Object recognition device, vehicle, and object recognition method

Abstract

The present invention provides an object recognition device, a vehicle, and an object recognition method that can stably recognize an object. The object recognition device includes: a recognition unit that, when a detection wave transmitted from a moving body to an object is reflected by the object and received by the moving body, recognizes whether the object is a control target object based on a comparison result between the reflection intensity of the detection wave and a recognition threshold; and a change unit that, when the detection wave is reflected by at least two points of the object and received by the moving body, changes the recognition sensitivity of the recognition unit according to the positions of the at least two points.

Description

Technical Field

[0001] The present invention relates to an object recognition device, a vehicle, and an object recognition method. Background Art

[0002] Conventionally, there has been known an object recognition device that can detect an object based on the round-trip of a detection wave between a moving body such as a vehicle and the object. For example, Patent Document 1 discloses the following configuration in which the reflection intensity of the detection wave can be corrected according to the height of the object and the distance from the vehicle to the object, and the type of the object is recognized based on the corrected reflection intensity.

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2012-247215 Summary of the Invention

[0006] Problems to be Solved by the Invention

[0007] However, the reflection intensity of the detection wave may deviate due to external disturbances (e.g., wind, rain, heat, etc.) or the change trend of the reflection intensity caused by the distance may be different depending on the shape of the object. Therefore, if only the reflection intensity is adjusted, it may not be possible to stably recognize the object.

[0008] An object of the present invention is to provide an object recognition device, a vehicle, and an object recognition method that can stably recognize an object.

[0009] Means for Solving the Problems

[0010] An object recognition device according to an embodiment of the present invention includes: a recognition unit that recognizes whether the object is a control target object based on a comparison result between the reflection intensity of the detection wave and a recognition threshold when the detection wave transmitted from the moving body to the object is reflected by the object and received by the moving body; and a change unit that changes the recognition sensitivity of the recognition unit according to the positions of at least two points when the detection wave is reflected by at least two points of the object and received by the moving body.

[0011] A vehicle according to an embodiment of the present invention includes: the above-described object recognition device; a wave transmitting sensor that transmits the detection wave; and at least two wave receiving sensors that receive the detection wave.

[0012] The object recognition method according to an embodiment of the present invention has the following steps: when a detection wave transmitted from a moving body to an object is reflected by the object and received by the moving body, based on the comparison result between the reflection intensity of the detection wave and an identification threshold value, identifying whether the object is a control target object. In this step, when the detection wave is reflected by at least two points of the object and received by the moving body, the identification sensitivity is changed according to the positions of the at least two points.

[0013] Effect of the Invention

[0014] According to an embodiment of the present invention, an object can be stably recognized. Description of the Drawings

[0015] Figure 1 It is a block diagram showing a structural example of a vehicle of a vehicle control unit to which an embodiment of the present invention is applied.

[0016] Figure 2 It is a diagram showing an example of the arrangement of an object detection unit in a vehicle.

[0017] Figure 3 It is a diagram for explaining a general method of setting an identification threshold value for the reflection intensity.

[0018] Figure 4 It is a diagram for explaining the relationship between a lower object and a detection wave.

[0019] Figure 5 It is a diagram showing an example of the change in the reflection intensity of a lower object with distance.

[0020] Figure 6 It is a diagram showing an example of the path of a detection wave when the object is a columnar object.

[0021] Figure 7 It is a diagram showing an example of the relationship between a shape determination threshold value and distance.

[0022] Figure 8 It is a diagram showing an example of the relationship between the reflection intensity of a columnar object and an identification threshold value.

[0023] Figure 9 It is a flowchart showing an operation example of identification control in a vehicle control unit.

[0024] Figure 10 It is a diagram showing an example of the arrangement of an object detection unit in a vehicle.

[0025] Description of Reference Numerals

[0026] 1 Vehicle

[0027] 10 Acceleration Unit

[0028] 20 Braking unit

[0029] 30 Vehicle speed information acquisition unit

[0030] 40 Object detection unit

[0031] 41 Transmission wave sensor

[0032] 42 Reception wave sensor

[0033] 100 Vehicle control unit

[0034] 110 Identification unit

[0035] 120 Shape determination unit

[0036] 130 Change unit

[0037] 140 Control unit Detailed implementation mode

[0038] (Implementation mode)

[0039] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Figure 1 It is a block diagram showing a structural example of a vehicle 1 of a vehicle control unit 100 to which an embodiment of the present invention is applied.

