JP4694441B2 - Vehicle perimeter monitoring system - Google Patents

Description

The present invention relates to a vehicle periphery monitoring system .

There has been proposed a technique for determining the presence or absence of an object such as a human who may come into contact with a vehicle based on a surrounding image of the vehicle captured by an in-vehicle infrared camera (see, for example, Patent Document 1).
JP 2001-6096 A

However, if a person and the building overlap, the target object P such as a person (shown by a broken line) is built in the background as shown in FIG. 4 in the grayscale image of the surrounding image of the vehicle. There is a case where it is difficult to recognize the presence of the target object P due to being mixed into an object.

Therefore, the present invention provides a vehicle periphery monitoring system that can recognize the presence of a target object with high accuracy even when the target object such as a human is mixed in the background in an image obtained through an in-vehicle imaging device. Let it be a solution issue.

The inventor of the present application paid attention to the fact that the vertical movement pattern of the object accompanying the pitching of the vehicle is different in the image obtained through the in-vehicle imaging device. Then, the inventor of the present application moves the vertical motion pattern of the target object P such as a human in the image (see FIG. 5 / white double arrows) and the building in the background of the target object P (distant from the target object as viewed from the vehicle) The idea was to identify the target object from the background using the difference between the vertical movement pattern of forest B or the like (see FIG. 5 / black double arrow).

Based on this idea, the vehicle periphery monitoring system according to the first aspect of the present invention measures a motion variable corresponding to the vertical motion of each of a plurality of target elements constituted by one or a plurality of high-luminance pixels in the image, A first processing unit that creates a distribution function of motion variables of the plurality of target elements, and the distribution function created by the first processing unit is different from a first value indicating a first maximum value, and the distribution A second processing unit for recognizing the target element including the motion variable as a target object or a part of the target object in a section including a second value indicating a second maximum value whose function is smaller than the first maximum value; It is characterized by having.

According to the vehicle periphery monitoring system of the first invention, a plurality of “target elements” constituted by one or a plurality of high-luminance images in an image obtained through the imaging device are recognized. Since the presence of the high luminance region indicates the presence of some object in the imaging range of the imaging apparatus, the target element may include at least a part of the target object.

In order to extract or select a target object or a part thereof from a plurality of target elements, a motion variable distribution function corresponding to the vertical motion of the target elements in the image is created. The “motion variable” includes the speed, amplitude, angular velocity (proportional to the reciprocal of the motion cycle), and the like. In addition, the distribution function is different from the “first value” indicating the “first maximum value”, and the distribution function includes a “second value” indicating the “second maximum value” smaller than the first maximum value. The target element belonging to the selected section is recognized as the target object or a part thereof.

There is a high possibility that the first value indicating the first maximum value of the distribution function represents the vertical movement pattern of the entire image reflecting the pitching of the vehicle and the like. For this reason, there is a high possibility that the target element to which the motion variable belongs to the section including the first value corresponds to a building, a forest, or the like or a part thereof. On the other hand, the target element to which the motion variable belongs in the section including the second value indicating the second maximum value whose distribution function is smaller than the first maximum value is a target object such as a human who moves up and down in a pattern different from the background or It may be part of it.

By these processes, even if a target object such as a human is mixed in the background in the image, the target object that moves up and down in a pattern different from the overall vertical movement pattern in the image or a part of the target object from a plurality of target elements It can be extracted with high accuracy. The presence of the target object can be recognized with high accuracy. In particular, the vehicle is in an environment where pitching is likely to occur, such as in front of the vehicle, where the forest spreads over the imaging range of the imaging device and target objects such as humans are likely to fall into this forest, and there are ups and downs and unevenness on the road. The true value can be demonstrated in the situation where is running.

The vehicle periphery monitoring system according to a second aspect of the present invention is the vehicle periphery monitoring system according to the first aspect, wherein the first processing unit takes a plurality of pixels constituting an upper or lower edge of a high luminance region in the image as the plurality of objects. It is recognized as an element, and the second processing unit recognizes a target element group including the motion variable in the section and having continuity as an upper or lower edge of the target object.

