Target detection device, image processing device, and computer program

Abstract

To further accurately detect an approach of a target hidden behind a shielding object.SOLUTION: A target detection device is mounted on a vehicle, which detects a movable target having a light source attached thereto that emits infrared light. The target detection device comprises an imaging device and an image processing device. The imaging device acquires an image that captures a road surface ahead in a traveling direction of the vehicle. The image processing device outputs a control signal that causes a controlled device mounted on the vehicle so as to execute a predetermined action in response to the approach of the target when the image processing device determines that the target is approaching the vehicle based on a brightness distribution of infrared light in the image.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an object detection device that detects the approach of an object hidden behind a shield. The present disclosure also relates to an image processing device mounted on the object detection device, and a computer program executable by a processing unit of the image processing device. [Background technology]

[0002] Patent Document 1 discloses, as an example of an object detection device, an out-of-field obstacle detection system that receives radio waves emitted from a radio wave source attached to the subject using a receiving unit in the vehicle and estimates the position of an object hidden behind an obstruction based on the received radio waves. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-36920 A Summary of the Invention [Problem to be solved by the invention]

[0004] When detecting an object using radio waves as in Patent Document 1, the radio waves emitted from the radio wave source are reflected by a third object between the radio wave source and the vehicle before reaching the receiving unit in the vehicle, making it difficult to accurately estimate the position of the object.

[0005] The present disclosure aims to more accurately detect the approach of an object hidden behind an obstruction. [Means for solving the problem]

[0006] An object detection device according to one aspect of the present disclosure includes: An object detection device mounted on a vehicle for detecting a movable object having a light source that emits infrared light, comprising: An imaging device for capturing an image of a road surface ahead in a traveling direction of the vehicle; an image processing device that, when it is determined that the object is approaching the vehicle based on the luminance distribution of infrared light in the image, outputs a control signal to a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object; It is equipped with:

[0007] An image processing device according to one aspect of the present disclosure includes: An image processing device that is installed in an object detection device that is mounted on a vehicle and detects a movable object having a light source that emits infrared light, comprising: A reception unit that receives an image including a road surface ahead in a traveling direction of the vehicle; a processing unit that determines whether the object is approaching the vehicle based on a luminance distribution of infrared light in the image; an output unit that outputs a control signal to cause a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object when it is determined that the object is approaching the vehicle; It is equipped with:

[0008] A computer program according to one aspect of the present disclosure includes: A computer program executable by a processing unit of an image processing device mounted on an object detection device that is mounted on a vehicle and detects a movable object having a light source that emits infrared light, the computer program comprising: When the above-mentioned program is executed, the image processing device Accepting an image showing a road surface ahead in a traveling direction of the vehicle; determining whether the object is approaching the vehicle based on a luminance distribution of infrared light in the image; When it is determined that the object is approaching the vehicle, a control signal is output to cause a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object. Effect of the Invention

[0009] According to the present disclosure, the approach of an object hidden behind an obstruction can be detected more accurately. [Brief description of the drawings]

[0010] [Figure 1] 2 illustrates an example of a functional configuration of an object detection system according to an embodiment. [Diagram 2] 2 illustrates an example of a flow of a process for detecting the approach of an object, which is executed by a processing unit of the image processing device. [Diagram 3] The figure illustrates an example of an image of a T-junction ahead of the vehicle in the direction of travel captured by an imaging device mounted on the vehicle. [Figure 4] 4 illustrates an example of an image capturing the road surface captured by an imaging device in the situation of FIG. 3. [Diagram 5] 1 illustrates an example of the configuration of a HUD mounted on a vehicle. [Figure 6] An example of approaching object information displayed in the HUD display area is shown. [Figure 7] 13 illustrates a flow of another example of a process for detecting the approach of an object, which is executed by the processing unit of the image processing device. [Figure 8] 2 illustrates a first image captured by an imaging device. [Figure 9] 1 illustrates a second image captured by an imaging device after the first image. [Figure 10] 13 shows the flow of another example of the process of detecting the approach of an object, which is executed by the image processing device of the object detection device. [Figure 11] 1 shows a diagram for determining the irradiation distance of a light pattern emitted from a light source. [Figure 12] 13 shows a graph illustrating the relationship between the vehicle speed and distance when Ln=Lb, when the irradiation distance of the light pattern is changed. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. For the sake of convenience of explanation, the dimensions of each component shown in the drawings may differ from the actual dimensions of each component.

[0012] 1 illustrates an example of a functional configuration of an object detection system 1 according to this embodiment. The object detection system 1 is a system that detects the approach of an object 40 hidden behind an obstruction based on an image that captures a road surface 100 ahead in the traveling direction of a vehicle 30, and alerts the occupants of the vehicle 30 and activates automatic braking. The object 40 is a movable object, and examples of the object 40 include a bicycle, a small mobility vehicle, a pedestrian, etc.

