed depending on the sensor SN. For example, if there is a sensor SN that detects a lot of noise, the selection unit 13 sets a wide range in which the sensor data ssd is selected for the sensor data sd acquired from the sensor SN.

[0117] The selector 13 may also limit the number of sensor data SSDs to be selected. For example, the selector 13 may set an upper limit on the total number of sensor data SSDs to be selected from the sensor data SD at time t, or may set an upper limit on the total number of sensor data SSDs to be selected for each position pp identified from the trajectory candidate lc. In this configuration, the selector 13 may select up to the limited number of sensor data SSDs in order of proximity to the position pp.

[0118] (Trajectory group generation unit 14) The trajectory group generation unit 14 generates a trajectory group lcg of the target object TO. As an example, the trajectory group generation unit 14 generates the trajectory group lcg based on the correlation between the trajectory candidate lc generated by the trajectory candidate generation unit 12 of the information processing device 1_1A and the trajectory candidate lc generated by the trajectory candidate generation unit 12 of the information processing device 1_2A. The trajectory group generation unit 14 stores the generated trajectory group lcg in the storage unit 11_1A.

[0119] An example of the process in which the trajectory group generation unit 14 generates the trajectory group lcg will be described with reference to Fig. 11. Fig. 11 is a diagram showing an example of the trajectory group lcg.

[0120] 11, the trajectory group generation unit 14 compares a trajectory candidate lc1 generated by the trajectory candidate generation unit 12 of the information processing device 1_1A with a trajectory candidate lc2 generated by the trajectory candidate generation unit 12 of the information processing device 1_2A. As an example, the trajectory group generation unit 14 generates a trajectory group lcg including multiple trajectory candidates lc having high similarity between the trajectory candidate lc1 and the trajectory candidate lc2 in each of the multiple sensors SN. In other words, the trajectory group generation unit 14 determines whether the similarity (degree of agreement) between the trajectory candidate lc1 and the trajectory candidate lc2 is high.

[0121] As an example of a method by which the trajectory group generation unit 14 determines whether the similarity between trajectory candidates is high, the trajectory group generation unit 14 refers to the distance between trajectory candidates lc. For example, the trajectory group generation unit 14 determines whether the distance between any multiple points on trajectory candidate lc1 and any multiple points on trajectory candidate lc2 at the same time as each of the multiple points is shorter than a predetermined distance.

[0122] 11, the trajectory group generation unit 14 calculates the distance between a point on trajectory candidate lc1 and a point on trajectory candidate lc2 at time t-3, the distance between a point on trajectory candidate lc1 and a point on trajectory candidate lc2 at time t-2, the distance between a point on trajectory candidate lc1 and a point on trajectory candidate lc2 at time t-1, and the distance between a point on trajectory candidate lc1 and a point on trajectory candidate lc2 at time t. If each of the calculated distances is shorter than a predetermined distance, the trajectory group generation unit 14 generates a trajectory group lcg including trajectory candidate lc1 and trajectory candidate lc2.

[0123] 11, when the trajectory candidate generated by the trajectory candidate generation unit 12 of the information processing device 1_1A is trajectory candidate lc3, the distance between a point at the same time on trajectory candidate lc2 generated by the trajectory candidate generation unit 12 of the information processing device 1_2A and a point at the same time on trajectory candidate lc3 generated by the trajectory candidate generation unit 12 of the information processing device 1_1A becomes long. Therefore, the trajectory group generation unit 14 does not include trajectory candidate lc3 in the trajectory group lcg.

[0124] With this configuration, the trajectory group generation unit 14 can suitably generate a trajectory group lcg including a plurality of trajectory candidates lc that are highly correlated.

[0125] As another example, the trajectory group generation unit 14 may be configured to refer to the selected sensor data SSD in addition to the processing shown in Fig. 11. As an example, the trajectory group generation unit 14 may generate the trajectory group lcg of the target object TO based on the correlation between the selected sensor data SSD of each of the multiple sensors SN.