According to the vehicle periphery monitoring system of the second invention, even when a target object such as a human is mixed in the background in the image, the upper side of the target object that moves up and down in a pattern different from the overall vertical movement pattern in the image or The lower edge can be extracted with high accuracy. Note that the continuity of a plurality of target elements (pixels) means that, for example, the vertical deviation of pixels in a horizontally adjacent pixel column is equal to or less than a threshold in an image obtained through an imaging device. In addition, as a requirement for a target element group (pixel group) having continuity to be recognized as an edge, it is set that the number of pixels belonging to the pixel group is equal to or greater than a specified value.

The vehicle periphery monitoring system according to a third aspect is the vehicle periphery monitoring system according to the first aspect, wherein the first processing unit recognizes a plurality of high luminance areas in the image as the plurality of target elements.

According to the vehicle periphery monitoring system of the third aspect of the invention, even when a target object such as a human is mixed in the background in the image, the target object that moves up and down in a pattern different from the overall vertical movement pattern in the image or one of the target objects. The part can be extracted with high accuracy.

A vehicle periphery monitoring system according to a fourth aspect of the present invention is the vehicle periphery monitoring system according to any one of the first to third aspects, wherein the first processing unit sets the target element including the motion variable in the section as a target object candidate. And the second processing unit measures the feature amount in the real space of the target object candidate recognized by the first processing unit, and the measured feature amount in the real space of the target object candidate is the target It is determined whether or not the requirement according to the feature amount of the object is satisfied, and the target object candidate determined to satisfy the requirement is recognized as the target object or a part of the target object.

According to the vehicle periphery monitoring system of the fourth aspect of the invention, as described above, the target element to which the motion variable belongs to the section including the second value different from the first value is moving up and down in a pattern different from the background. In view of the possibility of being a target object or a part of the target object. Further, the feature quantity in the real space of the target object candidate is measured. Then, when the measured feature quantity in the real space of the target object candidate satisfies the requirements set in view of the feature quantity of the target object, the target object candidate is recognized as the target object or a part thereof. As a result, even when a target object such as a human is mixed in the background in the image, the target object that moves up and down in a pattern different from the vertical movement pattern of the entire image or a part thereof is higher than the target element and thus the target object candidate. Can be extracted with accuracy.

The vehicle periphery monitoring system according to a fifth aspect of the present invention is the vehicle periphery monitoring system according to the fourth aspect of the invention, wherein the second processing unit uses the target object candidate position, shape, size, Alternatively, a combination of these is measured.

According to the vehicle periphery monitoring system of the fifth invention, among the target object candidates, the position, shape, size, or combination thereof in the real space satisfies the requirements according to the position, shape, size, or combination thereof of the target object. A thing is recognized as a target object or a part thereof. Here, the position, shape, size or a combination thereof means “position”, “shape”, “size”, “position and shape”, “shape and size”, “size and position” or “position, shape and size”. .

A vehicle periphery monitoring system according to a sixth aspect of the present invention is the vehicle periphery monitoring system according to any one of the first to fifth aspects, wherein the second processing unit performs time series measurement of the target object or a part of the target object. A third processing unit for evaluating the possibility of contact between the vehicle and the target object based on the position is further provided.

According to the vehicle periphery monitoring system of the sixth aspect of the invention, even when the target object is mixed into the background in the image obtained through the imaging device as described above, the target object or a part thereof can be recognized with high accuracy. The possibility of contact between the vehicle and the target object can be evaluated with high accuracy.

The vehicle periphery monitoring system according to a seventh aspect is the vehicle periphery monitoring system according to the sixth aspect, wherein the third processing unit notifies the presence of the target object based on an evaluation of the possibility of contact between the vehicle and the target object. Alternatively, the information to be emphasized is output to an in-vehicle information output device, or the behavior of the vehicle is controlled or the in-vehicle device is controlled.

According to the vehicle periphery monitoring system of the seventh aspect of the invention, since the possibility of contact between the vehicle and the target object can be evaluated with high accuracy as described above, from the viewpoint of avoiding contact between the vehicle and the target object, the target object Or the information which emphasizes the some object part etc. can be output appropriately. Here, the output of information means that the information is output in any form that allows the driver of the vehicle to recognize the information through the five senses, such as vision, hearing, and touch. This allows the driver of the vehicle to recognize the presence of the target object and appropriately control the behavior of the vehicle such as vehicle deceleration and steering in order to avoid contact between the vehicle and the target object.

Further, the in-vehicle device is controlled based on the possibility of contact between the vehicle and the target object evaluated with high accuracy as described above. Thereby, from the viewpoint of avoiding contact between the vehicle and the target object, the behavior of the vehicle such as deceleration or steering of the vehicle can be appropriately controlled.

