Object recognition device and program

Abstract

To provide an object recognition device capable of properly determining that the reliability of an actual distance from an own vehicle to an object is decreased.SOLUTION: An ECU 30 acquires an image captured by an imaging apparatus 22 and calculates a distance from the own vehicle for the object existing in the image. The ECU 30 includes a first calculation part 33 for calculating the distance from the own vehicle to the object as a first distance on the basis of a lower end position which is the position of the lower end part of the object in the image, a second calculation part 34 for calculating the distance from the own vehicle to the object as a second distance on the basis of the size of the object in the image, an actual distance calculation part 35 for calculating the actual distance from the own vehicle to the object as the actual distance on the basis of the first distance and the second distance, and a reliability determination part 36 for determining the reliability of the actual distance on the basis of a distance difference between the first distance and the second distance.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an object recognition device and a program.

Background Art

[0002] As an object recognition device, one that recognizes the distance from a host vehicle to an object based on an image captured by an imaging device is known. For example, the object recognition device described in Patent Document 1 recognizes the average value of the distance calculated based on the horizontal edge indicating the lower end of the object in the image and the distance calculated based on the vertical edges indicating the left and right ends of the object in the image as the actual distance from the host vehicle to the object.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Depending on the driving situation of the host vehicle, the accuracy of the distances calculated based on the horizontal edge and the vertical edge respectively may decrease due to a decrease in the recognition accuracy of the object in the image or the like. In this case, a decrease in the accuracy of the actual distance may occur. Here, in addition to using the horizontal edge and the vertical edge for calculating the actual distance, when calculating the actual distance using two different methods, the same problem occurs.

[0005] The present invention has been made in view of the above circumstances, and its main object is to provide an object recognition device and a program capable of appropriately determining that the reliability of the actual distance from the host vehicle to an object has decreased.

Means for Solving the Problems

[0006] The present invention is an object recognition device that acquires an image captured by an imaging device and calculates the distance from the host vehicle to an object existing in the image, a first calculation unit that calculates, as a first distance, the distance from the host vehicle to the object based on a lower end position that is the position of a lower end portion of the object in the image; a second calculation unit that calculates, as a second distance, the distance from the host vehicle to the object based on the size of the object in the image; an actual distance calculation unit that calculates, as an actual distance, the actual distance from the host vehicle to the object based on the first distance and the second distance; a reliability determination unit that determines the reliability of the actual distance based on a distance difference between the first distance and the second distance; and includes.

[0007] In a configuration in which the actual distance from the host vehicle to the object is calculated using the first distance calculated based on the lower end position of the object in the image and the second distance calculated based on the size of the object in the image, the accuracy of the actual distance can be increased as compared with the case where the actual distance is calculated by any one of these. However, if the accuracy of at least one of the first distance and the second distance decreases, it is conceivable that the accuracy of the actual distance will decrease.

[0008] Therefore, in the present invention, the reliability of each actual distance is determined based on the distance difference between the first distance and the second distance. In this case, if the distance difference between the first distance and the second distance is large, there is a possibility that the accuracy of either of these distances has decreased, and by grasping this distance difference, the reliability of the actual distance can be appropriately determined.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Mode for Carrying Out the Invention

[0010] <First Embodiment> Hereinafter, an embodiment in which the object recognition device according to the present invention is applied to a driving support system of a vehicle will be described with reference to the drawings.

[0011] As shown in FIG. 1, the driving support system 10 according to the present embodiment includes a radar device 21, an imaging device 22, a vehicle speed sensor 23, a steering angle sensor 24, an angle sensor 25, a receiving device 26, an ECU 30, and a controlled device 40. In the present embodiment, the ECU 30 corresponds to the driving support device.

