JP2021064149A - Image processing device - Google Patents

Abstract

To provide an image processing device capable of precisely detecting, from image data, an edge of a recognition target such as a division line on a road surface on which a vehicle is traveling.SOLUTION: One example of an image processing device according to an embodiment includes an acquisition unit that acquires image data obtained by capturing an image of the surrounding area of a vehicle through an image-capturing unit mounted on the vehicle, and an edge detection unit that detects an edge in a pixel, among the pixels of the image data, corresponding to a first image-capturing region of the image-capturing unit by using an edge detecting filter of a first filter size, and detects an edge in a pixel, among the pixels, corresponding to a second image-capturing region at a farther distance from the image-capturing unit than the first image-capturing region by using an edge detecting filter of a second filter size which is smaller than the first filter size.SELECTED DRAWING: Figure 5

Description

Embodiments of the present invention relate to an image processing apparatus.

Based on the steering angle of the steering wheel when the vehicle is parked, the surroundings of the vehicle are imaged by the imaging unit, and an area where the authentication target such as the lane marking of the parking target position can be detected is set for the image data. A technique for detecting an object to be certified from within the area has been developed.

Japanese Unexamined Patent Publication No. 10-216219

By the way, the noise of the road surface and the size of the lane markings existing in the image data change according to the distance from the imaging unit. Therefore, if the edge of the recognition target object in the image data is detected by using a filter of the same size regardless of the position in the image data, a lot of road noise is detected or the authentication target object is detected. You may not be able to do it.

Therefore, one of the problems of the embodiment is to provide an image processing device capable of detecting the edge of a recognition object such as a lane marking on a road surface on which a vehicle travels with high accuracy from image data.

As an example, the image processing apparatus of the embodiment includes an acquisition unit that acquires image data obtained by imaging the surroundings of the vehicle by an image pickup unit mounted on the vehicle, and a first image pickup of the image pickup unit among the pixels of the image data. Edges are detected for the pixels corresponding to the region using the edge detection filter of the first filter size, and the pixels correspond to the second imaging region in which the distance from the imaging unit is farther than the first imaging region. The pixel is provided with an edge detection unit that detects an edge using an edge detection filter having a second filter size smaller than the first filter size. Therefore, as an example, it is possible to improve the detection accuracy of the edge of the image of the recognition target object from the image data.

Further, in the image processing apparatus of the embodiment, as an example, the edge detection unit detects the edge of the pixel by using the edge detection filter having a width smaller than the width of the image corresponding to the authentication target in the image data. To do. Therefore, as an example, it is possible to further improve the detection accuracy of the edge of the image of the recognition target object from the image data.

Further, in the image processing apparatus of the embodiment, as an example, the edge detection unit uses the edge detection filter having a width of 1/2 of the width of the image corresponding to the object to be authenticated in the image data of the pixel. Detect edges. Therefore, as an example, it is possible to further improve the detection accuracy of the edge of the image of the recognition target object from the image data.

Further, in the image processing apparatus of the embodiment, as an example, the edge detection unit changes the filter size of the edge detection filter by multiplying the gradient of the area where the vehicle is parked. Therefore, as an example, it is possible to further improve the detection accuracy of the edge of the image of the recognition target object from the image data.

FIG. 1 is an exemplary perspective view showing a state in which a part of the passenger compartment of the vehicle according to the present embodiment is seen through. FIG. 2 is an exemplary plan view of the vehicle according to the present embodiment. FIG. 3 is a view of an example of the dashboard of the vehicle according to the present embodiment as viewed from the rear of the vehicle. FIG. 4 is an exemplary block diagram of the configuration of the parking support system included in the vehicle according to the present embodiment. FIG. 5 is a diagram showing an example of the functional configuration of the ECU included in the vehicle according to the present embodiment. FIG. 6 is a diagram for explaining an example of edge detection processing from image data by the ECU included in the vehicle according to the present embodiment. FIG. 7 is a diagram for explaining an example of the filter size change processing of the edge detection filter by the ECU included in the vehicle according to the present embodiment. FIG. 8 is a flowchart showing an example of a flow of edge detection processing by the ECU included in the vehicle according to the present embodiment.

