Exit assisting device, exit assisting computer program, and exit assisting method

Abstract

To provide an exit assisting device for assisting a driver in driving a vehicle out of a parking section on the basis of the direction of the visual line of a driver.SOLUTION: An exit assisting device includes: an estimation unit 232 that estimates a visual line direction of a driver on the basis of an image showing the vicinity of a driver's seat; and a determination unit 233 that determines an exit direction in which the vehicle exits from a parking section on the basis of the visual line of the driver estimated by the estimation unit 232.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to an exit support device, an exit support computer program, and an exit support method. [Background technology]

[0002] Conventionally, a parking assistance device has been proposed that assists in parking a vehicle in a parking space. The parking assistance device recognizes a parking space and assists a driver in parking the vehicle in the parking space while maintaining an appropriate distance from other adjacent vehicles.

[0003] For example, a parking assistance device has been proposed that, when a driver parks a vehicle in a parking space, determines one of a plurality of parking spaces in which to park the vehicle based on the driver's line of sight (see, for example, Patent Document 1). This allows the driver to notify the parking assistance device of the desired parking space without performing any operation to specify the parking space. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2006-071425 A Summary of the Invention [Problem to be solved by the invention]

[0005] Some parking assistance devices allow a driver to move a vehicle parked in a parking space in a direction designated by the driver's operation when the driver moves the vehicle out of the space.

[0006] Before starting the vehicle, the driver must adjust the position of the driver's seat, set up the navigation system, set up the air conditioning system, and so on.

[0007] Therefore, there is a need to reduce the burden on the driver when the vehicle exits a parking space.

[0008] Therefore, an object of the present disclosure is to provide an exit assistance device that assists a vehicle in exiting a parking space based on the direction of the driver's line of sight. [Means for solving the problem]

[0009] (1) According to one embodiment, there is provided an exit assistance device, characterized in that the exit assistance device includes an estimation unit that estimates a driver's line of sight direction based on an image depicting the vicinity of a driver's seat, and a determination unit that determines an exit direction for causing a vehicle to exit a parking space based on the driver's line of sight estimated by the estimation unit.

[0010] (2) In the exit assistance device of (1), it is preferable that the device has a recognition unit that recognizes multiple directions in which the vehicle can exit based on information representing the environment around the vehicle, and the determination unit determines the exit direction from among the multiple directions recognized by the recognition unit based on the driver's line of sight estimated by the estimation unit.

[0011] (3) In the exit assistance device of (1), it is preferable that the determination unit determines, from among the multiple directions recognized by the recognition unit, the direction in which the driver's line of sight is directed for the longest period of time as the exit direction.

[0012] (4) In the exit assistance device of (2), it is preferable that the device further has a detection unit that detects the number of movements of objects around the vehicle based on information representing the environment around the vehicle, and when the number of movements detected by the detection unit exceeds a predetermined reference value, the determination unit determines, among the multiple directions recognized by the recognition unit, the direction opposite to the direction in which the driver's gaze is directed for the longest time, as the exit direction, and when the number of movements detected by the detection unit does not exceed the reference value, the determination unit determines, among the multiple directions recognized by the recognition unit, the direction in which the driver's gaze is directed for the longest time, as the exit direction.

[0013] (5) According to another embodiment, there is provided an exit assistance method, which includes an exit assistance device estimating a driver's line of sight based on an image depicting an area near the driver's seat, and determining an exit direction for causing the vehicle to exit the parking space based on the driver's line of sight. Effect of the Invention

[0014] The exit assistance device according to the present disclosure assists the driver in exiting a parking space based on the direction of the driver's gaze, thereby reducing the burden on the driver. [Brief description of the drawings]

[0015] [Figure 1] 1A and 1B illustrate an overview of the operation of the assistance device of this embodiment, where 1A is a diagram showing a vehicle parked in a parking space, and 1B is a diagram showing the interior of the vehicle. [Diagram 2] 1 is a hardware configuration diagram of a vehicle in which an assistance device according to an embodiment of the present invention is implemented. [Diagram 3] 13 is an example of an operational flowchart relating to an exit support process of the support device of the present embodiment. [Figure 4] 13 is an example of an operational flowchart relating to an exit direction determination process of the support device of the present embodiment. [Diagram 5] 13 is another example of an operational flowchart relating to the exit direction determination process of the support device of the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] 1(A) and 1(B) explain an overview of the operation of the assistance device 13 of this embodiment. Fig. 1(A) is a diagram showing a vehicle 10 parked in a parking space 51, and Fig. 1(B) is a diagram showing the inside of a vehicle compartment 30. The assistance device 13 is an example of an exit assistance device.

