JP2014021709A - Object position detecting device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an object position detecting device capable of estimating a position of an object in a front and rear direction with high accuracy even though it becomes difficult to determine the position in the front and rear direction of the object by a radar system.SOLUTION: An object position detecting device 1 includes: a radar device 2 for detecting a front and rear direction position of an object around an own vehicle; and a camera 3a for detecting a left and right direction position of the object around the own vehicle. The object position detecting device 1 detects the front and rear position and the left and right position of the object based on the detection results of the radar device 2 and the camera 3a. It includes: a radar failure determination unit 13 for performing a failure determination of the radar device 2, and if the radar device 2 is determined to have failed by the radar failure determination unit 13, it estimates a moving direction of the object by the camera 3a, and estimates the front and rear direction position of the object based on the estimated moving direction.

Description

  The present invention relates to an object position detection device for detecting the position of an object existing around a host vehicle.

  As an object recognition device that recognizes objects such as pedestrians and vehicles that exist in the vicinity of the host vehicle, for example, in the forward direction of the host vehicle, the presence of the object is detected using both the radar device and the camera, and the detection results of both are used. And a type for discriminating the type of object.

In Patent Document 1, the transmission output of the radar device is switched between large and small, and the detection result based on the reflected wave received at the small transmission output is removed from the detection result based on the reflected wave received at the large transmission output. Thus, a technique is described in which an object other than a vehicle is extracted, a pattern matching process is performed on the extracted object based on an image captured by a camera, and a determination is made as to whether or not the object is a pedestrian.
Here, since the radar apparatus generally detects an object based on the reflected wave, the accuracy of position determination in the front-rear direction of the object is high, but the accuracy of position determination in the left-right direction is low. On the other hand, the accuracy of the position determination in the left-right direction of the object increases.

JP 2005-157765 A

  By the way, in the above-described prior art, when it becomes difficult to determine the position of the object in the front-rear direction due to a failure of the radar apparatus or the like, the position of the previous front-rear direction is continued or the radar apparatus before the failure of the radar apparatus. The position of the object in the front-rear direction is estimated from the moving speed detected by the. For this reason, when the moving direction and speed of an object change, there exists a subject that it becomes difficult to estimate the position of the front-back direction of the object after a failure of a radar apparatus with high precision.

  Therefore, the present invention has been made in view of the above-described circumstances, and even when it is difficult to determine the position of the object in the front-rear direction by the radar device, the position of the object in the front-rear direction is accurately determined. An object position detection device that can be estimated is provided.

  In order to solve the above problem, the invention described in claim 1 is a reflected wave generated by transmitting an electromagnetic wave toward a predetermined range around the host vehicle and reflecting the electromagnetic wave by an object existing around the host vehicle. By receiving a radar apparatus (for example, the radar apparatus 2 in the embodiment) that detects the position of the object in the front-rear direction, and a camera that detects a predetermined range around the host vehicle and detects the position of the object in the left-right direction ( For example, an object position detection device (for example, the object position detection device 1 in the embodiment) that includes the camera 3a) in the embodiment and detects the front-rear and left-right positions of the object based on the detection results of the radar device and the camera. ) Includes a radar failure determination unit (for example, a radar failure determination unit 13 in the embodiment) that performs failure determination of the radar device. When the radar unit determines that the radar device has failed, the camera estimates the moving direction of the object, and estimates the front-rear direction position of the object based on the estimated moving direction. .

  The invention described in claim 2 is characterized in that the object is a pedestrian, and the front-rear direction position is estimated based on the movement direction estimated by the camera and the movement state of the pedestrian. .

  According to a third aspect of the present invention, the object is a pedestrian, and the front-rear direction position is estimated based on the movement direction estimated by the camera and the height of the pedestrian.

  According to a fourth aspect of the present invention, when the object is a pedestrian and the movement direction estimated by the camera is determined to be an oblique direction, based on the movement in the left-right direction detected by the camera. The front-rear direction position is estimated.

  In the invention described in claim 5, when at least one of the moving distance in the left-right direction and the moving speed detected by the camera is equal to or less than a predetermined value, the moving direction of the pedestrian is determined to be an oblique direction. It is characterized by that.

  According to the first aspect of the present invention, even when it is difficult to determine the position of the object in the front-rear direction by the radar apparatus due to a failure of the radar apparatus, the position of the object in the front-rear direction is accurately determined. Can be estimated.