Hereinafter, exemplary embodiments of the present invention will be disclosed. The configurations of the embodiments shown below, as well as the actions, results, and effects produced by such configurations, are examples. The present invention can be realized by a configuration other than the configurations disclosed in the following embodiments, and at least one of various effects based on the basic configuration and derivative effects can be obtained. ..

The vehicle 1 of the present embodiment may be, for example, an automobile having an internal combustion engine as a drive source (not shown), that is, an internal combustion engine automobile, or an automobile having an electric motor (not shown) as a drive source, that is, an electric vehicle or a fuel cell. It may be an automobile or the like, a hybrid automobile using both of them as a drive source, or an automobile having another drive source. Further, the vehicle 1 can be equipped with various transmission devices, and can be equipped with various devices necessary for driving an internal combustion engine or an electric motor, such as a system or a component. In addition, the method, number, layout, and the like of the devices involved in driving the wheels 3 in the vehicle 1 can be set in various ways.

FIG. 1 is an exemplary perspective view showing a state in which a part of the passenger compartment of the vehicle according to the present embodiment is seen through. FIG. 2 is an exemplary plan view of the vehicle according to the present embodiment. FIG. 3 is a view of an example of the dashboard of the vehicle according to the present embodiment as viewed from the rear of the vehicle. FIG. 4 is an exemplary block diagram of the configuration of the parking support system included in the vehicle according to the present embodiment.

First, an example of the configuration of the vehicle 1 according to the present embodiment will be described with reference to FIGS. 1 to 4.

As illustrated in FIG. 1, the vehicle body 2 constitutes a passenger compartment 2a on which an occupant (not shown) rides. In the passenger compartment 2a, a steering unit 4, an acceleration operation unit 5, a braking operation unit 6, a speed change operation unit 7, and the like are provided so as to face the driver's seat 2b as a occupant.

The steering unit 4 is, for example, a steering wheel protruding from the dashboard 24. The acceleration operation unit 5 is, for example, an accelerator pedal located under the driver's feet. The braking operation unit 6 is, for example, a brake pedal located under the driver's feet. The speed change operation unit 7 is, for example, a shift lever protruding from the center console. The steering unit 4, the acceleration operation unit 5, the braking operation unit 6, the speed change operation unit 7, and the like are not limited thereto.

Further, in the vehicle interior 2a, a display device 8 as a display output unit and an audio output device 9 as an audio output unit are provided. The display device 8 is, for example, an LCD (Liquid Crystal Display), an OELD (Organic Electroluminescent Display), or the like. The audio output device 9 is, for example, a speaker. Further, the display device 8 is covered with a transparent operation input unit 10 such as a touch panel. The occupant can visually recognize the image displayed on the display screen of the display device 8 via the operation input unit 10. Further, the occupant can execute the operation input by touching, pushing or moving the operation input unit 10 with a finger or the like at a position corresponding to the image displayed on the display screen of the display device 8. ..

The display device 8, the voice output device 9, the operation input unit 10, and the like are provided, for example, in the monitor device 11 located at the center of the dashboard 24 in the vehicle width direction, that is, in the left-right direction. The monitoring device 11 can have operation input units (not shown) such as switches, dials, joysticks, and push buttons. Further, an audio output device (not shown) can be provided at another position in the vehicle interior 2a different from the monitor device 11, and audio is output from the audio output device 9 of the monitor device 11 and another audio output device. be able to. The monitoring device 11 can also be used as, for example, a navigation system or an audio system.

Further, a display device 12 different from the display device 8 is provided in the vehicle interior 2a. As illustrated in FIG. 3, the display device 12 is provided, for example, on the instrument panel 25 of the dashboard 24, and is located between the speed display 25a and the rotation speed display 25b at substantially the center of the instrument panel 25. Is located in. The size of the screen 12a of the display device 12 is smaller than the size of the screen 8a of the display device 8. The display device 12 may display an image mainly showing information regarding parking assistance of the vehicle 1. The amount of information displayed on the display device 12 may be less than the amount of information displayed on the display device 8. The display device 12 is, for example, an LCD, an OELD, or the like. The information displayed on the display device 12 may be displayed on the display device 8.