[0017] As shown in Fig. 1(A), a vehicle 10 has an automatic control device 12 and an assistance device 13. The automatic control device 12 controls the operation of the vehicle 10. The assistance device 13 assists the vehicle 10 in parking and in exiting the vehicle 10. The vehicle 10 may be an autonomous vehicle.

[0018] Vehicle 10 is parked in one parking space 51 of a parking lot 50 having multiple parking spaces 51. The parking lot is an area surrounded by a pair of demarcation lines 52, 52. Parking space 51 is demarcated by a pair of demarcation lines 53 and one demarcation line 52. Another vehicle 60 is parked next to vehicle 10.

[0019] The vehicle 10 is parked backwards in the parking space 51. The vehicle 10 can exit the parking space 51 and drive to the left or right.

[0020] The driver 40 gets into the vehicle 10 to go out in the vehicle 10. The driver 40 sits in the driver's seat 31 in the passenger compartment 30 of the vehicle 10. When the ignition is turned on, the assistance device 13 starts up. The driver 40 operates the user interface 7 to start an exit assistance operation in which the assistance device 13 assists the vehicle 10 in exiting the vehicle 10.

[0021] Since the driver 40 was planning to exit to the left, after sitting in the driver's seat 31, the driver turned his / her gaze to the left in front of the vehicle 10.

[0022] The support device 13 estimates the line of sight direction of the driver 40 based on a surveillance image including the face of the driver 40 captured by the surveillance camera 6. The support device 13 determines that the line of sight of the driver 40 is directed to the left with respect to the front of the vehicle 10.

[0023] Because the direction of the driver's line of sight is directed to the left of the front of the vehicle 10, the assistance device 13 determines the exit direction for the vehicle 10 to exit the parking space 51 to the left of the front of the vehicle 10. The automatic control device 12 drives the vehicle 10 so that the vehicle 10 exits the parking space 51 to the left. The exit direction means the direction in which the vehicle 10 travels after leaving the parking space 51.

[0024] As described above, in this embodiment, the driver 40 is assisted in withdrawing the vehicle 10 from the parking space 51 based on the direction of his / her line of sight, so that the burden on the driver 40 can be reduced.

[0025] 2 is a hardware configuration diagram of a vehicle 10 in which the assistance device 13 of this embodiment is implemented. The vehicle 10 has camera sensors 2a to 2d, sonar sensors 3a to 3l, a speed sensor 4, an angular velocity sensor 5, a surveillance camera 6, a user interface (UI) 7, an object detection device 11, an automatic control device 12, an assistance device 13, and the like.

[0026] The camera sensors 2a to 2d, sonar sensors 3a to 3l, speed sensor 4, angular velocity sensor 5, surveillance camera 6, user interface (UI) 7, object detection device 11, automatic control device 12, and assistance device 13 are communicatively connected via an in-vehicle network 14 that complies with a standard such as a controller area network.

[0027] The camera sensors 2a to 2d capture surrounding images that represent the environment around the vehicle 10 at surrounding image capture times that are set at predetermined intervals. The camera sensors 2a to 2d output the captured surrounding images together with the surrounding image capture times to the object detection device 11 and the like via the in-vehicle network 14. The surrounding images are used by the object detection device 11 in a process of detecting objects around the vehicle 10.

[0028] Camera sensor 2a is disposed at the front of vehicle 10, camera sensor 2b is disposed to the left of vehicle 10, camera sensor 2c is disposed at the rear of vehicle 10, and camera sensor 2d is disposed to the right of vehicle 10.

[0029] The camera sensors 2a to 2d each have a two-dimensional detector configured with an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The surrounding image is an example of surrounding environment information.

[0030] The sonar sensors 3a to 3l emit sound waves at the reflected wave information acquisition time set at a predetermined cycle, and receive the reflected waves reflected by a reflecting object. The sonar sensors 3a to 3l have distance information between the vehicle 10 and an object located in the direction of the sound waves emitted, which is the time required for the reflected wave reflected by the reflecting object to return. The sonar sensors 3a to 3l output reflected wave information including the direction of the sound waves and the time required for the reflected wave to return, together with the reflected wave information acquisition time when the sound waves were emitted, to the object detection device 11 or the like via the in-vehicle network 14. The reflected wave information is used in the object detection device 11 for processing to detect objects around the vehicle 10. Ultrasonic sensors can be used as the sonar sensors 3a to 3l. The reflected wave information is an example of surrounding environment information.

