Entry estimation system, entry estimation method, and control device

Abstract

This entry estimation system comprises: a detection unit for detecting a user within a second area that the user passes through before entering a predetermined first area; and a control device that continuously acquires the results of detecting the user in the second area from the detection unit, and estimates whether or not the detected user enters the first area on the basis of the acquired detection results.

Description

Approach estimation system, approach estimation method and control device

[0001] This application claims priority to Japanese Patent Application No. 2023-201094, filed November 28, 2023, and incorporates by reference all of the contents of that application.

[0002] Patent Document 1 discloses a technology for identifying people waiting to cross the crosswalk by analyzing the line of sight of people in the waiting area where the crosswalk traffic light is turned on, and controlling the traffic light associated with the crosswalk.

[0003] Japanese Patent Application Laid-Open No. 2017-208141

[0004] An entry estimation system according to one embodiment of the present disclosure includes a detection unit that is configured to detect a second area through which a user passes before entering a specified first area and that detects a user in the second area, and a control device that continuously acquires detection results of the user in the second area from the detection unit and estimates whether the detected user will enter the first area based on the acquired detection results.

[0005] FIG. 1 is a configuration diagram of an entry estimation system according to this embodiment. FIG. 2 is a diagram illustrating the detection range of a camera. FIG. 3 is a block diagram illustrating an example of the hardware configuration of an estimation device. FIG. 4 is a functional block diagram of the estimation device. FIG. 5 is a diagram illustrating entry estimation according to a user's trajectory. FIG. 6 is a flowchart illustrating entry estimation processing. FIG. 7 is a diagram illustrating entry estimation according to a comparative example.

[0006] [Problem to be Solved by the Present Disclosure] There is a demand for more accurate estimation of whether or not a user is entering a predetermined destination area such as a crosswalk.

[0007] Effect of the Present Disclosure According to the present disclosure, it is possible to estimate with higher accuracy whether a user is entering a predetermined destination area.

[0008] [Description of Embodiments of the Present Disclosure] First, the contents of the embodiments of the present disclosure will be listed and described.

[0009] [1] An entry estimation system according to one embodiment is provided for detecting a second area through which a user passes before entering a predetermined first area, and includes a detection unit that detects a user in the second area, and a control device that continuously acquires detection results of the user in the second area from the detection unit and estimates whether the detected user will enter the first area based on the acquired detection results.

[0010] In the entry estimation system described in [1] above, a detection unit provided for detecting a user in a second area through which the user passes before entering the first area detects the user passing through the second area, and based on the detection result, it is estimated whether the detected user will enter the first area. In this way, by using the detection result from the detection unit provided for detecting the user in the second area, it is possible to accurately obtain the user's status (position, orientation, etc.) in the second area, and ultimately to accurately estimate whether the user will enter the first area. For example, if a user is detected using a configuration that detects a wide area including the first area rather than a configuration that detects users in the second area, it may be impossible to properly detect the user's status (position, orientation, etc.) in the second area due to overlapping of multiple users, weather, etc. In this regard, by detecting the user in the second area using a detection unit provided for detecting users in the second area, it is possible to reduce the effects of overlapping of multiple users, weather, etc., and accurately obtain the user's status (position, orientation, etc.) in the second area. As described above, the entry estimation system of this embodiment can acquire the user's status (position, orientation, etc.) in the second area with high accuracy, and based on the acquired results, can estimate with high accuracy whether the user is entering the first area, which is the destination area.

[0011] [2] In the approach estimation system described in [1] above, the detection unit may be provided on a road that includes the second area but does not include the first area. By providing the detection unit in this manner, it is possible to prevent an object that is not a detection target (e.g., a vehicle traveling on a road that includes the first area) from being present between the detection unit and the second area, thereby improving the detection accuracy of the user in the second area.

[0012] [3] In the entry estimation system described in [2] above, the detection unit may be provided directly above the second area, and the detection range may be set to a downward direction as viewed from the detection unit, thereby detecting the user in the second area. By providing the detection unit in this manner, it is possible to detect the subtleties of the user's trajectory more precisely than when the detection unit is provided on the sidewalk on the opposite side of the second area, for example.