[0040] As Figure 1 shown, the vehicle 1 is a moving body having, for example, a function of identifying whether there is a possibility of the vehicle 1 colliding with an object existing around the traveling path. The vehicle 1 has an acceleration unit 10, a braking unit 20, a vehicle speed information acquisition unit 30, an object detection unit 40, and a vehicle control unit 100.

[0041] The acceleration unit 10 is an acceleration device that accelerates and decelerates the vehicle 1 according to an acceleration request from the vehicle control unit 100.

[0042] The braking unit 20 is a braking device that brakes the vehicle 1 according to a braking request from the vehicle control unit 100.

[0043] The vehicle speed information acquisition unit 30 acquires information related to the speed of the vehicle 1. Specifically, the vehicle speed information acquisition unit 30 acquires information on the vehicle speed and acceleration of the vehicle 1 from the acceleration unit 10 and the like, and acquires information such as braking information from the braking unit 20 and the like. In addition, the vehicle speed information acquisition unit 30 acquires information such as a steering angle from an operation unit such as a steering wheel (not shown).

[0044] The object detection unit 40 is, for example, an in-vehicle sensor such as a sonar or a radar. By transmitting detection waves such as ultrasonic waves or millimeter waves (electromagnetic waves) and receiving the detection waves reflected by an object and returned, it detects an object existing around the traveling path of the vehicle 1. The object detection unit 40 is provided at the front end or the rear end of the vehicle 1. For example, it includes a transmitting wave sensor 41 and two receiving wave sensors 42.

[0045] Figure 2 FIG. is an example showing the configuration of the object detection unit 40 in the vehicle 1. In addition, in the following description, an orthogonal coordinate system (X, Y, Z) is used. The same orthogonal coordinate system (X, Y, Z) is also used in the figures described later. For example, the X direction represents the left-right direction of the vehicle 1, the Y direction represents the front-rear direction (traveling direction) of the vehicle 1, and the Z direction represents the up-down direction (height direction) of the vehicle 1.

[0046] For example, as Figure 2 shown, at the + side end in the Y direction of the vehicle 1, the object detection unit 40 has a total of four sensors, one at each of the two ends in the X direction, and two at the center in the X direction. The transmitting wave sensor 41 is, for example, the sensor arranged on the - side among the two sensors at the center in the X direction. The receiving wave sensor 42 is the sensor arranged at the - side end in the X direction and the sensor arranged on the + side among the two sensors at the center in the X direction.

[0047] The transmitting wave sensor 41 is a sensor that transmits detection waves. For example, in the case of a sonar, by applying a voltage of a specified frequency to a piezoelectric element, ultrasonic waves (detection waves) of the same frequency are generated and transmitted. In addition, the transmitting wave sensor 41 can also be configured to be able to receive the transmitted detection waves.

[0048] The receiving wave sensor 42 is a sensor that receives the detection waves reflected by the object 2 after being transmitted from the transmitting wave sensor 41. For example, in the case of a sonar, the receiving wave sensor 42 converts the sound pressure of the detection wave into a voltage through a piezoelectric element and rectifies the converted voltage, thereby converting the received detection wave into an acoustic wave reception intensity (reflection intensity). In addition, the receiving wave sensor 42 can also be configured to be able to transmit detection waves.

[0049] By measuring the round-trip flight time of the detection waves from the transmitting wave sensor 41 via the object 2 to the receiving wave sensor 42, the distance between the vehicle 1 and the object 2 can be calculated. In addition, by calculating the distance between the vehicle 1 and the object 2, based on the principle of triangulation, the coordinates of the position where the detection wave is reflected by the object 2 can be calculated.

[0050] In addition, since two wave-receiving sensors 42 are provided, the detection wave transmitted from the wave-transmitting sensor 41 can be received by the two wave-receiving sensors 42 respectively. Therefore, the detection waves received by the two wave-receiving sensors 42 are the detection waves that return to each wave-receiving sensor 42 through different paths D1 and D2 respectively.