  According to the invention described in claim 2, in addition to the movement direction of the pedestrian, the position of the pedestrian in the front-rear direction is estimated in consideration of the movement state of whether the pedestrian is walking or running. can do. For this reason, it is possible to estimate the position of the pedestrian in the front-rear direction at the time of failure of the radar apparatus with higher accuracy.

  According to the invention described in claim 3, in addition to the direction of movement of the pedestrian, the stride of the pedestrian is estimated based on the height of the pedestrian. Can be estimated. For this reason, it is possible to estimate the position of the pedestrian in the front-rear direction at the time of failure of the radar apparatus with higher accuracy.

  According to the invention described in claim 4, when the pedestrian is moving obliquely, this is misjudged as movement in the left-right direction or movement in the vertical direction, and the movement distance in the front-rear direction is excessive. Can be prevented from being largely estimated. For this reason, even if the pedestrian is moving diagonally, the position of the pedestrian in the front-rear direction can be estimated with high accuracy.

  According to the invention described in claim 5, it is possible to determine with high accuracy whether or not the pedestrian is moving obliquely.

It is a block diagram of the object position detection apparatus in the embodiment of the present invention. The pedestrian extraction part in embodiment of this invention is shown, (a), (b) is explanatory drawing at the time of performing matching. It is explanatory drawing which shows an example of the image pattern in embodiment of this invention. It is a flowchart which shows the processing method of the object position detection apparatus in embodiment of this invention. It is explanatory drawing in the case of judging that the pedestrian is moving diagonally in embodiment of this invention.

(Object position detection device)
Next, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram of an object position detection apparatus.
As shown in FIG. 1, the object position detection device 1 uses, for example, a driving force of an internal combustion engine 21 as a driving source to transmit a transmission (T / M) 22 such as an automatic transmission (AT) or a continuously variable automatic transmission (CVT). It is mounted on a vehicle that travels by being transmitted to the drive wheels of the vehicle via the. The vehicle includes a brake actuator 23, a steering actuator 24, and a notification device 25 in addition to the object position detection device 1.
In the following description, the forward and rearward directions of the vehicle are simply referred to as the front-rear direction, and the left-right direction toward the vehicle-travel direction is simply referred to as the left-right direction.

The object position detection device 1 includes a radar device 2, a camera unit 3, a host vehicle state sensor 4, and an electronic control device 10.
The radar device 2 transmits an electromagnetic wave such as a laser beam or a millimeter wave toward the front in the traveling direction of the host vehicle, and the transmitted electromagnetic wave is an object outside the host vehicle (for example, a structure, a pedestrian, another vehicle). Etc.) is received, and the transmitted electromagnetic wave and the received electromagnetic wave (reflected wave) are mixed to generate a beat signal and output to the electronic control unit 10.

  The camera unit 3 includes a camera 3a composed of a CCD camera or a CMOS camera, and an image processing unit 3b. The image processing unit 3b performs predetermined image processing, such as filtering and binarization processing, on the image of the external world ahead of the traveling direction of the host vehicle obtained by capturing with the camera 3a. Image data is generated and output to the electronic control unit 10.

  The host vehicle state sensor 4 includes, as vehicle information about the host vehicle, for example, a vehicle speed sensor that detects the speed (vehicle speed) of the host vehicle, a yaw rate sensor that detects a yaw rate (rotational angular velocity about the vertical axis of the center of gravity of the vehicle), steering, A steering angle sensor that detects an angle (direction and magnitude of a steering angle input by the driver) and an actual steering angle (steering angle) according to the steering angle, a steering torque sensor that detects steering torque, and an artificial satellite, for example Positioning signals such as GPS (Global Positioning System) signals for measuring the position of the vehicle using GPS, position signals transmitted from information transmission devices outside the host vehicle, and other appropriate gyro sensors and acceleration sensors Position sensors that detect the current position and traveling direction of the vehicle, sensors that detect the amount of depression of the accelerator pedal, It includes a sensor that detects the depression state of the key pedal. The own vehicle state sensor 4 outputs a vehicle information signal corresponding to the detected information to the electronic control device 10.

