JP6677133B2 - Driving support device - Google Patents

Description

  The present invention relates to a driving support device.

  2. Description of the Related Art Conventionally, a technology for automatically driving a four-wheel vehicle has been proposed. In addition, a technique for providing driving assistance to a passenger manually driving a four-wheeled vehicle has also been proposed.

  In these techniques, when a pedestrian and a motorcycle are present around the own vehicle, it is difficult to predict the behavior of the monitored object because the object to be monitored is relatively small and the direction can be changed quickly. For this reason, it has been studied to accurately predict the actions of a pedestrian and a motorcycle (for example, see Patent Document 1).

JP 2009-53925 A

  However, the technology disclosed in Patent Literature 1 is intended for a pedestrian and a motorcycle existing around a host vehicle traveling on a road, and pedestrians and a motorcycle in a parking lot are not studied. .

  In a service area or a parking area on an expressway, or in a large parking lot such as an outlet mall, pedestrians, motorcycles, and automobiles (including large trucks) are mixed. In addition, a parking lot is a place where normal traffic rules are more difficult to observe than a road. For this reason, the monitoring target of the own vehicle, particularly a motorcycle or a pedestrian, often behaves irregularly, and driving requires more attention than when traveling on a road. Furthermore, when the parking lot is congested, there are very many monitoring targets in a narrow area, and the environment becomes more complicated.

  For this reason, accurate prediction of the behavior of a motorcycle, which is particularly agile, is important for preventive safety.

  The present invention has been made in view of such a point, and provides a driving support device that can accurately predict the behavior of a straddle-type vehicle such as a motorcycle or a motorcycle that is present around a vehicle in a parking lot. One of the purposes is to provide.

One aspect of the driving support device of the present invention recognizes a saddle-ride type vehicle based on image information output from an imaging unit , and detects the saddle-ride type vehicle based on a driving posture of an occupant of the saddle-ride type vehicle. A traveling direction prediction unit that predicts a traveling direction, and a determination unit that determines whether the traveling direction of the saddle-ride type vehicle predicted by the traveling direction prediction unit affects the path of the own vehicle , The driving posture of the occupant is determined based on an outline extending from the head to the arm of the occupant .

  Advantageous Effects of Invention According to the present invention, it is possible to accurately predict the behavior of a straddle-type vehicle such as a motorcycle or a tricycle existing around a host vehicle in a parking lot.

It is a schematic diagram which shows the relationship between the own vehicle and another monitoring target in the service area of an expressway. It is a schematic structure figure of a driving support device concerning this embodiment. It is a figure showing the control flow of the driving support device concerning this embodiment. It is a figure showing the control flow of the driving support device concerning this embodiment. It is a figure showing the control flow of the driving support device concerning this embodiment. FIG. 2 is a schematic diagram showing a relationship between a host vehicle and a motorcycle. It is a figure showing the control flow of the driving support device concerning this embodiment. FIG. 2 is a schematic diagram showing a riding posture of a rider of a motorcycle. FIG. 2 is a schematic diagram showing a relationship between a host vehicle and a motorcycle. It is a figure showing the control flow of the driving support device concerning this embodiment. It is a figure showing the control flow of the driving support device concerning this embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following, an example in which the driving assistance device according to the present invention is applied to an automatic driving type four-wheeled vehicle will be described, but the application target can be changed without being limited to this. For example, the driving assistance device according to the present invention may be applied to other types of vehicles (for example, straddle-type vehicles such as non-self-driving four-wheeled vehicles and three-wheeled vehicles).

  A problem in a large parking lot to which the driving assistance device according to the present embodiment is applied will be described with reference to FIG. FIG. 1 is a schematic diagram showing a relationship between a host vehicle and another monitoring target in a service area of an expressway. As shown in FIG. 1, a large number of pedestrians 3, motorcycles 4, four-wheeled vehicles 5, sightseeing buses 6, and large trucks 7 are present ahead of the vehicle 2 entering the service area 1. .

  For example, in the service area 1, a motorcycle parking lot 10 for the motorcycle 4 is often provided near a toilet 9 attached to a shop 8. For this reason, when the pedestrian 3 who gets off the four-wheeled vehicle 5 and the sightseeing bus 6 goes to the toilet 9, a large number of pedestrians 3 and the motorcycle 4 are likely to be in a mixed state near the toilet 9.

  A rest bench 11 and a gas station 12 also exist around the two-wheeled parking lot 10, which is further complicated.