Further, as illustrated in FIGS. 1 and 2, the vehicle 1 is, for example, a four-wheeled vehicle, and has two left and right front wheels 3F and two left and right rear wheels 3R. All of these four wheels 3 can be configured to be steerable. As illustrated in FIG. 4, vehicle 1 has a steering system 13 that steers at least two wheels 3.

The steering system 13 has an actuator 13a and a torque sensor 13b. The steering system 13 is electrically controlled by an ECU 14 (Electronic Control Unit) or the like to operate the actuator 13a. The steering system 13 is, for example, an electric power steering system, an SBW (Steer By Wire) system, or the like. The steering system 13 adds torque, that is, assist torque, to the steering portion 4 by the actuator 13a to supplement the steering force, or steers the wheels 3 by the actuator 13a. In this case, the actuator 13a may steer one wheel 3 or a plurality of wheels 3. Further, the torque sensor 13b detects, for example, the torque given to the steering unit 4 by the driver.

Further, as illustrated in FIG. 2, the vehicle body 2 is provided with, for example, four imaging units 15a to 15d as a plurality of imaging units 15. The image pickup unit 15 is, for example, a digital camera having a built-in image pickup element such as a CCD (Charge Coupled Device) or a CIS (CMOS Image Sensor). The imaging unit 15 can output moving image data at a predetermined frame rate. The imaging unit 15 has a wide-angle lens or a fisheye lens, respectively, and can photograph a range of, for example, 140 ° to 190 ° in the horizontal direction. Further, the optical axis of the imaging unit 15 is set obliquely downward. Therefore, the imaging unit 15 sequentially photographs the external environment around the vehicle body 2 including the road surface on which the vehicle 1 can move and the area where the vehicle 1 can park, and outputs the captured image data.

The image pickup unit 15a is located, for example, at the rear end portion 2e of the vehicle body 2 and is provided on the wall portion below the door 2h of the rear trunk. The imaging unit 15b is located, for example, at the right end 2f of the vehicle body 2 and is provided on the right door mirror 2g. The image pickup unit 15c is located, for example, on the front side of the vehicle body 2, that is, on the front end portion 2c in the front-rear direction of the vehicle, and is provided on the front bumper or the like. The image pickup unit 15d is located, for example, on the left side of the vehicle body 2, that is, on the left end portion 2d in the vehicle width direction, and is provided on the door mirror 2g as a protrusion on the left side. The ECU 14 executes arithmetic processing and image processing based on the image data obtained by the plurality of imaging units 15, generates an image with a wider viewing angle, and obtains a virtual bird's-eye view image of the vehicle 1 viewed from above. Can be generated. The bird's-eye view image may also be referred to as a flat image.

Further, the ECU 14 identifies the lane markings and the like shown on the road surface around the vehicle 1 from the image data of the imaging unit 15, and detects (extracts) the parking lot and the like shown by the lane markings and the like.

Further, as illustrated in FIGS. 1 and 2, the vehicle body 2 is provided with, for example, four distance measuring units 16a to 16d and eight distance measuring units 17a to 17h as a plurality of distance measuring units 16 and 17. Has been done. The ranging units 16 and 17 are, for example, sonars that emit ultrasonic waves and capture the reflected waves. Sonar can also be referred to as a sonar sensor, or ultrasonic detector. The ECU 14 can measure the presence or absence of an object such as an obstacle located around the vehicle 1 and the distance to the object based on the detection results of the distance measuring units 16 and 17. That is, the distance measuring units 16 and 17 are examples of detection units that detect an object. The ranging unit 17 can be used, for example, to detect an object at a relatively short distance, and the ranging unit 16 can be used, for example, to detect an object at a relatively long distance farther than the ranging unit 17. Further, the distance measuring unit 17 can be used for detecting an object in front of and behind the vehicle 1, for example, and the distance measuring unit 16 can be used for detecting an object on the side of the vehicle 1.