[0013] [4] In the entry estimation system described in any one of [1] to [3] above, the control device may derive a trajectory related to the movement of the detected user from multiple detection results, and if the direction of the trajectory is oriented toward the first area, estimate that the detected user will enter the first area. In this way, by estimating that the user will enter the first area if the trajectory related to the user's movement is oriented toward the first area, it is possible to estimate with high accuracy whether the user is entering the first area.

[0014] [5] In the entry estimation system described in any one of [1] to [4] above, the control device may derive a trajectory related to the movement of the detected user from multiple detection results, and if the direction of the trajectory is not facing the first area, estimate that the detected user will not enter the first area. In this way, by estimating that the user will not enter the first area if the trajectory related to the user's movement is not facing the first area, it is possible to estimate with high accuracy whether the user will enter the first area.

[0015] [6] In the approach estimation system described in any one of [1] to [5] above, the first area may be an area including a pedestrian crossing, and the second area may be a waiting area on a sidewalk adjacent to the pedestrian crossing. With this configuration, it is possible to estimate with high accuracy whether a user on the sidewalk adjacent to the pedestrian crossing is a user entering the pedestrian crossing.

[0016] [7] In the entry estimation system according to any one of [1] to [6] above, the first area and the second area may be adjacent to each other. With this configuration, it is possible to estimate whether a user is entering the first area based on a detection result in an area (second area) through which the user passes immediately before entering the first area. By using the detection result in an area close to the first area, it is possible to more accurately estimate whether the user is entering the first area.

[0017] [8] An entry estimation method according to one embodiment is an entry estimation method executed by an entry estimation system, and includes the steps of: detecting a user in a second area using a detection unit provided for detecting a second area through which the user passes before entering a specified first area; and estimating whether the detected user will enter the first area based on the user detection results continuously obtained.

[0018] [9] In one embodiment, a control device is provided for detecting a second area through which a user passes before entering a predetermined first area, and continuously acquires detection results of the user in the second area from a detection unit that detects the user in the second area, and estimates whether the detected user will enter the first area based on the acquired detection results.

[0019] [Details of the embodiments of the present disclosure] Specific examples of the embodiments of the present disclosure will be described below with reference to the drawings. The present invention is not limited to these examples, but is defined by the claims, and is intended to include all modifications within the meaning and scope equivalent to the claims. In the description of the drawings, the same elements are given the same reference numerals, and duplicate explanations will be omitted.

[0020] 1 is a configuration diagram of an approach estimation system 1 according to this embodiment. First, an overview of the approach estimation system 1 will be described.

[0021] The entry estimation system 1 is a system that estimates whether a user will enter a first area, which is a predetermined destination area, based on the user detection result by the camera 20. More specifically, the entry estimation system 1 estimates whether a user will enter a first area based on the user detection result in a second area through which the user passes before entering the first area. In this embodiment, an area including a crosswalk E1 is exemplified as an example of the first area. Furthermore, a waiting area E2 on a sidewalk adjacent to the crosswalk E1 is exemplified as an example of the second area. That is, in this embodiment, the first area and the second area are adjacent to each other. The waiting area E2 is an area through which a user Y who is entering the crosswalk E1 passes just before entering the crosswalk E1, and is an area where the user Y who plans to enter the crosswalk E1 waits while a vehicle is passing over the crosswalk E1. For example, the user Y enters the crosswalk E1 after waiting for a traffic light in the waiting area E2, crosses the crosswalk E1, and reaches the sidewalk E3 on the opposite bank. Examples of user Y include not only people walking, but also people traveling by vehicle (bicycle, wheelchair, kick scooter, stroller, etc.). Examples of user Y also include people using smartphones while walking (smartphone zombies), people carrying white canes, etc. User Y may also include moving objects other than people (animals, robots, etc.).

[0022] As shown in FIG. 1, the intrusion estimation system 1 includes a camera 20 (detection unit) and an estimation device 10 (control device).

