JP2018194538A - Information processing system and program - Google Patents

Abstract

To provide an information processing system and a program capable of precisely estimating the distance from a monocular camera to an object.SOLUTION: An information processing system 100 comprises: an image acquisition part 110 configured to acquire an image picked up by one monocular camera 10; an area determination part 120 configured to determine an area of an object in the image; an area division part 150 configured to divide the area of the object on the basis of changes of an end portion of the area of the determined object in a Y axial direction with respect to the Y axial direction; and a distance estimation part 170 configured to estimate the distance from the monocular camera 10 to the object corresponding to a partial area of the object with respect to at least one of the partial area of the object obtained by division of the object area.SELECTED DRAWING: Figure 4

Description

  The present disclosure relates to an information processing apparatus and a program.

  In recent years, a distance estimation device that recognizes an obstacle from an image obtained by imaging with a camera and calculates a distance from the vehicle to the obstacle based on a predetermined distance table is known. However, simply calculating the distance from the vehicle to the obstacle based on the distance table may make it difficult to calculate the correct distance when the road is inclined.

  Therefore, Patent Document 1 discloses a distance estimation device that can calculate the distance from the vehicle to an obstacle even when the road is inclined. The distance estimation apparatus includes a video camera for imaging mounted on the own vehicle and a distance calculation unit that calculates the distance between the own vehicle and the obstacle.

  The distance estimation device extracts a normal vector of an obstacle from an image obtained by imaging with a video camera, and based on the extracted normal vector, is the vehicle traveling on a ramp Determine whether or not. Then, when it is determined that the host vehicle is traveling on an inclined road, the distance estimating device calculates an inclination angle of the inclined road with respect to the flat road. The distance calculation unit corrects the distance from the boundary between the flat road and the slope to the obstacle based on the calculated inclination angle, and calculates the distance between the vehicle and the obstacle.

JP2013-92820A

  However, in the distance estimation device disclosed in Patent Document 1, it may be difficult to accurately estimate the distance from the company to the obstacle. For example, in the distance estimation device, although the distance from the vehicle to the obstacle can be corrected based on the inclination angle, it may be difficult to accurately calculate the contact position between the obstacle and the road surface. . For this reason, an error occurs between the distance from the vehicle to the obstacle.

  Therefore, the present disclosure provides an information processing apparatus and a program that can accurately estimate the distance from a monocular camera to an object.

  In order to achieve the above object, an information processing apparatus according to an embodiment of the present disclosure includes an image acquisition unit that acquires an image obtained by imaging with a single monocular camera, and an area determination that determines an area of an object in the image A region dividing unit that divides the region of the object based on a change in the predetermined direction of an end portion of the determined region of the object in a predetermined direction, and the object obtained by dividing the region of the object A distance estimation unit that estimates a distance from the monocular camera to the object corresponding to the partial area of the object for at least one of the partial areas.

  The program according to an embodiment of the present disclosure acquires an image obtained by imaging with a single monocular camera, determines an object region in the image, and determines a predetermined region of the object. Dividing the region of the object based on a change in the predetermined direction at the end of the direction, and at least one of the partial regions of the object obtained by dividing the region of the object, from the monocular camera Causing a computer to perform a method comprising estimating a distance to the object corresponding to a partial region of the object.

  According to the information processing apparatus and program of the present disclosure, it is possible to accurately estimate the distance from the monocular camera to the object.

FIG. 1 is a schematic diagram illustrating a vehicle equipped with an information processing apparatus according to an embodiment. FIG. 2 is a block diagram illustrating a functional configuration of the information processing apparatus according to the embodiment. FIG. 3 is a diagram for explaining processing performed by the information processing apparatus according to the embodiment. FIG. 4 is a flowchart illustrating the operation of the information processing apparatus according to the embodiment.

  As described above, there has been a distance measuring technique using a monocular camera (hereinafter also simply referred to as a camera), but the conventional technique has various problems. Specifically, when measuring the distance based on the road surface reflected on the camera and the ground contact surface of the object, it is necessary to detect the ground contact surface of the object from the camera image. May be difficult. On the other hand, the inventor of the present application considered using a region division technique. The area division technique is a technique that divides an image into areas corresponding to objects reflected in the image. However, even when the region division technique is used, when a plurality of objects overlap or are adjacent to each other on the image, it may be difficult to accurately calculate the distance from the camera to each of the plurality of objects.