[0012] The radar device 21 is, for example, a known millimeter-wave radar that uses a high-frequency signal in the millimeter-wave band as a transmission wave. The radar device 21 is attached, for example, at the front of the host vehicle so that its optical axis faces forward of the host vehicle, and sets a detection range in which an object can be detected within a predetermined detection angle, and detects the position of the object within the detection range. Specifically, the radar device 21 transmits a search wave at a predetermined cycle and receives the reflected wave with a plurality of antennas. The radar device 21 calculates the distance to the object based on the transmission time of the search wave and the reception time of the reflected wave. Further, the radar device 21 calculates the relative speed based on the frequency changed by the Doppler effect of the reflected wave reflected by the object. In addition, the azimuth of the object is calculated based on the phase difference of the reflected waves received by the plurality of antennas. The radar device 21 outputs detection data such as the distance to the object, the relative speed, and the azimuth of the object to the ECU 30.

[0013] The imaging device 22 is a monocular camera installed only once on the host vehicle. The imaging device 22 is, for example, a CCD camera, a CMOS image sensor, a near-infrared camera, or the like. The imaging device 22 is attached, for example, at a predetermined height at the center in the vehicle width direction of the vehicle, and images a region spreading in a predetermined angle range toward the front of the host vehicle from an overhead viewpoint. The imaging device 22 sequentially outputs the captured images captured sequentially to the ECU 30. Note that the imaging device 22 may be a stereo camera installed a plurality of times on the host vehicle.

[0014] The vehicle speed sensor 23 is a sensor that detects the traveling speed of the host vehicle, and outputs a traveling speed signal corresponding to the traveling speed of the host vehicle to the ECU 30. The steering angle sensor 24 is a sensor that detects the steering angle of the steering wheel, and outputs a steering angle signal corresponding to the change in the steering angle to the ECU 30. The angle sensor 25 includes a gyro sensor and an acceleration sensor attached to the vehicle body of the host vehicle, and detects the pitch angle of the host vehicle from the angular velocity detected by the gyro sensor and the acceleration detected by the acceleration sensor. The angle sensor 25 outputs the detected pitch angle signal of the host vehicle to the ECU 30.

[0015] The receiving device 26 is a receiving device for a positioning signal from a satellite positioning system, for example, a GPS receiving device. The receiving device 26 receives road information about the road on which the host vehicle travels and the surrounding roads, and outputs the received road information to the ECU 30. The road information includes at least road gradient information.

[0016] The functions provided by the ECU 30 can be provided by software recorded in a physical memory device and a computer that executes it, software only, hardware only, or a combination thereof. For example, when the ECU 30 is provided by an electronic circuit that is hardware, it can be provided by a digital circuit including a number of logic circuits or an analog circuit. For example, the ECU 30 executes a program stored in a non-transitory tangible storage medium as a storage unit provided therein. The program includes programs for each arithmetic process described later. When the program is executed, a method corresponding to the program is executed. The storage unit is, for example, a non-volatile memory. Note that the program stored in the storage unit can be updated via a network such as the Internet, for example.

[0017] The ECU 30 performs an object recognition process of recognizing an object existing around the host vehicle based on input information. In the object recognition process, at least the distance from the host vehicle to the object is recognized. The objects include four-wheeled automobiles, motorcycles, bicycles, people (pedestrians), and the like. Note that the object recognition process will be described later.

[0018] The ECU 30 performs driving support control based on the result of the object recognition process. In the present embodiment, the ECU 30 performs a collision suppression operation for suppressing a collision with an object as the driving support control.

[0019] The ECU 30 determines that the implementation condition of the collision suppression operation is satisfied when the time to collision (TTC) with an object existing in front of the host vehicle is less than a predetermined threshold value. The time to collision (TTC) is an evaluation value indicating how many seconds later the vehicle will collide with the object when traveling at the current vehicle speed. The smaller the time to collision (TTC), the higher the risk of collision, and the larger the time to collision (TTC), the lower the risk of collision. The time to collision (TTC) is, for example, a value obtained by dividing the relative distance of the object with respect to the host vehicle by the relative speed of the object with respect to the host vehicle.

