JP2005170290A - Obstacle detecting device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an obstacle detecting device for determining a behavior of an obstacle. <P>SOLUTION: The obstacle detecting device comprises an image pick-up means 1 for photographing a periphery of a movable body with a predetermined period, a tracking region detecting means 2 for detecting a tracking region corresponding to an image of at least relatively moving obstacle based on the image picked up by the image pick-up means, a region moving amount calculating means 3 for determining an image coordinate value before and after the movement of the tracking region detected by the tracking region detecting means based on two images picked up by the image pick-up means with different timings, a calculating means 4 of an image pick-up means moving amount for detecting the moving amount of the image pick-up means 1, an obstacle indication value calculating means 5 for calculating an indication value related to a relative position of the obstacle based on the image coordinate value of the tracking region before the movement, the image coordinate value of the tracking region after the movement, and a movement mount of the image pick-up means, and a determining means 6 for determining the behavior of the obstacle based on the indication value. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an obstacle detection device that detects an obstacle, and more particularly to an obstacle detection device that detects the presence or absence of an obstacle.

There is a device that detects an obstacle that may collide with the host vehicle by capturing an image of the periphery of the host vehicle using a single camera device mounted on the vehicle. As this type of device, a parking assistance device that detects the same object from images taken at different points as the vehicle moves and calculates the distance to the stationary object from the parallax and the amount of movement of the vehicle (See Patent Document 1).
JP 2001-187553 A

However, in the conventional technology, since the distance to the obstacle is calculated using images with different imaging timings, an accurate distance can be calculated if the obstacle to be imaged is a stationary object, but the obstacle moves. In the case of the body, there is a problem that the position of the obstacle and the relative positional relationship with the host vehicle cannot be detected accurately. For this reason, there is a problem that it is impossible to recognize whether the obstacle is a moving object, whether the obstacle is a moving object jumping out of the own vehicle, or whether the obstacle may collide with the own vehicle. It was.
The present invention has been proposed to solve the above-described problems, and an object thereof is to provide an obstacle detection device that specifically recognizes the movement of an existing obstacle.

  According to the present invention, there is provided an obstacle detection device that is mounted on a moving body and detects obstacles around the moving body, the imaging unit that images the periphery of the moving body at a predetermined cycle, and the imaging unit A tracking area detecting means for detecting a tracking area corresponding to an image of an obstacle moving at least relative to the captured image, and a tracking area detecting means based on two images taken at different timings by the imaging means. Area movement amount calculation means for obtaining image coordinate values before and after the movement of the detected tracking area, imaging means movement amount calculation means for detecting the movement amount of the imaging means, image coordinate values of the tracking area before movement, and after movement Obstacle index value calculating means for calculating an index value related to the relative position of the obstacle from the image coordinate value of the tracking area and the moving amount of the imaging means, and a determining means for determining the behavior of the obstacle based on the index value , Obstacle detection device including a is provided.

  Whether the obstacle is a moving object, whether the obstacle is a stationary object, whether the obstacle may jump out of the host vehicle, or whether the obstacle may collide with the host vehicle It is possible to provide an obstacle detection device that determines the behavior of such an obstacle.

  Hereinafter, the obstacle detection apparatus 100 of the present embodiment will be described with reference to the drawings. The obstacle detection apparatus 100 according to the present embodiment is mounted on a vehicle on which a user is boarded, determines the behavior of an obstacle existing around the vehicle, and detects the presence of the obstacle whose behavior is specified. That is, the obstacle detection apparatus 100 according to the present embodiment is configured such that the obstacle is a moving object, whether the obstacle is a stationary object, whether the obstacle is an object approaching the own vehicle, or whether the obstacle is on the own vehicle. It is a device that determines the possibility of a collision, identifies the behavior of an obstacle, and detects its presence.

  FIG. 1 shows a block configuration of an obstacle detection apparatus 100 according to the present embodiment.

  As shown in FIG. 1, the obstacle detection apparatus 100 includes an imaging unit 1, a tracking area detection unit 2, an area movement amount calculation unit 3, an imaging unit movement amount calculation unit 4, and an obstacle index value calculation unit 5. And a determination means 6 and an output means 7. Specifically, an index relating to the relative position of the obstacle from at least the position coordinates of the tracking area detected by the tracking area detection means 2 and the movement amount of the imaging means 1 calculated by the imaging means movement amount calculation means 4. A ROM that stores a program that calculates a value and determines the behavior of an obstacle based on the calculated index value, and an obstacle index value calculation unit 5 and a determination unit 6 are executed by executing the program stored in the ROM. And a RAM functioning as the storage means 8.

  In addition, the obstacle detection device 100 can exchange information with at least one of the warning device 200 that issues various warnings based on the detection result of the obstacle and the driving support device 300 that supports driving. It is connected by an in-vehicle LAN.

  Each configuration will be described below.

  The “imaging means 1” is, for example, a video camera, and images the front of the vehicle at a constant cycle (time interval Δt). The captured image is stored in the image storage unit 81. The left and right optical axes of the camera serving as the imaging unit 1 are set to coincide with the straight traveling direction of the vehicle, and the vertical optical axis of the camera is set to be horizontal.

  The “tracking region detection unit 2” detects an obstacle moving at least relative to the vehicle based on two images captured by the imaging unit 1 at different timings. Therefore, the tracking region corresponding to the image of the obstacle Is detected. The tracking area may be arbitrarily set, but in the present embodiment, an area where the moving body can be tracked is detected based on a change in lightness and darkness of the image. That is, the tracking area detection unit 2 of the present embodiment detects an image area having a change in shading in a plurality of directions as a tracking area. This is because the area that can be tracked by the detection target is an area that has light and shade changes in multiple directions, and in areas that have uniform light and shade changes on the image, such as white lines on the road, the movement direction This is because it is difficult to detect the amount of movement of the tracking target when is perpendicular to the direction of light and shade change.