[0031] Sonar sensors 3a, 3b, and 3l are disposed in the front of the vehicle 10, sonar sensors 3c to 3e are disposed to the left of the vehicle 10, sonar sensors 3f to 3h are disposed in the rear of the vehicle 10, and sonar sensors 3i to 3k are disposed to the right of the vehicle 10.

[0032] The speed sensor 4 detects the speed information of the vehicle 10, and outputs the speed information and the time when the speed information was acquired to the automatic control device 12, the assistance device 13, etc. via the in-vehicle network 14. The speed sensor 4 is attached to, for example, an axle (not shown), detects the rotation speed of the axle, and outputs a pulse signal proportional to the rotation speed.

[0033] The angular velocity sensor 5 detects the yaw rate of the vehicle 10 and outputs the yaw rate and the time when the yaw rate was acquired to the automatic control device 12, the assistance device 13, etc. via the in-vehicle network 14. As the angular velocity sensor 5, for example, a gyroscope or the like can be used.

[0034] The surveillance camera 6 is an example of an image acquisition unit. The surveillance camera 6 acquires a surveillance image showing the vicinity of the driver's seat 31 at a surveillance image acquisition time having a predetermined period, for example. The surveillance image shows the face of the driver 40 seated in the driver's seat 31. The surveillance camera 6 is disposed, for example, above a steering column.

[0035] The surveillance camera 6 has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to infrared light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be captured on the two-dimensional detector.

[0036] Every time the surveillance camera 6 captures a surveillance image, it outputs the surveillance image and the image capture time when the surveillance image was captured to the assistance device 13 via the in-vehicle network 14. The surveillance image is used by the assistance device 13 to estimate the driver's line of sight direction.

[0037] The UI7 is an example of a notification unit. The UI7 is controlled by the automatic control device 12 or the assistance device 13 to notify the driver 40 of information related to the vehicle 10. For example, the UI7 is controlled by the assistance device 13 to notify the driver 40 of the exit direction of the vehicle 10. The UI7 has a display device 7a such as a liquid crystal display or a touch panel to display information. The UI7 may also have an audio output device (not shown) for notifying the driver 40 of information. The UI7 also has, for example, a touch panel or an operation button as an input device for inputting operation information from the driver 40 to the vehicle 10. For example, the operation information may be an operation to request assistance for parking or exiting. The UI7 outputs the input operation information to the automatic control device 12 or the assistance device 13 via the in-vehicle network 14.

[0038] The object detection device 11 detects objects and their types around the vehicle 10 based on the surrounding image. The objects include other vehicles, pedestrians, and parking space markings around the vehicle 10. The object detection device 11 has, for example, a classifier that detects objects depicted in the image by inputting the surrounding image.

[0039] As the classifier, for example, a deep neural network (DNN) that has been trained in advance to detect an object depicted in an input image from the image can be used. The object detection device 11 may use a classifier other than a DNN. For example, the object detection device 11 may use, as the classifier, a support vector machine (SVM) that has been trained in advance to input a feature amount (e.g., Histograms of Oriented Gradients, HOG) calculated from a window set on the surrounding image and output a confidence that the object to be detected is depicted in the window. Alternatively, the object detection device 11 may detect an object region by performing template matching between a template depicting the object to be detected and the image.

[0040] Furthermore, the object detection device 11 may detect objects around the vehicle 10 based on the reflected wave information output by the sonar sensors 3a to 3l. Furthermore, the object detection device 11 may determine the orientation of the object relative to the vehicle 10 based on the position of the object in the surrounding image, and determine the distance between the object and the vehicle 10 based on the orientation and the reflected wave information. The object detection device 11 estimates the position of the object, expressed for example in the vehicle coordinate system, based on the current position of the vehicle 10 and the distance and orientation to the object relative to the vehicle 10.

[0041] In addition, when a lane marking on the ground is detected, the object detection device 11 estimates the position of the lane marking based on internal parameters such as the focal length of the camera sensors 2a to 2d and external parameters such as the installation position and installation orientation of the camera sensors 2a to 2d.