  In the vicinity of such a toilet 9, the driver of the host vehicle 2 may be distracted by a specific object in order to avoid oversight, and may overlook another object. For this reason, attention must be paid to the vicinity of the toilet 9 in order to ensure safety.

  In a driving support device using a detecting unit, when many detection targets are present in a narrow range at the same time (for example, when many pedestrians 3 and the motorcycle 4 are mixed around the own vehicle 2), the ultrasonic wave is used. In the detection of, even if many detection targets can be recognized at one time, it is very difficult to identify and manage the detection targets and predict an action. The same applies to detection by radar, and detection means using reflected waves is not suitable.

  When the host vehicle (automobile) 2 is an autonomous driving vehicle, accurate behavior prediction of the motorcycle 4 that makes a small turn and moves quickly is very important for accurate driving control.

  Therefore, as described above, the present inventor uses an imaging unit as a detection unit in order to realize accurate behavior prediction of the motorcycle 4 even in a situation where a large number of pedestrians 3 and the motorcycle 4 are mixed. Focusing on the parts before and after the motorcycle 4 and the posture of the occupant (rider) of the motorcycle 4, it has been found that the behavior of the motorcycle 4 is predicted, and the present invention has been completed.

  That is, the driving assistance device of the present invention is an imaging unit, which recognizes a saddle-ride type vehicle based on image information output from the imaging unit, and a component disposed on the front or rear surface of the saddle-ride type vehicle, or A traveling direction predicting means for predicting a traveling direction of the saddle-ride type vehicle based on a driving posture of an occupant of the saddle-ride type vehicle; and Determining means for determining whether or not it affects the course.

  The monitoring target of the driving assistance device of the present invention is a straddle-type vehicle such as a motorcycle and a motorcycle. A straddle-type vehicle is characterized in that it is smaller in size and more agile than an automobile.

  Hereinafter, embodiments of the present invention will be described in more detail with reference to the drawings. First, the configuration of the driving support device 100 according to the present embodiment will be described. FIG. 2 is a schematic configuration diagram of the driving support device according to the present embodiment. It is assumed that the vehicle 2 (see FIG. 1) to which the driving assistance device 100 is applied has a configuration (engine, tire, and the like) normally provided in a four-wheeled vehicle (automatically driven vehicle). Omitted. In the following description, a vehicle existing around the host vehicle 2 will be described as a motorcycle 4 (see FIG. 1).

  The driving support device 100 according to the present embodiment (see FIG. 2) includes a driving support information providing unit 101 that monitors the motorcycle 4, a driving control unit 102 that controls automatic driving of the vehicle 2, and an imaging unit 103. , A storage unit 104, a GPS reception unit 105, a gyro sensor 106, an acceleration sensor 107, a vehicle speed sensor 108, an alarm unit 109, and a deceleration unit 110.

  The driving support information providing unit 101 and the driving control unit 102 are provided in an ECU (Electronic Control Unit), and are configured by, for example, a processor that executes various processes.

  The storage unit 104 includes one or a plurality of storage media such as a read only memory (ROM) and a random access memory (RAM) depending on the application. The storage unit 104 stores information about a parking lot to be described later.

  The imaging unit 103 captures an image of the front of the host vehicle 2 and outputs image information. Specifically, the imaging unit 103 is configured by a CCD camera, and is provided, for example, in front of the host vehicle 2. Further, the imaging means 103 may be constituted by an infrared camera for night use.

  The image information captured by the imaging unit 103 is output to the driving support information providing unit 101. The driving support information providing unit 101 analyzes the image information, recognizes the motorcycle 4 and the person (including the pedestrian 3 (see FIG. 1) and the occupant of the motorcycle 4), and drives the occupant of the motorcycle 4. Are configured to be identified.

  In addition, as described later, the driving support information providing unit 101 includes a headlight, which is a component in front and behind the motorcycle 4, and a component disposed at the rear end of the muffler (for example, exhaust of the muffler shown in FIGS. 6 and 9). It is configured to recognize the mouth 4a).

  The driving support information providing means 101 includes a headlight disposed on the front of the motorcycle 4 or a component disposed on the rear end of the muffler disposed on the rear (for example, an exhaust port 4 a of the muffler) or the motorcycle 4. Is configured to function as a traveling direction predicting unit that predicts the course of the motorcycle 4 based on the driving posture of the occupant.