[0020] As a collision suppression operation, the ECU 30 activates the controlled device 40 including the warning device 41, the accelerator device 42, the brake device 43, and the steering device 44. The warning device 41 is a device that gives a warning to the driver of the host vehicle, and is, for example, a device that gives an auditory notification such as a speaker or a buzzer installed in the vehicle interior, or a device that gives a visual notification such as a display or a warning light. The accelerator device 42 is an engine or a motor as a vehicle power source, and is a device that applies a driving force to the host vehicle. The brake device 43 is a device that brakes the host vehicle by the operation of a hydraulic actuator or the like. The steering device 44 is a device that steers the host vehicle by the operation of a steering motor or the like. In the present embodiment, the ECU 30 brakes the host vehicle by the brake device 43 as a collision suppression operation.

[0021] Hereinafter, the object recognition process performed by the ECU 30 will be described. As an object recognition process, the ECU 30 acquires an image captured by the imaging device 22, and performs an image recognition process for calculating the distance from the host vehicle to an object existing in the image. In the present embodiment, the ECU 30 includes a type recognition unit 31, a setting unit 32, a first calculation unit 33, a second calculation unit 34, and an actual distance calculation unit 35. Hereinafter, the image recognition process will be described while using FIG. 2. FIG. 2 is an example of an image G that captures the front in the traveling direction of the host vehicle. In the image G, a person 50 is captured as an object.

[0022] The type recognition unit 31 recognizes the type of an object in the image. In the present embodiment, the type recognition unit 31 extracts a rectangular region surrounding the object in the image, and calculates a type score indicating the likelihood of the object type for the image within the rectangular region. The type recognition unit 31 predefines a plurality of type recognition targets (for example, buses, trucks, ordinary automobiles, motorcycles, bicycles, adults, children, etc.), and individually calculates the type score for the image within the rectangular region using the training data that defines the recognition targets. The form of the training data is arbitrary, but for example, it is advisable to use training data generated by deep learning. The type score may be represented by the probability of which type it corresponds to for each image within the rectangular region. In FIG. 2, the type recognition unit 31 extracts a rectangular region R surrounding the person 50 in the image G, and calculates the type score of the person 50 as, for example, "child: 85%", "adult: 10%", "other object: 5%". In this case, since the probability that the type score is a child is the highest, the type recognition unit 31 recognizes the type of the person 50 as a child. Note that instead of recognizing the type of the object based on the type score, the type recognition unit 31 may recognize the type of the object by performing template matching processing on the image within the rectangular region.

[0023] Note that the type recognition unit 31 may, for example, calculate a motion vector for each pixel in the image, and extract a rectangular region surrounding the object by assuming that a collection of pixels having the same direction and magnitude of the motion vector are pixels constituting the same object. The motion vector is a vector indicating the change direction and magnitude in the time series at each pixel constituting the object in the image.

[0024] The setting unit 32 sets a size reference value, which is a reference value for the actual size of an object in the image. The size reference value is predetermined for each type of object. In this embodiment, the setting unit 32 sets, as the size reference value, the height-width value of the object corresponding to the type of the object. The setting unit 32 associates 1.7 m with an adult, 1.2 m with a child, 2.0 m with a normal passenger car, and 3.5 m with a large vehicle such as a bus as the height-width values. In FIG. 2, the setting unit 32 sets the size reference value of the person 50 recognized as a child to 1.2 m. Note that the setting unit 32 may set, as the size reference value, the horizontal width value of the object corresponding to the type of the object instead of the height-width value of the object.