[0042] The object detection device 11 notifies the automatic control device 12, the assistance device 13, or the like of object detection information including information indicating the type of the detected object and information indicating its position via the in-vehicle network 14. The object detection device 11 may assign identification information to the same object and track it using, for example, optical flow. This identification information is included in the object detection information.

[0043] The automatic control device 12 controls the operation of the vehicle 10. The automatic control device 12 has an automatic driving mode in which the vehicle 10 is driven automatically, and a manual driving mode in which the operation of the vehicle 10 is controlled based on the operation of the driver 40. In the automatic driving mode, the automatic control device 12 mainly drives the vehicle 10. In the automatic driving mode, the automatic control device 12 controls operations such as steering, driving, and braking based on detection information and the like from camera sensors 2a-2d and sonar sensors 3a-3k mounted on the vehicle 10.

[0044] In addition, in the automatic driving mode, the automatic control device 12 parks the vehicle 10 in a parking space and also causes the vehicle 10 to exit from the parking space based on assistance information notified from the assistance device 13.

[0045] In addition, in the manual driving mode, the automatic control device 12 controls the operation of the vehicle 10, such as steering, driving, and braking, based on the operation of the driver 40. In the manual driving mode, the driver 40 takes the lead in driving the vehicle 10. In the manual driving mode, the automatic control device 12 controls the operation of the vehicle 10 based on the operation of at least one of the steering wheel, the brake pedal, and the accelerator pedal by the driver 40.

[0046] The assistance device 13 executes a recognition process, an estimation process, a determination process, and a detection process. To this end, the assistance device 13 has a communication interface (IF) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the assistance device 13 to the in-vehicle network 14.

[0047] The memory 22 is an example of a storage unit and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores computer programs of applications used in the information processing executed by the processor 23 and various data.

[0048] All or part of the functions of the support device 13 are functional modules realized by, for example, a computer program running on the processor 23. The processor 23 has a recognition unit 231, an estimation unit 232, a determination unit 233, and a detection unit 234. Alternatively, the functional modules of the processor 23 may be dedicated arithmetic circuits provided in the processor 23. The processor 23 has one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit.

[0049] The object detection device 11, the automatic control device 12, and the assistance device 13 are, for example, electronic control devices (Electronic Control Units: ECUs). In Fig. 3, the object detection device 11, the automatic control device 12, and the assistance device 13 are described as separate devices (for example, Electronic Control Units: ECUs), but all or some of these devices may be configured as a single device.

[0050] Next, an operation of the assistance device 13 to assist the vehicle 10 in parking in a parking space will be described below. When the vehicle 10 reaches a position in front of the parking space where the vehicle 10 is to be parked (see position P in the example shown in FIG. 1(A)), the driver 40 operates the UI 7 to request parking assistance.

[0051] When a parking assistance request is made, the automatic control device 12 drives the vehicle 10 straight ahead for a predetermined distance from the current position of the vehicle 10 (see the dashed arrow in the example shown in FIG. 1(A)). The estimation unit 232 starts estimating the line of sight of the driver 40 based on the monitored image. The line of sight direction is represented as a horizontal angle with respect to the front of the vehicle 10.

[0052] The estimation unit 232 inputs the acquired surveillance image to a classifier trained to detect specific facial features such as the corner and the outer corner of the eye, thereby identifying the position of the specific feature included in the surveillance image. The estimation unit 232 obtains the position of the pupil center and the position of the eyeball center based on the positions of the corner and the outer corner of the eye, and estimates the direction connecting the positions of the eyeball center and the pupil center as the gaze direction of the driver 40.

[0053] The recognition unit 231 estimates the current position and orientation of the vehicle 10 based on the speed information and yaw rate. In addition, the recognition unit 231 acquires the positions of the lane lines and objects around the vehicle 10 based on the object detection information input from the object detection device 11, and stores the lane lines and object positions expressed in the vehicle coordinate system.

[0054] The recognition unit 231 recognizes a space where the vehicle 10 can be parked as a parking space based on the partition lines and the positions of objects around the vehicle 10. The determination unit 233 determines, among the parking spaces recognized by the recognition unit 231, a parking space that is located in a position that coincides with the line of sight of the driver 40 estimated by the estimation unit 232, as the parking space in which the vehicle 10 will be parked.