[0023] The camera 20 is provided for detection in the waiting area E2 and serves as a detection unit for detecting users passing through the waiting area E2. The camera 20 is provided on a sidewalk that includes the waiting area E2 but does not include the crosswalk E1. Specifically, the camera 20 is provided on a pole 50 provided on the sidewalk that includes the waiting area E2. The pole 50 may be, for example, a traffic signal pole, a sign pole, or a lighting pole. The pole 50 has a vertical extension portion 51 and a support portion 52. The vertical extension portion 51 extends vertically. The height h of the vertical extension portion 51 is set to be equal to or greater than the height of traffic signal poles in Japan and other countries, including the United States, and may be set to 3 m or more. The support portion 52 extends horizontally from the upper end of the vertical extension portion 51 and supports the camera 20. The support portion 52 may also support a support object other than the camera 20 (e.g., a traffic signal, a sign, etc.). The camera 20 is provided on the underside of the support portion 52, and its detection range is downward.

[0024] The camera 20 is installed, for example, directly above the waiting area E2, and detects the user Y in the waiting area E2 by setting the detection range to the downward direction as viewed from the camera 20. Directly above the waiting area E2 means vertically above a portion of the waiting area E2. Note that the camera 20 does not necessarily have to be installed directly above the waiting area E2, and may be installed diagonally above the waiting area E2 as long as it is in a position where the entire waiting area E2 can be detected.

[0025] The waiting area E2 may be set, for example, as a square (square in plan view) measuring several meters by several meters, e.g., 4 m by 4 m. In the example shown in FIG. 1 , the waiting area E2 is set 2 m from the entrance to the crosswalk E1. This is because the waiting area E2 is set a short distance from the entrance to the crosswalk E1 to enable the alternative processing of push-button signals (described in detail later). Even when the waiting area E2 is set only approximately 2 m from the entrance to the crosswalk E1, the waiting area E2 is considered to be an "area adjacent to the crosswalk E1" and an "area through which a user entering the crosswalk E1 passes immediately before entering the crosswalk E1." The waiting area E2 may be set to be continuous with the entrance to the crosswalk E1. In other words, the boundary between the crosswalk E1 and the waiting area E2 may simply be a line. In this case, a user entering the crosswalk E1 means that the user passes over the boundary line. Furthermore, the waiting area E2 does not necessarily have to be square, as long as it is within the detection range of the camera 20, but may be rectangular, circular, or any other shape that is set arbitrarily.

[0026] The horizontal and vertical angles of the camera 20 need only be set so that the entire waiting area E2 can be detected, and for example, the horizontal and vertical angles may be set to about ±20° as shown in Fig. 2. Note that the waiting area E2 may be the entire detection range of the camera 20, or may be a part of it.

[0027] The camera 20 continuously captures images of the waiting area E2 and continuously transmits the captured images (detection results) to the estimation device 10. The camera 20 transmits the captured images (detection results) to the estimation device 10 via a base station (not shown) or by direct wireless or wired communication without using a base station.

[0028] In this embodiment, the camera 20 is used as an example of the detection unit, but the detection unit may be configured as anything other than the camera 20 as long as it can detect the user. Specifically, the detection unit may be a detection mechanism such as a laser or a lidar.

[0029] The estimation device 10 is composed of one or more control computers. FIG. 3 is a block diagram illustrating an example of the hardware configuration of the estimation device 10. For example, the estimation device 10 includes a circuit 120 shown in FIG. 3. The circuit 120 includes one or more processors 121, a memory 122, a storage 123, and an input / output port 124. The storage 123 includes a computer-readable storage medium, such as a hard disk. The storage medium stores a program for executing a predetermined intrusion estimation processing procedure. The storage medium may be a removable medium, such as a non-volatile semiconductor memory, a magnetic disk, or an optical disk. The memory 122 temporarily stores the program loaded from the storage medium of the storage 123 and the results of calculations performed by the processor 121. The processor 121 executes the program in cooperation with the memory 122 to configure each functional module described below. The input / output port 124 inputs and outputs electrical signals in accordance with instructions from the processor 121.