[0025] The first calculation unit 33 calculates, as a first distance, the distance from the host vehicle to the object based on the lower end position, which is the position of the lower end portion of the object in the image. In this embodiment, as shown in FIG. 2, the first calculation unit 33 calculates the first distance based on the number of pixels L corresponding to the distance between the lower end position of the person 50 and the infinity point FOE of the imaging device 22. When the number of pixels L is small, the first calculation unit 33 calculates the first distance to be longer than when the number of pixels L is large. Note that the first calculation unit 33 may calculate the first distance based on the number of pixels corresponding to the distance between the lower end position of the person 50 and the lower end position of the image G instead of the number of pixels L. In this case, when the number of pixels corresponding to the distance between the lower end position of the person 50 and the lower end position of the image G is large, the first calculation unit 33 may calculate the first distance to be longer than when the number of pixels is small.

[0026] The second calculation unit 34 calculates the distance from the host vehicle to the object as a second distance based on the size of the object in the image and the size reference value of the object set by the setting unit 32. If the size reference value of the object is the same, the second calculation unit 34 calculates a shorter second distance when the size of the object in the image is larger than when the size of the object in the image is smaller. Also, if the size of the object in the image is the same, the second calculation unit 34 calculates a shorter second distance when the size reference value of the object is smaller than when the size reference value of the object is larger. In the present embodiment, as shown in FIG. 2, the second calculation unit 34 uses the number of pixels H corresponding to the distance from the upper end position to the lower end position of the rectangular region R as the size of the object in the image. Note that the second calculation unit 34 may use the number of pixels corresponding to the distance from the left end position to the right end position of the rectangular region R instead of the number of pixels H as the size of the object in the image.

[0027] The actual distance calculation unit 35 calculates the actual distance from the host vehicle to the object as the actual distance based on the first distance and the second distance. The actual distance is used, for example, in the calculation of the time to collision (TTC) in the collision suppression operation. In the present embodiment, the actual distance calculation unit 35 calculates the average value of the first distance and the second distance as the actual distance.

[0028] Here, in a configuration in which the first distance calculated based on the lower end position of the object in the image and the second distance calculated based on the size of the object in the image are used to calculate the actual distance from the host vehicle to the object, the accuracy of the actual distance can be improved as compared with the case where the actual distance is calculated by either one of these. However, depending on the driving situation of the host vehicle, it is conceivable that the accuracy of at least one of the first distance and the second distance decreases, resulting in a decrease in the accuracy of the actual distance.

[0029] Therefore, in the present embodiment, the ECU 30 includes a reliability determination unit 36 to determine the reliability of the actual distance. The reliability determination unit 36 determines the reliability of the actual distance based on the distance difference between the first distance and the second distance. Here, the distance difference between the first distance and the second distance is the absolute value of the difference between the first distance and the second distance.

[0030] Figure 3 shows the processing procedure of the image recognition process performed by the ECU 30. This process is repeatedly performed at a predetermined cycle.

[0031] In step S10, the image captured by the imaging device 22 and the driving situation information are acquired. The driving situation information is information regarding the pitch angle of the host vehicle and information regarding the gradient of the road on which the host vehicle travels. The information regarding the gradient of the road on which the host vehicle travels is, for example, road information acquired from the receiving device 26. The information regarding the pitch angle of the host vehicle is, for example, the pitch angle signal of the angle sensor 25. In the present embodiment, step S10 corresponds to the "acquisition unit".

[0032] In step S11, the first distance D1 is calculated. In the present embodiment, the first distance D1 is calculated based on the number of pixels corresponding to the distance between the lower end position of the object in the image and the infinite focus point FOE of the imaging device 22.

[0033] In step S12, the type recognition process is performed. In the present embodiment, the type recognition process is a process of extracting a rectangular region surrounding the object in the image and recognizing the type of the object based on the type score of the image within the rectangular region. In step S13, it is determined whether or not the type of the object in the image has been recognized by the type recognition process. If a negative determination is made in step S13, the process proceeds to step S22. On the other hand, if an affirmative determination is made in step S13, the process proceeds to step S14.

[0034] In step S14, a size reference value of the object in the image is set. In the present embodiment, as the size reference value, a height-width value of an object corresponding to the type of the object recognized by the type recognition process is set.