  Further, the driving support information providing unit 101 is configured to function as a determining unit that determines whether the predicted path of the saddle-ride type vehicle affects the path of the host vehicle 2. Then, the driving support information providing unit 101 outputs the determination result to the driving control unit 102 as driving support information.

  The driving control means 102 mainly executes automatic driving control of the own vehicle 2. It is configured to accelerate, decelerate, and steer the vehicle 2 based on outputs from the GPS receiving unit 105, the gyro sensor 106, the acceleration sensor 107, and the vehicle speed sensor 108. When the host vehicle 2 is a manually driven vehicle, the gyro sensor 106 is required to detect the traveling direction of the host vehicle 2, but the acceleration sensor 107 and the vehicle speed sensor 108 are not necessarily required.

  The driving control unit 102 is configured to cause the warning unit 109 to perform a warning according to the output (driving support information) from the driving support information providing unit 101 or to cause the deceleration unit 110 to decelerate the vehicle 2. ing.

  The alarm means 109 is for giving an alarm to the driver of the vehicle 2. The warning means 109 may be configured by, for example, a warning sound generator and a speaker, or may be configured by a display for displaying information related to a warning, for example, a display of a speedometer or a display of a navigation system.

  The speed reduction unit 110 reduces the speed of the host vehicle 2. An example of the deceleration unit 110 is a brake device that brakes the rotation of the wheels. Note that the deceleration means 110 is not limited to a brake device that operates in response to a direct operation by the driver, and may be automatically controlled by an ECU or the like such as a regenerative brake in a hybrid vehicle or an electric vehicle, an engine brake associated with a shift, and the like. Means to be performed.

  Further, the driving control unit 102 is configured to input the outputs from the GPS receiving unit 105, the gyro sensor 106, the acceleration sensor 107, and the vehicle speed sensor 108 to the driving support information providing unit 101.

  Next, a control flow of the driving assistance device according to the present embodiment will be described. FIGS. 3 to 5, FIG. 7, FIG. 10, and FIG. 11 are diagrams showing a control flow of the driving assistance device according to the present embodiment.

  In the following description, a case where a saddle-ride type vehicle is a motorcycle and one motorcycle 4 is recognized from image information and monitoring is performed will be described as an example. In practice, however, a plurality of motorcycles 4 are simultaneously operated. It is possible to recognize and monitor in parallel.

  First, as shown in FIG. 3, the driving support information providing unit 101 (see FIG. 2) determines whether the vehicle 2 is in a parking lot (ST101). This determination is made based on, for example, the vehicle position information (for example, coordinates) input from the GPS receiving unit 105 and the information about the parking lot stored in the storage unit 104 (for example, the coordinates of the service area 1 in the map data). Can be based on In addition, for example, it may be determined whether or not the vehicle is in the parking lot by using information from an external device such as a beacon or an RFID tag.

  In ST101, if the determination is NO, ST101 is repeated.

  If the determination in ST101 is YES, driving support information providing means 101 determines whether or not motorcycle 4 (see FIG. 1) has been detected based on the image information from imaging means 103 (ST102).

  In ST102, if the determination is NO, the process returns to ST101.

  In ST102, if the determination is YES, it is determined whether or not the detected motorcycle 4 has a possibility of starting (starting possibility determination processing). FIG. 4 shows an example of a flow of the departure possibility determination.

  In the departure possibility determining process, as shown in FIG. 4, first, the driving support information providing unit 101 determines whether or not there is a person near the motorcycle 4 (ST201). If the determination is NO, it is determined that there is no possibility of departure (ST202), and the process ends.

  In ST201, if the determination is YES, it is determined whether or not a person near motorcycle 4 is wearing a helmet (ST203). If the determination is NO, it is determined that there is no possibility of departure (ST202), and the process ends.

  In ST203, if the determination is YES, it is determined whether the headlights of motorcycle 4 are turned on (ST204). If the determination is YES, it is determined that there is a possibility that the motorcycle 4 will start (ST205). If the determination is NO, it is determined that there is no possibility of departure (ST202), and the process ends.

  The control flow described with reference to FIG. 4 is an example of the departure possibility determination processing, and it is possible to add and delete determination conditions and change the order.

  For example, when the determination is YES in ST204, it is not determined that there is a possibility of departure immediately, but after a predetermined time has elapsed, whether or not the person has taken off the helmet, whether or not the person has left the motorcycle 4 It is determined whether or not the headlights are turned off, and if both are NO, it may be determined that there is a possibility of starting (ST205).