[0126] 11, the trajectory group generation unit 14 determines whether or not there is a high degree of similarity (degree of agreement) between the sensor data ssd at time t selected by the selection unit 13 of the information processing device 1_1A and the sensor data ssd at time t selected by the selection unit 13 of the information processing device 1_2A. As an example, the trajectory group generation unit 14 determines whether or not the distance between the sensor data ssd at time t selected by the selection unit 13 of the information processing device 1_1A and the sensor data ssd at time t selected by the selection unit 13 of the information processing device 1_2A is shorter than a predetermined distance.

[0127] When it is determined that the distance of the sensor data SSD between the trajectory candidate lc1 and the trajectory candidate lc2, which have a high similarity between the trajectory candidates, is also shorter than a predetermined distance, the trajectory group generation unit 14 generates a trajectory group lcg including the trajectory candidate lc1 and the trajectory candidate lc2. On the other hand, when it is determined that the distance of the sensor data SSD is equal to or greater than the predetermined distance, the trajectory group generation unit 14 does not generate a trajectory group lcg including the trajectory candidate lc1 and the trajectory candidate lc2.

[0128] With this configuration, the trajectory group generating unit 14 can accurately determine whether or not there is a high correlation between trajectory candidates (whether or not there is a high degree of similarity or agreement).

[0129] (Output section 15) The output unit 15 outputs data via the communication unit 13_1A or to the input / output unit 12_1A. As an example, the output unit 15 outputs the selected sensor data ssd and the trajectory group lcg to the information processing device 2A via the communication unit 13_1A.

[0130] As an example, the output unit 15 outputs the selected sensor data ssd and the trajectory candidate lc corresponding to the sensor data ssd and included in the trajectory group lcg, in association with each other. For example, in the diagram shown in FIG. 10, if the trajectory group lcg includes trajectory candidate lc1_1 and trajectory candidate lc2_1, the output unit 15 associates the sensor data ssd of the trajectory candidate lc1_1 around the position pp1_1 at time t with the sensor data ssd of the trajectory candidate lc2_1 around the position pp2_1 at time t, and outputs the sensor data ssd and the trajectory group lcg to the information processing device 2A. With this configuration, the output unit 15 can easily detect the integrated trajectory clc in the information processing device 2A, which will be described later.

[0131] As another example, the output unit 15 outputs the trajectory group lcg and a sensor data group ssdg generated by the sensor data group generation unit 16 (described later) to the information processing device 2A.

[0132] (Sensor data group generator 16) The sensor data group generation unit 16 generates the sensor data group ssdg. As an example, the sensor data group generation unit 16 generates the sensor data group ssdg based on the correlation between the sensor data ssd selected by the selection unit 13 for each of the multiple sensors SN. Furthermore, as described above, the sensor data group ssdg generated by the sensor data group generation unit 16 is output by the output unit 15 together with the trajectory group lcg.

[0133] For example, consider sensor data ssd1 selected from sensor data sd acquired from sensor SN1 at time t, and sensor data ssd2 selected from sensor data sd acquired from sensor SN2 at time t.

[0134] In this case, the sensor data group generation unit 16 calculates the correlation between the sensor data ssd1 and the sensor data ssd2. As an example, the sensor data group generation unit 16 calculates the distance between the position indicated by the sensor data ssd1 and the position indicated by the sensor data ssd2. If the distance is shorter than a predetermined distance, the sensor data group generation unit 16 generates a sensor data group ssdg including the sensor data ssd1 and the sensor data ssd2. On the other hand, if the distance is equal to or greater than the predetermined distance, the sensor data group generation unit 16 does not generate a sensor data group ssdg including the sensor data ssd1 and the sensor data ssd2.

[0135] With this configuration, the sensor data group generator 16 generates the sensor data group ssdg including the sensor data SSD having a high correlation, and therefore, the information processing device 2A can easily detect the integrated trajectory clc.

[0136] (Configuration of information processing device 2A) The configuration of the information processing device 2A will be described again with reference to Fig. 8. The information processing device 2A includes a control unit 20, a storage unit 25, an input / output unit 26, and a communication unit 27, as shown in Fig. 8.

[0137] (Storage unit 25) The storage unit 25 stores data referenced by the control unit 20. Examples of the storage unit 25 include, but are not limited to, a flash memory, an HDD, an SSD, or a combination thereof.