[0035] In step S15, the second distance D2 is calculated. In the present embodiment, the second distance D2 is calculated based on the number of pixels corresponding to the distance from the upper end position to the lower end position of the rectangular region surrounding the object in the image and the size reference value of the object.

[0036] In step S16, it is determined whether the object in the image is a person of short stature. In the present embodiment, when the object in the image is a person and its size reference value is lower than the short-stature threshold value, it is determined that the object in the image is a person of short stature. For example, when the short-stature threshold value is set to 1.7 m as the size reference value when the object type is an adult and 1.2 m as the size reference value when the object type is a child, it may be set to a value between 1.2 m and 1.7 m.

[0037] If a negative determination is made in step S16, the process proceeds to step S20. On the other hand, if an affirmative determination is made in step S16, the process proceeds to step S17.

[0038] In step S17, it is determined whether the gradient of the road on which the host vehicle travels is either an uphill gradient or a downhill gradient in front of the host vehicle. The determination of the road gradient in front of the host vehicle may be made based on at least the information regarding the gradient of the road on which the host vehicle travels among the driving situation information. If an affirmative determination is made in step S17, the process proceeds to step S21. On the other hand, if a negative determination is made in step S17, the process proceeds to step S18.

[0039] In step S18, it is determined whether pitching of the host vehicle has occurred. The pitching of the host vehicle includes pitching generated by acceleration and deceleration of the host vehicle and pitching instantaneously generated due to the road environment on which the host vehicle travels. The determination of whether pitching of the host vehicle has occurred may be made based on at least the information regarding the pitch angle of the host vehicle among the driving situation information. If an affirmative determination is made in step S18, the process proceeds to step S21. If a negative determination is made in step S18, the process proceeds to step S19.

[0040] In step S19, the reliability of the actual distance is determined. In the present embodiment, the reliability of the actual distance is determined by determining whether the distance difference ΔD, which is the absolute value of the difference between the first distance D1 and the second distance D2, is less than or equal to the distance difference threshold Dth. Here, the distance difference threshold Dth is a fixed value. If an affirmative determination is made in step S19, the process proceeds to step S20, and it is determined that the reliability of the actual distance is high. On the other hand, if a negative determination is made in step S19, the process proceeds to step S21, and it is determined that the reliability of the actual distance is low.

[0041] In the present embodiment, when it is determined in step S20 that the reliability of the actual distance is high, the process proceeds to step S22, and the actual distance, which is the average value of the first distance D1 and the second distance D2, is adopted as the processing result of the image recognition processing. In this case, for example, in the collision suppression operation, the actual distance is used to calculate the time to collision TTC. On the other hand, when it is determined in step S21 that the reliability of the actual distance is low, the process proceeds to step S23, and the actual distance is not adopted as the processing result of the image recognition processing. In this case, for example, in the collision suppression operation, the distance and relative speed to the object detected by the radar device 21 are used to calculate the time to collision TTC.

[0042] According to the present embodiment described in detail above, the following effects can be obtained.

[0043] A configuration is adopted in which the reliability of the actual distance is determined based on the distance difference ΔD between the first distance D1 and the second distance D2. In this case, if the distance difference ΔD between the first distance D1 and the second distance D2 is large, there is a possibility that the accuracy of either of the distances D1 and D2 has decreased. By grasping the distance difference ΔD, the reliability of the actual distance can be appropriately determined.

[0044] It is conceivable that the reference value of the object size is set smaller than the actual size of the object. For example, it is conceivable that the type of the object as a person is erroneously determined to be a child even though the actual person is an adult. In this case, there is a concern that the reference value of the object size is set smaller than the actual size of the object, and the second distance D2 is calculated to be shorter than the actual distance.