[0030] The hardware configuration of the estimation device 10 is not necessarily limited to configuring each functional module by a program. For example, each functional module of the estimation device 10 may be configured by a dedicated logic circuit or an ASIC (Application Specific Integrated Circuit) that integrates such a dedicated logic circuit.

[0031] The estimation device 10 continuously acquires detection results of the user Y in the waiting area E2 from the camera 20, and estimates whether the detected user Y will enter the crosswalk E1 based on the acquired detection results. Fig. 4 is a functional block diagram of the estimation device 10. The estimation device 10 includes an acquisition unit 11, a trajectory derivation unit 12, an estimation unit 13, and a control unit 14.

[0032] The acquisition unit 11 continuously acquires detection results of the user Y in the waiting area E2 by receiving imaging results from the camera 20. The imaging results acquired by the acquisition unit 11 are input to the trajectory derivation unit 12.

[0033] The trajectory derivation unit 12 derives a trajectory related to the movement of user Y by performing an analysis process on the input imaging results (video image data). If the imaging results (video image data) include multiple users Y, the trajectory derivation unit 12 derives the trajectory of each user Y. The above-mentioned analysis process may include a known object detection process, including a process for determining the difference between frames, and a known feature extraction process. Such processing can determine feature amounts (detection time, position, movement speed, movement direction, size, shape, color, etc.) related to the detected moving object. This makes it possible to distinguish, for example, a pedestrian who is an example of the detected user Y from other moving objects, and also to determine whether they are the same pedestrian or different pedestrians.

[0034] The trajectory derivation unit 12 detects the position and signs as feature quantities for each detected user Y (each pedestrian). The signs refer to information for predicting the future position of the detected user Y. Here, the body orientation and facial orientation of the detected user Y are detected as the signs. Well-known techniques can be used to detect the body orientation and facial orientation, and for example, a detection method using HOG (Histograms of Oriented Gradients) features or Haar-Like features may be used. Alternatively, a detection method combining one of these features with AdaBoost (Adaptive Boosting) may be used. Each of the body orientation and facial orientation is calculated, for example, as a two-dimensional vector in a horizontal plane. The trajectory derivation unit 12 derives the trajectory of the user Y based on the transition of the position of the same user Y and the above-mentioned signs. The trajectory here includes information on the route that the user Y has taken so far, as well as information on the future route that the user Y will take. Such information about the future route is estimated from the above-mentioned body orientation, face orientation, etc. The trajectory derivation unit 12 outputs the derived information (trajectory for each user Y) to the estimation unit 13.

[0035] The estimation unit 13 estimates whether user Y will enter the crosswalk E1 based on the trajectory of user Y, which is information derived by the trajectory derivation unit 12. Specifically, when the vectors of user Y's trajectories point toward the crosswalk E1, for example, as in the trajectories A and B shown in the left diagram of FIG. 5 , the estimation unit 13 estimates that user Y associated with these trajectories will enter the crosswalk E1. On the other hand, when the vectors of user Y's trajectories do not point toward the crosswalk E1, for example, as in the trajectories C, D, and E shown in the right diagram of FIG. 5 , the estimation unit 13 estimates that user Y associated with these trajectories will not enter the crosswalk E1. Note that, for example, as in the trajectory C shown in the right diagram of FIG. 5 , user Y may change direction and the trajectory may no longer point toward the crosswalk E1 midway. Therefore, the estimation results by the estimation unit 13 may change over time even for the same user Y.