[0055] The determination unit 233 outputs the parking space information indicating the position of the parking space to the automatic control device 12 via the in-vehicle network 14. The automatic control device 12 parks the vehicle 10 in the parking space indicated by the parking space information. In the example shown in Fig. 1(A), the vehicle 10 is parked backwards in the parking space 51.

[0056] Furthermore, the recognition unit 231 recognizes whether the vehicle 10 will exit facing forward or backward when exiting the parking space. Furthermore, the recognition unit 231 recognizes the possible exit directions. The possible exit directions indicate, for example, whether the vehicle 10 will continue to move to the left, move to the right, or move straight after exiting the parking space.

[0057] The recognition unit 231 identifies the direction in which the vehicle 10 can travel from the parking space based on the lane lines or the positions of objects around the vehicle 10, and determines whether the vehicle 10 should exit forward or backward. The recognition unit 231 also recognizes the direction in which the vehicle 10 can exit. In the example shown in FIG. 1(A), the recognition unit 231 determines that after exiting forward, the vehicle 10 can exit to the left and right with respect to the front of the vehicle 10.

[0058] The recognition unit 231 expresses the directions in which the vehicle 10 can exit as horizontal angles with respect to the front of the vehicle 10. The directions in which the vehicle 10 can exit to the left can be in the range of -90 degrees to -30 degrees, with the front direction of the vehicle 10 being zero degrees. The directions in which the vehicle 10 can exit to the right can be in the range of 30 degrees to 90 degrees, with the front direction of the vehicle 10 being zero degrees.

[0059] The recognition unit 231 notifies the determination unit 233 of the forward / rearward direction indicating whether the vehicle 10 will exit the parking space facing forward or backward, and the possible exit direction.

[0060] 3 is an example of an operation flowchart relating to the exit support process of the support device 13 of this embodiment. The support device 13 executes the exit support according to the operation flowchart shown in FIG. 3 every time the driver 40 in the vehicle 10 parked in a parking space turns on the ignition and the support device 13 is started.

[0061] First, the driver 40 in the vehicle 10 turns on the ignition. This starts the assistance device 13 (step S101). Together with the assistance device 13, the camera sensors 2a to 2d, the sonar sensors 3a to 3l, the speed sensor 4, the angular velocity sensor 5, the surveillance camera 6, the user interface (UI) 7, the object detection device 11, and the automatic control device 12 also start up.

[0062] Next, the estimation unit 232 starts estimating the line of sight of the driver 40 based on the monitoring image (step S102). The line of sight direction detected by the estimation unit 232 is expressed as an angle in the horizontal direction and the vertical direction with respect to the front of the vehicle 10. For example, the line of sight direction is expressed as an angle of up to 90 degrees to the right and up to -90 degrees to the left, with the front direction of the vehicle 10 being zero degrees in the horizontal direction. Also, the line of sight direction is expressed as an angle of up to 90 degrees upward and up to -90 degrees downward, with the front direction of the vehicle 10 being zero degrees in the vertical direction.

[0063] The estimation unit 232 detects the gaze direction at a predetermined time interval and generates a frequency distribution of the gaze direction expressed in 10-degree intervals from -90 degrees to 90 degrees. The time interval can be, for example, 0.2 seconds to 1 second. The generation of the frequency distribution continues until a determination is made in step S103 described later.

[0064] Here, from the viewpoint of detecting the line of sight of the driver 40 when the line of sight is directed outside through the window of the vehicle interior 30, it is preferable that the estimation unit 232 counts the number of degrees when the line of sight of the driver 40 is within a predetermined vertical range. The vertical range can be set based on the position of the driver's seat 31 and the positional relationship with the window.

[0065] Next, the determination unit 233 determines whether or not an exit support request has been requested (step S103). When the driver 40 requests an exit support request, the driver 40 operates the UI 7 to input the exit support request. When a parking support request is input before the vehicle 10 starts traveling, the determination unit 233 determines that an exit support request has been requested.

[0066] On the other hand, if the parking assistance request is not input before the vehicle 10 starts traveling, the determination unit 233 determines that the parking assistance request is not requested. If the parking assistance request is not requested (step S103-No), the series of processes ends. If the driver 40 drives the vehicle by himself / herself to exit the parking space, the parking assistance request is not input.