[0138] Examples of data stored in the memory unit 25 include, but are not limited to, selected sensor data ssd, a trajectory group lcg, an updated integrated trajectory clc, and a predicted integrated trajectory pclc of the predicted target object TO.

[0139] (Input / output section 26) The input / output unit 26 is an interface that receives input of data and outputs data. Examples of the input / output unit 26 include, but are not limited to, a microphone, a camera, an eye-gaze input device, a keyboard, a touchpad, a speaker, and a liquid crystal display.

[0140] (Communications Department 27) The communication unit 27 is an interface that transmits and receives data via the network N, or transmits and receives data directly to and from a device that can communicate with the information processing device 2A. Examples of the communication unit 27 include, but are not limited to, communication chips for various communication standards such as Ethernet, Wi-Fi, and wireless communication standards for mobile data communication networks, and USB-compliant connectors.

[0141] As one example, the communication unit 27 receives selected sensor data SSD and a trajectory group LCg from the information processing system 1A. As another example, the communication unit 27 receives a sensor data group SSDG and a trajectory group LCg from the information processing system 1A. As yet another example, the communication unit 27 transmits a predicted integrated trajectory group PLCLG, which will be described later, to the information processing system 1A.

[0142] (control unit 20) The control unit 20 controls each component included in the information processing device 2A. As shown in Fig. 8, the control unit 20 also includes an acquisition unit 21, an update unit 22, a prediction unit 23, and an output unit 24. In this exemplary embodiment, the acquisition unit 21, the update unit 22, the prediction unit 23, and the output unit 24 respectively realize an acquisition means, an update means, a prediction means, and an output means.

[0143] (Acquisition part 21) The acquisition unit 21 acquires data via the input / output unit 26 or the communication unit 27. The acquisition unit 21 stores the acquired data in the storage unit 25. As one example, the acquisition unit 21 acquires selected sensor data SSD and trajectory group LCG. As another example, the acquisition unit 21 acquires a sensor data group SSDG and a trajectory group LCG.

[0144] (Updated part 22) The update unit 22 updates the trajectory of the target object TO. As an example, the update unit 22 updates the trajectory of the target object TO by referring to the sensor data ssd (or the sensor data group ssdg) and the trajectory group lcg acquired by the acquisition unit 21. The trajectory updated by the update unit 22 is also referred to as an integrated trajectory clc. The process executed by the update unit 22 corresponds to an update step in a Kalman filter.

[0145] As one example, the update unit 22 updates the integrated trajectory clc at time t-1 to the integrated trajectory clc at time t by referring to the position indicated by the sensor data SSD at time t and the trajectory candidate lc included in the trajectory group lcg at time t associated with the sensor data SSD. As another example, the update unit 22 updates the integrated trajectory clc at time t-1 to the integrated trajectory clc at time t by referring to the sensor data group SSDg and the trajectory group lcg.

[0146] Here, even if the sensor data SSD referenced by the update unit 22 contains noise or the trajectory group lcg contains an incorrect trajectory candidate lc, the sensor data SSD referenced by the update unit 22 also contains sensor data other than noise, and the trajectory group lcg also contains the correct trajectory candidate lc, so the update unit 22 can generate a highly accurate integrated trajectory clc.

[0147] Furthermore, when there are multiple integrated trajectories clc at time t-1, the update unit 22 updates each of the multiple integrated trajectories clc to an integrated trajectory clc at time t. In other words, the update unit 22 updates each of one or multiple integrated trajectories clc at time t-1 to one or multiple integrated trajectories clc at time t.

[0148] (Prediction Section 23) The prediction unit 23 predicts one or more integrated trajectories clc of the target object TO at time t+1. As an example, the prediction unit 23 predicts one or more integrated trajectories clc of the target object TO at time t+1 with reference to one or more integrated trajectories clc at time t updated by the update unit 22. The predicted integrated trajectory clc at time t+1 is also referred to as a predicted integrated trajectory pclc at time t+1.

[0149] As an example, the prediction unit 23 receives the trajectory at time t as input and predicts one or more predicted integrated trajectories pclc of the target object TO at time t+1 using a prediction model that predicts the trajectory at time t+1.