[0036] The estimation by the estimation unit 13 may be performed taking into account the learning results of the route prediction. In this case, when trajectory information for each user Y is input from the trajectory derivation unit 12, the learning unit (not shown) included in the estimation device 10 stores the information for a predetermined period. The learning unit then performs learning of the route prediction based on the trajectory information of multiple users Y. The learning unit may perform learning for each attribute of user Y (e.g., whether the user is a pedestrian or a cyclist), for each time period in which the trajectory is acquired, or for each season in which the trajectory is acquired. Any learning algorithm may be used; for example, a neural network, a Markov decision process, a Gaussian process, or the like may be used depending on the model used. The learning unit outputs the learning results to the estimation unit 13. In this case, the estimation unit 13 may apply the learning result input from the learning unit to a predetermined prediction model, and input the trajectory of user Y derived by the trajectory derivation unit 12 into the prediction model (the learned prediction model), thereby deriving a future movement route and estimating whether user Y will enter the crosswalk E1. The estimation unit 13 outputs the estimation result to the control unit 14.

[0037] The control unit 14 controls the external device 30 based on the estimation result by the estimation unit 13. Here, the external device 30 is, for example, a signal control device that controls a push-button signal. The signal control device typically performs signal control to change the vehicle signal for the crosswalk E1 from green to yellow and then to red when a user who wants to cross the crosswalk E1 presses a button to request crossing. In this embodiment, as an alternative to the processing performed in such a push-button signal, when the estimation unit 13 estimates that the user Y will enter the crosswalk E1, an instruction signal is sent to the signal control device, and the above-mentioned signal control is performed. That is, when the estimation unit 13 estimates that the user Y will enter the crosswalk E1, the control unit 14 sends an instruction signal to the external device 30 (signal control device) so that the external device 30 (signal control device) performs the above-mentioned signal control. In this case, the external device 30 (signal control device) performs the above-mentioned signal control in response to the instruction signal. Considering that this process is performed as an alternative to the push-button signal process, it is preferable that the signal control is completed approximately 2 m before the entrance to the crosswalk E1. Therefore, as shown in Figure 1, a waiting area E2 is set up 2 m away from the entrance to the crosswalk E1.

[0038] The control unit 14 may control an external device 30 other than a signal control device based on the estimation result by the estimation unit 13. For example, the control unit 14 may transmit a signal indicating the estimation result by the estimation unit 13 to the external device 30, which is an in-vehicle device of a vehicle traveling near the crosswalk E1. In this case, the external device 30 (in-vehicle device) can use the estimation result by the estimation unit 13 as driving assistance information, for example.

[0039] Next, the approach estimation process executed by the estimation device 10 will be described with reference to the flowchart of Fig. 6. Fig. 6 is a flowchart illustrating the approach estimation process.

[0040] 6, the estimation device 10 receives an image capture result from the camera 20, thereby acquiring a detection result of the user Y in the waiting area E2 (step S1). The camera 20 is installed on the sidewalk that includes the waiting area E2 but does not include the crosswalk E1, and has an image capture range that covers the entire waiting area E2.

[0041] Next, the estimation device 10 performs an analysis process on the captured image results, and derives a trajectory of the movement of the user Y (step S2).

[0042] Next, the estimation device 10 estimates whether or not the user Y will enter the crosswalk E1 based on the derived trajectory of the user Y (step S3). Specifically, the estimation device 10 estimates that the user Y will enter the crosswalk E1 if the vector of the trajectory of the user Y is pointing toward the crosswalk E1, and estimates that the user Y will not enter the crosswalk E1 if the vector of the trajectory of the user Y is not pointing toward the crosswalk E1.

[0043] Then, the estimation device 10 controls the external device 30 based on the above-described estimation result (step S4). Specifically, when it is estimated that the user Y will enter the crosswalk E1, an instruction signal to change the vehicle signal to red may be transmitted to a signal control device that controls the push-button signal. Also, a signal indicating the above-described estimation result may be transmitted to an in-vehicle device of a vehicle traveling near the crosswalk E1.

[0044] Next, the effects of the approach estimation system 1 according to this embodiment will be described.

[0045] The entry estimation system 1 is provided for detecting a waiting area E2 through which a user passes before entering a crosswalk E1, and includes a camera 20 that detects users in the waiting area E2, and an estimation device 10 that continuously acquires detection results of users in the waiting area E2 from the camera 20 and estimates whether the detected user will enter the crosswalk E1 based on the acquired detection results.