[0013] 1, the object detection system 1 includes a light source 10. The light source 10 is configured to emit infrared light L. For example, the light source 10 is configured to emit light having a wavelength included in the range of 900 nm to 1100 nm in the infrared light wavelength range.

[0014] In addition, the expression "light having a wavelength within the range of 900 nm to 1100 nm" used in this specification means light having all wavelength components from 900 nm to 1100 nm, or light having only a part of the wavelength components within the range of 900 nm to 1100 nm. For example, the infrared light L emitted from the light source 10 may be light having wavelength components from 925 nm to 975 nm with a peak wavelength of 950 nm. In addition, even if the light includes wavelength components outside the range of 900 nm to 1100 nm, it can be interpreted as light having a wavelength within the range of 900 nm to 1100 nm as long as the brightness of the wavelength components outside the range is substantially negligible.

[0015] The light source 10 is attached to the object 40 so that at least a part of the infrared light L is irradiated onto a road surface 100 ahead in the traveling direction of the object 40. For example, the light source 10 is attached to the object 40 so that the infrared light L is emitted onto the road surface 100 3 m ahead in the traveling direction.

[0016] The light source 10 is configured, for example, so that the infrared light L irradiated onto the road surface 100 forms a predetermined light pattern LP. Examples of the predetermined light pattern LP include a light pattern indicating the presence of the object 40 and a light pattern indicating the moving direction of the object 40. The light pattern indicating the presence of the object 40 is not particularly limited as long as it indicates the presence of the object 40, and includes, for example, a pattern indicating a figure such as a circle or a square. An example of a light pattern indicating the moving direction of the object is a pattern indicating a direction such as an arrow.

[0017] The object detection system 1 includes an object detection device 20. The object detection device 20 is mounted on a vehicle 30. The object detection device 20 includes an imaging device 21 and an image processing device 22.

[0018] The imaging device 21 is disposed at an appropriate location on the vehicle 30 so that an image of the area ahead in the traveling direction of the vehicle 30, including at least the road surface 100, is captured. The imaging device 21 is, for example, sensitive to infrared light and generates an image based on the infrared light. For example, the imaging device 21 is a silicon CMOS image sensor having only infrared pixels. The imaging device 21 acquires images at a prescribed frame rate. The imaging device 21 is configured to output image data ID. The image data ID corresponds to an image based on the infrared light. The image data ID may be in the form of analog data or digital data.

[0019] The image processing device 22 includes a reception unit 221, a processing unit 222, and an output unit 223. The reception unit 221 is configured to receive image data ID from the imaging device 21. When the image data ID is in the form of analog data, the reception unit 221 may include an appropriate conversion circuit including an A / D converter. The processing unit 222 processes the image data ID in the form of digital data.

[0020] The processing unit 222 is configured to determine, based on the luminance distribution in the image based on infrared light, whether the object 40 is approaching the vehicle 30. The details of this processing will be described later.

[0021] The processing unit 222 is configured to output a control signal CS through the output unit 223 when it is determined that the object 40 is approaching the vehicle 30. The control signal CS may be in the form of digital data or analog data. When the control signal CS is in the form of analog data, the output unit 223 may include an appropriate conversion circuit including a D / A converter.

[0022] The object detection system 1 includes a control device 31. The control device 31 is, for example, a vehicle control device that controls the traveling of the vehicle 30. The control device 31 causes a controlled device mounted on the vehicle 30 to execute a predetermined operation accompanying the approach of the object 40 based on a control signal CS output from the image processing device 22. For example, the controlled device is an alarm device 32 that notifies the occupants of the vehicle 30 of predetermined information. Based on the control signal CS, the control device 31 notifies the occupants of the vehicle 30 of the approach of the object 40 by the alarm device 32. Examples of the alarm device 32 include a head-up display (HUD), interior lighting, and a warning alarm.

[0023] Alternatively, the controlled device is a brake device 33 that brakes the traveling of the vehicle 30. The control device 31 operates the brake device 33 based on the control signal CS.

[0024] Next, the process of detecting the approach of the target object 40 executed by the processing unit 222 of the image processing device 22 will be described in detail with reference to Fig. 2 to Fig. 6. Fig. 2 illustrates the flow of this process.

[0025] The processing unit 222 receives the image data ID from the imaging device 21 through the receiving unit 221 (STEP 1). The image data ID corresponds to an image based on infrared light.

[0026] Next, the processing unit 222 determines whether the object 40 is approaching the vehicle 30 based on the luminance distribution in the image based on the infrared light (STEP 2).

[0027] Specifically, first, the processing unit 222 judges whether or not a light pattern LP appears in an image based on infrared light, based on the luminance distribution in the image. That is, the processing unit 222 judges whether or not a pixel group whose luminance is equal to or greater than a predetermined value exists in the image based on infrared light. The image used by the processing unit 222 for the judgment is a collection of pixels having a brightness according to the luminance of infrared light. For example, when a predetermined number or more of pixels having a brightness equal to or greater than a predetermined value are connected in the image based on infrared light, or when pixels having a brightness equal to or greater than a predetermined value occupy an area equal to or greater than a predetermined value, the processing unit 222 judges that a light distribution pattern LP appears in the image.