  Therefore, an information processing apparatus according to an embodiment of the present disclosure is determined with an image acquisition unit that acquires an image obtained by imaging with a single monocular camera, and an area determination unit that determines an area of an object in the image. An area dividing unit that divides the object area based on a change in the predetermined direction at an end of the object area in a predetermined direction, and at least one of the object partial areas obtained by dividing the object area And a distance estimation unit that estimates a distance from the monocular camera to the object corresponding to the partial region of the object.

  As described above, since the object region is divided based on the change in the predetermined direction at the end of the object region shown in the image, individual objects are distinguished even when the object region includes a plurality of objects. be able to. For this reason, the distance from the monocular camera to each object can be estimated.

  Therefore, in this information processing apparatus, it is possible to accurately estimate the distance from the monocular camera to the desired object even when a plurality of objects appear in the image.

  The program according to an embodiment of the present disclosure acquires an image obtained by imaging with a single monocular camera, determines an object region in the image, and determines a predetermined region of the object. Dividing the region of the object based on a change in the predetermined direction at the end of the direction, and at least one of the partial regions of the object obtained by dividing the region of the object, from the monocular camera Causing a computer to perform a method comprising estimating a distance to the object corresponding to a partial region of the object.

  As described above, the information processing apparatus exhibits the above-described effects by executing the program.

  These comprehensive or specific modes may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM. The system, method, integrated circuit, computer program And any combination of recording media.

  Hereinafter, embodiments will be specifically described with reference to the drawings. Note that each of the embodiments described below shows a specific example of the present disclosure. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are merely examples, and are not intended to limit the present disclosure. In addition, among the constituent elements in the following embodiments, constituent elements that are not described in the independent claims indicating the highest concept are described as optional constituent elements.

  Each figure is a schematic diagram and is not necessarily illustrated strictly. Moreover, in each figure, the same code | symbol is attached | subjected to the substantially same structure, The overlapping description is abbreviate | omitted or simplified.

  Hereinafter, an information processing apparatus and a program according to an embodiment of the present disclosure will be described.

(Embodiment)
[Constitution]
First, the configuration of the information processing apparatus 100 according to the present embodiment and the vehicle 3 on which the information processing apparatus 100 is mounted will be described with reference to FIGS.

  FIG. 1 is a schematic diagram showing a vehicle 3 equipped with an information processing apparatus 100 according to an embodiment. FIG. 2 is a block diagram illustrating a functional configuration of the information processing apparatus 100 according to the embodiment. FIG. 3 is a diagram for explaining processing performed by the information processing apparatus 100 according to the embodiment.

  As illustrated in FIGS. 1 and 2, the information processing apparatus 100 is an apparatus that can estimate a distance from the monocular camera 10 to an object based on an image obtained by imaging with the monocular camera 10. A monocular camera 10 and an information processing apparatus 100 are mounted on the vehicle 3. The image may be a still image or a moving image.

  The monocular camera 10 is disposed on the vehicle 3 so that the surroundings of the vehicle 3 can be imaged. In the present embodiment, the monocular camera 10 is disposed so as to image the front in the vehicle 3, but may be disposed, for example, on a radiator grill, a hood, or the like, and is disposed so as to be able to image an object. If it is, it may be arranged in any way.

  The monocular camera 10 is electrically connected to the information processing apparatus 100, performs predetermined processing on an image obtained by imaging, generates image data, and outputs the image data to the information processing apparatus 100. The monocular camera 10 images the surroundings of the vehicle 3 at predetermined time intervals. In the present embodiment, the monocular camera 10 is arranged outside the information processing apparatus 100, but the monocular camera 10 may be built in the information processing apparatus 100.

  The information processing apparatus 100 includes an image acquisition unit 110, an area determination unit 120, an extraction unit 130, a calculation unit 140, an area division unit 150, a road surface contact determination unit 160, a distance estimation unit 170, and an output unit 180. With.

  FIG. 3 a shows image data obtained by imaging with the monocular camera 10. As shown in a of FIG. 3, the image acquisition unit 110 acquires image data obtained by imaging with one monocular camera 10. Specifically, the image acquisition unit 110 outputs the image data to the region determination unit 120 and the road surface contact determination unit 160.

  The area determination unit 120 acquires image data from the image acquisition unit 110. FIG. 3B shows the determination result of the area in the image indicated by the image data. As shown in b of FIG. 3, the region determination unit 120 determines at least the region of the object in the image and the region of the road surface in the image. Specifically, the region determination unit 120 determines the type of an object appearing in the image for each pixel of the image, which is called semantic segmentation, and determines the region of the object for each type of object based on the determination result. Use detection technology. For example, the area determination unit 120 determines the vehicle as the object in the image, the roadway and the background as the road surface by semantic segmentation, and determines the vehicle area, the roadway area, and the background area as shown in FIG. Extract. Then, the region determination unit 120 outputs region data indicating the extracted object region, road surface region, and the like to the extraction unit 130, the region division unit 150, and the road surface contact determination unit 160. The object is, for example, a person, a car, a motorcycle or a bicycle. The road surface is a road through which objects such as roadways and sidewalks pass.