Further, as illustrated in FIG. 4, in the parking support system 100, in addition to the ECU 14, the monitor device 11, the steering system 13, the distance measuring units 16, 17, and the like, the brake system 18, the steering angle sensor 19, and the accelerator sensor 20 , The shift sensor 21, the wheel speed sensor 22, and the like are electrically connected via the in-vehicle network 23 as a telecommunications line. The in-vehicle network 23 is configured as, for example, a CAN (controller area network).

The ECU 14 can control the steering system 13, the brake system 18, and the like by sending a control signal through the in-vehicle network 23. Further, the ECU 14 detects the torque sensor 13b, the brake sensor 18b, the steering angle sensor 19, the distance measuring unit 16, the distance measuring unit 17, the accelerator sensor 20, the shift sensor 21, the wheel speed sensor 22, and the like via the in-vehicle network 23. The result, the operation signal of the operation input unit 10 and the like can be received.

The ECU 14 includes, for example, a CPU 14a (Central Processing Unit), a ROM (Read Only Memory) 14b, a RAM (Random Access Memory) 14c, a display control unit 14d, a voice control unit 14e, an SSD (Solid State Drive, flash memory) 14f, and the like. have.

The CPU 14a, for example, performs image processing related to images displayed on the display devices 8 and 12, determines a target position of the vehicle 1, calculates a movement path of the vehicle 1, determines whether or not there is interference with an object, and determines whether or not the vehicle 1 interferes with the vehicle 1. Various arithmetic processes and controls such as automatic control and cancellation of automatic control can be executed. The CPU 14a can read a program installed and stored in a non-volatile storage device such as a ROM 14b, and execute arithmetic processing according to the program.

The RAM 14c temporarily stores various data used in the calculation by the CPU 14a. Further, the display control unit 14d mainly executes image processing using the image data obtained by the imaging unit 15 and synthesizing the image data displayed by the display device 8 among the arithmetic processes in the ECU 14. Further, the voice control unit 14e mainly executes the processing of the voice data output by the voice output device 9 among the arithmetic processing in the ECU 14. Further, the SSD 14f is a rewritable non-volatile storage unit, and can store data even when the power supply of the ECU 14 is turned off. The CPU 14a, ROM 14b, RAM 14c, and the like can be integrated in the same package. Further, the ECU 14 may have a configuration in which another logical operation processor such as a DSP (Digital Signal Processor), a logic circuit, or the like is used instead of the CPU 14a. Further, an HDD (Hard Disk Drive) may be provided instead of the SSD 14f, and the SSD 14f and the HDD may be provided separately from the ECU 14. The ECU 14 is an example of an image processing device.

The brake system 18 includes, for example, an ABS (Anti-lock Brake System) that suppresses the lock of the brake, a sideslip prevention device (ESC: Electronic Stability Control) that suppresses the sideslip of the vehicle 1 during cornering, and enhances the braking force (ESC: Electronic Stability Control). An electric brake system (which executes brake assist), BBW (Brake By Wire), etc. The brake system 18 applies a braking force to the wheels 3 and thus to the vehicle 1 via the actuator 18a. Further, the brake system 18 can execute various controls by detecting signs of brake lock, idling of the wheels 3, skidding, etc. from the difference in rotation between the left and right wheels 3. The brake sensor 18b is, for example, a sensor that detects the position of the movable portion of the braking operation portion 6. The brake sensor 18b can detect the position of the brake pedal as a movable part. The brake sensor 18b includes a displacement sensor.

The steering angle sensor 19 is, for example, a sensor that detects the steering amount of the steering unit 4 such as the steering wheel. The rudder angle sensor 19 is configured by using, for example, a Hall element or the like. The ECU 14 acquires the steering amount of the steering unit 4 by the driver, the steering amount of each wheel 3 at the time of automatic steering, and the like from the steering angle sensor 19 and executes various controls. The steering angle sensor 19 detects the rotation angle of the rotating portion included in the steering unit 4. The steering angle sensor 19 is an example of an angle sensor.