[0051] In paths D1 and D2, the detection waves are reflected at different positions P1 and P2 of the object 2. Therefore, when the detection waves can be received by the two wave-receiving sensors 42, the two coordinates at the positions P1 and P2 of the object 2 can be calculated. In addition, Figure 2 the object 2 in [[ ]] is a wall having a plane parallel to the X direction.

[0052] Return to Figure 1 , the vehicle control unit 100 is, for example, an ECU (Electronic Control Unit), etc., and includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and an input / output circuit (not shown). The vehicle control unit 100 identifies whether an object existing around the traveling path is a control object (for example, an object that may be collided with) based on a preset program, and performs prescribed driving control.

[0053] The vehicle control unit 100 includes an identification unit 110, a shape determination unit 120, a change unit 130, and a control unit 140. The identification unit 110, the shape determination unit 120, and the change unit 130 correspond to the "object identification device" of the present invention.

[0054] When the detection wave transmitted from the vehicle 1 to the object is reflected by the object and received by the vehicle 1, the identification unit 110 identifies whether the object is a control object based on the comparison result between the reflection intensity of the detection wave and the identification threshold.

[0055] Specifically, when the reflection intensity of the detection wave received by the wave-receiving sensor 42 is equal to or higher than the identification threshold, the identification unit 110 identifies that the object is a control object, and when the reflection intensity is lower than the identification threshold, the identification unit 110 identifies that the object is a non-control object, that is, an object that is not a control object. In addition, when the wave-transmitting sensor 41 receives the transmitted detection wave, the identification unit 110 identifies whether the object is a control object according to the reflection intensity of the detection wave received by the wave-transmitting sensor 41.

[0056] The recognition threshold is a threshold that functions as a recognition criterion for identifying whether an object is a control target (obstacle) of the vehicle 1 by comparing it with the reflection intensity of the detection wave received by the wave receiving sensor 42. In the recognition unit 110, if the reflection intensity is equal to or greater than the recognition threshold, the object is recognized as a control target.

[0057] In addition, since the detection wave attenuates rapidly in the air, the longer the distance between the vehicle 1 and the object, the greater the attenuation of the detection wave. Therefore, for example, as Figure 3 shown, the reflection intensity of the detection wave received by the wave receiving sensor 42 also decreases as the distance between the vehicle 1 and the object increases. Therefore, generally, in accordance with this reflection intensity, the recognition threshold is set such that the longer the distance between the vehicle 1 and the object, the lower the recognition threshold.

[0058] However, for a lower object such as a curb, due to the relationship between the incident angle and the reflection angle of the detection wave, the change trend of the reflection intensity with distance will be different from Figure 3 such a change trend. For example, as Figure 4 shown, when there is a lower object 2A close to the vehicle 1, the lower object 2A is located at a position where the detection wave transmitted from the wave transmitting sensor 41 is not easily reachable. Therefore, the reflection intensity of the lower object 2A at a relatively close position will be small.

[0059] In contrast, if there is a lower object 2B at a position far from the vehicle 1, the detection wave is easily reachable, and in addition, the detection wave reflected by the lower object 2B is also easily incident on the wave receiving sensor 42. Therefore, the reflection intensity will be large. Specifically, as Figure 5 shown, the change trend of the reflection intensity with distance becomes as follows: as the distance is increased from the position at a distance T1, the reflection intensity gradually rises, and after the reflection intensity reaches the maximum value at a distance T2, the reflection intensity gradually decreases.

[0060] Therefore, if the recognition threshold is set to decrease as the distance is increased as Figure 3 shown, the reflection intensity of the lower object will exceed the recognition threshold. Since the lower object is located on the road surface and has a height that does not collide with the main body of the vehicle 1, it is an object that will not become an obstacle (non-control target). Such a lower object may be recognized as a control target due to the emphasized reflection intensity. In addition, Figure 4 shows an example of an object (lower object) located at the rear of the vehicle 1, but the same applies even if the object is located in front of the vehicle 1.