An embodiment of a vehicle periphery monitoring system of the present invention will be described with reference to the drawings.

The configuration and function of the vehicle periphery monitoring system according to the first embodiment of the present invention will be described with reference to FIGS.

First, the structure of the vehicle periphery monitoring system which is 1st Embodiment of this invention is demonstrated using FIG. 1 and FIG.

As shown in FIG. 1, the vehicle 1 includes a vehicle periphery monitoring system 10, a pair of infrared cameras (imaging devices) 102 disposed substantially symmetrically at the center in the vehicle width direction at the front portion of the vehicle 1, A HUD 104 is mounted on the front window so as not to obstruct the driver's view. As shown in FIG. 2, various sensors such as a yaw rate sensor 122 and a speed sensor 124 are mounted on the vehicle 1.

The vehicle periphery monitoring system 10 is a system that monitors the periphery of a vehicle based on images obtained through a pair of in-vehicle imaging devices. The vehicle periphery monitoring system 10 is stored in a memory and an ECU or a computer (configured by a CPU, ROM, RAM, I / O, etc.) as hardware mounted on the vehicle 1, and has various functions in the computer. It is comprised with the "vehicle periphery monitoring program" of this invention as software which provides. The vehicle periphery monitoring program may be stored in the memory of the in-vehicle computer from the beginning. However, a part or all of the program may be stored in a server (construction system) at an arbitrary timing such as when there is a request from the in-vehicle computer. It may be distributed or broadcast from 20 to the in-vehicle computer via a network or an artificial satellite and stored in its memory.

As shown in FIG. 2, the vehicle periphery monitoring system 10 includes a first processing unit 11, a second processing unit 12, and a third processing unit 13.

The first processing unit 11 recognizes the upper edge of the high luminance region in the image obtained by the infrared camera 102 as the first edge E ₁ . Further, the first processing unit 11 measures the vertical motion speed (motion variable) v in the image of a plurality of pixels (corresponding to a plurality of “target elements”) constituting the first edge E ₁ . Further, the first processing unit 11 creates a distribution function f (v) of the vertical motion speed v of the plurality of pixels. Then, based on the distribution function, the first processing unit 11 recognizes a second edge (corresponding to a “target object candidate”) E ₂ constituted by a part of the pixel group constituting the first edge E ₁ . .

The second processing unit 12 measures a feature amount such as a real space position in the real space of the second edge E ₂ recognized by the first processing unit 11. Further, the second processing unit 12 determines whether or not the feature quantity such as the real space position of the second edge E ₂ satisfies the requirement according to the feature quantity such as the standard size of the target object P, and the requirement The second edge E ₂ determined to satisfy the condition is recognized as the upper edge of the target object P.

The third processing unit 13 may contact the vehicle 1 with the target object P based on the time-series measurement position of the second edge E ₂ recognized as the upper edge of the target object P by the second processing unit 12. To evaluate. Further, the third processing unit 13 displays on the HUD (information output device) 104 an image that informs or emphasizes the presence of the target object P according to the evaluation of the possibility of contact between the vehicle 1 and the target object P. Control the operation of in-vehicle equipment.

The function of the vehicle periphery monitoring system 10 having the above-described configuration according to the first embodiment of the present invention will be described with reference to FIGS.

First, the first processing unit 11 executes “first processing” (S11 in FIG. 3).

The first processing unit 11 recognizes the upper or lower edge of the high luminance region in the binarized image obtained through the pair of infrared cameras 102 as the first edge E ₁ (FIG. 3 / S111). The binarized image is obtained by binarizing a grayscale image obtained by A / D converting an infrared image. For example, when the binarized image shown in FIG. 4 is obtained, a high luminance area as shown in white in FIG. 6 is recognized, and as shown by a thick line in FIG. First edge (horizontal edge, meaning a continuous high-luminance pixel group in which the spread in the vertical direction of the image is equal to or less than a threshold value and the spread in the horizontal direction of the image is equal to or greater than a specified value) E ₁ Be recognized.