The accelerator sensor 20 is, for example, a sensor that detects the position of a movable portion of the acceleration operation unit 5. The accelerator sensor 20 can detect the position of the accelerator pedal as a movable part. The accelerator sensor 20 includes a displacement sensor.

The shift sensor 21 is, for example, a sensor that detects the position of the movable portion of the shift operation unit 7. The shift sensor 21 can detect the positions of levers, arms, buttons, etc. as movable parts. The shift sensor 21 may include a displacement sensor or may be configured as a switch.

The wheel speed sensor 22 is a sensor that detects the amount of rotation of the wheel 3 and the number of rotations per unit time. The wheel speed sensor 22 outputs the number of wheel speed pulses indicating the detected rotation speed as a sensor value. The wheel speed sensor 22 may be configured by using, for example, a Hall element or the like. The ECU 14 calculates the movement amount of the vehicle 1 based on the sensor value acquired from the wheel speed sensor 22, and executes various controls. The wheel speed sensor 22 may be provided in the brake system 18. In that case, the ECU 14 acquires the detection result of the wheel speed sensor 22 via the brake system 18.

The configurations, arrangements, electrical connection forms, etc. of the various sensors and actuators described above are examples and can be set (changed) in various ways.

FIG. 5 is a diagram showing an example of the functional configuration of the ECU included in the vehicle according to the present embodiment.

Next, an example of the functional configuration of the ECU 14 included in the vehicle 1 according to the present embodiment will be described with reference to FIG.

As shown in FIG. 5, the ECU 14 according to the present embodiment includes an information acquisition unit 141, an ROI setting unit 142, an edge detection unit 143, a feature point extraction unit 144, a straight line detection unit 145, a lane marking unit 146, and information update. It functions as an example of an image processing device having a unit 147. In the present embodiment, the CPU 14a reads and executes a program stored in a storage device such as a ROM 14b or SSD 14f to execute the information acquisition unit 141, the ROI setting unit 142, the edge detection unit 143, the feature point extraction unit 144, and the straight line. Various functional modules such as a detection unit 145, a lane marking unit 146, and an information update unit 147 are realized.

In the present embodiment, various functional modules such as the information acquisition unit 141, the ROI setting unit 142, the edge detection unit 143, the feature point extraction unit 144, the straight line detection unit 145, the lane marking unit 146, and the information update unit 147 are This is realized by a processor such as the CPU 14a reading and executing a program stored in a storage device such as the ROM 14b or the SSD 14f, but the present invention is not limited to this. For example, various functional modules such as the information acquisition unit 141, the ROI setting unit 142, the edge detection unit 143, the feature point extraction unit 144, the straight line detection unit 145, the lane marking unit 146, and the information update unit 147 are independent hardware. It can also be realized by wear. Further, various functional modules such as an information acquisition unit 141, an ROI setting unit 142, an edge detection unit 143, a feature point extraction unit 144, a straight line detection unit 145, a lane marking detection unit 146, and an information update unit 147 are examples. , Each functional module may be integrated or subdivided as long as the same function can be realized.

The information acquisition unit 141 is an example of an acquisition unit that acquires various information such as image data obtained by imaging the surroundings of the vehicle 1 by the image pickup unit 15. In the present embodiment, the information acquisition unit 141 acquires image data from each of the plurality of imaging units 15a to 15d.

The ROI setting unit 142 is an example of a setting unit that sets a search range (ROI: Region Of Interest) for image data. Here, the search range is a range for detecting an image of an authentication target such as a lane marking included in the image data. For example, the ROI setting unit 142 sets the area of the image data excluding the image of the vehicle body 2 of the vehicle 1 as the search range.

The edge detection unit 143 is an example of an image processing unit that detects the edge of the image data (search range set by the ROI setting unit 142 in the present embodiment) acquired by the information acquisition unit 141.