[0150] As an example, the prediction unit 23 predicts one or more predicted integrated trajectories pclc of the target object TO at time t+1 using a prediction model that predicts a trajectory at time t+1 when the movement of the target object TO is uniform linear motion or uniform acceleration motion. In this case, the prediction model may be a model that takes air resistance into account (a model in which parameters for air resistance are set).

[0151] As another example, the prediction unit 23 predicts one or more predicted integrated trajectories pclc of the target object TO at time t+1 using a prediction model generated by machine learning.

[0152] An example of the process executed by the prediction unit 23 will be described with reference to Fig. 12. Fig. 12 is a diagram showing an example of a predicted integrated trajectory pclc.

[0153] The prediction unit 23 refers to the integrated trajectory clc1 up to time t, and predicts one or more predicted integrated trajectories pclc. For example, as shown in Fig. 12 , the prediction unit 23 refers to the integrated trajectory clc1 up to time t, and predicts one or more predicted integrated trajectories pclc1_1 of the target object TO at time t+1, using a prediction model that predicts a trajectory at time t+1 when the movement of the target object TO is uniform linear motion or uniform acceleration motion.

[0154] In addition, as shown in Figure 12, the prediction unit 23 changes the parameter settings of the prediction model that predicted pclc1 (for example, changes the air resistance parameters), and uses the changed prediction model to predict one or more predicted integrated trajectories pclc1_2 of the target object TO at time t+1.

[0155] Furthermore, the prediction unit 23 predicts one or more predicted integrated trajectories pclc1_3 of the target object TO at time t+1 using a prediction model generated by machine learning.

[0156] Similarly, the prediction unit 23 predicts one or more predicted integrated trajectories pclc2 of the target object TO at time t+1 based on the integrated trajectory clc2 up to time t.

[0157] (output unit 24) The output unit 24 outputs data via the communication unit 27 or to the input / output unit 26. As one example, the output unit 24 outputs a predicted integrated trajectory group pclcg including one or more predicted integrated trajectories pclc predicted by the prediction unit 23 to the information processing system 1A. As another example, the output unit 24 outputs an image including the integrated trajectory clc updated by the update unit 22 and one or more predicted integrated trajectories pclc predicted by the prediction unit 23 to the input / output unit 26.

[0158] (Processing executed in information processing system 3A) The flow of processing (S3A) executed in the information processing system 3A will be described with reference to Fig. 13. Fig. 13 is a sequence diagram showing the flow of processing executed in the information processing system 3A.

[0159] (Step S31) In step S31, the acquisition unit 11 of the information processing system 1A acquires sensor data sd at time t. The acquisition unit 11 stores the acquired sensor data sd in the storage unit 11_1A.

[0160] (Step S32) In step S32, the trajectory candidate generation unit 12 generates one or more trajectory candidates lc related to the target object TO at time t by referring to the sensor data sd up to time t-1, which indicates the position of the target object TO. The trajectory candidate generation unit 12 stores the generated one or more trajectory candidates lc in the storage unit 11_1A.

[0161] (Step S33) In step S33, the selection unit 13 refers to the trajectory candidate lc of the target object TO generated by the trajectory candidate generation unit 12, and selects sensor data ssd indicating the position of the target object TO from the sensor data sd acquired from the sensor SN1 at time t. The selection unit 13 stores the selected sensor data ssd in the storage unit 11_1A.

[0162] (Step S34) In step S34, the trajectory group generation unit 14 generates a trajectory group lcg based on the correlation between the trajectory candidates lc in each of the multiple sensors SN. The trajectory group generation unit 14 stores the generated trajectory group lcg in the storage unit 11_1A.

[0163] (Step S35) In step S35, the output unit 15 associates the selected sensor data ssd with the trajectory candidate lc that corresponds to the sensor data ssd and is included in the trajectory group lcg, and outputs the associated data to the information processing device 2A. Alternatively, the output unit 15 outputs the trajectory group lcg and the sensor data group ssdg generated by the sensor data group generation unit 16 to the information processing device 2A.