[0028] 3 illustrates an example of a state in which the imaging device 21 mounted on the vehicle 30 captures an image of a T-junction ahead of the vehicle 30 in the traveling direction. The T-junction is an example of an intersection. The T-shape in the figure is a white line indicating the T-junction.

[0029] As illustrated in Fig. 3, a bicycle 41 is moving toward a T-junction, and a light pattern LP emitted from a light source 10 attached to the bicycle 41 is projected onto a road surface 100 of the T-junction. Note that a building 200 exists between the bicycle 41 and the vehicle 30, and the bicycle 41 cannot be recognized from the vehicle 30. The bicycle 41 is an example of an object 40. The building 200 is an example of an obstruction.

[0030] Fig. 4 illustrates an image IM in which the road surface 100 is captured by the imaging device 21 in the situation of Fig. 3. In Fig. 4, the image IM is an image based on infrared light, and areas with high brightness are indicated by solid lines and areas with low brightness are indicated by dashed lines.

[0031] As illustrated in FIG. 4, the light pattern LP emitted from the light source 10 and projected onto the road surface 100 is captured in the image IM captured by the imaging device 21.

[0032] Furthermore, the image IM also includes buildings 200 and a road surface 100 due to reflection of sunlight. However, since the energy of the infrared light wavelength component contained in sunlight is relatively low, the luminance of the pixel group in which the building 200 and the road surface 100 are reflected is lower than the luminance of the pixel group in which the light pattern LP is reflected.

[0033] Therefore, when a pixel group whose luminance is equal to or greater than a predetermined value exists in the image IM, the processing unit 222 determines that the light pattern LP is reflected in the image IM. On the other hand, when a pixel group whose luminance is equal to or greater than a predetermined value exists in the image IM, the processing unit 222 determines that the light pattern LP is not reflected in the image IM. The predetermined value can be appropriately set to a value at which the light pattern LP can be detected.

[0034] When the processing unit 222 determines that the light pattern LP is captured in the image IM, the processing unit 222 determines the moving direction of the object 40 based on the light pattern LP in the image IM. For example, the processing unit 222 determines the moving direction of the object 40 based on the shape of the light pattern LP in the image IM. That is, the processing unit 222 determines the moving direction of the object 40 based on the shape of a pixel group in the image IM whose luminance is equal to or greater than a predetermined value.

[0035] 4, in this example, the light pattern LP projected onto the road surface 100 has the shape of an arrow mark indicating the moving direction of the object 40. Therefore, the processing unit 222 determines that the object 40 to which the light source 10 that projects the light pattern LP is attached is moving in the direction indicated by the arrow mark.

[0036] Then, the processing unit 222 determines whether the object 40 is approaching the vehicle 30 based on the determined moving direction of the object 40. In this example, the arrow mark indicates that the object 40 is moving toward the T-junction where the vehicle 30 is about to enter, and the processing unit 222 determines that the object 40 is approaching the vehicle 30.

[0037] When the processing unit 222 determines that the object 40 is approaching the vehicle 30 (YES in STEP 2), it outputs a control signal CS from the output unit 223 (STEP 3). The control signal CS is transmitted to the control device 31. The control device 31, for example, causes the HUD to display information about the approach of the object 40 based on the control signal CS. The HUD is an example of the notification device 32.

[0038] 5 illustrates an example of the configuration of the HUD 321 mounted on the vehicle 30. The HUD 321 is configured to display predetermined information to an occupant of the vehicle 30 such that the predetermined information is superimposed on the real space outside the vehicle 30.

[0039] Specifically, the HUD 321 has a HUD main body 321A and a transparent screen 321B. The transparent screen 321B is formed by a part of the windshield W. The transparent screen 321B has a HUD display area D1 in which HUD information can be displayed (see FIG. 6). Light (image) emitted from the HUD main body 321A is irradiated onto the HUD display area D1 of the transparent screen 321B. Next, the HUD display area D1 reflects the light emitted from the HUD main body 321A toward the viewpoint E of the occupant H. As a result, the occupant H recognizes the light (image) emitted from the HUD main body 321A as a virtual image formed at a predetermined position in front of the transparent screen 321B. In this way, the HUD information (image) displayed by the HUD 321 is superimposed on the real space in front of the vehicle 30, so that the occupant H feels as if the HUD information is floating above the road.

[0040] 6 illustrates an example of a HUD display area D1 in which information on the approach of an object 40 is displayed as HUD information. The information on the approach of the object 40 includes, for example, information indicating the presence of the object 40 and information indicating the moving direction of the object 40. In this example, a bicycle mark M1 is displayed as information indicating the presence of the object 40. Also, an arrow mark M2 is displayed as information indicating the moving direction of the object. Note that this information may include text information in addition to or instead of graphic information such as marks.