  Here, the determination is performed based on the still image information at a certain point in time captured by the imaging unit 103, but the determination may be dynamic based on the moving image information captured by the imaging unit 103. . For example, in ST201, it may be determined whether a person is approaching or away from motorcycle 4. Further, in ST203, it may be determined whether or not a person is going to wear a helmet or whether to take off the helmet.

  Returning to FIG. 3, based on the result of the departure possibility determination process (ST103), the driving support information providing unit 101 determines whether or not it is determined that the motorcycle 4 may depart (ST104). If the determination is NO, the process returns to ST101. If the determination is YES in ST104, the process proceeds to ST105 shown in FIG.

  In ST105, it is determined whether or not a person near the motorcycle 4 (hereinafter, referred to as an occupant (rider)) is straddling the motorcycle 4. If the determination is NO, it is considered that the motorcycle 4 will not start immediately, but it cannot be determined that the motorcycle will not start. Therefore, the process returns to ST103 (see FIG. 3), and the processing from the start possibility determination processing is performed again to monitor. To continue.

  If the determination in ST105 is YES, driving support information providing means 101 determines whether or not the exhaust port of the muffler of motorcycle 4 has been recognized (ST106). Recognition of the exhaust port of the muffler means a state in which the exhaust port of the muffler is directly visible from the host vehicle 2 side, and therefore, a state in which the motorcycle 4 is traveling in the same direction as the host vehicle 2.

  In this state, it can be determined that the motorcycle 4 has no possibility of affecting the course of the host vehicle 2. However, the motorcycle 4 is agile, and may depart instantly and change directions. FIG. 6 is a schematic diagram illustrating a relationship between the host vehicle 2 and the motorcycle 4. In FIG. 6, solid arrows indicate the traveling directions of the own vehicle 2 and the motorcycle 4, and dashed lines indicate the shooting range of the own vehicle 2 by the imaging unit 103.

  As shown in FIG. 6, it is assumed that the motorcycle 4 changes its direction from the state in which the exhaust port 4 a of the muffler of the motorcycle 4 is directly seen from the own vehicle 2 and moves toward the own vehicle 2. . To cope with such a case, if the determination is YES in ST106 (see FIG. 5), the driving support information providing unit 101 proceeds to ST301 shown in FIG. 7 to determine whether a predetermined time has elapsed. After a predetermined time has elapsed (YES in ST301), it is determined whether the headlights of the motorcycle 4 can be seen (ST302). When the motorcycle 4 starts within a predetermined time and changes direction, the headlights become visible as shown in FIG. Therefore, if the determination is YES, the driving support information providing unit 101 determines that there is a direction change (ST303), proceeds to ST107 (see FIG. 5), and monitors the traveling direction of the motorcycle 4 described later.

  On the other hand, if the determination is NO in ST302, driving support information providing means 101 determines that motorcycle 4 is heading in the same direction, and returns to ST101 (see FIG. 3) to monitor motorcycle 4. finish.

  Returning to FIG. 5, the driving support information providing means 101 determines whether or not the headlights of the motorcycle 4 face the own vehicle 2 (ST107). If the determination is YES, the process proceeds to ST111 shown in FIG. 11, and it is determined that if the motorcycle 4 proceeds as it is, there is a great possibility that the motorcycle 4 will have an effect on the course of the host vehicle 2.

  On the other hand, in ST107, when the determination is NO and the headlight is not facing the own vehicle 2, the determination is made based on the driving posture of the occupant. First, the driving support information providing means 101 determines whether or not the occupant's riding posture can be recognized (ST108). If the determination is NO, the process returns to ST105, and monitoring of the motorcycle 4 is continued. To be able to recognize the occupant's riding posture refers to, for example, a state in which a contour line 62 (see FIG. 8A) extending across the arm along the head of the occupant 61 described later can be recognized.

  In ST108, if the determination is YES, it is determined whether or not the occupant's arm is extended forward of motorcycle 4 (ST109). FIG. 8 is a schematic diagram showing the riding posture of the occupant of the motorcycle. FIG. 8A shows a motorcycle 4 of a sports type, and FIG. 8B shows a motorcycle 4 of a naked type. In FIG. 8, arrows indicate the traveling direction of the motorcycle 4. As shown in FIG. 8A, in the motorcycle 4 of the sports type, it is determined whether or not the arm extends forward in the traveling direction of the motorcycle 4 based on the outline 62 extending from the head to the arm of the occupant 61. As shown in FIG. 8B, in the naked type motorcycle 4, when a two-seater rider is a driver sitting on the front seat from the head of the occupant 63 sitting on the rear seat. It is determined whether or not the arm extends forward in the traveling direction of the motorcycle 4 with reference to an outline 65 extending across the arm along the head of the occupant 64.