[0164] (Step S36) The acquisition unit 21 of the information processing device 2A acquires the selected sensor data SSD and trajectory group LCg. Alternatively, the acquisition unit 21 acquires the sensor data group SSDG and trajectory group LCg. The acquisition unit 21 stores the acquired sensor data SSD or sensor data group SSDG and trajectory group LCg in the storage unit 25.

[0165] (Step S37) The update unit 22 updates the trajectory of the target object TO by referring to the sensor data ssd (or the sensor data group ssdg) and the trajectory group lcg acquired by the acquisition unit 21, and generates one or more integrated trajectories clc at the time t. The update unit 22 stores the generated one or more integrated trajectories clc in the storage unit 25.

[0166] (Step S38) In step S38, the prediction unit 23 predicts one or more integrated trajectories clc of the target object TO at time t+1 by referring to one or more integrated trajectories clc at time t updated by the update unit 22, and generates a predicted integrated trajectory pclc. The prediction unit 23 stores the generated predicted integrated trajectory pclc in the storage unit 25.

[0167] (Step S39) In step S39, the output unit 24 outputs a predicted integrated trajectory group pclcg including one or more predicted integrated trajectories pclc predicted by the prediction unit 23 to the information processing system 1A.

[0168] (Step S40) In step S40, the acquisition unit 11 in the information processing system 1A acquires a predicted integrated trajectory group plclg. In other words, the acquisition unit 11 acquires a predicted integrated trajectory group including a predicted integrated trajectory pclc (a predicted integrated trajectory pclc at time t+1) which is one or more trajectories of the target object TO predicted with reference to the sensor data ssd and the trajectory group lcg (the sensor data ssd and the trajectory group lcg at time t) previously output by the output unit 15. The acquisition unit 11 stores the acquired predicted integrated trajectory group plclg in the storage unit 11_1A.

[0169] (Processing after step S40) After step S40 is executed, the information processing system 1A executes the processes from step S31 onwards again.

[0170] In step S31, the acquisition unit 11 acquires the sensor data sd at time t+1.

[0171] In step S32, the trajectory candidate generation unit 12 includes one or more predicted integrated trajectories pclc at time t+1 included in the predicted integrated trajectory group plclg in one or more trajectory candidates lc related to the target object TO at time t+1. For example, as shown in Fig. 9 , the trajectory candidate generation unit 12 sets the predicted integrated trajectory pclc1 and the predicted integrated trajectory pclc1 included in the predicted integrated trajectory group plclg as trajectory candidates lc3_1 and lc3_2.

[0172] In step S33, the selection unit 13 further refers to the predicted integrated trajectory pclc and selects sensor data ssd indicating the position of the target object TO from the sensor data sd acquired from the sensor SN1 at time t+1. For example, as shown in Fig. 10, the selection unit 13 refers to trajectory candidates lc3_1 and lc3_2 and identifies positions pp3_1 and pp3_2. The selection unit 13 also selects sensor data ssd in the vicinity of each of positions pp3_1 and pp3_2.

[0173] Next, in step S34, the trajectory group generation unit 14 generates a trajectory group lcg based on the correlation between the trajectory candidates lc including the trajectory candidate lc3_1 and the trajectory candidate lc3_2. Steps S35 and S36 are as described above.

[0174] Subsequently, in step S37, the update unit 22 generates an integrated trajectory clc by referring to the sensor data ssd and the trajectory group lcg. Then, in step S37, the prediction unit 23 generates a predicted integrated trajectory pclc at time t+2 by referring to the generated integrated trajectory clc.

[0175] That is, in the information processing system 3A, a predicted integrated trajectory pclc at time t+1 is generated with reference to the trajectory candidate lc at time t. Then, in addition to the trajectory candidate lc generated with reference to the sensor data sd at time t+1, a predicted integrated trajectory pclc at time t+2 is generated with reference to the predicted integrated trajectory pclc at time t+1.

[0176] In this way, in the information processing system 3A, the highly accurate predicted integrated trajectory pclc generated with reference to the highly accurate integrated trajectory clc is fed back to the information processing system 1A, thereby enabling the selection of sensor data SSD with higher accuracy and the generation of a trajectory group lcg with higher accuracy. Furthermore, the integrated trajectory clc is generated with reference to the highly accurate sensor data SSD and the trajectory group lcg. Therefore, the information processing system 3A can track the target object TO with high accuracy.