[0041] 2, if the processing unit 222 determines in STEP 2 that the object 40 is not approaching (NO in STEP 2), the processing unit 222 ends this process without outputting the control signal CS. Note that this process is repeated every time image data ID is received in accordance with the frame rate of the imaging device 21.

[0042] In this way, according to the image processing device 22 of the present disclosure, the approach of the object 40 is determined based on the luminance distribution of infrared light in the image IM in which the road surface 100 is captured. Since infrared light has a relatively low energy among the wavelength components contained in sunlight, the luminance of the infrared light emitted from the light source 10 and reflected by the road surface 100 in the image IM is higher than the luminance of the infrared wavelength component of the sunlight reflected by the road surface 100. Therefore, the light pattern LP emitted from the light source 10 and irradiated onto the road surface 100 can be detected from the image IM. In addition, the light emitted from the light source 10 and irradiated onto the road surface 100 is less susceptible to the influence of reflection by a third object present between the light source 10 and the vehicle 30. Therefore, the approach of the object 40 hidden behind a shield can be detected more accurately.

[0043] In particular, sunlight contains fewer wavelength components within the wavelength range of 900 nm to 1100 nm than light components in other wavelength ranges. Therefore, when light with a wavelength within the range of 900 nm to 1100 nm is used as the light emitted from the light source 10, the difference in luminance between the light emitted from the light source 10 and reflected by the road surface 100 and the luminance of the infrared wavelength component of the sunlight reflected by the road surface 100 becomes larger, so that the light pattern LP emitted from the light source 10 and irradiated onto the road surface 100 can be more accurately detected from the image IM.

[0044] In addition, in this embodiment, the image processing device 22 determines the movement direction of the object 40 based on the shape of the light pattern LP projected onto the road surface 100, and therefore can determine the movement direction of the object 40 based on a single image IM.

[0045] In this embodiment, the image processing device 22 notifies the occupant H of the vehicle 30 of the approach of the object 40 via the HUD 321. This allows the occupant H to visually grasp the approach of the object 40 by superimposing it on the real space in front of the vehicle 30.

[0046] Note that the image processing device 22 may be configured to notify the approach of the object 40 using other notification devices 32 such as interior lighting and an alarm, in addition to or instead of the HUD 321.

[0047] Alternatively, the image processing device 22 may be configured to activate the brake device 33 in addition to or instead of the alarm device 32 when it is determined that the object 40 is approaching the vehicle 30. With such a configuration, the automatic brake functions to avoid a collision with the object 40.

[0048] (Variation 1) In the above embodiment, the moving direction of the object 40 is determined based on the shape of the light pattern LP. However, the moving direction of the object 40 may be determined from the positional relationship of the light pattern LP in a plurality of images acquired by the imaging device 21 at different times.

[0049] FIG. 7 illustrates a flow of another example of the process of detecting the approach of the target object 40 executed by the processing unit 222 of the image processing device 22. In FIG.

[0050] 7, the processing unit 222 receives image data ID from the imaging device 21 through the receiving unit 221 (STEP 11). The image data ID corresponds to a first image IM1 based on infrared light.

[0051] Next, the processing unit 222 determines whether the light pattern LP1 is captured in the first image IM1 based on the luminance distribution in the first image IM1 (STEP 12). Specifically, the processing unit 222 determines whether a pixel group whose luminance is equal to or greater than a predetermined value exists in the first image IM1.

[0052] When there is no pixel group whose luminance is equal to or greater than a predetermined value in the first image IM1, the processing unit 222 determines that the light pattern LP1 is not reflected in the first image IM1. On the other hand, when there is a pixel group whose luminance is equal to or greater than a predetermined value in the first image IM1, the processing unit 222 determines that the light pattern LP1 is reflected in the first image IM1.

[0053] When the processing unit 222 determines that the light pattern LP is not captured in the first image IM1 (NO in STEP 12), the processing ends.

[0054] On the other hand, when the processing unit 222 determines that the light pattern LP1 is captured in the first image IM1 (YES in STEP 12), the processing unit 222 receives image data ID from the imaging device 21 through the receiving unit 221 (STEP 13). The image data ID corresponds to the second image IM2 based on infrared light. Note that the processing in STEP 13 may be performed before the processing in STEP 12.

[0055] Next, the processing unit 222 determines whether the light pattern LP2 is captured in the second image IM2 based on the luminance distribution in the second image IM2 (STEP 14). Specifically, the processing unit 222 determines whether a pixel group whose luminance is equal to or greater than a predetermined value exists in the second image IM2.

[0056] When there is no pixel group in the second image IM2 whose luminance is equal to or greater than a predetermined value, the processing unit 222 determines that the light pattern LP2 is not reflected in the second image IM2. On the other hand, when there is a pixel group in the second image IM2 whose luminance is equal to or greater than a predetermined value, the processing unit 222 determines that the light pattern LP2 is reflected in the second image IM2.