At that time, the edge detection unit 143 has a filter size for the pixels included in the image data acquired by the information acquisition unit 141 and corresponding to the image pickup region on the front side, which is close to the image pickup unit 15. Detect edges using a large edge detection filter. On the other hand, the edge detection unit 143 uses an edge detection filter having a small filter size for the pixels included in the image data and corresponding to the image pickup region on the far side, which is far from the image pickup unit 15. Detect edges.

That is, the edge detection unit 143 has an edge detection filter having a first filter size for pixels corresponding to an imaging region (an example of a first imaging region) that is close to the imaging unit 15 among the pixels of the image data. Detect edges using. On the other hand, the edge detection unit 143 first filters the pixels of the image data corresponding to the imaging region (an example of the second imaging region) in which the distance from the imaging unit 15 is farther than the first imaging region. Edges are detected using an edge detection filter with a second filter size larger than the size.

As a result, the edge of the image of the recognition object existing in the imaging region far from the imaging unit 15 cannot be detected, or noise other than the recognition object existing in the imaging region close to the imaging unit 15 (for example). , It is possible to suppress the detection of many edges of road surface noise that exists like sesame salt. As a result, it is possible to improve the detection accuracy of the edge of the image of the recognition target object from the image data.

In the present embodiment, a storage device such as ROM 14b or SSD 14f stores edge detection filters having a plurality of filter sizes (pixels). Then, the edge detection unit 143 obtains the filter size (pixel) of the edge detection filter based on the pixel resolution R (mm / pixel) and the width W (mm) of the recognition target object in the real space. Here, the pixel resolution R is the pixel resolution of an image having a width (pixel) corresponding to the width W (mm) of the authentication target object in the real space and including the pixel of interest in the image data.

For example, the edge detection unit 143 obtains the number of pixels (= (W / 2) / R) corresponding to 1/2 of the width W of the authentication target object in the real space in the image data. Next, the edge detection unit 143 reads out an edge detection filter having a filter size having the obtained number of pixels in each of the width direction and the height direction from the storage device. Then, the edge detection unit 143 detects the edge of the pixel of interest by using the read edge detection filter.

That is, the edge detection unit 143 detects the edge of the pixel of interest in the image data by using an edge detection filter having a width and height of 1/2 of the image corresponding to the authentication target in the real space. As a result, it is possible to prevent the edge of the pixel of interest from being detected by using an edge detection filter having a width larger than the number of pixels corresponding to the width W of the recognition target in the real space, so that the recognition target from the image data can be prevented. The edge detection accuracy of an object image can be further improved.

In the present embodiment, the edge detection unit 143 detects the edge of the pixel of interest in the image data by using an edge detection filter having a width and height of 1/2 of the image corresponding to the recognition target in the real space. However, the image data is not limited to this as long as it detects the edge of the pixel of interest by using an edge detection filter having a width and height smaller than the image corresponding to the recognition target in the real space. ..

Further, in the present embodiment, the edge detection unit 143 detects the edge of the pixel of interest in the image data by using an edge detection filter having a width and height smaller than the image corresponding to the authentication target in the real space. However, in the image data, the edge of the pixel of interest may be detected by using an edge detection filter having a width smaller than the image corresponding to the object to be authenticated in the real space.

Further, the edge detection unit 143 can change the filter size of the edge detection filter used for detecting the edge of the image data by multiplying the gradient of the area where the vehicle 1 is parked. For example, the edge detection unit 143 reduces the filter size of the edge detection filter when the slope of the area where the vehicle 1 is parked is inclined downward from the current position of the vehicle 1. On the other hand, the edge detection unit 143 increases the filter size of the edge detection filter when the slope of the area where the vehicle 1 is parked is inclined upward from the current position of the vehicle 1.

As a result, even if the size of the image of the recognition object included in the image data changes due to the change in the gradient of the area where the vehicle 1 is parked, the edge detection filter according to the gradient is used to obtain an edge from the image data. Can be detected. As a result, the accuracy of detecting the edge of the image of the recognition object from the image data can be further improved.