[0177] (Effects of Information Processing System 3A) In the information processing system 3A, the information processing system 1A outputs the selected sensor data SSD and a trajectory group lcg including the correlation-based trajectory candidate lc from among the one or more generated trajectory candidates lc to the information processing device 2A. The information processing device 2A generates one or more integrated trajectories CLc by referring to the selected sensor data SSD and the trajectory group LCg.

[0178] In this way, in the information processing system 3A, the information processing device 2A generates one or more integrated trajectories clc by referring to both the sensor data SSD and the trajectory group lcg, so even if the sensor data SSD contains noise or the trajectory group lcg contains an incorrect trajectory candidate lc, it can be corrected. As a result, the information processing system 3A can track a target object with high accuracy.

[0179] Furthermore, the information processing system 3A does not output all of the sensor data sd and all of the trajectory candidates lc to the information processing device 2A, but outputs selected sensor data ssd and a trajectory group lcg including a trajectory candidate lc based on correlation among the one or more generated trajectory candidates lc to the information processing device 2A. Therefore, the information processing system 3A can perform low-load target object tracking processing because the amount of data referenced to generate the integrated trajectory clc is small.

[0180] (Variation) In the information processing system 3A, the information processing system 1A may not include the trajectory group generator 14.

[0181] In this case, the output unit 15 outputs the sensor data ssd selected by the selection unit 13 to the information processing device 2A. When the acquisition unit 21 of the information processing device 2A acquires the sensor data ssd output from the information processing system 1A, the update unit 22 refers to the sensor data ssd to update the trajectory of the target object TO and generate one or more integrated trajectories clc at time t.

[0182] Furthermore, as described above, the prediction unit 23 of the information processing device 2A may refer to one or more integrated trajectories clc at time t and predict one or more integrated trajectories clc of the target object TO at time t+1, and the output unit 24 may output a predicted integrated trajectory group pclcg including one or more predicted integrated trajectories pclc to the information processing system 1A.

[0183] With this configuration, the information processing system 3A generates one or more integrated trajectories clc by referring to the selected sensor data SSD, and therefore, can track a target object with a lower load and higher accuracy.

[0184] [Software implementation example] Some or all of the functions of the information processing systems 1, 1A, 3, 3A and information processing devices 2, 2A (hereinafter also referred to as "the above systems and devices") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0185] In the latter case, each of the above systems and devices is realized, for example, by a computer that executes instructions from a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 14. Figure 14 is a block diagram showing the hardware configuration of computer C that functions as each of the above systems and devices.

[0186] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to function as each of the above systems and devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above systems and devices.

[0187] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0188] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0189] The program P can also be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communications network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0190] [Additional Notes] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0191] (Appendix 1) acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output means for outputting the selected sensor data and the group of trajectories; An information processing system comprising:

[0192] (Appendix 2) further comprising an integrated trajectory group acquisition means for acquiring a predicted integrated trajectory group, which is one or more trajectories of the target object predicted with reference to the sensor data and the trajectory group previously output by the output means; The selection means further refers to one or more trajectories included in the group of predicted integrated trajectories, and selects sensor data indicating the position of the target object. 10. The information processing system of claim 1.

[0193] (Appendix 3) the output means outputs the selected sensor data in association with a trajectory candidate corresponding to the sensor data and included in the trajectory group. 3. The information processing system according to claim 1 or 2.

[0194] (Appendix 4) further comprising a sensor data group generating means for generating a sensor data group based on the correlation between the sensor data selected by the selecting means for each of the plurality of sensors; The output means outputs the group of trajectories and the group of sensor data. 3. The information processing system according to claim 1 or 2.

[0195] (Appendix 5) The selection means selects sensor data indicating the position of the target object based on a degree of dispersion of sensor data present around the position of the target object indicated by the trajectory candidate of the target object. 5. An information processing system according to any one of appendices 1 to 4.

[0196] (Appendix 6) The trajectory group generating means generates the trajectory group including a plurality of trajectory candidates having a high degree of similarity between the trajectory candidates for each of the plurality of sensors. 6. An information processing system according to any one of appendices 1 to 5.