Further, the first processing unit 11 measures the vertical motion speed v in the image of each pixel (target element) constituting the first edge E ₁ (FIG. 3 / S112). Further, the first processing unit 11 creates a distribution function f (v) of the vertical motion speed v of the plurality of pixels (FIG. 3 / S113). Accordingly, for example, as shown in FIG. 7, the distribution function f (1) which shows the first maximum value at the first speed v ₁ while showing the second maximum value smaller than the first maximum value at the second speed v ₂ . v) is obtained.

Then, the first processing unit 11 extracts or recognizes the second edge E ₂ from the first edge E ₁ based on the distribution function f (v) (FIG. 3 / S114). Specifically, for example, the distribution function f (v) shown in FIG. 7 is different from the first speed v ₁ where the maximum value is shown, and the distribution function f (v) is the maximum value f (v ₁ ). The edge (part of the first edge E ₁ ) composed of continuous pixels belonging to the section including the second velocity v ₂ showing another maximum value is recognized as the second edge E ₂ . The pixel continuity means that, for example, the vertical deviation of the pixels constituting the edge in the pixel row adjacent to the image is equal to or less than a threshold value. Thereby, for example, the second edge E ₂ as shown in FIG. 6 is recognized.

Next, the second processing unit 12 executes “second processing” (S12 in FIG. 3).

The second processing unit 12 uses the parallax of the pair of infrared cameras 102 to determine the Y coordinate value (“feature value” (specifically, “actual amount”) of the center of gravity of the second edge E ₂ recognized by the first processing unit 11. Corresponds to the spatial position “)”) (FIG. 3 / S121). At this time, the second processing unit 12 corrects the positional deviation in the image due to the turning of the vehicle 1 based on the outputs of the yaw rate sensor 122 and the speed sensor 124. The measurement position of the edge E _P corrected for the turning angle is stored in the memory in time series. As shown in FIG. 1, the real space position is the origin O at the midpoint of the mounting position of the pair of infrared cameras 102, and the horizontal, vertical and front-rear directions are the X, Y and Z axes, respectively. Means a position in the coordinate system. Since the method for measuring the real space position and the method for correcting the turning angle are described in, for example, Patent Document 1, detailed description thereof is omitted in this specification.

Further, the second processing unit 12, Y-coordinate value of the second edge E ₂ is, (the "feature amount" (specifically. Corresponding to the "size")) human standard height is set in view of the It is determined whether or not the requirement of being included in the range (stored in the memory) is satisfied (S122 in FIG. 3).
If the second processing unit 12 determines that the requirement is satisfied (FIG. 3 / S122... YES), the second processing unit 12 recognizes the second edge E ₂ as the upper edge E _P of the target object (human) P ( FIG. 3 / S123). Thereby, for example, the edge E _P as shown in FIG. 6 is recognized, and the presence of the target object P as shown by the broken line in FIG. 6 is also recognized.

Subsequently, the third processing unit 13 executes “third processing” (S13 in FIG. 3).

The third processing unit 13 reads the time-series measurement position of the second edge E ₂ recognized as the upper edge E _P of the target object P by the second processing unit 12 from the memory, and reads the read time-series measurement position. Based on the above, the relative speed (including the size and direction) of the target object P with respect to the vehicle 1 is calculated (FIG. 3 / S131).

Further, the third processing unit 13 evaluates the possibility of contact between the vehicle 1 and the target object P (FIG. 3 / S132). For example, as shown in FIG. 6, the product of the relative speed v _s of the human (target object) P with respect to the vehicle 1 and the margin time T (v _s ×) rather than the triangular area A _{0 that} can be monitored by the infrared camera 102. A triangular area (alarm determination area) that is lower by T) is defined. Among the triangular regions, a first region (approaching determination region) A ₁ having a width in the X direction centered on the Z axis of α + 2β (α: vehicle width, β: margin width) and the first region A ₁ The left and right second areas (intrusion determination areas) A _2L and A _2R are defined. Then, when the object x is in the first area A ₁ or the target object P is in the left and right second areas A ₂ and enters the first area A ₁ in view of the relative velocity vector v _s. Is predicted, the possibility that the target object P and the vehicle 1 will contact each other is highly evaluated.

When the third processing unit 13 highly evaluates the possibility of contact between the vehicle 1 and the target object (human) P (FIG. 3 / S133... YES), the third processing unit 13 executes the “first control process” (FIG. 3 / S134). ). Accordingly, for example, in order to emphasize the presence of the target object P, an orange frame f surrounding the edge E _P of the target object P is displayed on the HUD 104 as “first information” as shown in FIG. The shape of the frame f as a requirement that surrounds the edge E _P of the target object P, size, and may be arbitrarily changed each color. Note that the first information may be output from a speaker (not shown) such as “beep”.