[0046] In the entry estimation system 1, a camera 20 provided for detecting a user in a waiting area E2 that the user passes through before entering the crosswalk E1 detects the user passing through the waiting area E2, and based on the detection result, it is estimated whether the detected user will enter the crosswalk E1. In this way, by using the detection result of the camera 20 provided for detecting the user in the waiting area E2, it is possible to obtain with high accuracy the state of the user in the waiting area E2 (position, orientation, etc.), and ultimately to estimate with high accuracy whether the user will enter the crosswalk E1.

[0047] For example, when a user is detected by a configuration that detects a wide area including the crosswalk E1 rather than by a configuration that detects users in the waiting area E2, the state (position, orientation, etc.) of the user in the waiting area E2 may not be detected appropriately due to overlapping of multiple users, weather, etc. That is, as shown in Fig. 7 , when a user is detected by a camera 520 that is installed on the sidewalk E3 on the opposite side of the waiting area E2 and detects a wide area, it is possible that multiple users Y overlap in the detection direction of the camera 520, or that a vehicle C1 overlaps with user Y. Furthermore, depending on the weather, it may not be possible to accurately detect user Y in the waiting area E2 from the sidewalk E3 on the opposite side of the crosswalk E1.

[0048] In this regard, by detecting users in the waiting area E2 using the camera 20 provided for detecting users in the waiting area E2, it is possible to suppress the above-mentioned overlap of multiple users, the effects of weather, etc., and to acquire with high accuracy the status (position, orientation, etc.) of the user in the waiting area E2. As described above, the entry estimation system 1 according to this embodiment can acquire with high accuracy the status (position, orientation, etc.) of the user in the waiting area E2, and based on the acquired results, it can estimate with high accuracy whether the user is entering the crosswalk E1, which is the destination area.

[0049] In the entry estimation system 1, the camera 20 may be provided on a sidewalk that includes the waiting area E2 but does not include the crosswalk E1. By providing the camera 20 in this manner, as described with reference to Fig. 7 , it is possible to prevent an object that is not a detection target (e.g., a vehicle C1 traveling on a road that includes the crosswalk E1) from being present between the camera 520 and the waiting area E2, thereby improving the detection accuracy of the user in the waiting area E2.

[0050] In the entry estimation system 1, the camera 20 may be installed directly above the waiting area E2, and the detection range may be set to the downward direction as viewed from the camera 20, thereby detecting a user in the waiting area E2. Installing the camera 20 in this manner allows for more subtle detection of the user's trajectory than, for example, when a camera 520 is installed on the sidewalk E3 on the opposite bank of the waiting area E2, as shown in FIG. 7 . That is, for example, for a trajectory such as trajectory A in the left diagram of FIG. 5 , the camera 520 on the sidewalk E3 on the opposite bank detects a small displacement, making estimation difficult. In contrast, the camera 20 installed directly above the waiting area E2 detects a trajectory only along two axes, the X and Y axes, allowing for highly accurate detection of even subtle changes such as trajectory A in the left diagram of FIG. 5 . That is, compared to the case where, for example, the three-axis components of X, Y and Z are detected by the camera 520 on the sidewalk E3 on the opposite bank, only the two-axis components of the X and Y axes are detected from directly above, so that the information on the direction (X and Y directions) required to derive the trajectory can be obtained with high accuracy.

[0051] In the entry estimation system 1, the estimation device 10 may derive a trajectory related to the movement of the detected user from multiple detection results, and may estimate that the detected user will enter the crosswalk E1 if the direction of the trajectory is oriented toward the crosswalk E1. In this way, by estimating that the user will enter the crosswalk E1 if the trajectory related to the user's movement is oriented toward the crosswalk E1, it is possible to estimate with high accuracy whether the user will enter the crosswalk E1.

[0052] In the entry estimation system 1, the estimation device 10 may derive a trajectory related to the movement of the detected user from multiple detection results, and may estimate that the detected user will not enter the crosswalk E1 if the direction of the trajectory is not pointing toward the crosswalk E1. In this way, by estimating that the user will not enter the crosswalk E1 if the trajectory related to the user's movement is not pointing toward the crosswalk E1, it is possible to estimate with high accuracy whether the user will enter the crosswalk E1.