[0045] In consideration of this point, a configuration is adopted to determine whether to perform the reliability determination of the actual distance based on the size reference value of the object. Specifically, when the object in the image is a person and the size reference value is lower than the short stature threshold, it is determined that the object in the image is a person with a short stature. When it is determined that the object in the image is a person with a short stature, the reliability determination of the actual distance is performed based on the gradient of the road on which the host vehicle travels, the occurrence of pitching of the host vehicle, and the distance difference ΔD. Thereby, in a situation where there is a concern that the second distance D2 may be calculated shorter than the actual value due to an incorrect setting of the size reference value of the object and an unnecessary collision suppression operation may be performed, the reliability of the actual distance can be determined.

[0046] In a situation where pitching occurs in the host vehicle or in a situation where the road on which the host vehicle travels has a gradient in front of the host vehicle, there is a high possibility that an error will occur in the first distance D1 calculated based on the lower end position of the object in the image. In this case, there is a concern that the reliability determination of the actual distance cannot be appropriately performed.

[0047] Therefore, in the present embodiment, it is determined whether to perform the reliability determination of the actual distance based on the driving situation information. Thereby, it is possible to suppress the reliability determination of the actual distance from being performed in a situation where the reliability determination of the actual distance cannot be appropriately performed.

[0048] <Second Embodiment> Hereinafter, the second embodiment will be described centering on the differences from the first embodiment. In the first embodiment, based on the determination result by the reliability determination unit 36, it is determined whether to adopt, as the processing result of the image recognition processing, the actual distance that is the average value of the first distance D1 and the second distance D2. On the other hand, in the present embodiment, based on the determination result by the reliability determination unit 36, the value of the actual distance adopted as the processing result of the image recognition processing is changed.

[0049] FIG. 4 shows the processing procedure of the image recognition processing performed by the ECU 30. This processing is repeatedly performed at a predetermined cycle. In FIG. 4, the same step numbers are assigned to the processing that overlaps with FIG. 3.

[0050] If a negative determination is made in step S13, since the accuracy of the second distance D2 decreases, it is determined that the process of step S19 cannot be appropriately performed, and the process proceeds to step S30. In step S30, it is determined that the reliability of the actual distance is low. In this case, in step S31, the actual distance calculated based on the first distance D1 and the second distance D2 is not adopted as the processing result of the image recognition process.

[0051] If an affirmative determination is made in step S17, it is determined that the accuracy of the first distance D1 decreases, and the process proceeds to step S30. Also, if an affirmative determination is made in step S18, it is determined that the accuracy of the first distance D1 decreases, and the process proceeds to step S30.

[0052] If an affirmative determination is made in step S13 and negative determinations are made in steps S17 to S19, the process proceeds to step S32. In step S32, it is determined that the reliability of the second distance D2 is low. In this case, in step S33, the first distance D1 among the first distance D1 and the second distance D2 is adopted as the actual distance that is the processing result of the image recognition process. In the present embodiment, steps S13 to S15, S17 to S20, S22, and S30 to S33 correspond to the "modification part".

[0053] In the present embodiment, in the process of step S19, as the distance difference threshold Dth, different values are used according to the type of the object in the image. Specifically, when the type recognized by the type recognition process is a human type, the value of the distance difference threshold Dth used for determining the reliability of the actual distance is made smaller than the value of the distance difference threshold Dth used for determining the reliability of the actual distance when the type recognized by the type recognition process is a vehicle type. Here, the human type is a type recognized as a human, and includes, for example, adults and children. Also, the vehicle type is a type recognized as a vehicle, and includes, for example, ordinary automobiles, trucks, and buses.

[0054] According to the present embodiment described in detail above, the following effects can be obtained.

[0055] According to this embodiment, based on the distance difference ΔD, the type of the object, and the driving situation information, the factor causing the decrease in the reliability of the actual distance is determined. When it is determined that the factor causing the decrease in the reliability of the actual distance is the decrease in the reliability of the second distance D2, the first distance D1 is adopted as the actual distance that is the processing result of the image recognition process. Thereby, even in a situation where the reliability of the actual distance decreases, it is possible to calculate the actual distance based on the first distance D1 and the second distance D2 while suppressing the decrease in the accuracy of the actual distance.