  The extraction unit 130 acquires region data from the region determination unit 120. FIG. 3c shows the contour extraction result of the object region. As illustrated in c of FIG. 3, the extraction unit 130 extracts the contour of the object region from the region data. Specifically, the extraction unit 130 extracts the contour of the object region in the region indicated by the region data. For example, the extraction unit 130 extracts the outline of a region of one object including two vehicles, as illustrated in FIG.

  FIG. 3d shows the extraction result of the lower end of the contour of the object region. As illustrated in d of FIG. 3, the extraction unit 130 extracts an end of the contour in a predetermined direction from the contour extraction result of the object region. For example, when the horizontal direction of the image is the X-axis direction and the vertical direction of the image is the Y-axis direction, the extraction unit 130 extracts the lower end of the contour in the Y-axis direction with the Y-axis direction as a predetermined direction. Then, the extraction unit 130 outputs the lower end data indicating the lower end of the contour of the extracted object region to the calculation unit 140. Further, the extraction unit 130 outputs contour data indicating the contour of the extracted region of the object to the region dividing unit 150. Note that the region determination unit 120 may extract the contour of the object region and extract the lower end of the contour of the object region. The set of end points in the Y-axis direction of the object region is an example of the lower end of the contour of the object region.

  The calculation unit 140 acquires the lower end data from the extraction unit 130. FIG. 3e shows a change in the Y-axis direction at the lower end of the contour of the object region. As illustrated in e of FIG. 3, the calculation unit 140 detects a change in the Y-axis direction at the end of the object region. Specifically, the calculation unit 140 calculates the amount of change ΔY in the Y-axis direction at the lower end of the contour of the object region. The calculating unit 140 outputs the change amount data indicating the calculated change amount ΔY to the region dividing unit 150 in association with the contour data.

  The area dividing unit 150 acquires the contour data output from the extraction unit 130 and the change amount data output from the calculation unit 140. The region dividing unit 150 determines whether or not the change amount ΔY indicated by the change amount data is greater than or equal to a predetermined threshold value, and divides the object region based on the end portion where the change amount ΔY is greater than or equal to the predetermined threshold value. .

  FIG. 3f shows a region of the divided object. As illustrated in f of FIG. 3, the region dividing unit 150 cuts the region of the object in the Y-axis direction based on the lower end portion in which the change amount calculated by the calculation unit 140 is equal to or greater than a predetermined threshold. For example, the region dividing unit 150 identifies two lower end points whose amount of change in the Y-axis direction is equal to or greater than a predetermined threshold among the lower end points constituting the lower end of the contour of the object region, and out of the two lower end points The contour of the object region is divided by cutting the contour of the object region along the straight line in the Y-axis direction passing through the lower end point on the X-axis direction side. The contour of the object region is divided into two or more by the region dividing unit 150. The area dividing unit 150 outputs division data indicating the result of dividing the contour of the object area to the road surface contact determination unit 160. Although the example in which the contour of the object region is divided has been described, the object region itself may be divided.

  Further, the region dividing unit 150 identifies the two lower end points, and cuts the contour of the object region by cutting the contour of the object region with a straight line passing through one of the two lower end points. However, the dividing method is not limited to this.

  Here, the threshold value of the change amount is set according to the size of the object region, for example. For example, the region dividing unit 150 sets the first threshold value as the threshold value of the amount of change if the object region is larger than a predetermined value, and sets the first threshold value if the size of the object region is equal to or smaller than the predetermined value. A small second threshold value may be set.

  Specifically, as a case where the area of the object is larger than a predetermined value, a case where an object exists near the vehicle 3 is assumed. Since the area of the object increases as the object is closer to the vehicle 3, the amount of change in the Y-axis direction tends to increase according to the size of the area of the object. For this reason, the region dividing unit 150 may set a first threshold value that is larger than the second threshold value.

  Further, as a case where the area of the object is smaller than a predetermined value, a case where the object exists in the distance of the vehicle 3 is assumed. Since the area of the object is smaller as the object is farther from the vehicle 3, the amount of change in the Y-axis direction is likely to be smaller depending on the size of the area of the object. For this reason, the area dividing unit 150 may set a second threshold value smaller than the first threshold value.