The feature point extraction unit 144 is an example of an extraction unit that extracts feature points included in the image data based on the edge detection result by the edge detection unit 143.

The straight line detection unit 145 detects a straight line included in the image data based on the extraction result of the feature points from the image data.

The lane marking detection unit 146 detects the authentication target included in the image data based on the detection result of the straight line from the image data.

The information update unit 147 determines the target position of the vehicle 1, calculates the movement path of the vehicle 1, and determines whether or not there is interference with the object, based on the detection result of the recognition target object from the image data by the lane marking detection unit 146. , Various arithmetic processing and control such as automatic driving of vehicle 1 and cancellation of automatic driving shall be executed.

FIG. 6 is a diagram for explaining an example of edge detection processing from image data by the ECU included in the vehicle according to the present embodiment.

Next, an example of edge detection processing from image data by the ECU 14 will be described with reference to FIG.

For example, as shown in FIG. 6, when the vehicle 1 is parked in the parking area surrounded by the parking frame 601 (an example of the recognition target object), the information acquisition unit 141 is transmitted from the image pickup unit 15d provided on the left side of the vehicle body 2. Get image data.

As shown in FIG. 6, the edge detection unit 143 acquires the width (line width) W (mm) of the parking frame 601 in the real space.

Next, the edge detection unit 143 pays attention to the number of pixels (pixel resolution R) of the image having a width and height corresponding to 1/2 of the width W of the parking frame 601 and including the pixel of interest in the image data. Obtained as the filter size of the pixel edge detection filter.

After that, the edge detection unit 143 reads an edge detection filter having a obtained filter size from a storage device such as ROM 14b or SSD 14f, and detects the edge of the pixel of interest using the read edge detection filter.

FIG. 7 is a diagram for explaining an example of the filter size change processing of the edge detection filter by the ECU included in the vehicle according to the present embodiment.

Next, an example of the process of changing the size of the edge detection filter by the ECU 14 will be described with reference to FIG. 7.

When the image data G is acquired by the information acquisition unit 141, the edge detection unit 143 shifts the pixel of interest in the x-axis direction of the image data G in order from the upper left pixel of the image data G, as shown in FIG. , Detects the edge of the pixel of interest. Then, as shown in FIG. 7, the edge detection unit 143 shifts the pixel of interest in the y-axis direction when the edge detection of the pixels in one row in the x-axis direction is completed, and again, the x-axis of the image data G The edge of the pixel of interest is detected while shifting the pixel of interest in the direction.

As shown in FIG. 7, the edge detection unit 143 repeats the above process until the edge detection of the lower right pixel of the image data G is completed. That is, the edge detection unit 143 detects the edges of the pixels included in the image data G while moving the pixels of interest on the image data G by raster scanning.

By the way, the width of the image TG of the authentication target such as the parking frame included in the image data G changes according to the distance from the imaging unit 15 to the authentication target. Specifically, as shown in FIG. 7, the width of the image TG of the authentication target becomes smaller as the distance from the imaging unit 15 to the authentication target becomes longer.

Therefore, in the image data G, an edge detection filter having the same filter size is used for the image on the front side, which is close to the image pickup unit 15, and the image on the back side, which is far from the image pickup unit 15. , Edge detection may reduce the edge detection accuracy of the image data G.

For example, when edge detection is performed using an edge detection filter having a small filter size for both the front side image and the back side image, the edge of the image TG of the image TG of the back side authentication target is used. Although the detection accuracy can be increased, fine noise contained in the image on the front side may be detected as an edge.

Further, for example, when edge detection is performed using an edge detection filter having a large filter size for both the front side image and the back side image, fine noise contained in the front side image is generated. Although it is possible to suppress the detection as an edge, the detection accuracy of the edge of the image TG of the authentication target on the back side may be lowered.