The electronic control device 10 includes an object detection unit 11, a pedestrian extraction unit 12, a radar failure determination unit 13, a longitudinal position estimation unit 14, a pedestrian information integration unit 15, and a vehicle control unit 16.
The object detection unit 11 calculates the position, speed, reflection level, and the like of the object that reflected the electromagnetic wave based on the beat signal input from the radar device 2. Then, the calculated information is output to the radar failure determination unit 13 as the front-rear direction position information of the object (hereinafter simply referred to as front-rear position information) and also output to the pedestrian extraction unit 12. Note that the speed of the object can be calculated from the relative speed of the host vehicle detected by the radar device 2 with a time difference and calculated based on the position information of the object, and the speed of the host vehicle.

FIG. 2A and FIG. 2B are explanatory diagrams of the pedestrian extraction unit 12.
As shown in FIGS. 1 and 2A, image data D <b> 1 is input from the camera unit 3 to the pedestrian extraction unit 12, and position information of the object is input from the object detection unit 11. The pedestrian extraction unit 12 sets a region R1 of a predetermined size centered on the input position information (hereinafter referred to as an integrated range R1), and an object B1 in the integrated range R1 and a pedestrian extraction unit in advance. 12 is matched with the pedestrian image pattern P1 stored in FIG.

FIG. 3 is an explanatory diagram illustrating an example of an image pattern.
As shown in the figure, the image pattern P1 is large and includes an adult pattern set to a predetermined height and a child pattern set to a low height. Adult patterns and children's patterns can be sorted by stride, etc. in addition to height.
In addition, each of the adult pattern and the child pattern includes a plurality of image patterns P1 facing in the left-right direction, the front-rear direction, and the diagonal direction in the stationary state, the walking state, the running state, and the walking state and the running state. There is. The orientation of the pedestrian can be determined from the orientation of the body, face, feet, etc.

The pedestrian extraction unit 12 performs matching between the plurality of image patterns P1 and the object B1 in the integrated range R1, and determines whether or not the object B1 is a pedestrian. When it is determined that the object B1 is a pedestrian, the pedestrian information indicating which pedestrian state, that is, which image pattern P1 is matched, is sent to the radar failure determination unit 13 and the pedestrian information integration unit 15. Output.
For the diagonal movement, the image pattern P1 is not prepared, and the pedestrian moves diagonally according to the difference between the predetermined horizontal movement speed and the actually detected horizontal movement speed. It is also possible to judge that Details of this will be described later.

In addition, as shown in FIG. 2B, the pedestrian extraction unit 12 does not receive position information from the object detection unit 11 and cannot identify the integrated range R1. The object B1 is compared with the pedestrian image pattern P1, and it is determined whether or not the object B1 on the image data D1 is a pedestrian. Also in this case, when it is determined that the object B1 on the image data D1 is a pedestrian, the pedestrian information is output to the radar failure determination unit 13 and the pedestrian information integration unit 15.
Furthermore, when it is determined that the object B1 on the image data D1 is a pedestrian, the pedestrian extraction unit 12 integrates the pedestrian's left-right direction position information (hereinafter simply referred to as left-right position information) into pedestrian information integration. To the unit 15.

  The radar failure determination unit 13 determines whether or not the radar device 2 has failed. Specifically, when the determination result that the pedestrian is detected is input from the pedestrian extraction unit 12 even though the position information is not input from the object detection unit 11 (in the state shown in FIG. 2B). In the case), it is determined that the radar device 2 is out of order. That is, when the front / rear position information is not input from the object detection unit 11 on the image data from the camera unit 3 even though the pedestrian is detected, the position information of the object is detected due to the failure of the radar device 2. It is determined that cannot be obtained. A determination result when it is determined that the radar device 2 is out of order is output to the front-rear direction position estimation unit 14 and also to the pedestrian information integration unit 15.

  On the other hand, when the front and rear position information from the object detection unit 11 is input to the radar failure determination unit 13 and the determination result that the pedestrian is detected from the pedestrian extraction unit 12 is input (FIG. 2 ( In the case of the state shown in a)), it is determined that the radar apparatus 2 has not failed. The determination result when it is determined that the radar device 2 is not broken is output to the pedestrian information integration unit 15 together with the front / rear position information of the object detection unit 11.

  When the determination result that the radar apparatus 2 is not broken is input from the radar failure determination unit 13 to the pedestrian information integration unit 15, the front and rear position information of the object detection unit 11 input together with the determination result, and the walking The position of the pedestrian is obtained based on the left and right position information input from the person extraction unit 12. Then, the position information of the pedestrian is output to the vehicle control unit 16.