On the other hand, when it is determined that the possibility that the vehicle 1 and the target object P are in contact with each other is low (FIG. 3 / S133... NO), the third processing unit 13 executes the “second control process” (FIG. 3 / S135). . Thus, for example, in order to conspicuously emphasize the presence of the target object P, a yellow frame f surrounding the edge E _P of the target object P is displayed on the HUD 104 as “second information” as shown in FIG. . Note that the second information may be output from a speaker (not shown), such as “beep”, which is shorter (or lower in volume) than the first information.

According to the vehicle periphery monitoring system 10, which is the first embodiment of the present invention that exhibits the above function, in the image (grayscale image) obtained through the infrared camera (imaging device) 102, the upper side or the lower side of the high luminance region. The edge (first edge) E ₁ is recognized (FIG. 3 / S111, FIG. 6). The presence of the high luminance region, it indicates the presence of an object in the imaging range of the infrared camera 102, the first edge E ₁ might contain edge E _P of the human (object) P.

To extract the edge E _P of the target object P from the first edge E _1, a plurality of pixels constituting the first edge E _1, the distribution function f of vertical movement velocity v in the image (v) is created ( FIG. 3 / S113, FIG. 7). Further, unlike the first speed v _{1 in} which the distribution function f (v) has a maximum value, the speed function includes a second speed v _{2 in} which the distribution function f (v) has a maximum value different from the maximum value. The second edge E ₂ constituted by the continuous pixels to which it belongs is recognized (FIG. 3 / S114, FIG. 6, FIG. 7).

The first speed v _{1 at} which the distribution function f (v) has the maximum value represents the vertical motion pattern of the entire image, and thus the pitching state of the vehicle 1. For this reason, the pixel belonging to the section including the first speed v ₁ is highly likely to correspond to an upper or lower edge of a building or a forest. On the other hand, the second edge E ₂ constituted by pixels having continuity in the image belonging to the section including the second velocity v ₂ where the distribution function f (v) has a local maximum value different from the maximum value is the background and May be the upper or lower edge E _P of the target object P moving up and down in different patterns.

Furthermore, when the position (Y coordinate) of the second edge E _{2 in} the real space satisfies the requirements set in view of the standard height (size) of the target object (human) P, the second edge E ₂ It is recognized as the upper edge E _P of the target object P (FIG. 3 / S122 to S123, FIG. 6). Thus, as shown in FIG. 4, even when the target object P is mixed into the background in the grayscale image, the upper edge E _P of the target object P that moves up and down in a pattern different from the vertical motion pattern of the entire image. Can be identified with high accuracy from the first edge E ₁ . The presence of the target object P can be recognized with high accuracy. In particular, in an environment where a forest spreads in front of the vehicle 1, that is, in the imaging range of the infrared camera 102, and a target object such as a human is likely to be mixed in the forest and pitching is likely to occur such as up and down or unevenness on the road. In the situation where the vehicle 1 is traveling, the true value can be exhibited.

In addition, even when the target object P is mixed in the background as described above, the presence of the target object P or its edge E _P can be recognized with high accuracy, so there is a possibility that the vehicle 1 and the target object P come into contact with each other. It can be evaluated with high accuracy (FIG. 3 / S132).

Furthermore, since the possibility of contact between the vehicle 1 and the target object P can be evaluated with high accuracy as described above, the target object P or a portion thereof is emphasized from the viewpoint of avoiding contact between the vehicle 1 and the target object P. The first or second information to be displayed can be appropriately displayed (output) on the HUD 104 (FIG. 3 / S134, S135, FIG. 9). This allows the driver of the vehicle 1 to recognize the presence of the target object P and appropriately control the behavior of the vehicle 1 such as deceleration or steering of the vehicle 1 in order to avoid contact between the vehicle 1 and the target object P. Can do.

In the first embodiment the upper edge of the highlighted image in the obtained image through the infrared camera 102 is recognized as the first edge E _1, from the first edge E ₁ second edge E ₂ is extracted, the second It is determined whether or not the edge E ₂ corresponds to the upper edge E _P of the target object P (FIG. 3 / S111, S114, S123). lower edge is recognized as the first edge E _1, it is extracted from the first edge E ₁ second edge E ₂ is, whether the second edge E ₂ corresponds to the lower edge of the target object P is It may be determined.