[0061] Therefore, in the present embodiment, as Figure 5Set the recognition threshold in such a way that the reflection intensity of the lower object does not exceed the recognition threshold, as shown by the dashed line. Specifically, set the recognition threshold in the following manner: from the position at a distance T1 from the vehicle 1 to the distance T2 where the reflection intensity reaches the maximum value, gradually increase the recognition threshold in stages, and then gradually decrease the recognition threshold as the distance from the vehicle 1 increases.

[0062] Thereby, it is possible to suppress the situation where a lower object such as a curb is recognized as a control object (obstacle).

[0063] The shape determination unit 120 determines the shape of the object based on two coordinates of the object calculated by detecting the detection waves transmitted through different paths. Specifically, the shape determination unit 120 determines whether the object is a columnar object based on the two coordinates. A columnar object is, for example, a cylindrical object such as a pole installed on the roadside.

[0064] Specifically, the shape determination unit 120 calculates the coordinates representing the position where the detection wave hits the object in the object based on the principle of triangulation according to the distance between the vehicle 1 and the object calculated by the round trip of the detection wave.

[0065] As described above, since two wave receiving sensors 42 are provided, the shape determination unit 120 calculates two coordinates based on the detection waves received by each wave receiving sensor 42. Moreover, the shape determination unit 120 determines whether the object is a columnar object according to the coordinate difference between the two coordinates. Specifically, the shape determination unit 120 determines that the object is not a columnar object when the coordinate difference is equal to or greater than the shape determination threshold, and determines that the object is a columnar object when the coordinate difference is less than the shape determination threshold.

[0066] The shape determination threshold is a threshold corresponding to a value where the coordinate difference between the two coordinates is small because the object is relatively thin, such as in a columnar object, and can be appropriately set according to the thickness of the columnar object, etc. The shape determination threshold corresponds to the "specified threshold" of the present invention.

[0067] As Figure 6 shown, since the columnar object 2C has a circumferential surface, the columnar object 2C reflects the detection wave in such a way that the detection waves are respectively reflected from two different points P3 and P4 with close coordinate positions through different paths D3 and D4 to the two wave receiving sensors 42.

[0068] In contrast, a non-columnar object other than the columnar object 2C (for example, Figure 2 an object 2 such as a wall having a plane along the X direction as shown) reflects the detection wave in such a way that the detection waves are respectively reflected from two different points P1 and P2 with a large distance between the coordinate positions through different paths D1 and D2 to the two wave receiving sensors 42.

[0069] As described above, the coordinate difference between the two coordinates is significantly different between a columnar object and a non-columnar object, so it is possible to determine whether the object is a columnar object based on the shape determination threshold. In addition, the value of the reflection intensity is easily affected by external interference (wind, rain, heat, etc.) and changes, but the coordinate difference is less susceptible to external interference, so it is possible to accurately determine whether the object is a columnar object.

[0070] The coordinate difference is represented by the distance of at least the X-direction component of the X-direction component and the Y-direction component of the two coordinates. In addition, the distance of the Y-direction component may be considered for the coordinate difference in addition to the X-direction component.

[0071] In addition, sometimes the calculated coordinate difference is different due to the difference in distance between the vehicle 1 and the object. In this case, for example, Figure 7 As shown in FIG. 1 , different shape determination thresholds are set according to the distance between the vehicle 1 and the object. Figure 7 In the example shown, the shape determination threshold is set so that the shape determination threshold gradually increases as the distance between the vehicle 1 and the object increases.

[0072] When the detection wave is reflected by two points of the object and received by the vehicle 1, the change unit 130 changes the recognition sensitivity of the recognition unit 110 when recognizing whether the object is a control object according to the positions of the two points. Specifically, the change unit 130 changes the recognition threshold according to the coordinate difference between the two coordinates. In other words, the change unit 130 changes the recognition threshold according to whether the object is a columnar object based on the determination result of the shape determination unit 120, thereby changing the above-mentioned recognition sensitivity.