[0057] When the processing unit 222 determines that the light pattern LP2 is not captured in the second image IM2 (NO in STEP 14), the processing ends.

[0058] On the other hand, if the processing unit 222 determines that the light pattern LP2 is captured in the second image IM2 (YES in STEP 14), it determines whether the object 40 is approaching the vehicle 30 (STEP 15).

[0059] Specifically, first, the processing unit 222 determines the moving direction of the object 40 based on the position of the light pattern LP1 in the first image IM1 and the position of the light pattern LP2 in the second image IM2. That is, the processing unit 222 determines the moving direction of the object 40 based on the positions of the pixel groups in the first image IM1 whose luminance is equal to or greater than a predetermined value and the positions of the pixel groups in the second image IM2 whose luminance is equal to or greater than a predetermined value.

[0060] Fig. 8 illustrates a first image IM1 acquired by the imaging device 21. Fig. 9 illustrates a second image IM2 acquired by the imaging device 21 after the first image IM1. The first image IM1 and the second image IM2 are, for example, images acquired consecutively. Figs. 8 and 9 show images acquired by the imaging device 21 in the situation of Fig. 3 when the light pattern LP emitted from the light source 10 is a circular light pattern. In Figs. 8 and 9, areas with high brightness are indicated by solid lines, and areas with low brightness are indicated by dashed lines.

[0061] In this example, the light pattern LP2 in the second image IM2 is closer to the T-junction than the light pattern LP1 in the first image IM1. Therefore, the processing unit 222 determines that the object 40 to which the light source 10 that emits the light pattern is attached is approaching the vehicle 30.

[0062] When the processing unit 222 determines that the object 40 is approaching (YES in STEP 15), it outputs a control signal CS from the output unit 223 (STEP 16). The control signal CS is transmitted to the control device 31. Based on the control signal CS, the control device 31 causes the HUD 321 to display information on the approach of the object 40, for example, as shown in FIG.

[0063] On the other hand, if the processing unit 222 determines that the target object 40 is not approaching (NO in STEP 15), it does not output the control signal CS and ends this process.

[0064] With this configuration, the moving direction of the target object 40 can be determined regardless of the shape of the light pattern LP.

[0065] In addition, when the shape of the light pattern LP emitted from the light source 10 is configured to be changeable / settable for each object 40, the processing unit 222 may be configured to compare the shape of the light pattern LP1 included in the first image IM1 with the shape of the light pattern LP2 included in the second image IM2. For example, the processing unit 222 may be configured to determine the moving direction of the object 40 when the shape of the light pattern LP1 included in the first image IM1 is the same as the shape of the light pattern LP2 included in the second image IM2. With this configuration, even when multiple objects 40 exist ahead of the vehicle 30 in the traveling direction, the approach of each object 40 can be determined more accurately.

[0066] (Variation 2) In the above embodiment and modification 1, the image processing device 22 controls a predetermined controlled device when it is determined that the object 40 is approaching the vehicle 30. However, the image processing device 22 may be configured to determine the controlled device to be controlled based on the distance to the intersection ahead of the vehicle 30 when it is determined that the object 40 is approaching the vehicle 30.

[0067] For example, as illustrated in Fig. 1, the object detection device 20 may include a distance measuring device 23. The distance measuring device 23 is configured to measure the distance from the vehicle 30 to an intersection ahead of the vehicle 30. Examples of the distance measuring device 23 include a stereo camera, a millimeter wave radar, a microwave radar, and a laser radar (e.g., a LiDAR unit). The distance measuring device 23 is configured to output distance data DD corresponding to the distance to the intersection ahead of the vehicle 30.

[0068] Fig. 10 shows another example of the flow of the process of detecting the approach of the object 40, which is executed by the image processing device 22 of the object detection device 20 configured as described above. Note that the same reference numerals are given to the processing elements common to the processing flow illustrated in Fig. 2, and repeated explanations will be omitted.

[0069] The processing unit 222 receives the image data ID from the imaging device 21 through the receiving unit 221 (STEP 1). The image data ID corresponds to an image based on infrared light.

[0070] Next, the processing unit 222 determines whether the object 40 is approaching the vehicle 30 based on the luminance distribution in the image based on the infrared light (STEP 2).

[0071] When the processing unit 222 determines that the object 40 is approaching (YES in STEP 2), it receives the speed data VD of the vehicle 30 from the control device 31 through the receiving unit 221 (STEP 21). For example, as shown in Fig. 1, a vehicle speed sensor 34 mounted on the vehicle 30 is connected to the control device 31, and the control device 31 acquires the speed data VD of the vehicle 30 from the vehicle speed sensor 34.

[0072] Furthermore, the processing unit 222 receives distance data DD from the distance measuring device 23 to the intersection ahead of the vehicle 30 through the receiving unit 221 (STEP 22). Note that the process of STEP 22 may be performed before the process of STEP 21.