[0056] In the type recognition process of step S12, it is conceivable to distinguish and recognize at least a plurality of human types with different sizes and a plurality of vehicle types with different sizes. In this case, it is considered that the human type of a person as the target object may be misrecognized, and the vehicle type of a vehicle as the target object may be misrecognized. For example, it is considered that the type of a person as the target object may be erroneously recognized as a child even though the person is actually an adult, or the type of a vehicle as the target object may be erroneously recognized as an ordinary car even though the vehicle is actually a bus. If the human type or vehicle type is misrecognized, the size reference value of the target object is set erroneously, the accuracy of the second distance D2 decreases, and the distance difference ΔD increases.

[0057] However, in this case, when comparing the difference in size when distinguishing human types with the difference in size when distinguishing vehicle types, the former has a smaller difference. Therefore, if a fixed value is used as the distance difference threshold Dth, there is a concern that an incorrect determination of high reliability may occur during reliability determination when the type of the target object is included in the human type.

[0058] Therefore, in this embodiment, the value of the distance difference threshold Dth used for determining the reliability of the actual distance when the type recognized by the type recognition process is a human type is made smaller than the value of the distance difference threshold Dth used for determining the reliability of the actual distance when the type recognized by the type recognition process is a vehicle type. Thereby, when the type of the target object is a human type, it is possible to appropriately determine the decrease in the reliability of the actual distance caused by the occurrence of misrecognition of the human type.

[0059] <Other Embodiments> The above embodiment may be modified as follows, for example.

[0060] · In the above embodiment, the setting unit 32 sets the size reference value for the object in the image based on the type of the object recognized by the type recognition unit 31, but this may be changed.

[0061] The setting unit 32 may estimate the actual size of the object based on the first distance calculated by the first calculation unit 33 and the size of the object in the image, and set the size reference value for the object based on the estimated value. In this case, if the sizes of the objects in the image are the same, when the first distance based on the lower end position of the object in the image is long, the setting unit 32 may estimate a larger estimated value of the object size than when the first distance is short. Also, if the first distances are the same, when the size of the object in the image is large, the setting unit 32 may estimate a larger estimated value of the object size than when the size of the object in the image is small. The setting unit 32 may select, as the size reference value for the object, the category value among the category values that are assumed values for the object size and that is closest to the estimated value of the object size.

[0062] In this embodiment, in the image recognition process shown in FIG. 3 above, the processes of steps S12 and S13 may not be performed. That is, in the image recognition process, the calculation of the actual distance and the determination of the reliability of the actual distance can be performed without performing the type recognition process.

[0063] · In the above embodiment, as the collision suppression operation, the configuration is such that the braking of the host vehicle is performed by the braking device 43, but this may be changed. For example, as the collision suppression operation, the configuration may be such that either an alarm by the alarm device 41 or the steering of the host vehicle by the steering device 44 is implemented.

[0064] ·In the above-described embodiment, the running assistance control is configured to perform a collision suppression operation, but this may be changed. For example, as the running assistance control, a configuration for performing ACC (Adaptive Cruise Control) control may be adopted. In ACC control, another vehicle traveling ahead in the traveling direction of the host vehicle is selected as the preceding vehicle, and the host vehicle is controlled using the accelerator device 42, the brake device 43, and the steering device 44, so that the host vehicle performs following running with respect to the preceding vehicle. Further, for example, as the running assistance control, the distance from the host vehicle to an object recognized by the object recognition process may be displayed on a display or the like.