  On the other hand, the pedestrian information integration unit 15 receives the front / rear position information estimated by the front / rear direction position estimation unit 14 when the determination result that the radar apparatus 2 is broken is input from the radar failure determination unit 13. The position of the pedestrian is obtained based on the front-rear position information and the left-right position information input from the pedestrian extraction unit 12 with reference to the reference. The reference method of the front-rear position information estimated by the front-rear direction position estimation unit 14 is as follows.

  Here, first, the front-rear direction position estimation unit 14 will be described. The front-rear direction position estimation unit 14 receives front-rear position information immediately before the radar apparatus 2 fails through the radar failure determination unit 13. The front-rear direction position estimation unit 14 has a map in which each pedestrian information is associated with the estimated pedestrian movement speed. In this map, when an adult pedestrian is walking and moving in the front-rear direction, the moving speed is set to 1.5 m / s, for example. On the other hand, when an adult pedestrian is moving while running in the front-rear direction, the moving speed is set to 3 m / s, for example. On the other hand, when the child pedestrian is walking and moving in the front-rear direction, the moving speed is set to 1 m / s, for example. Further, when the child pedestrian is moving in the front-rear direction, the moving speed is set to 2 m / s, for example. These moving speed settings can be changed as appropriate.

  And the pedestrian information integration part 15 is based on the pedestrian information input from the pedestrian extraction part 12, when the judgment result that the radar apparatus 2 is out of order is input from the radar failure determination part 13. The position of the pedestrian is obtained by referring to the map of the front-rear direction position estimation unit 14 and the front-rear position information immediately before the radar apparatus 2 breaks down. Then, the position information of the pedestrian is output to the vehicle control unit 16. Here, a more specific method for calculating the position of the pedestrian at the time of failure of the radar apparatus 2 will be described later.

The vehicle control unit 16 responds to the position information of the pedestrian obtained by the pedestrian information integration unit 15 and, for example, if the pedestrian may contact the own vehicle, the vehicle control unit 16 avoids the contact. To control the running. For example, the vehicle control unit 16 includes a control signal for controlling the driving force of the internal combustion engine 21, a control signal for controlling the speed change operation of the transmission 22, a control signal for controlling the deceleration operation by the brake actuator 23, and the steering actuator 24. At least one of the control signals for controlling the steering operation of the steering mechanism (not shown) of the host vehicle is output, and deceleration control or steering control of the host vehicle is executed as the contact avoiding operation.
Further, the vehicle control unit 16 controls at least one of the alarm output timing and the output content by the notification device 25 according to the degree of possibility of contact with the pedestrian.

(Processing method of object position detection device)
Next, a processing method of the object position detection apparatus 1 will be described based on FIGS.
FIG. 4 is a flowchart illustrating a processing method of the object position detection apparatus.
As shown in FIGS. 1 and 4, based on the beat signal input from the radar device 2, the object detection unit 11 first calculates the position, speed, reflection level, and the like of the object B <b> 1 that reflects the electromagnetic wave. Then, the front-rear position information of the object B1 is obtained from the calculated information (ST101).

Next, based on the image data D1 obtained by the camera unit 3 (see FIG. 2A), the pedestrian extraction unit 12 detects a pedestrian and obtains left and right position information of the pedestrian (ST102).
Subsequently, whether or not the radar failure determination unit 13 cannot match the object B1 within the integrated range R1 specified by the radar device 2 and the object B1 (pedestrian) on the image data D1 obtained by the camera unit 3 is determined. Is determined (ST103).

  When the determination in ST103 is “No”, that is, matching between the object B1 within the integrated range R1 specified by the radar apparatus 2 and the object B1 (pedestrian) on the image data D1 obtained by the camera unit 3 is performed. If it is determined that it is possible, the pedestrian information integration unit 15 obtains the position of the pedestrian based on the front and rear position information and the left and right position information (ST104). Thereby, the process of the object position detection apparatus 1 is completed.

  On the other hand, when the determination in ST103 is “Yes”, that is, when the pedestrian is detected by the camera unit 3 even though the integrated range R1 is not specified, the left and right position information of the pedestrian is the pedestrian extraction unit. Although the position information is determined based on the information obtained in step 12, the front-rear position information is estimated by the front-rear direction position estimation unit 14 and the pedestrian information integration unit 15 (ST200).