In the first embodiment, depending on whether or not the Y coordinate value (real space position) of the second edge E ₂ is included in an appropriate range in view of the standard height (size) of the target object (human) P. Although it has been determined whether or not the second edge E ₂ is the upper edge E _P of the target object P (FIG. 3 / S122), as another embodiment, the shape and size of the second edge E ₂ in real space, etc. It may be determined whether the other feature amount satisfies various requirements in view of the feature amount such as the standard real space position and shape of the target object P. For example, whether the width of the second real space edge E ₂ are either human (object) standard second edge according to the width and shoulder width, etc. of the head E ₂ of P is an edge E _P of the target object P May be determined.

Next, the configuration and function of the vehicle periphery monitoring system according to the second embodiment of the present invention will be described with reference to FIGS. 1, 2, and 10 to 12.

First, the structure of the vehicle periphery monitoring system which is 2nd Embodiment of this invention is demonstrated using FIG. 1 and FIG. The configuration of the vehicle, the vehicle periphery monitoring system, and the server according to the second embodiment of the present invention is shown in FIGS. 1 and 2 except for the functions of the first processing unit 11, the second processing unit 12, and the third processing unit 13. Since it is the same as that of the vehicle etc. which are 1st Embodiment currently performed, description is abbreviate | omitted about the said same structure.

The first processing unit 11 recognizes a plurality of high-luminance regions in an image (grayscale image or binarized image) obtained through the infrared camera 102 as a primary target object candidate (corresponding to “target element”) P ₁ . To do. The first processing unit 11 measures the vertical movement velocity (motion variable) v in the respective primary target object candidate P ₁ of the image, the distribution function f of vertical movement velocity v of the primary target object candidate P ₁ Create (v). The first processing unit 11 is different from the first speed v _{1 in} which the distribution function f (v) has a maximum value, and the distribution function f (v) has a maximum value different from the maximum value. A primary target object candidate P ₁ belonging to a speed section including two speeds v ₂ is recognized as a secondary target object candidate (corresponding to “target object candidate”) P ₂ .

The second processing unit 12 measures a feature quantity such as a real space position of the secondary target object candidate P ₂ recognized by the first processing unit 11. Further, the second processing unit 12 determines whether or not the measurement feature quantity in the real space of the secondary target object candidate P ₂ satisfies the requirements set in view of the feature quantity such as the standard size of the target object P. judge. Then, the second processing unit 12 recognizes the secondary target object candidate P ₂ that satisfies the requirement as the target object P.

The third processing unit 13 evaluates the possibility of contact between the vehicle 1 and the target object P based on the time-series measurement position of the secondary target object candidate P ₂ recognized as the target object P by the second processing unit 12. . Further, the third processing unit 13 displays on the HUD (information output device) 104 an image that informs or emphasizes the presence of the target object P according to the evaluation of the possibility of contact between the vehicle 1 and the target object P. Control the operation of in-vehicle equipment.

The function of the vehicle periphery monitoring system 10 having the above-described configuration according to the second embodiment of the present invention will be described with reference to FIGS.

First, the first processing unit 11 executes “first processing” (FIG. 10 / S21).

The first processing unit 11 recognizes a plurality of high luminance regions in an image (grayscale image or binarized image) obtained through the infrared camera 102 as the primary target object candidate P ₁ (FIG. 10 / S211). Thereby, for example, as shown in FIG. 11, a plurality of primary target object candidates P ₁ are recognized in the image. Further, the first processing unit 11 measures the vertical motion speed v in the image of each primary target object candidate P ₁ (more accurately, a representative point such as the center of gravity) (FIG. 10 / S212). Furthermore, the first processing unit 11 creates a distribution function f (v) of the vertical motion velocity v of each primary target object candidate P ₁ (FIG. 10 / S213). Thereby, for example, the distribution function f (v) as shown in FIG. 7 can be created in the same way as created by the first processing in the first embodiment of the present invention.