[0073] Next, the processing unit 222 determines whether the distance to the intersection ahead of the vehicle 30 is equal to or greater than the braking distance of the vehicle 30 (STEP 23). Specifically, the processing unit 222 calculates the braking distance of the vehicle 30 based on the speed of the vehicle 30. Then, the processing unit 222 compares the distance to the intersection ahead of the vehicle 30 with the calculated braking distance of the vehicle 30.

[0074] In this specification, the "braking distance of vehicle 30" includes the distance (free running distance) traveled by vehicle 30 from when occupant H of vehicle 30 recognizes the approach of object 40 until the brake pedal is operated and the braking device is activated, and the distance traveled by vehicle 30 from when the braking device is actually activated until the vehicle 30 stops.

[0075] The braking distance Lb of the vehicle 30 is calculated by the following formula.

[0076]

number

[0077] Here, Vy is the speed of the vehicle 30 [km / h], Ty is the free running time [s], and a is the deceleration of the vehicle 30 [m / s 2 ].

[0078] When the processing unit 222 determines that the distance to the intersection ahead of the vehicle 30 is equal to or greater than the braking distance of the vehicle 30 (YES in STEP 23), it outputs a control signal CS1 (STEP 24). The control signal CS1 is transmitted to the control device 31. Based on the control signal CS1, the control device 31 notifies the occupant H of the vehicle 30 of the approach of the object 40 by the notification device 32.

[0079] On the other hand, when the processing unit 222 determines that the distance to the intersection ahead of the vehicle 30 is shorter than the braking distance of the vehicle 30 (NO in STEP 23), it outputs a control signal CS2 (STEP 25). The control signal CS2 is transmitted to the control device 31. The control device 31 activates the brake device 33 based on the control signal CS2.

[0080] According to this configuration, when the operation of the occupant H of the vehicle 30 determines that the vehicle 30 can be stopped before the intersection, the notification device 32 notifies the occupant H of the vehicle 30 of the approach of the object 40, so that the occupant H of the vehicle 30 can take action to avoid a collision with the object 40. Also, when the operation of the occupant H of the vehicle 30 determines that the vehicle 30 cannot be stopped before the intersection, the automatic brake functions to avoid a collision with the object 40.

[0081] In addition, after processing STEP 24, the processing unit 222 may be configured to compare the distance to the intersection ahead of the vehicle 30 with the braking distance of the vehicle 30, and if it determines that the distance to the intersection ahead of the vehicle 30 is shorter than the braking distance of the vehicle 30, output a control signal CS2 to activate the braking device 33.

[0082] Each function of the processing unit 222 described above can be realized by a general-purpose microprocessor that operates in cooperation with a general-purpose memory. Examples of the general-purpose microprocessor include a CPU, an MPU, and a GPU. Examples of the general-purpose memory include a ROM and a RAM. In this case, the ROM can store a computer program that executes the above-mentioned processing. The ROM is an example of a non-transitory computer-readable medium. The general-purpose microprocessor specifies at least a part of the computer program stored on the ROM, deploys it on the RAM, and executes the above-mentioned processing in cooperation with the RAM. The above-mentioned computer program may be pre-installed in the general-purpose memory, or may be downloaded from an external server device via a communication network and installed in the general-purpose memory. In this case, the external server device is an example of a non-transitory computer-readable medium.

[0083] The functions of the processing unit 222 described above may be realized by a dedicated integrated circuit capable of executing the above computer program, such as a microcontroller, an ASIC, or an FPGA. In this case, the computer program is pre-installed in a storage element included in the dedicated integrated circuit. The storage element is an example of a non-transitory computer-readable medium. The functions of the processing unit 222 may also be realized by a combination of a general-purpose microprocessor and a dedicated integrated circuit.

[0084] (Light pattern irradiation distance) Next, the irradiation distance of the light pattern LP emitted from the light source 10 will be described with reference to FIGS.

[0085] Figure 11 is a diagram for determining the irradiation distance of the light pattern LP emitted from the light source 10. Figure 11 shows the positional relationship between the vehicle 30 and the bicycle 41 when the vehicle 30 is able to recognize the light pattern LP irradiated onto the road surface 100 from the light source 10 attached to the bicycle 41 or the bicycle 41 (when the light source 10 is not installed).

[0086] In FIG. 11, Vy is the speed of the vehicle 30. Vj is the speed of the bicycle 41. C is the collision point at the intersection where the vehicle 30 and the bicycle 41 are predicted to collide when the vehicle 30 travels at the speed Vy and the bicycle 41 travels at the speed Vj. Py is the distance from the vehicle 30 to the building 200 along the traveling direction of the bicycle 41. Px is the distance from the bicycle 41 to the building 200 (obstructing object) along the traveling direction of the vehicle 30. A is the irradiation distance of the light pattern LP along the traveling direction of the bicycle 41 from the light source 10 to the light pattern LP irradiated onto the road surface 100. X is the distance from the light pattern LP to the collision point C along the traveling direction of the bicycle 41. Lb is the braking distance of the vehicle 30. Ln is the recognizable distance from the vehicle 30 to the collision point C. If the recognizable distance Ln is greater than the braking distance Lb, the collision at the collision point C can be prevented.