In ST200, first, the pedestrian information integration unit 15 obtains pedestrian information from the pedestrian extraction unit 12 (ST201). That is, the pedestrian information integration unit 15 is information regarding which image pattern P1 is matched with the object B1 detected by the camera unit 3 among the plurality of image patterns P1 stored in the pedestrian extraction unit 12 in advance. (See FIG. 3).
Then, the matched image pattern P1 is used as pedestrian information, and based on this pedestrian information, the front-rear direction position estimation unit 14 is referred to, and the front-rear position information is estimated.

Specifically, if the pedestrian information obtained by the pedestrian information integration unit 15 is stationary or moving in the left-right direction, it is not moving in the front-rear direction. Regardless, the front-rear position information immediately before the radar apparatus 2 fails is used as it is (ST202).
Note that the front-rear position information immediately before being used at this time is that the object B1 detected before the radar device 2 breaks down is determined by the pedestrian extraction unit 12 to be a pedestrian (the pedestrian is detected). Needless to say, this is the position information of the front and rear of the reflection level. The same applies to the case of “previous position information before and after”.

  Next, the case where the pedestrian information obtained by the pedestrian information integration unit 15 is moving in the front-rear direction will be described. In this case, the moving speed of the pedestrian is estimated by referring to the front-rear direction position estimating unit 14 depending on whether the pedestrian is an adult or a child, and whether the pedestrian is walking or running. Then, the estimated integrated value of the moving speed is added to the front / rear position information immediately before the radar apparatus 2 breaks down to obtain the current front / rear position information (ST203).

Next, a case where the pedestrian information obtained by the pedestrian information integration unit 15 is moving in an oblique direction will be described.
Here, based on FIG. 5, the case where it is judged that the pedestrian is moving in the diagonal direction will be described in detail. FIG. 5 is an explanatory diagram when it is determined that the pedestrian is moving obliquely.
First, the front-rear direction position estimation unit 14 sets and stores the front-rear direction moving speed for each pedestrian information. In addition, the left-right direction moving speed is also used for adults, children, walking, and running. It is set and stored accordingly. In the following description, the lateral movement speed stored in advance in the front-rear direction position estimation unit 14 is referred to as a predetermined lateral movement speed value.

  Usually, the front-rear direction position estimation unit 14 does not use a predetermined left-right direction moving speed value, but uses left-right position information obtained from the camera unit 3. However, when the pedestrian moves diagonally, the moving speed in the front-rear direction of the pedestrian is estimated based on a predetermined horizontal moving speed value.

That is, as shown in FIG. 4, for example, when a pedestrian is walking while moving diagonally, the moving speed component b in the left-right direction can be obtained from the moving speed a of the diagonal walking. This moving speed component b becomes slower than a predetermined left-right moving speed value b ′.
Here, in the case where it is determined that the pedestrian is walking diagonally, the case where the image pattern P1 (see FIG. 3) is referred to is described above. However, the pedestrian's horizontal movement speed component b and a predetermined horizontal movement speed are described. It is also possible to determine that the pedestrian is walking diagonally according to the difference from the value b ′.

Subsequently, the predetermined left-right direction moving speed value b ′ and the moving speed a of the oblique walking are set to the same speed. When the moving speed component in the front-rear direction of the pedestrian is c, the moving speed component c is
c = √ (a2-b2) (1)
Calculated by

  The moving speed component c calculated by the equation (1) is estimated as the moving speed in the front-rear direction of the pedestrian. Then, the integrated value of the estimated moving speed component c is added to the front-rear position information immediately before the radar apparatus 2 breaks down to obtain the current front-rear position information (ST204). Thereby, the process of the object position detection apparatus 1 is completed.

(effect)
Therefore, according to the above-described embodiment, even if it is difficult for the radar apparatus 2 to determine the position of the object B1 in the front-rear direction due to a failure of the radar apparatus 2, the front-rear position information of the pedestrian is increased. The accuracy can be estimated.

  Further, pedestrian information is obtained by matching the image data D1 obtained from the camera unit 3 with the pedestrian image pattern P1 stored in the pedestrian extraction unit 12, and based on this pedestrian information. The position of the pedestrian in the front-rear direction after the failure of the radar apparatus 2 is estimated. That is, the position in the front-rear direction of the pedestrian can be estimated in consideration of the movement state such as whether the pedestrian is walking or running. For this reason, even if it is difficult for the radar device 2 to determine the position of the object B1 in the front-rear direction, the front-rear position information of the pedestrian can be obtained with higher accuracy.