  If the determination is NO in ST109, the process returns to ST105, and the monitoring of the motorcycle 4 is continued.

  In ST109, if the determination is YES, the direction in which the arm is extended and the traveling direction of host vehicle 2 are compared, and it is determined whether the two intersect (ST110).

  Here, the direction in which the arm extends can be assumed to be the traveling direction of the motorcycle 4. The traveling direction of the host vehicle 2 can be obtained from the output of the gyro sensor 106 (see FIG. 2).

  In ST110, if the determination is YES, the process proceeds to ST111 (see FIG. 11), and it is determined that if the motorcycle 4 proceeds as it is, there is a great possibility that the motorcycle 4 will have an effect on the course of the vehicle 2.

  If the determination is NO in ST110, it is possible to determine that there is no possibility that the motorcycle 4 will affect the course of the vehicle 2 if the motorcycle 4 starts and goes straight ahead. However, the motorcycle 4 is agile, and may depart instantly and change directions. FIG. 9 is a schematic diagram illustrating a relationship between the host vehicle 2 and the motorcycle 4. In FIG. 9, solid arrows indicate the traveling directions of the own vehicle 2 and the motorcycle 4, and dashed lines indicate the photographing range of the own vehicle 2 by the imaging unit 103.

  As shown in FIG. 9, the motorcycle 4 departs and changes direction from the state where the motorcycle 4 is facing left when viewed from the own vehicle 2, and moves forward in the traveling direction of the own vehicle 2. It is assumed that To cope with such a case, if the determination is NO in ST110 (see FIG. 5), the driving support information providing unit 101 proceeds to ST401 shown in FIG. 10 and determines whether a predetermined time has elapsed. After the predetermined time has elapsed (YES in ST401), it is determined whether the exhaust port 4a of the muffler of the motorcycle 4 can be recognized (ST402). When the motorcycle 4 departs within a predetermined time and changes direction, the exhaust port 4a of the muffler becomes visible as shown in FIG. Therefore, if the determination is YES, the driving support information providing unit 101 determines that there is a direction change (ST403), returns to ST107 (see FIG. 5), and continues monitoring the motorcycle 4.

  In ST111 shown in FIG. 11, when it is determined that the motorcycle 4 has a high possibility of affecting the course of the vehicle 2, the driving support information providing unit 101 outputs a determination result to the driving control unit 102 (ST112). ).

  The driving control unit 102 causes the driver of the own vehicle 2 to display a warning sound or a warning by the warning unit 109 in accordance with the determination result input from the driving support information providing unit 101. Further, the operation control means 102 causes the speed reduction means 110 to reduce the speed to, for example, the slowest speed. Either warning or deceleration may be performed, or both may be performed.

  The order of each process shown in the control flow in the driving support device 100 described above is an example, and those skilled in the art can easily understand that the change can be made.

  As described above, according to the present embodiment, the motorcycle 4 is recognized based on the image information output from the imaging unit 103, and the headlights and exhaust ports of the muffler disposed before and after the motorcycle 4 are provided. Alternatively, the traveling direction of the motorcycle 4 is predicted based on the driving posture of the occupant of the motorcycle 4 and the result is used to determine whether or not the traveling direction of the vehicle 2 is affected.

  With such a configuration, since the imaging unit 103 is used as the detection unit, the detection unit using the reflected wave is not used, so that the configuration of the device is simple, compact, and easy to mount on the host vehicle 2.

  Further, since the driving support information providing means 101 uses the vehicle characteristics (arrangement of parts) of the motorcycle 4 and the driving posture of the occupant for the behavior prediction, it is easy to improve the accuracy of the determination while being simple. As a result, the behavior of the straddle-type vehicle in the parking lot can be predicted with a simple configuration, and the preventive safety effect can be easily improved.

  In addition, the driving support information providing unit 101 performs an action prediction by image processing and uses a small number of parameters. Therefore, the operation formula is simple, the calculation processing speed is easily increased, and the cost is advantageous.