[0087] The recognizable distance Ln can be calculated as follows:

[0088] First, the following formula (2) can be derived from the similarity relationship between the two right triangles shown with different hatching in FIG.

[0089]

number

[0090] Furthermore, if the bicycle 41 and the vehicle 30 continue traveling at speeds Vy and Vj, respectively, they will collide at a collision point C, and the following equation (3) holds true.

[0091]

number

[0092] By eliminating x from equation (2) and substituting it into equation (3) and solving the quadratic equation for Ln, we obtain the following equation (4).

[0093]

number

[0094] Here, A=0 (when no light pattern is irradiated) is given by the following formula (5).

[0095]

number

[0096] Taking into account equation (5), the following equation (6) can be derived from equation (4).

[0097]

number

[0098] Fig. 12 is a graph showing the relationship between the speed Vy of the vehicle 30 and the distance Px when Ln=Lb when the irradiation distance A of the light pattern LP is changed in the situation of Fig. 11. In this graph, the horizontal axis represents the distance Px [m]. The vertical axis represents the speed Vy of the vehicle 30 when Ln=Lb in the case where the brake device 33 of the vehicle 30 is automatically operated (i.e., the free running time Ty=0 [sec]). The speed V of the vehicle 30 when Ln=Lb is the maximum value of the speed Vy of the vehicle 30 at which a collision with the bicycle 41 can be avoided.

[0099] Note that Py is 1 [m], Px is 1 to 5 [m], and the road surface is dry asphalt (a = 6.86 [m / s 2 ]), the speed Vj of the bicycle 41 was 11.4 [km / h], and the speed Vy and distance Px of the vehicle 30 when Ln = Lb were calculated when the irradiation distance A of the light pattern LP was 0, 1, 2, 3 or 4 [m].

[0100] As described above, the distance Px is the distance from the bicycle 41 to the building 200 in Fig. 11 along the traveling direction of the vehicle 30, so the shorter the distance Px, the worse the visibility of the intersection from the vehicle 30. Therefore, in the graph shown in Fig. 12, the shorter the distance Px, the smaller the speed Vy of the vehicle 30 when Ln = Lb.

[0101] Furthermore, the greater the irradiation distance A of the light pattern LP, the earlier the vehicle 30 can detect the approach of the object 40, and therefore the greater the speed Vy of the vehicle 30 when Ln=Lb.

[0102] Here, there are cases where a vehicle equipped with an automatic braking function is unable to stop before an intersection and a collision with a bicycle occurs, and statistical data shows that nearly 90% of traffic accidents between bicycles and vehicles occur when the vehicle's speed is less than 60 km / h.

[0103] Therefore, by setting the irradiation distance A of the light pattern LP emitted from the light source 10 to be the irradiation distance when the speed Vy of the vehicle 30 when Ln=Lb is 60km / h or more, the possibility of avoiding a collision accident between the bicycle 41 and the vehicle 30 is increased. In this example, from the graph in Fig. 12, when the irradiation distance A of the light pattern LP is 3m or more, the speed Vy of the vehicle 30 when Ln=Lb is 60km / h or more. In other words, by equipping the vehicle 30 with an automatic braking function and configuring the light source 10 so that the irradiation distance A of the light pattern LP is 3m or more, the possibility of avoiding a collision accident between the bicycle 41 and the vehicle 30 can be increased.

[0104] The above-described embodiment is merely an example for facilitating understanding of the present invention. The configurations according to the above-described embodiment may be appropriately modified or improved without departing from the spirit and scope of the present invention.

[0105] In the above embodiment, the bicycle 41 has been taken as an example of the object 40. However, the object 40 may be an object other than the bicycle 41, such as a pedestrian.

[0106] In the above embodiment, the light source 10 is configured to emit a predetermined light pattern LP onto the road surface 100. However, as long as the light source 10 is configured so that at least a part of the light emitted from the light source 10 is irradiated onto the road surface 100 ahead of the object 40 in the traveling direction, the light irradiated onto the road surface 100 does not need to form a light pattern.

[0107] In the above embodiment, the processing unit 222 determines whether the object 40 is approaching the vehicle 30 based on the luminance distribution in the image based on infrared light. However, for example, when the light source 10 is configured to emit light having a wavelength included in the range of 900 nm to 1100 nm in the infrared light wavelength range, the processing unit 222 may be configured to determine whether the object 40 is approaching the vehicle 30 based on the luminance distribution of only light having a wavelength included in the range of 900 nm to 1100 nm in the image based on infrared light.