[0197] (Appendix 7) sensor data selected as sensor data indicating the position of the target object from a plurality of sensor data acquired from a plurality of sensors that detect the position of the target object; and For each of the plurality of sensors, one or more trajectory candidates for the target object are generated with reference to sensor data previously acquired from the sensor, the sensor data indicating the position of the target object. Among these, a group of trajectories of the target object is generated based on the correlation between the trajectory candidates. and an acquisition means for acquiring the an updating means for updating the trajectory of the target object by referring to the selected sensor data and the group of trajectories of the target object; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; an output means for outputting a group of predicted integrated trajectories, which are one or more trajectories predicted by the prediction means, to the device for selecting the sensor data and the device for generating a group of trajectories of the target object; An information processing device comprising:

[0198] (Appendix 8) acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an updating means for updating the trajectory of the target object by referring to the selected sensor data and the trajectory group; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing system comprising:

[0199] (Appendix 9) At least one processor an acquisition process for acquiring a plurality of sensor data from a plurality of sensors that detect the position of the target object; For each of the plurality of sensors, a trajectory candidate generation process for generating one or more trajectory candidates related to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection process of selecting sensor data indicating the position of the target object from the sensor data acquired from the sensor by referring to the trajectory candidates of the target object; a trajectory group generation process for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output process for outputting the selected sensor data and the trajectory group; An information processing method including:

[0200] (Appendix 10) Computer, acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output means for outputting the selected sensor data and the group of trajectories; An information processing program that functions as a

[0201] (Appendix 11) The trajectory generation means generates a group of trajectories of the target object based on correlations between the selected sensor data from each of the plurality of sensors. 7. The information processing system according to claim 6.

[0202] (Appendix 12) The target object is at least one of an object moving in the air, an object and a person moving on the ground, and an object moving on water. An information processing device according to any one of appendices 1 to 6 and 7.

[0203] (Appendix 13) At least one processor sensor data selected as sensor data indicating the position of the target object from a plurality of sensor data acquired from a plurality of sensors that detect the position of the target object; and For each of the plurality of sensors, one or more trajectory candidates for the target object are generated with reference to sensor data previously acquired from the sensor, the sensor data indicating the position of the target object. Among these, a group of trajectories of the target object is generated based on the correlation between the trajectory candidates. an acquisition process to acquire the an update process of updating the trajectory of the target object by referring to the selected sensor data and the trajectory group of the target object; a prediction process for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing method including:

[0204] (Appendix 14) At least one processor an acquisition process for acquiring a plurality of sensor data from a plurality of sensors that detect the position of the target object; For each of the plurality of sensors, a trajectory candidate generation process for generating one or more trajectory candidates related to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection process of selecting sensor data indicating the position of the target object from the sensor data acquired from the sensor by referring to the trajectory candidates of the target object; a trajectory group generation process for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an update process for updating the trajectory of the target object by referring to the selected sensor data and the trajectory group; a prediction process for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing method including:

[0205] (Appendix 15) Computer, sensor data selected as sensor data indicating the position of the target object from a plurality of sensor data acquired from a plurality of sensors that detect the position of the target object; and For each of the plurality of sensors, one or more trajectory candidates for the target object are generated with reference to sensor data previously acquired from the sensor, the sensor data indicating the position of the target object. Among these, a group of trajectories of the target object is generated based on the correlation between the trajectory candidates. and an acquisition means for acquiring the an updating means for updating the trajectory of the target object by referring to the selected sensor data and the group of trajectories of the target object; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing program that functions as a

[0206] (Appendix 16) Computer, acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an updating means for updating the trajectory of the target object by referring to the selected sensor data and the trajectory group; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing program that functions as a

[0207] (Appendix 17) acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; an output means for outputting the selected sensor data; An information processing system comprising:

[0208] (Appendix 18) At least one processor an acquisition process for acquiring a plurality of sensor data from a plurality of sensors that detect the position of the target object; For each of the plurality of sensors, a trajectory candidate generation process for generating one or more trajectory candidates related to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection process of selecting sensor data indicating the position of the target object from the sensor data acquired from the sensor by referring to the trajectory candidates of the target object; an output process for outputting the selected sensor data; Information processing method including.