  Note that the first threshold value and the second threshold value are examples of predetermined threshold values, and thus the change amount threshold value is not limited to two threshold values, and three or more threshold values may be prepared. The change amount threshold value may be a value calculated using the size of the object region as an input. In addition, the predetermined value, the first threshold value, and the second threshold value can be arbitrarily set. The predetermined value is not limited to one, and a plurality of predetermined values may be set.

  The road surface contact determination unit 160 acquires region data from the region determination unit 120. In addition, the road surface contact determination unit 160 acquires the divided data from the region dividing unit 150. The road surface contact determination unit 160 determines whether or not the partial region of the object obtained by dividing the object region indicated by the divided data is in contact with the road surface region. Specifically, the road surface contact determination unit 160 sets a ground contact determination region including the lower end of the contour of the partial region of the object, and determines whether there is a ground contact based on the degree of inclusion of the road surface region with respect to the ground contact determination region. In the present embodiment, the road surface contact determination unit 160 sets, for example, a predetermined number of pixels from the lower end of the contour of the partial region of the object as the ground contact determination region, and the road surface region has a predetermined ratio within the ground contact determination region. It is determined whether or not it is included. Then, the road surface contact determination unit 160 outputs to the distance estimation unit 170 ground contact data indicating a partial region of the object in which the road surface region is included in the ground contact determination region in a predetermined ratio or more.

  The distance estimation unit 170 estimates the distance from the monocular camera 10 to the object corresponding to the partial area of the object for the partial area of the object. Specifically, when the road surface contact determination unit 160 determines that the partial area of the object is in contact with the road surface area, the distance estimation unit 170 moves from the monocular camera 10 to the object corresponding to the partial area of the object. Estimate the distance. For this reason, when the partial area of the object is not in contact with the road area, the distance estimation unit 170 does not estimate the distance from the monocular camera 10 to the object corresponding to the partial area of the object.

  When the partial region of the object is in contact with the road surface region, the distance estimation unit 170 further estimates the distance from the monocular camera 10 to the object corresponding to the partial region of the object for a predetermined type of road surface. . The type of road surface is determined by the road surface contact determination unit 160. For example, an automobile traveling on the roadway (that is, grounding on the roadway) may affect the course of the vehicle 3 traveling on the roadway. Therefore, the distance estimation unit 170 estimates the distance when the road surface type is a roadway. On the other hand, for example, a roadside tree planted on a sidewalk (that is, grounded on the sidewalk) hardly affects the course of the vehicle 3 traveling on the roadway. Therefore, the distance estimation unit 170 does not estimate the distance when the road surface type is a sidewalk.

  Further, when the partial area of the object is in contact with the road surface area, the distance estimation unit 170 further calculates the distance from the monocular camera 10 to the object corresponding to the partial area of the object for a predetermined type of object. presume. For example, a moving object such as a person or a car may affect the course of the vehicle 3. Therefore, the distance estimation unit 170 estimates the distance when the type of the object is a moving object. On the other hand, for example, a fixed object such as a building or a tree hardly affects the course of the vehicle 3. Therefore, the distance estimation unit 170 does not estimate the distance when the type of the object is a fixed object. Thus, the type of road surface and the type of object may be determined depending on whether or not the behavior or control of the vehicle 3 such as the course or speed of the vehicle 3 is affected.

  Further, the distance estimation unit 170 may further estimate the distance when the combination of the road surface type and the object type is a predetermined group. Specifically, the distance estimation unit 170 may determine whether the determined road surface type and object type group is a predetermined group such as a roadway and car group, a sidewalk and person group, a sidewalk and street tree group, or the like. For example, the distance from the monocular camera 10 to the object corresponding to the partial region of the object may be estimated.

  The distance estimation unit 170 estimates the distance from the monocular camera 10 to the object based on the lower end coordinates for each object included in the divided data and the characteristics of the monocular camera 10. For example, the distance estimation unit 170 uses the lower end coordinates corresponding to the partial region of the object, the focal length of the lens of the monocular camera 10, and installation information of the monocular camera 10 on the vehicle 3, from the monocular camera 10 to the object. Estimate distance. In addition, the other method of estimating a distance for every object corresponding to the partial area | region of an object may be used for the estimation of the said distance. In addition, the distance may be estimated by using the actual size of the object corresponding to the partial region of the object and the size of the object on the image.