[0067] When a parking assistance request is made (step S103-Yes), the determination unit 233 determines an exit direction for causing the vehicle 10 to exit the parking space based on the line of sight of the driver 40 (step S104). The determination unit 233 notifies the recognition unit 231 of the exit direction. The exit direction determination process by the determination unit 233 will be described later with reference to Figs. 4 and 5.

[0068] Next, the recognition unit 231 generates a driving route for causing the vehicle 10 to exit based on the exit direction notified by the determination unit 233 (step S105), notifies the automatic control device 12 of this driving route, and ends a series of processes. The recognition unit 231 also notifies the driver 40 of the exit direction of the vehicle 10 via the UI 7. The automatic control device 12 causes the vehicle 10 to exit the parking space based on the driving route.

[0069] Next, the exit direction determination process by the determination unit 233 will be described below with reference to Fig. 4 and Fig. 5. Fig. 4 is an example of an operational flowchart relating to the exit direction determination process of the support device of this embodiment.

[0070] First, the determination unit 233 acquires the forward / rearward direction and the possible exit direction of the vehicle 10 from the recognition unit 231 (step S201). The forward / rearward direction indicates whether the vehicle 10 exits the parking space facing forward or backward. The possible exit direction of the vehicle 10 is expressed as a horizontal angle with respect to the front of the vehicle 10. For example, the possible exit direction to the left is expressed in a range from -90 degrees to -30 degrees, with the forward direction of the vehicle 10 being zero degrees. Also, the possible exit direction to the right is expressed in a range from 30 degrees to 90 degrees, with the forward direction of the vehicle 10 being zero degrees.

[0071] Next, the determination unit 233 calculates the time during which the line of sight of the driver 40 is directed toward each of the multiple possible exit directions, based on the frequency distribution of the line of sight directions generated by the estimation unit 232 (step S202).

[0072] For example, the determination unit 233 calculates the sum of the frequencies of the gaze directions distributed in the range of -90 degrees to -30 degrees as the time during which the gaze of the driver 40 faces leftward. Also, the determination unit 233 calculates the sum of the frequencies of the gaze directions distributed in the range of 30 degrees to 90 degrees as the time during which the gaze of the driver 40 faces rightward.

[0073] Next, the determination unit 233 determines, among a plurality of directions in which the vehicle 10 can exit, the direction in which the driver 40 is looking for the longest period of time as the exit direction (step S203), and ends the series of processes.

[0074] The exit direction determination process by the determination unit 233 is not limited to that shown in Fig. 4. For example, the determination unit 233 may execute the exit direction determination process according to the operation flowchart shown in Fig. 5. Fig. 5 is another example of the operation flowchart related to the exit direction determination process of the support device of this embodiment.

[0075] In the operational flowchart shown in Fig. 5, steps S301, S302, and S306 are similar to steps S201, S202, and S203 in the above-mentioned operational flowchart shown in Fig. 4. The explanations of steps S201, S202, and S203 are appropriately applied to the explanations of steps S301, S302, and S306.

[0076] After calculating the time that the driver 40 is looking toward each of the multiple possible exit directions (step S302), the detection unit 234 calculates the number of movements of objects around the vehicle 10 based on the object detection information (step S303).

[0077] After being started, the object detection device 11 outputs object detection information indicating objects detected around the vehicle 10 to the assistance device 13. The detection unit 234 calculates the number of objects detected in front of or behind the vehicle 10 as the number of movements based on the object detection information. Examples of objects include other vehicles and pedestrians. When the vehicle 10 moves forward from the parking space, the number of movements of objects moving in front of the vehicle 10 is calculated. When the vehicle 10 moves backward from the parking space, the number of movements of objects moving backward of the vehicle 10 is calculated.

[0078] 1A, the vehicle 10 moves forward out of the parking space. The detection unit 234 calculates the number of objects moving in front of the vehicle 10.

[0079] Next, the detection unit 234 judges whether the number of movements exceeds a predetermined reference value (step S304). When the number of objects moving around the parked vehicle 10 is large, the driver 40 tends to check for the presence or absence of objects approaching from the direction opposite to the exit direction in which the vehicle 10 is exiting. On the other hand, when the number of objects moving around the parked vehicle 10 is small, the driver 40 tends to check for the presence or absence of objects approaching from the exit direction in which the vehicle 10 is exiting. The reference value can be, for example, 3 to 5.

[0080] If the number of movements exceeds the reference value (step S304-Yes), the determination unit 233 determines, among the multiple possible exit directions, the direction opposite to the direction in which the driver 40's gaze is directed for the longest period of time as the exit direction (step S305), and ends the series of processes.