[0209] (Appendix 19) Computer, acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; an output means for outputting the selected sensor data; An information processing program that functions as a [Explanation of symbols]

[0210] 1, 1A, 3, 3A Information Processing System 1_1A, 1_2A, 1_3A, 2, 2A Information processing equipment 10_1A, 20 Control unit 11, 21 Acquisition Department 11_1A, 25 storage section 12 Trajectory candidate generator 12_1A, 26 input / output section 13 Selection section 13_1A, 27 Communications Department 14 Trajectory group generator 15, 24 Output section 16 Sensor data group generation unit 22 Update section 23 Prediction Department SN sensor clc integration trajectory lc trajectory candidate lcg trajectory group PCLC predictive integrated trajectory pclcg Predicted Integrated Trajectory Group sd, ssd sensor data ssdg sensor data set pp position

Claims

1. acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output means for outputting the selected sensor data and the group of trajectories; An information processing system comprising:

2. further comprising an integrated trajectory group acquisition means for acquiring a predicted integrated trajectory group, which is one or more trajectories of the target object predicted with reference to the sensor data and the trajectory group previously output by the output means; The selection means further refers to one or more trajectories included in the group of predicted integrated trajectories, and selects sensor data indicating the position of the target object. The information processing system according to claim 1 .

3. the output means outputs the selected sensor data in association with a trajectory candidate corresponding to the sensor data and included in the trajectory group.

3. The information processing system according to claim 1.

4. further comprising a sensor data group generating means for generating a sensor data group based on the correlation between the sensor data selected by the selecting means for each of the plurality of sensors; The output means outputs the group of trajectories and the group of sensor data.

3. The information processing system according to claim 1.

5. The selection means selects sensor data indicating the position of the target object based on a degree of dispersion of sensor data present around the position of the target object indicated by the trajectory candidate of the target object.

3. The information processing system according to claim 1.

6. The trajectory group generating means generates the trajectory group including a plurality of trajectory candidates having a high degree of similarity between the trajectory candidates for each of the plurality of sensors.

3. The information processing system according to claim 1.

7. sensor data selected as sensor data indicating the position of the target object from a plurality of sensor data acquired from a plurality of sensors that detect the position of the target object; and For each of the plurality of sensors, a group of trajectories of the target object generated based on correlations between the trajectory candidates among one or more trajectory candidates for the target object generated with reference to sensor data previously acquired from the sensor and indicating the position of the target object. and an acquisition means for acquiring the an updating means for updating the trajectory of the target object by referring to the selected sensor data and the group of trajectories of the target object; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; an output means for outputting a group of predicted integrated trajectories, which are one or more trajectories predicted by the prediction means, to the device for selecting the sensor data and the device for generating a group of trajectories of the target object; An information processing device comprising:

8. acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an updating means for updating the trajectory of the target object by referring to the selected sensor data and the trajectory group; a prediction means for predicting one or more future trajectories of the target object by referring to the updated trajectory; An information processing system comprising:

9. At least one processor an acquisition process for acquiring a plurality of sensor data from a plurality of sensors that detect the position of the target object; For each of the plurality of sensors, a trajectory candidate generation process for generating one or more trajectory candidates related to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection process of selecting sensor data indicating the position of the target object from the sensor data acquired from the sensor by referring to the trajectory candidates of the target object; a trajectory group generation process for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output process for outputting the selected sensor data and the trajectory group; An information processing method including:

10. Computer, acquiring means for acquiring a plurality of sensor data from a plurality of sensors for detecting the position of a target object; For each of the plurality of sensors, a trajectory candidate generating means for generating one or more trajectory candidates relating to the target object by referring to sensor data previously acquired from the sensor and indicating the position of the target object; a selection means for selecting sensor data indicating the position of the target object from among the sensor data acquired from the sensor, by referring to the trajectory candidates of the target object; a trajectory group generating means for generating a trajectory group of the target object based on the correlation between the trajectory candidates in each of the plurality of sensors; an output means for outputting the selected sensor data and the group of trajectories; An information processing program that functions as a

Images