  The distance estimation unit 170 outputs distance data indicating the estimated distance to the output unit 180. The distance data may be a numerical value of the estimated distance (one-dimensional data) or data (two-dimensional or three-dimensional data) indicating a positional relationship in a two-dimensional or three-dimensional space. In addition, the distance estimation unit 170 may output image data based on the distance data to the output unit 180. FIG. 3G is an example showing an image in which the recognition result of the object and the estimated distance are superimposed. As illustrated in g of FIG. 3, the distance estimation unit 170 may associate data indicating the distance from the monocular camera 10 to the object with the image data obtained from the image acquisition unit 110 and output the data to the output unit 180. . For example, the distance estimation unit 170 outputs, to the output unit 180, image data in which an object indicating the extracted partial region of the object and an object indicating the distance estimated for each partial region of the object are superimposed on the image data. To do.

  The output unit 180 outputs the distance from the monocular camera 110 estimated by the distance estimation unit 170 to the object shown in the image to an external device. Specifically, the output unit 180 outputs the distance data acquired from the distance estimation unit 170 to an external device. The output unit 180 may output the image data acquired from the distance estimation unit 170 to an external device. The external device is, for example, a control device included in the vehicle 3 for performing automatic driving, or a car navigation, a smartphone, or the like as a display device that displays an image. For example, the control device executes control such as acceleration, deceleration, steering, or travel route setting of the vehicle 3 using the acquired distance data.

[Operation]
Next, the operation of the information processing apparatus 100 in the present embodiment will be described with reference to FIGS.

  FIG. 4 is a flowchart showing the operation of the information processing apparatus 100 according to the embodiment.

  In this flowchart, it is assumed that there is another vehicle traveling on the road surface while the vehicle equipped with the information processing apparatus 100 is traveling.

  As illustrated in a of FIG. 3 and S1 of FIG. 4, first, the monocular camera 10 transmits image data obtained by imaging to the image acquisition unit 110, and the image acquisition unit 110 receives the image data. The image acquisition unit 110 outputs the image data to the region determination unit 120 and the road surface contact determination unit 160.

  Next, as illustrated in b of FIG. 3 and S2 of FIG. 4, the region determination unit 120 next determines the region of the object and the region of the road surface in the image data based on the image data acquired from the image acquisition unit 110. The area determination unit 120 outputs area data indicating the determined object area and road surface area to the extraction unit 130 and the road surface contact determination unit 160.

  Next, as illustrated in c of FIG. 3 and S3 of FIG. 4, the extraction unit 130 extracts an object region and a road surface region based on the acquired region data, and the object region is extracted from the extracted object region. The outline of the region is extracted.

  Next, as illustrated in d of FIG. 3 and S4 of FIG. 4, the extraction unit 130 extracts the lower end of the contour of the object region from the contour of the extracted object region. Specifically, the extraction unit 130 extracts the lower end in the Y-axis direction of the contour of the extracted object region. The extraction unit 130 outputs lower end data indicating the lower end of the contour of the extracted object region to the calculation unit 140 and the region division unit 150. Further, the extraction unit 130 outputs contour data indicating the contour of the extracted region of the object to the region dividing unit 150.

  Next, as shown in e of FIG. 3 and S5 of FIG. 4, the calculation unit 140 calculates the amount of change ΔY in the Y-axis direction of the lower end of the contour of the object region indicated by the acquired lower end data. The calculating unit 140 outputs the change amount data indicating the calculated change amount ΔY to the region dividing unit 150.

  Next, as shown in S6 of FIG. 4, the region dividing unit 150 determines whether or not the object region is larger than a predetermined value among the contours of one or more object regions included in the acquired contour data. To do.

  As illustrated in S <b> 7 of FIG. 4, when the region of the object is larger than the predetermined value (YES in S <b> 6), the region dividing unit 150 sets the predetermined threshold as the first threshold. On the other hand, as shown in S8 of FIG. 4, when the size of the area of the object is equal to or smaller than the predetermined value (NO in S6), the area dividing unit 150 sets the predetermined threshold as the second threshold.

  As shown in S9 of FIG. 4, the area dividing unit 150 next determines whether the change amount ΔY indicated by the acquired change amount data is equal to or greater than the first threshold value or the second threshold value set in step S7 or S8. Judge whether or not.

  As shown in f of FIG. 3 and S10 of FIG. 4, when the change amount is equal to or greater than the first threshold value or the second threshold value (YES in S9), the region dividing unit 150 corresponds to the change amount data. At the lower end portion of the contour of the object region, the contour of the object region is divided in the Y-axis direction. When a plurality of changes greater than or equal to the first threshold value or the second threshold value are detected, the region dividing unit 150 divides the contour of the object region into a plurality of regions. Then, the region dividing unit 150 outputs divided data indicating the divided partial regions of the object to the road surface contact determining unit 160.