Therefore, as shown in FIG. 7, the edge detection unit 143 has a large filter size (for example, 12) for the attention pixel of the image G1 on the front side where the size of the image TG of the authentication target is large in the image data G. The edge is detected by using the edge detection filter F1 of × 12). As a result, it is possible to suppress the detection of fine noise contained in the front image G1 as an edge.

Further, as shown in FIG. 7, the edge detection unit 143 has a small filter size (for example, 3) for the attention pixel of the image G2 on the back side where the size of the image TG of the authentication target is small in the image data G. The edge is detected by using the edge detection filter F2 of × 3). As a result, even when the size of the image TG of the authentication target on the back side is small, the edge of the image TG can be detected.

Further, as shown in FIG. 7, the edge detection unit 143 filters the attention pixel of the central image G3, which is intermediate between the front image G2 and the back image G1, in the image data G. Edges are detected using an edge detection filter F3 of size (eg, 9x9). As a result, it is possible to improve the detection accuracy of the image TG of the authentication target object included in the central image G3 while suppressing the detection of fine noise contained in the central image G3 as an edge.

FIG. 8 is a flowchart showing an example of a flow of edge detection processing by the ECU included in the vehicle according to the present embodiment.

Next, an example of the flow of the edge detection process by the ECU 14 according to the present embodiment will be described with reference to FIG.

When the image data is acquired by the information acquisition unit 141, the ROI setting unit 142 sets the search range for the image data (step S801).

Next, the edge detection unit 143 acquires the pixel resolution R of the image including the pixel of interest among the pixels in the search range (step S802). Further, the edge detection unit 143 acquires the width W of the recognition object to be detected.

Next, the edge detection unit 143 obtains the filter size of the edge detection filter used for detecting the edge of the pixel of interest based on the pixel resolution R and the width W of the recognition object to be detected (step S803).

Next, the edge detection unit 143 detects the edge of the pixel of interest using the edge detection filter of the obtained filter size (step S804). The edge detection unit 143 repeats the processes shown in steps S802 to S804 while moving the pixel of interest on the image data by raster scanning.

When the edges of all the pixels in the search range are detected, the feature point extraction unit 144 extracts the feature points in the search range based on the detection result of the edges of the pixels in the search range (step S805).

The straight line detection unit 145 detects a straight line included in the search range based on the extraction result of the feature points from the search range (step S806).

The lane marking detection unit 146 detects a recognition target such as a lane marking within the search range based on the straight line detection result by the straight line detection unit 145 (step S807).

As described above, according to the vehicle 1 according to the present embodiment, the edge of the pixel of interest is detected by using the edge detection filter having a width larger than the number of pixels corresponding to the width W of the recognition object in the real space. Therefore, it is possible to improve the detection accuracy of the edge of the image of the recognition target object from the image data.

1 vehicle 14 ECU
14a CPU
14b ROM
14c RAM
14f SSD
15 Imaging unit 141 Information acquisition unit 142 ROI setting unit 143 Edge detection unit 144 Feature point extraction unit 145 Straight line detection unit 146 Section line detection unit 147 Information update unit

Claims (4)

An acquisition unit that acquires image data obtained by imaging the surroundings of the vehicle by an imaging unit mounted on the vehicle,
Among the pixels of the image data, the edge of the pixel corresponding to the first imaging region of the imaging unit is detected by using the edge detection filter of the first filter size, and among the pixels, the pixel from the imaging unit is detected. An edge detection unit that detects an edge of a pixel corresponding to a second imaging region whose distance is farther than the first imaging region by using an edge detection filter having a second filter size smaller than the first filter size.
An image processing device comprising. The image processing apparatus according to claim 1, wherein the edge detection unit detects the edge of the pixel by using the edge detection filter having a width smaller than the width of the image corresponding to the authentication target in the image data. The image processing apparatus according to claim 2, wherein the edge detection unit detects the edge of the pixel by using the edge detection filter having a width of 1/2 of the width of the image corresponding to the object to be authenticated in the image data. .. The image processing device according to any one of claims 1 to 3, wherein the edge detection unit multiplies the gradient of the area where the vehicle is parked to change the filter size of the edge detection filter.

Images