[0073] In this embodiment, if Figure 8 As shown, the recognition threshold in the case of a non-columnar object is set to a first threshold corresponding to a lower object such as a curb. The first threshold is the above Figure 5 That is, when the coordinate difference between two coordinates (the distance between two points) is greater than the shape determination threshold, the identification threshold is set in accordance with the reflection intensity of the detection wave when reflected by the non-control object.

[0074] The columnar object stands on the road surface at a certain height, and therefore unlike lower objects, the reflection intensity increases with distance. Therefore, the reflection intensity of the detection wave of the columnar object decreases as the distance between the vehicle 1 and the columnar object increases.

[0075] If a certain distance has been created between the vehicle 1 and the columnar object, the reflection intensity of the columnar object will be lower than the first threshold value, and therefore the recognition unit 110 will recognize the columnar object as a non-control object, that is, an object that is not a control object.

[0076] Therefore, when the object is a columnar object, the change unit 130 changes the recognition threshold to a second threshold corresponding to the reflection intensity of the columnar object. Similar to the reflection intensity of the columnar object, the second threshold changes in such a way that it becomes smaller as the distance between the vehicle 1 and the columnar object becomes farther.

[0077] With such a configuration, the recognition unit 110 can reliably recognize the case where the columnar object is the object to be controlled.

[0078] Alternatively, the change unit 130 may determine whether to perform the control of changing the recognition threshold according to the distance between the vehicle 1 and the object. The farther the distance between the vehicle 1 and the object, the greater the error in the calculated coordinates of the object. Therefore, it is more likely to affect the determination accuracy of the columnar object.

[0079] Therefore, when the distance between the vehicle 1 and the object is equal to or less than a specified distance, the change unit 130 performs the above-described control of changing the recognition threshold. The specified distance is, for example, a distance that can ensure the calculation accuracy of the coordinates of the object to a certain extent, and this specified distance is appropriately set according to the reflection intensity of the detection wave of the object detection unit 40 and the like.

[0080] By doing so, it is possible to perform the recognition of whether the columnar object is the object to be controlled within the range where the determination accuracy of the columnar object can be ensured.

[0081] The control unit 140 predicts the collision possibility between the vehicle 1 and the object to be controlled based on the movement of the object to be controlled recognized by the recognition unit 110 and the relative speed of the object to be controlled based on the movement of the vehicle 1 (information on vehicle speed). For the method of predicting the collision possibility, for example, a known technique can be used.

[0082] Moreover, the control unit 140 outputs an acceleration request or a braking request according to the collision possibility and the state of the acceleration of the vehicle 1.

[0083] Thereby, it is possible to perform appropriate driving control. For example, it is possible to control the braking operation for the accurately recognized object to be controlled.

[0084] An operation example of the recognition control in the vehicle control unit 100 configured as described above will be described. Figure 9 It is a flowchart showing an operation example of the recognition control in the vehicle control unit 100. For example, it is appropriately executed when the vehicle 1 is running Figure 9 the processing in. In addition, in this flowchart, it is premised that the detection wave is transmitted from the transmission wave sensor 41.

[0085] As Figure 9As shown, the vehicle control unit 100 determines whether detection waves are received by two wave receiving sensors 42 (step S101). If the determination result is that detection waves are not received by the two wave receiving sensors 42 (step S101: "No"), the process of step S101 is repeated.

[0086] On the other hand, if detection waves are received by the two wave receiving sensors 42 (step S101: "Yes"), the vehicle control unit 100 acquires information on the distance between the vehicle 1 and the object and the reflection intensity of the detection wave (step S102).

[0087] Next, the vehicle control unit 100 determines whether the distance between the vehicle 1 and the object is within a specified distance (step S103). If the determination result is that the distance is greater than the specified distance (step S103: "No"), the process proceeds to step S105.

[0088] On the other hand, if the distance is within the specified distance (step S103: "Yes"), the vehicle control unit 100 determines whether the coordinate difference between the two coordinates is lower than the shape determination threshold (step S104).

[0089] If the determination result is that the coordinate difference is equal to or greater than the shape determination threshold (step S104: "No"), the vehicle control unit 100 sets the recognition threshold to the first threshold for non-columnar objects (step S105). On the other hand, if the coordinate difference is lower than the shape determination threshold (step S104: "Yes"), the vehicle control unit 100 sets the recognition threshold to the second threshold for columnar objects (step S106).