  On the other hand, when the amount of change is not equal to or greater than the first threshold value or the second threshold value (NO in S9), the process returns to step S1.

  Next, as shown in S11 of FIG. 4, the road surface contact determination unit 160 determines whether or not the partial region of the object indicated by the acquired divided data is in contact with the road surface region. In the present embodiment, the road surface contact determination unit 160 determines whether or not the partial area of the object is in contact with the road surface area depending on whether or not the road surface area exists in the ground contact determination area for the partial area of the object. Determine.

  As shown in g of FIG. 3 and S12 of FIG. 4, when it is determined that the partial region of one or more objects is in contact with the road surface region (YES in S11), the distance estimation unit 170 determines the type of the road surface and It is determined whether the set of object types is a predetermined set. If the combination of the road surface type and the object type is not a predetermined group (NO in S12), the process returns to S1. Note that the process may proceed to S13 without performing the process of S12.

  On the other hand, as shown in S13 of FIG. 4, when the combination of the road surface type and the object type is a predetermined group (YES in S12), the distance estimation unit 170 corresponds to the partial region of the object from the monocular camera 10. Estimate the distance to the target object. Then, the distance estimation unit 170 outputs the estimated distance to an external device via the output unit 180. And a process returns to step S1 and the same operation | movement is repeated.

  On the other hand, when it is determined that the partial areas of all objects are not in contact with the road area (NO in S11), the distance estimation unit 170 does not estimate the distance from the monocular camera 10 to the object. And a process returns to step S1 and the same operation | movement is repeated.

[Function and effect]
Next, the effects of the information processing apparatus 100 and the program according to the present embodiment will be described.

  As described above, the information processing apparatus 100 according to the present embodiment includes the image acquisition unit 110 that acquires an image obtained by imaging with one monocular camera 10 and the region determination unit 120 that determines the region of an object in the image. A region dividing unit 150 that divides the object region based on a change in the Y-axis direction at the end of the determined object region in the Y-axis direction, and a partial region of the object obtained by dividing the object region A distance estimation unit 170 that estimates a distance from the monocular camera 10 to an object corresponding to the partial region of the object.

  As described above, since the object region is divided based on the change in the Y-axis direction at the end of the object region shown in the image, individual objects are distinguished even when the object region includes a plurality of objects. can do. For this reason, the distance from the monocular camera 10 to each object can be estimated.

  Therefore, in this information processing apparatus 100, the distance from the monocular camera 10 to the desired object can be accurately estimated even when a plurality of objects appear in the image.

  The program according to the present embodiment acquires an image obtained by imaging with one monocular camera 10, determines an object region in the image, and the Y-axis direction of the determined object region. The object region is divided based on the change in the Y-axis direction at the end of the object, and at least one of the object partial regions obtained by dividing the object region is changed from the monocular camera 10 to the object partial region. Causing a computer to perform a method including estimating a distance to a corresponding object.

  As described above, the information processing apparatus 1 exhibits the above-described effects by executing the program.

  In the information processing apparatus 100 according to the present embodiment, the region determination unit 120 further determines a road surface region in the image. The information processing apparatus 100 further includes a road surface contact determination unit 160 that determines whether or not the partial region of the object is in contact with the region of the road surface. The distance estimation unit 170 estimates the distance when the road surface contact determination unit 160 determines that the partial region of the object is in contact with the road surface region.

  As described above, when the road surface contact determination unit 160 determines that the object partial area and the road surface area are in contact with each other, the distance estimation unit 170 corresponds to the partial area of the object in contact with the road surface area from the monocular camera 10. Therefore, the distance from the monocular camera 10 to an object other than the object corresponding to the partial area of the object in contact with the road surface area is not estimated. For this reason, erroneous detection of distance can be suppressed.

  In the information processing apparatus 100 according to the present embodiment, the road surface contact determination unit 160 further determines whether or not the road surface area in contact with the partial area of the object is a predetermined type of road surface area. . The distance estimation unit 170 further estimates the distance when the road surface contact determination unit 160 determines that the road surface area in contact with the partial region of the object is a predetermined type of road surface area.

  For example, an automobile traveling on a roadway may affect the course of the vehicle 3 traveling on the roadway. On the other hand, for example, a roadside tree planted on a sidewalk hardly affects the course of the vehicle 3 traveling on the roadway. On the other hand, according to the above configuration, the distance estimation unit 170 estimates the distance when the road surface type is a roadway, and does not estimate the distance when the road surface type is a sidewalk. For this reason, the processing by the distance estimation unit 170 can be speeded up, and the estimated distance can be provided with a time lag suppressed to processing that requires real-time performance such as vehicle control processing.