  Furthermore, the pedestrian image pattern P1 is divided into an adult pattern and a child pattern according to the height and stride (see FIG. 3), and the front-rear direction position estimation unit 14 separates the adult pattern from the child pattern. The moving speed is set to. For this reason, the moving speed in the front-rear direction of the pedestrian after the failure of the radar apparatus 2 can be estimated with high accuracy.

  And when the pedestrian information which the pedestrian information integration part 15 was obtained is the state which is moving in the diagonal direction, based on the moving speed component b (refer FIG. 5) of the left-right direction of a pedestrian, pedestrian information Estimate front and rear position information. For this reason, when a pedestrian is moving diagonally, this is misjudged as a movement in the left-right direction or a movement in the front-rear direction, and the movement distance in the front-rear direction is excessively large. Can be prevented. Therefore, even if the pedestrian is moving diagonally, the position of the pedestrian in the front-rear direction can be estimated with high accuracy.

  In addition, when the pedestrian is walking and moving diagonally, the horizontal movement speed component b is compared with a predetermined horizontal movement speed value b ′ to determine that the pedestrian is walking diagonally. This makes it possible to determine with high accuracy whether or not the pedestrian is moving diagonally. That is, even when the pedestrian is walking diagonally, for example, by referring to the image pattern P1, it is determined that the pedestrian is walking in the left-right direction. By comparing the speed component b and the predetermined lateral movement speed value b ′ to determine the state of the pedestrian, erroneous determination of the object position detection device 1 can be prevented. For this reason, the highly reliable object position detection apparatus 1 can be provided.

The present invention is not limited to the above-described embodiment, and includes various modifications made to the above-described embodiment without departing from the spirit of the present invention.
For example, in the above-described embodiment, the description has been given of the case where the front-rear position information of the pedestrian is estimated when the position determination of the front-rear direction of the object B1 by the radar device 2 becomes difficult. However, the present invention is not limited to this, and the present invention can also be applied to the case where the front-rear position information of another moving body such as a vehicle is estimated instead of the pedestrian. In this case, an image pattern such as the direction of the vehicle may be prepared as the image pattern P1.

  Moreover, in the above-described embodiment, the case where the object position detection device 1 is used for travel control for avoiding contact between the host vehicle and the object B1 (pedestrian) has been described. However, the present invention is not limited to this, and various types of control that the own vehicle can take with respect to the specific object B1, such as follow-up running control in which the specific object B1 is a preceding vehicle and the own vehicle follows the preceding vehicle. Is possible.

DESCRIPTION OF SYMBOLS 1 Object position detection apparatus 2 Radar apparatus 3 Camera unit 3a Camera 13 Radar failure determination part 14 Front-back direction position estimation part B1 Object

Subsequently, the predetermined left-right direction moving speed value b ′ and the moving speed a of the oblique walking are set to the same speed.
When the moving speed component in the front-rear direction of the pedestrian is c, the moving speed component c is
c = √ (a ² −b ² ) (1)
Calculated by

Claims (5)

A radar device that detects an anteroposterior position of the object by transmitting an electromagnetic wave toward a predetermined range around the host vehicle and receiving a reflected wave generated by the reflection of the electromagnetic wave by an object existing around the host vehicle; ,
An image of a predetermined range around the host vehicle, and a camera that detects a position in the left-right direction of the object,
In the object position detection device that detects the front-rear and left-right positions of the object based on the detection results of the radar device and the camera,
A radar failure determination unit that performs failure determination of the radar device,
When the radar failure determination unit determines that the radar device has failed, the moving direction of the object is estimated by the camera, and the front-rear direction position of the object is estimated based on the estimated moving direction. An object position detecting device characterized by the above. The object is a pedestrian;
The object position detection device according to claim 1, wherein the front-rear direction position is estimated based on the movement direction estimated by the camera and the movement state of the pedestrian. The object is a pedestrian;
The object position detection apparatus according to claim 1, wherein the front-rear direction position is estimated based on the movement direction estimated by the camera and the height of the pedestrian. The object is a pedestrian;
The front-rear direction position is estimated based on movement in the left-right direction detected by the camera when it is determined that the movement direction estimated by the camera is an oblique direction. The object position detection apparatus according to claim 3.   5. The moving direction of the pedestrian is determined to be an oblique direction when at least one of a moving distance and a moving speed detected by the camera is equal to or less than a predetermined value. The object position detection apparatus described in 1.

Images