Then, the first processing unit 11 extracts or recognizes the secondary target object candidate P ₂ from the plurality of primary target object candidates P ₁ based on the distribution function f (v) (FIG. 10 / S214). Specifically, the distribution function f (v) shown in FIG. 7 is different from the first speed v ₁ where the maximum value is shown, and the distribution function f (v) is the maximum value f (v ₁ ). The primary target object candidate P ₁ belonging to the section including the second speed v ₂ showing another maximum value is recognized as the secondary target object candidate P ₂ . Thereby, for example, among the plurality of primary target object candidates P shown in FIG. 11, the second primary target object candidate from the left is recognized as the secondary target object candidate P ₂ .

Next, the second processing unit 12 executes the second process (FIG. 10 / S22).

The second processing unit 12 measures the Y coordinate value (corresponding to “feature amount” (specifically “real space position”)) of the secondary target object candidate P ₂ recognized by the first processing unit 11. (FIG. 10 / S221). In the second processing unit 12, the Y coordinate value of the secondary target object candidate P ₂ corresponds to the standard height (“feature amount” (specifically, “size”) of the target object (human) P. ) Is determined whether or not the requirement set (stored in the memory) is satisfied (FIG. 10 / S222). If the second processing unit 12 determines that the Y coordinate value of the secondary target object candidate P ₂ satisfies the requirement (FIG. 10 / S222... YES), the secondary target object candidate P ₂ is set as the target object P. Recognize (FIG. 10 / S223).

Further, the third processing unit 13 executes “third processing” (S23 in FIG. 10).

The third processing unit 13 reads a time-series measurement position of the secondary target object candidate P ₂ recognized as the target object P by the second processing unit 12 from the memory, and the vehicle 1 based on the read time-series measurement position. the relative speed of the object P relative to the (including magnitude and direction.) v _s is calculated (FIG. 10 / S231).

Since the contents of the third process thereafter are the same as the contents of the third process in the first embodiment of the present invention, the third process unit 13 will determine the possibility of contact between the vehicle 1 and the target object P. Evaluate (FIG. 10 / S232). Then, the third processing unit 13 executes “first control processing” or “second control processing” according to the possibility of contact between the vehicle 1 and the target object P (FIG. 10 / S234, S235). For example, in order to emphasize the presence of the target object P by the first control process or the second control process, the frame f surrounding the target object P as shown in FIG. 12 is “first information” or “second information”. Can be displayed on the HUD 104.

According to the vehicle periphery monitoring system 10 that is the second embodiment of the present invention that exhibits the above function, the target object P such as a human is in the background in the image (grayscale image or binarized image) obtained through the infrared camera 102. In this case, the primary target object candidate P ₁ that moves up and down in a pattern different from the vertical motion pattern of the entire image is extracted as the secondary target object candidate P ₂ (S21 in FIG. 10). Further, when the position or the like of the secondary target object candidate P _{2 in} the real space satisfies the requirements set in view of the position or the like of the target object P, the secondary target object candidate P ₂ is recognized as the target object P. (FIG. 10 / S22). As described above, the presence of the target object P can be recognized with high accuracy.

In the first and second embodiments, it is determined that the feature quantity in the real space of the target object candidate (secondary edge E ₂ or secondary target object candidate P ₂ ) satisfies the requirements in view of the feature quantity of the target object P. In this case, the target object candidate is recognized as the target object P (see FIG. 3 / S121 to S123, FIG. 10 / S221 to S223), but such requirement satisfaction is determined as another embodiment. Instead, the target object candidate may be recognized as the target object P as it is.
In the first and second embodiments, the third processing unit 13 causes the HUD 104 to display the first or second information that emphasizes the presence of the target object P as the first or second control process (FIG. 9). 12), as another embodiment, the third processing unit 13 controls in-vehicle devices such as a steering system and a brake system in order to control the behavior of the vehicle 1 as the first or second control processing, or the in-vehicle You may make an apparatus control the behavior of the vehicle 1. FIG. According to the vehicle periphery monitoring system 10 having the above configuration, the in-vehicle device is controlled based on the possibility of contact between the vehicle 1 and the target object P evaluated with high accuracy as described above, whereby the vehicle 1 and the target object are controlled. From the viewpoint of avoiding contact with P, the behavior of the vehicle 1 such as deceleration and steering can be appropriately controlled.

In the above embodiment, the motion speed v is measured as a motion variable corresponding to the vertical motion of the first edge E ₁ or the first target object candidate P ₁ (FIG. 3 / S112, FIG. 10 / S212). As such, the amplitude, angular velocity, frequency, etc. of the vertical motion of the first edge E ₁ or the first target object candidate P ₁ may be measured.