  In the information processing apparatus 100 according to the present embodiment, the road surface contact determination unit 160 further determines whether or not the object corresponding to the partial area of the object in contact with the road surface area is a predetermined type of object. judge. The distance estimation unit 170 further estimates the distance when the road surface contact determination unit 160 determines that the object corresponding to the partial region of the object in contact with the road surface region is a predetermined type of object.

  For example, a moving object such as a person or a car may affect the course of the vehicle 3. On the other hand, for example, a fixed object such as a building or a tree hardly affects the course of the vehicle 3 traveling on the roadway. On the other hand, according to the above configuration, the distance estimation unit 170 estimates the distance when the type of the object is a moving object, and does not estimate the distance when the type of the object is not a moving object. For this reason, the processing by the distance estimation unit 170 can be speeded up, and the estimated distance can be provided with a time lag suppressed to processing that requires real-time performance such as vehicle control processing.

  In the information processing apparatus 100 according to the present embodiment, the road surface contact determination unit 160 is further in contact with the road surface type corresponding to the road surface area in contact with the partial area of the object and the road surface area. The type of the object corresponding to the partial area of the object is determined. Then, the distance estimation unit 170 estimates the distance when the combination of the road surface type and the object type is a predetermined group.

  As described above, the road surface contact determination unit 160 determines the type of the road surface and the type of the object, and the distance estimation unit 170 estimates the distance when the combination of the road surface type and the object type is a predetermined group. On the other hand, when the combination of the road surface type and the object type is not a predetermined group, the distance estimation unit 170 does not estimate the distance. For this reason, the processing by the distance estimation unit 170 can be speeded up, and the estimated distance can be provided with a time lag suppressed to processing that requires real-time performance such as vehicle control processing.

  The information processing apparatus 100 according to the present embodiment further includes a calculation unit 140 that calculates the amount of change in the Y-axis direction at the end. Then, the region dividing unit 150 divides the region of the object based on the end portion whose change amount calculated by the calculating unit 140 is equal to or greater than a predetermined threshold.

  Thus, the calculation unit 140 calculates the amount of change in the Y-axis direction, and the region dividing unit 150 divides the object by cutting the region of the object based on the end portion where the amount of change is equal to or greater than a predetermined threshold. For this reason, it is possible to specify a portion where the change is steep, and to appropriately divide the object region. Therefore, the distance from the monocular camera 10 can be accurately estimated for each object.

  In the information processing apparatus 100 according to the present embodiment, the predetermined threshold is set according to the size of the object region.

  For example, the closer the object is to the vehicle 3, the larger the area of the object in the image, so the amount of change at the lower end of the object area also increases. Here, when the predetermined threshold value is constant, there is a possibility that the object region of a single object is divided. On the other hand, since the area of the object in the image becomes smaller as the object is farther from the vehicle 3, the amount of change at the lower end of the area of the object is also reduced. Here, when the predetermined threshold value is constant, there is a possibility that the object regions of the plurality of objects are not divided. On the other hand, according to the said structure, it can suppress that the area | region of the object about a single object is divided | segmented, and the area | region of the object about several objects is not divided | segmented.

  In the information processing apparatus 100 according to the present embodiment, the region dividing unit 150 divides the object region in the Y-axis direction.

  According to this configuration, the object region can be divided along the direction of change of the lower end of the object region. For this reason, it is possible to divide the object region into a shape close to the shape of the object.

(Other variations)
Although the information processing apparatus and the program according to the embodiments of the present disclosure have been described above, the embodiments of the present disclosure are not limited to the above-described embodiments. For example, in the above-described embodiment, an example in which the vehicle 3 on which the information processing apparatus 100 is mounted is a four-wheeled vehicle has been described, but the information processing apparatus 100 may be mounted on other types of mobile objects.

  In the above embodiment, the end of the object region in the predetermined direction is a set of lower end points in the road surface direction (Y-axis direction) of the object region, and the road surface direction (Y-axis) of the set of lower end points. Although the example in which the object region is divided based on the change in the (direction) has been described, the division of the object region is not limited to this example. Specifically, the end in the predetermined direction of the object region may be a road boundary in the object region or a partial region in the road direction of the object region. For example, the object region may be divided based on a change in the road surface direction component of the boundary line that becomes the boundary between the object region and the road surface, and the shape change in the road surface direction of the partial region in contact with the road surface in the object region The region of the object may be divided based on

  Each processing unit included in the information processing apparatus and the vehicle according to the above embodiment is typically realized as an LSI which is an integrated circuit. These may be individually made into one chip, or may be made into one chip so as to include a part or all of them.