  In addition, in a situation where there are a large number of pedestrians 3 and the motorcycle 4 such as in the vicinity of the toilet 9 in the service area 1, even if a large number of the motorcycles 4 are to be monitored, the behavior can be predicted in a short time, Driving support with improved preventive safety effects can be provided even during congestion.

  In addition, when a large number of pedestrians 3 and the motorcycle 4 coexist in front of the host vehicle 2, the driver generally tends to concentrate his attention on pedestrians in terms of preventive safety. However, in the present embodiment, since the driving support information providing unit 101 determines the behavior prediction of the motorcycle 4 and causes the driving control unit 102 to perform a warning or a deceleration, the preventive safety effect is easily increased.

  Further, in the above-described embodiment, as shown in FIG. 4, the occupant of the motorcycle 4 occupies the helmet (ST 203), whether or not the headlights are on (ST 204). The monitoring target of the behavior prediction shown in FIGS. 5, 7, 10, and 11 is narrowed down using a pattern, a routine, or a habit for ensuring safety. Accordingly, even in an environment where there are a large number of motorcycles 4 that can be monitored, such as a large parking lot, the load on the operation control unit 102 can be reduced, and the accuracy and processing speed of behavior prediction can be further increased.

  The present invention is not limited to the above embodiment, and can be implemented with various modifications. In the above embodiment, the size, shape, and the like illustrated in the accompanying drawings are not limited thereto, and can be appropriately changed without departing from the effects of the present invention. In addition, the present invention can be appropriately modified and implemented without departing from the scope of the object of the present invention.

  For example, in the above-described embodiment, in ST110 shown in FIG. Thus, it is determined whether or not the motorcycle 4 has a high possibility of affecting the course of the vehicle 2. However, the relative speed of the host vehicle 2 and the motorcycle 4 may be further taken into consideration. That is, it may be determined whether or not the motorcycle 4 has a great possibility of affecting the course of the host vehicle 2 based on whether or not there is a possibility that both will come into contact also from the viewpoint of timing. In this case, the driving support information providing unit 101 uses, for example, a stereo camera as the imaging unit 103, and calculates a relative speed with respect to the motorcycle 4 based on a change in distance for each image frame based on moving image information output from the stereo camera. Can be calculated.

  Further, in the above-described embodiment, the configuration is such that an alarm is issued to the host vehicle 2, but the present invention is not limited to this configuration. For example, the motorcycle 4 may emit a sound such as a horn. In this case, it is possible to call attention to the motorcycle 4 that may affect the course of the host vehicle 2.

  Further, in the above-described embodiment, the service area 1 of the expressway has been described as an example, but the present invention can be applied to a large parking lot such as a parking area and an outlet mall.

  As described above, the present invention can improve the accuracy of predicting the behavior of a saddle-ride type vehicle in an environment where a large number of pedestrians and straddle-type vehicles exist, such as a large parking lot, and achieve preventive safety. It has an effect, and is particularly useful for a driving assistance device for an automatic driving vehicle.

1 service area 2 own vehicle 3 pedestrian 4 motorcycle (saddle-riding type vehicle)
100 Driving support device 101 Driving support information providing means (traveling direction prediction means, determination means)
102 operation control means 103 imaging means 104 storage means 105 GPS receiving unit 106 gyro sensor 107 acceleration sensor 108 vehicle speed sensor 109 alarm means 110 deceleration means

Claims (4)

Recognizes the straddle-type vehicle on the basis of the image information output from the imaging unit, based on the occupant's driving position of the straddle-type vehicle, the traveling direction prediction means for predicting the traveling direction of the straddle type vehicle,
Determining means for determining whether or not the traveling direction of the saddle-ride type vehicle predicted by the traveling direction prediction means has an effect on the course of the own vehicle ;
A driving support device , wherein the driving posture of the occupant is determined based on an outline extending from the head to the arm of the occupant . An alarming unit for issuing an alarm to an occupant of the host vehicle when the determining unit determines that the traveling direction of the saddle-ride type vehicle predicted by the traveling direction estimating unit has an effect on the course of the host vehicle; The driving assistance device according to claim 1, further comprising: When the determination unit determines that the traveling direction of the saddle-ride type vehicle predicted by the traveling direction prediction unit has an effect on the course of the host vehicle, the determination unit further includes a deceleration unit that decelerates the host vehicle. The driving support device according to claim 1 or 2 , wherein: The driving support device according to any one of claims 1 to 3 , wherein the host vehicle is an automatic driving vehicle.

Images