Also, for any motion variable x corresponding to the vertical movement of the first edge E ₁ or the first target object candidate P _1, the second value x ₂ higher than the first value x ₁ first maximum value f (x ₁ In addition to the case where the distribution function f (v) indicating the second maximum value f (x ₂ ) lower than the first value x ₁ is obtained (see FIG. 7), the first maximum at the second value x ₂ lower than the first value x ₁ is obtained. In some cases, a distribution function f (v) indicating a second maximum value f (x ₂ ) lower than the value f (x ₁ ) may be obtained. Further, a plurality of first values _{x 1i (i = 1,2, ‥} ) while indicating first maximum value f (x _1i) in each, and these first value x _1i with different second value x _1i In some cases, a distribution function f (x) indicating a second maximum value f (x ₂ ) smaller than all the first maximum values f (x _1i ) may be obtained.

Configuration explanatory diagram of vehicle, vehicle periphery monitoring system and construction system of the present invention Configuration explanatory diagram of the vehicle periphery monitoring system of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory diagram of the vehicle periphery monitoring system according to the first embodiment of the present invention Functional explanatory drawing of the vehicle periphery monitoring system which is a 2nd embodiment of the present invention. Functional explanatory drawing of the vehicle periphery monitoring system which is a 2nd embodiment of the present invention. Functional explanatory drawing of the vehicle periphery monitoring system which is a 2nd embodiment of the present invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Vehicle, 10 ... Vehicle periphery monitoring system, 11 ... 1st process part, 12 ... 2nd process part, 13 ... 3rd process part, 20 ... Server, 102 ... Infrared camera (imaging device), 104 ... HUD (information Output device (vehicle equipment)), 122 ... yaw rate sensor, 124 ... speed sensor

Claims (7)

A system for monitoring the periphery of a vehicle based on an image obtained through an in-vehicle imaging device,
Measuring a motion variable corresponding to the vertical motion of each of a plurality of target elements constituted by one or a plurality of high-luminance pixels in the image, and creating a distribution function of the motion variables of the plurality of target elements; One processing unit;
The distribution function created by the first processing unit is different from the first value indicating the first maximum value, and the distribution function is a second value indicating the second maximum value smaller than the first maximum value. A vehicle periphery monitoring system comprising: a second processing unit that recognizes the target element including the motion variable in a section including the target element as a target object or a part of the target object. In the vehicle periphery monitoring system according to claim 1,
The first processing unit recognizes a plurality of pixels constituting an upper or lower edge of a high-luminance region in the image as the plurality of target elements;
The vehicle periphery monitoring system, wherein the second processing unit recognizes a target element group including the motion variable in the section and having continuity as an upper or lower edge of the target object. In the vehicle periphery monitoring system according to claim 1,
The vehicle periphery monitoring system, wherein the first processing unit recognizes a plurality of high luminance regions in the image as the plurality of target elements. The vehicle periphery monitoring system according to any one of claims 1 to 3, wherein the first processing unit recognizes the target element including the motion variable in the section as a target object candidate,
The second processing unit measures a feature amount in the real space of the target object candidate recognized by the first processing unit, and the measured feature amount in the real space of the target object candidate is the feature amount of the target object. A vehicle periphery monitoring system that determines whether or not a requirement according to the requirement is satisfied and recognizes the target object candidate determined to satisfy the requirement as the target object or a part of the target object. In the vehicle periphery monitoring system according to claim 4,
5. The vehicle periphery monitoring according to claim 4, wherein the second processing unit measures a position, a shape, a size, or a combination of the target object candidates as the feature amount in the real space of the target object candidates. system. The vehicle periphery monitoring system according to any one of claims 1 to 5, wherein the vehicle is based on a time-series measurement position of the target object or a part of the target object recognized by the second processing unit. A vehicle periphery monitoring system, further comprising a third processing unit that evaluates the possibility of contact with the target object. The vehicle periphery monitoring system according to claim 6,
Based on the evaluation of the possibility of contact between the vehicle and the target object, the third processing unit causes the in-vehicle information output device to output information that informs or emphasizes the presence of the target object, or determines the behavior of the vehicle. A vehicle periphery monitoring system characterized by being controlled or controlled by an in-vehicle device.

Images