  Further, the circuit integration is not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI or a reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.

  In each of the above embodiments, each component may be configured by dedicated hardware or may be realized by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

  One embodiment of the present disclosure may be realized as an information processing method executed by an information processing device and a program.

  Moreover, all the numbers used above are illustrated for specifically explaining the present disclosure, and embodiments of the present disclosure are not limited to the illustrated numbers.

  In addition, division of functional blocks in the block diagram is an example, and a plurality of functional blocks can be realized as one functional block, a single functional block can be divided into a plurality of functions, or some functions can be transferred to other functional blocks. May be. In addition, functions of a plurality of functional blocks having similar functions may be processed in parallel or time-division by a single hardware or software.

  In addition, the order in which the steps in the flowchart are executed is for illustration in order to specifically describe the present disclosure, and may be in an order other than the above. Also, some of the above steps may be executed simultaneously (in parallel) with other steps.

  As described above, the information processing apparatus and the program according to one or a plurality of aspects have been described based on the embodiments, but the embodiments of the present disclosure are not limited to the plurality of aspects. Unless it deviates from the gist of the present disclosure, various modifications conceived by those skilled in the art have been made in this embodiment, and forms constructed by combining components in different embodiments are also within the scope of one or more aspects. May be included.

DESCRIPTION OF SYMBOLS 100 Information processing apparatus 110 Image acquisition part 120 Area determination part 140 Calculation part 150 Area division part 160 Road surface contact determination part 170 Distance estimation part

Claims (10)

An image acquisition unit for acquiring an image obtained by imaging with one monocular camera;
An area determination unit for determining an area of an object in the image;
A region dividing unit that divides the region of the object based on a change in the predetermined direction of an end portion of the determined region of the object in a predetermined direction;
A distance estimation unit that estimates a distance from the monocular camera to the object corresponding to the partial area of the object for at least one of the partial areas of the object obtained by dividing the region of the object. The region determination unit further determines a region of the road surface in the image,
Furthermore, a road surface contact determination unit that determines whether or not the partial region of the object is in contact with the region of the road surface,
The information processing apparatus according to claim 1, wherein the distance estimation unit estimates the distance when the road surface contact determination unit determines that the partial region of the object is in contact with the road surface region. The road surface contact determination unit further determines whether or not the road surface area in contact with the partial area of the object is a predetermined type of the road surface area,
The distance estimation unit further estimates the distance when the road surface contact determination unit determines that the road surface area in contact with the partial area of the object is a predetermined type of the road surface area. Item 3. The information processing device according to Item 2. The road surface contact determination unit further determines whether or not the object corresponding to the partial area of the object in contact with the road surface area is a predetermined type of object,
The distance estimation unit further estimates the distance when the road surface contact determination unit determines that the object corresponding to the partial region of the object in contact with the road surface region is a predetermined type of object. The information processing apparatus according to claim 2 or 3. The road surface contact determination unit further includes a road surface type corresponding to the road surface area in contact with the partial area of the object, and an object type corresponding to the partial area of the object in contact with the road surface area. , And
The information processing apparatus according to claim 2, wherein the distance estimation unit estimates the distance when the combination of the road surface type and the object type is a predetermined group. Further, a calculation unit that calculates a change amount of the end portion in the predetermined direction is provided.
The information processing according to any one of claims 1 to 5, wherein the region dividing unit divides the region of the object based on the end portion in which the change amount calculated by the calculating unit is equal to or greater than a predetermined threshold. apparatus. The information processing apparatus according to claim 6, wherein the predetermined threshold is set according to a size of an area of the object. The region dividing unit divides the region of the object in the predetermined direction.
The information processing apparatus according to claim 1. The predetermined direction is a road surface direction toward the road surface in the image,
The end portion is a set of end points in the road surface direction of the object region, a boundary line in the road surface direction of the object region, or a partial region in the road surface direction of the object region.
The information processing apparatus according to any one of claims 1 to 8. Obtaining an image obtained by imaging with a single monocular camera;
Determining the area of the object in the image;
Dividing the region of the object based on a change in the predetermined direction of an end portion of the determined region of the object in the predetermined direction;
Causing a computer to execute a method including estimating a distance from the monocular camera to the object corresponding to the partial region of the object for at least one of the partial regions of the object obtained by dividing the region of the object program.

Images