[0090] After step S105 or step S106, the vehicle control unit 100 determines whether the reflection intensity is equal to or greater than the recognition threshold (step S107). If the determination result is that the reflection intensity is equal to or greater than the recognition threshold (step S107: "Yes"), the vehicle control unit 100 identifies the object as a control target object (step S108).

[0091] On the other hand, if the reflection intensity is lower than the recognition threshold (step S107: "No"), the vehicle control unit 100 identifies the object as a non-control target object (step S109). After step S108 or step S109, this control ends.

[0092] In addition, after step S108, the vehicle control unit 100 performs specified driving control on the vehicle 1.

[0093] With the present embodiment configured as described above, the recognition threshold is changed according to whether the object is a columnar object, so that the columnar object can be accurately identified as a control target object.

[0094] In addition, the recognition threshold (first threshold) is set in accordance with the reflection intensity of the non-control object. Therefore, when the object is a non-control object, the situation of misidentifying the object as a control object can be reliably suppressed.

[0095] That is, in the present embodiment, the situation of misidentifying an object due to the variation trend of the reflection intensity being different depending on the shape of the object can be suppressed. As a result, in the present embodiment, the object can be stably recognized.

[0096] In addition, since it is determined whether the object is a columnar object based on the coordinate difference between two coordinates, the situation of misjudging the shape of the object due to the influence of external interference can be suppressed. As a result, in the present embodiment, the shape of the object can be accurately determined.

[0097] In addition, since it is determined whether to change the recognition sensitivity based on the distance between the vehicle 1 and the object, the recognition of whether the columnar object is a control object can be performed within a range where the determination accuracy of the columnar object can be ensured. As a result, it can be accurately determined that the object is a columnar object.

[0098] Furthermore, in the above-described embodiment, the recognition threshold is used as the recognition sensitivity and the recognition threshold is changed. However, the present invention is not limited thereto. For example, the reflection intensity may be used as the recognition sensitivity, and instead of changing the recognition threshold, the reflection intensity may be changed. When the reflection intensity is used as the recognition sensitivity, the reflection intensity is changed by changing the output pressure (such as sound pressure) of the detection wave or the gain of the detection wave.

[0099] Specifically, when the object is a columnar object, the changing unit 130 changes the reflection intensity in such a manner that the reflection intensity exceeds the recognition threshold (first threshold) by enhancing the output pressure of the detection wave or the gain of the detection wave.

[0100] Even with such a configuration, the object can be stably recognized.

[0101] In addition, in the above-described embodiment, as the columnar object, a cylindrical object such as a pole is exemplified. However, the present invention is not limited thereto, and any object having a shape that can reflect the detection wave transmitted from the wave transmitting sensor 41 to the two wave receiving sensors 42 at two points of the object (for example, a columnar object having a plurality of reflection parts such as an H-shaped steel) can be used.

[0102] In addition, in the above-described embodiment, the object detection unit 40 is configured to have four sensors. However, the present invention is not limited thereto, and as long as there is at least one wave transmitting sensor and two wave receiving sensors, any number of sensors can be used. For example, as Figure 10As shown, the object detection unit 40 has six sensors including one transmission wave sensor 41 and two reception wave sensors 42.

[0103] The six sensors are arranged as follows: two are arranged at the central part in the X direction, one is arranged at each of the two end parts in the X direction, and one is arranged on each of the two sides of the vehicle 1. In Figure 10 the example shown, the transmission wave sensor 41 is arranged at one end part on the - side in the X direction. In addition, in Figure 10 the example shown, for the reception wave sensors 42, there are a total of two, that is, one of the two sensors at the central part in the X direction arranged on the - side, and one reception wave sensor 42 arranged on the - side surface of the vehicle 1 in the X direction. In addition, if considering the case where the detection wave is received by the sensors adjacent to both sides of the transmission wave sensor, in the case where the object detection unit 40 has a structure with four sensors as shown in Figure 2 the example shown, the two sensors at the central part in the X direction can be set as the transmission wave sensors. In contrast, in the case where the object detection unit 40 has a structure with six sensors, the two at the central part in the X direction and the sensors at each of the two end parts in the X direction, a total of four sensors, can be set as the transmission wave sensors. Therefore, compared with the structure shown in Figure 2 the example shown, the types of combinations of the transmission wave sensors and the reception wave sensors can be increased.