[0065] ·The vehicle control device and its method described in the present disclosure may be realized by a dedicated computer provided by configuring a processor and a memory programmed to execute one or more functions embodied by a computer program. Alternatively, the vehicle control device and its method described in the present disclosure may be realized by a dedicated computer provided by configuring a processor with one or more dedicated hardware logic circuits. Or, the vehicle control device and its method described in the present disclosure may be realized by one or more dedicated computers configured by a combination of a processor and a memory programmed to execute one or more functions and a processor configured by one or more hardware logic circuits. Further, the computer program may be stored in a computer-readable non-transitory tangible recording medium as instructions to be executed by a computer.

Description of Reference Numerals

[0066] 22... imaging device, 30... ECU, 33... first calculation unit, 34... second calculation unit, 35... actual distance calculation unit, 36... reliability determination unit, 50... person.

Claims

1. An object recognition device (30) that acquires an image captured by an imaging device (22) and calculates the distance from the host vehicle to an object (50) existing in the image, comprising: a first calculation unit (33) that calculates, as a first distance, the distance from the host vehicle to the object based on a lower end position that is the position of the lower end portion of the object in the image; a second calculation unit (34) that calculates, as a second distance, the distance from the host vehicle to the object based on the size of the object in the image; an actual distance calculation unit (35) that calculates, as an actual distance, the actual distance from the host vehicle to the object based on the first distance and the second distance; a reliability determination unit (36) that determines the reliability of the actual distance based on the distance difference between the first distance and the second distance; An object recognition device comprising the above.

2. Comprising a setting unit (32) that sets a size reference value that is a reference value for the actual size of the object, The second calculation unit calculates the second distance based on the size of the object in the image and the size reference value of the object set by the setting unit, The reliability determination unit determines whether to perform reliability determination of the actual distance of the object based on the size reference value of the object. The object recognition device according to claim 1.

3. Comprising an acquisition unit that acquires driving situation information of the host vehicle, which is at least one of information regarding the pitch angle of the host vehicle and information regarding the gradient of the road on which the host vehicle travels, The reliability determination unit determines whether to perform reliability determination of the actual distance based on the driving situation information. The object recognition device according to claim 1 or 2.

4. Including a person and a vehicle as target objects, and comprising a type recognition unit (31) that, as object type recognition, distinguishes and recognizes at least a plurality of person types with different sizes and a plurality of vehicle types with different sizes, The second calculation unit calculates the second distance based on the size of the object in the image and the type recognized by the type recognition unit, The reliability determination unit determines that the reliability of the actual distance is low if the distance difference is greater than a threshold value, and determines that the reliability of the actual distance is high if the distance difference is less than the threshold value. The object recognition device according to claim 1, wherein a threshold value used for determining the reliability of the actual distance calculated by the actual distance calculation unit when the type recognized by the type recognition unit is a person is made smaller than a threshold value used for determining the reliability of the actual distance calculated by the actual distance calculation unit when the type recognized by the type recognition unit is a vehicle.

5. a type recognition unit (31) that recognizes the type of the object; an acquisition unit that acquires driving state information of the host vehicle, which is at least one of the pitch angle of the host vehicle and the gradient of the road on which the host vehicle travels; the reliability determination unit determines a factor causing a decrease in the reliability of the actual distance based on the distance difference, the type of the object, and the driving state information; The object recognition device according to claim 1, further comprising a change unit that changes a value of the actual distance calculated by the actual distance calculation unit according to the factor causing the decrease.

6. A program executed by a control device (30) to acquire an image captured by an imaging device (22) and calculate a distance from the host vehicle to an object (50) existing in the image, the program including: a first calculation step of calculating, as a first distance, the distance from the host vehicle to the object based on a lower end position that is a position of a lower end portion of the object in the image; a second calculation step of calculating, as a second distance, the distance from the host vehicle to the object based on the size of the object in the image; an actual distance calculation step of calculating, as an actual distance, the actual distance from the host vehicle to the object based on the first distance and the second distance; a reliability determination step of determining the reliability of the actual distance based on a distance difference between the first distance and the second distance; A program including the above.

Images