[0053] In the entry estimation system 1, the first area may be an area including a crosswalk, and the second area may be a waiting area on a sidewalk adjacent to the crosswalk. With this configuration, it is possible to estimate with high accuracy whether a user on a sidewalk adjacent to the crosswalk is entering the crosswalk.

[0054] The crosswalk E1 and the waiting area E2 may be adjacent to each other. With this configuration, it is possible to estimate whether the user will enter the crosswalk E1 based on the detection result in the area (waiting area E2) that the user passes through immediately before entering the crosswalk E1. By using the detection result in the area close to the crosswalk E1, it is possible to more accurately estimate whether the user will enter the crosswalk E1.

[0055] Although various embodiments and modifications according to the present disclosure have been described above, the present disclosure is not limited to the exemplified embodiments.

[0056] For example, although the example in which the first area, which is the predetermined destination area, is a crosswalk has been described, the present invention is not limited to this. The first area may be an area other than a crosswalk, specifically, a road other than a crosswalk or an area at the entrance to a predetermined facility. Even in this case, the second area may be an area adjacent to the first area that a user entering the first area passes through immediately before entering the first area. Furthermore, the first area and the second area do not necessarily have to be adjacent to each other; there may be another area (gap) between them. Furthermore, the functions of the estimation device 10 described above may be allotted to a server device configured to be able to communicate with the camera 20, or may be allocated separately to the server device and a roadside device that communicates with the server device, or may be allotted to the roadside device.

[0057] The various embodiments and modifications described above may be combined as appropriate without departing from the spirit of the present disclosure.

[0058] 1... Entry estimation system 10... Estimation device (control unit) 11... Acquisition unit 12... Trajectory derivation unit 13... Estimation unit 14... Control unit 20... Camera (detection unit) 30... External device 50... Pillar 51... Vertical extension unit 52... Support unit 120... Circuit 121... Processor 122... Memory 123... Storage 124... Input / output port 520... Camera E1... Crosswalk E2... Waiting area E3... Sidewalk on the opposite bank Y... User

Claims

1. An entry estimation system comprising: a detection unit provided for detecting a second area through which a user passes before entering a specified first area, and detecting a user in the second area; and a control unit that continuously acquires detection results of the user in the second area from the detection unit, and estimates whether the detected user will enter the first area based on the acquired detection results.

2. The approach estimation system according to claim 1, wherein the detection unit is provided on a road that includes the second area but does not include the first area.

3. An entry estimation system as described in claim 2, wherein the detection unit is provided directly above the second area, and detects users in the second area by setting the detection range to the downward direction as viewed from the detection unit.

4. An entry estimation system as described in any one of claims 1 to 3, wherein the control device derives a trajectory of the movement of the detected user from multiple detection results, and if the direction of the trajectory is toward the first area, estimates that the detected user will enter the first area.

5. An entry estimation system as described in any one of claims 1 to 4, wherein the control device derives a trajectory relating to the movement of the detected user from a plurality of the detection results, and if the direction of the trajectory is not toward the first area, estimates that the detected user is not entering the first area.

6. An approach estimation system according to any one of claims 1 to 5, wherein the first area is an area including a pedestrian crossing, and the second area is a waiting area on a sidewalk adjacent to the pedestrian crossing.

7. The approach estimation system according to any one of claims 1 to 6, wherein the first area and the second area are adjacent to each other.

8. An entry estimation method executed by an entry estimation system, comprising: a step of detecting a user in a specified first area by a detection unit provided for detecting a second area through which the user passes before entering the second area; and a step of estimating whether the detected user will enter the first area based on the user detection results that are continuously obtained.

9. A control device provided for detecting a second area through which a user passes before entering a specified first area, which continuously acquires detection results of the user in the second area from a detection unit that detects the user in the second area, and which estimates whether the detected user will enter the first area based on the acquired detection results.

Images