[0104] In addition, in the above - mentioned embodiment, when the detection wave is reflected by two points of the object and received by the vehicle 1, the recognition sensitivity is changed. However, the present invention is not limited to this. It may also be the case that when the detection wave is reflected by three or more points of the object and received by the vehicle 1, the recognition sensitivity is changed. In addition, in this case, it is only necessary to provide three or more reception wave sensors.

[0105] In addition, in the above - mentioned embodiment, there is a shape determination unit. However, the present invention is not limited to this. As long as the information of two coordinates and the information of the shape of the object can be obtained from the outside, the shape determination unit may not be provided.

[0106] In addition, in the above - mentioned embodiment, when the detection wave is received by two reception wave sensors, recognition control is performed. However, the present invention is not limited to this. It may also be the case that when the detection wave is received by only one reception wave sensor, the recognition threshold is set to the first threshold for non - columnar objects to recognize the object.

[0107] In addition, in the above - mentioned embodiment, the object recognition device (recognition unit, shape determination unit, and change unit) is incorporated into the vehicle control unit. However, the present invention is not limited to this, and these may not be incorporated into the vehicle control unit.

[0108] In addition, the above-described embodiments merely show an example of the implementation when carrying out the present invention, and the technical scope of the present invention should not be limitatively construed by these explanations. That is, the present invention can be implemented in various forms without departing from its gist or its main features.

[0109] Industrial Applicability

[0110] The object recognition device, vehicle, and object recognition method of the present invention are useful as an object recognition device, vehicle, and object recognition method that can stably recognize an object.

Claims

1. An object recognition device, characterized in that, Comprising: An identification unit that, when a detection wave transmitted from a moving body to an object is reflected by the object and received by the moving body, identifies whether the object is a control target object based on a comparison result between the reflection intensity of the detection wave and an identification threshold, where the identification threshold is an identification sensitivity; and A change unit that, when the detection wave is reflected by at least two points of the object and received by the moving body, determines whether the object is a columnar object having a circumferential surface based on the positions of the at least two points, and changes the identification sensitivity of the identification unit when it is determined that the object is a columnar object having a circumferential surface.

2. The object identification device according to claim 1, wherein It further comprises a shape determination unit that determines the shape of the object based on a plurality of coordinates of the object calculated by detecting the detection wave transmitted through different paths, The change unit changes the identification sensitivity according to the plurality of coordinates.

3. The object identification device according to claim 1, wherein When the distance between the at least two points is equal to or greater than a specified threshold, the identification threshold is set to match the reflection intensity of the detection wave when reflected by an object that is not the control target object, i.e., a non-control target object.

4. The object identification device according to claim 3, wherein The non-control target object is a lower object located on the road surface and having a height that does not collide with the main body of the moving body.

5. The object identification device according to claim 1, wherein The change unit changes the identification sensitivity by changing the identification threshold.

6. The object identification device according to claim 1, wherein The change unit changes the identification sensitivity by changing the reflection intensity.

7. The object identification device according to claim 1, wherein The change unit performs control to change the identification sensitivity according to the distance between the moving body and the object.

8. A vehicle, characterized in that, Comprising: The object identification device according to claim 1; A wave transmitting sensor that transmits the detection wave; and At least two wave receiving sensors that receive the detection wave.

9. An object identification method, characterized in that It has the following steps, that is, when a detection wave transmitted from a moving body to an object is reflected by the object and received by the moving body, an identification step of identifying whether the object is a control target object based on a comparison result between the reflection intensity of the detection wave and an identification threshold, In the step, the identification threshold is an identification sensitivity, the detection wave is reflected by at least two points of the object and received by the moving body, and it is determined whether the object is a columnar object having a circumferential surface based on the positions of the at least two points. When it is determined that the object is a columnar object having a circumferential surface, the identification sensitivity is changed.

Images