[0081] In the example shown in Fig. 1(A), the possible exit directions are the left and the right. For example, if the number of movements exceeds a reference value and the direction in which the driver 40 is looking is the longest is the right, the exit direction is the left.

[0082] On the other hand, if the number of movements does not exceed the reference value (step S304-No), the determination unit 233 determines, among the multiple possible exit directions, the direction in which the driver 40's gaze is directed for the longest period of time as the exit direction (step S306), and ends the series of processes.

[0083] In the example shown in Fig. 1(A), the possible exit directions are the left and the right. For example, if the number of movements does not exceed the reference value and the direction in which the driver 40 is looking is the longest is the left, the exit direction is the left.

[0084] As described above in detail, the assistance device of the present embodiment assists the driver in moving the vehicle out of a parking space based on the direction of the driver's line of sight, thereby reducing the burden on the driver.

[0085] In the present disclosure, the above-described embodiments of the exit support device, the exit support computer program, and the exit support method can be modified as appropriate without departing from the spirit of the present disclosure. Furthermore, the technical scope of the present disclosure is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.

[0086] For example, in the above-described embodiment, the vehicle is parked in the parking space facing backwards, and exits the parking space facing forwards when exiting. The present invention is also applicable to the case where the vehicle is parked in the parking space facing forwards, and exits the parking space facing backwards when exiting. When the recognition unit notifies the assistance device that the vehicle will exit backwards, the estimation unit detects the driver's line of sight as follows. First, the estimation unit determines whether the driver's line of sight is directed toward the position of the room mirror (see FIG. 1(B)). When the driver's line of sight is directed toward the room mirror, the estimation unit detects the driver's line of sight. When the vehicle is parked in the parking space facing forwards, the driver looks at the room mirror to check the environment in the direction in which the vehicle will exit. As described above, the line of sight is expressed as either the left or right side with respect to the front of the vehicle.

[0087] In the above embodiment, the vehicle is parked in a parking space, but the vehicle may be parked in a space that is not divided by a dividing line. The assistance device assists the vehicle in parking in a space where parking is possible. The assistance device also monitors the exit of a vehicle parked in a space that is not divided by a dividing line from the space. [Explanation of symbols]

[0088] 2a~2d Camera sensor 3a~3l Sonar sensors 4 Speed ​​Sensor 5 Angular Rate Sensor 6. Surveillance Cameras 7 User Interface (UI) 7a Display device 10 Vehicles 11 Object detection device 12 Automatic control device 13 Support equipment 21 Communication Interface 22 Memory 23 Processors 231 Recognition part 232 Estimation Department 233 Decision Section 234 Detection Unit 14 In-vehicle network 30 Cabin 31 Driver's seat 32 Rearview mirror

Claims

1. an estimation unit that estimates a driver's line of sight direction based on an image showing the vicinity of the driver's seat; a determination unit that determines an exit direction in which the vehicle exits the parking space based on the line of sight of the driver estimated by the estimation unit; An exit assistance device comprising:

2. a recognition unit that recognizes a plurality of directions from which the vehicle can exit based on information representing an environment around the vehicle; The exit assistance device according to claim 1 , wherein the determination unit determines the exit direction from among the plurality of directions recognized by the recognition unit, based on a line of sight of the driver estimated by the estimation unit.

3. The exit assistance device according to claim 2 , wherein the determination unit determines, as the exit direction, a direction in which the driver's line of sight is directed for the longest period of time among the plurality of directions recognized by the recognition unit.

4. The vehicle further includes a detection unit that detects the number of objects moving around the vehicle based on information representing an environment around the vehicle, 3. The exit support device of claim 2, wherein, when the number of movements detected by the detection unit exceeds a predetermined reference value, the determination unit determines, among the multiple directions recognized by the recognition unit, a direction opposite to a direction in which the driver's gaze is directed for the longest time, as the exit direction, and when the number of movements detected by the detection unit does not exceed the reference value, the determination unit determines, among the multiple directions recognized by the recognition unit, a direction in which the driver's gaze is directed for the longest time, as the exit direction.

5. The exit assistance device, A driver's line of sight direction is estimated based on an image showing the vicinity of the driver's seat; determining an exit direction for the vehicle to exit the parking space based on the driver's line of sight; An exit support method comprising:

Images