[0108] In the above embodiment, the imaging device 21 is sensitive to infrared light and generates an image based on infrared light, and the processing unit 222 determines whether the object 40 is approaching the vehicle 30 based on the luminance distribution of the image. However, the imaging device 21 may be configured to be sensitive to visible light and infrared light and generate an image based on visible light and infrared light. For example, the imaging device 21 may be a silicon CMOS image sensor having R, G, B, and infrared pixels. The processing unit 222 may be configured to determine whether the object 40 is approaching the vehicle 30 based on the luminance distribution of only infrared light in the image based on visible light and infrared light. [Explanation of symbols]

[0109] 1. Object Detection System 10 light source 20 Object detection device 21 Imaging device 22 Image processing device 23 Ranging device 30 Vehicles 31 Control device 32 Notification device 33 Brake device 34 Vehicle speed sensor 40 Object 41 Bicycle 100 Road surface 200 Buildings 221 Reception 222 Processing section 223 Output section 321 HUD 321A HUD main body 321B Transparent Screen A Beam Distance C Collision point CS Control Signal CS1 Control Signal CS2 Control Signal D1 HUD display area DD Distance Data E. Viewpoint H Crew ID Image data IM Image IM1 1st image IM2 2nd image L light Lb braking distance Ln Perceivable distance LP Light Pattern LP1 Light Pattern LP2 Light Pattern M1 Bicycle mark M2 Arrow mark Px distance Ty free running time V Vehicle speed VD Speed ​​Data Vj Bicycle Speed Vy Vehicle speed W Windshield

Claims

1. An object detection device mounted on a vehicle for detecting a movable object having a light source that emits infrared light, comprising: An imaging device for capturing an image of a road surface ahead in a traveling direction of the vehicle; an image processing device that, when it is determined that the object is approaching the vehicle based on the luminance distribution of infrared light in the image, outputs a control signal to a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object; An object detection device comprising:

2. the controlled device is an alarm device that notifies a passenger of the vehicle of predetermined information, The object detection device according to claim 1 , wherein, when the image processing device determines that the object is approaching the vehicle, the image processing device outputs a control signal to cause the alarm device to notify an occupant of the vehicle of the approach of the object.

3. the controlled device is a brake device that brakes the traveling of the vehicle, The object detection device according to claim 1 , wherein the image processing device outputs a control signal for activating the brake device when it is determined that the object is approaching the vehicle.

4. 2. The object detection device according to claim 1, wherein the image processing device determines the moving direction of the object based on the positions of pixels in a first image acquired by the imaging device, where the infrared light luminance is equal to or greater than a predetermined value, and the positions of pixels in a second image acquired after the first image, where the infrared light luminance is equal to or greater than a predetermined value.

5. The object detection device according to claim 1 , wherein the image processing device determines the moving direction of the object based on a shape of a pixel group in which a luminance of infrared light in the image acquired by the imaging device is equal to or greater than a predetermined value.

6. a distance measuring device for measuring a distance from the vehicle to an intersection in front of the vehicle where the object is approaching; The object detection device of claim 2, wherein the image processing device acquires information on the speed of the vehicle, and when the distance to the intersection measured by the distance measuring device is equal to or greater than the braking distance of the vehicle, outputs a control signal to the alarm device to cause the alarm device to alert an occupant of the vehicle of the approach of the object.

7. a distance measuring device for measuring a distance from the vehicle to an intersection in front of the vehicle where the object is approaching; The object detection device of claim 3, wherein the image processing device acquires information on the speed of the vehicle, and based on the speed of the vehicle and the distance to the intersection measured by the distance measuring device, outputs a control signal to activate the braking device if the distance is shorter than the braking distance of the vehicle.

8. the notification device is a head-up display configured to display the predetermined information toward an occupant of the vehicle so that the predetermined information is superimposed on a real space outside the vehicle, The object detection device according to claim 2 , wherein the image processing device outputs a control signal for causing the head-up display to display information about the approach of the object when the image processing device determines that the object is approaching the vehicle.

9. The light source is configured to emit light having a wavelength in the infrared wavelength range of 900 nm to 1100 nm; 9. The object detection device according to claim 1, wherein the image processing device determines whether the object is approaching the vehicle based on a luminance distribution of light having a wavelength within a range of 900 nm to 1100 nm in the image.

10. An image processing device installed in an object detection device that is mounted on a vehicle and detects a movable object having a light source that emits infrared light, A reception unit that receives an image including a road surface ahead in a traveling direction of the vehicle; a processing unit that determines whether the object is approaching the vehicle based on a luminance distribution of infrared light in the image; an output unit that outputs a control signal to cause a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object when it is determined that the object is approaching the vehicle; The image processing device comprises:

11. A computer program executable by a processing unit of an image processing device mounted on an object detection device that is mounted on a vehicle and detects a movable object having a light source that emits infrared light, the computer program comprising: When the above-mentioned program is executed, the image processing device Accepting an image showing a road surface ahead in a traveling direction of the vehicle; determining whether the object is approaching the vehicle based on a luminance distribution of infrared light in the image; When it is determined that the object is approaching the vehicle, a control signal is output to cause a controlled device mounted on the vehicle to execute a predetermined operation associated with the approach of the object. Computer program.

Images