  Specifically, the tracking region detection unit 2 includes an edge detection unit 21, a variance value calculation unit 22, and a tracking region determination unit 23. The edge detection unit 21 detects the edge of the image captured by the imaging unit 1. The edge detection unit 21 of the present embodiment reads an image stored in the image storage unit 81, applies a filter for detecting vertical and horizontal edges, and determines the size of the vertical and horizontal components of the edge ( dI / dx, dI / dy: I is a pixel value). Next, in order to remove a noise component included in the detected edge, a pixel whose sum of squares of the obtained vertical and horizontal edge components is greater than or equal to a threshold th1 is extracted, and based on the extracted pixel To detect edges.

  Since the variance value calculation unit 22 detects a region having light and shade changes in a plurality of directions, the variance value of the ratio of the size of the vertical component and the horizontal component of the edge detected by the edge detection unit is calculated. Calculation is performed for each predetermined area of the image. Specifically, the variance value calculation unit 22 obtains the density gradient direction by obtaining the ratio of the magnitudes of the vertical and horizontal components of the edge. Next, the image in which the edge from which the noise has been removed is shown is divided into a lattice shape at equal intervals along the vertical direction and the horizontal direction. FIG. 2 is a schematic diagram illustrating a state in which an image in which an edge is detected from a captured image using the above-described method is divided into a lattice shape. One divided grid shown in FIG. 2 is a unit area for performing the tracking area detection process. The variance value calculation unit 22 obtains a variance value of the ratio of the size of the vertical component and the horizontal component of the edge for each of the divided unit regions.

  The tracking area determination unit 23 determines a predetermined area whose variance value calculated by the variance value calculation unit 22 is larger than a predetermined value as a tracking area for tracking the movement of the obstacle. This is based on the tendency that if the edge gradient direction in the divided rectangular area is one direction, the variance value is small, and if the edge gradient direction is in a plurality of directions, the variance value is large. In other words, the tracking area determination unit 23 moves in a direction perpendicular to the density gradient because the edge gradient direction is likely to be one direction if the obtained variance value of the unit area is smaller than the predetermined threshold th2. It is determined that it is difficult to detect the object to be moved. On the other hand, if the obtained dispersion value is equal to or larger than the predetermined threshold th2, the moving body moves in any direction because it has edge gradients in multiple directions. Even so, it is determined that the area corresponding to the obstacle can be traced. That is, the tracking area determination unit 23 determines that an area where the obtained variance value is equal to or greater than the predetermined threshold th2 is a tracking area. The tracking area determined by the tracking area determination unit 23 based on the captured image shown in FIG. 2 is shown in FIG.

  The tracking area determination unit 23 of the tracking area detection unit 2 determines the start point position (for example, the upper left corner) of the area determined as the tracking area, the image size (width and height), and the image pattern of the original image as each unit area. The tracking area information storage unit 82 stores the identification number in association with the identification number. Hereinafter, the image pattern of the tracking area before movement, which is a reference for calculating the movement amount and the correlation value, is referred to as “reference pattern”.

  The tracking area detection unit 2 detects a new tracking area for each image captured by the imaging unit 1 at an interval of time Δt. If the newly detected tracking area is an area different from the area where the area movement amount is being calculated, the starting position, image size, and image pattern are stored in the tracking area information storage unit 82 as a new tracking area. To do. Whether or not it is a new tracking area is determined based on the starting point position and size of the tracking area stored in the tracking area information storage unit 82.

  When information related to a new image captured by the imaging unit 1 is input to the image storage unit 81, the “region movement amount calculation unit 3” tracks based on the two images captured at different timings by the imaging unit 1. The amount of movement of the area is calculated. The area movement amount calculation means 3 includes a correlation value calculation unit 31, a determination unit 32, and a calculation unit 33.

  The movement amount calculation method will be described. First, the correlation value calculation unit 31 sets a search area in order to detect the movement destination of the tracking area. This search area is an area that includes the tracking area and is extended by a predetermined number of pixels toward the outside of the tracking area. In the present embodiment, a search area is set that is expanded by one pixel outward in the vertical direction with respect to the four sides of the tracking area. The correlation value between the reference pattern and the tracking area of the new image data is calculated while shifting the reference pattern (the stored tracking area image pattern) by one pixel within the search area. In calculating the correlation value, the position of the reference pattern is moved (shifted) in units of one pixel, so the position where the correlation value is obtained is also in units of one pixel, but interpolation calculation is performed using a plurality of correlation values. Thus, the position where the correlation value is maximized can be obtained with an accuracy of 1 pixel or less. As a result, the movement destination of the tracking area can be obtained with an accuracy of 1 pixel or less.

  The determination unit 32 determines that the obstacle image after movement exists in the search region where the correlation value calculated by the correlation value calculation unit 31 is maximum, and determines the search region as the tracking region after movement. In the present embodiment, the area where the calculated correlation value is equal to or greater than the threshold th3 and is the maximum is determined as the tracking area after the movement of the reference pattern.

  The calculation unit 33 compares the position of the tracking region after movement determined by the determination unit 32 with the position of the tracking region (tracking region corresponding to the reference pattern) detected by the tracking region detection unit 2, and the amount of movement Is calculated. The amount of movement of the tracking area is expressed as each direction component in the horizontal direction x and the vertical direction y based on the image coordinate values. In FIG. 4, the movement component of the movement amount calculated for each tracking region shown in FIG. 3 is shown as a vector.

  The tracking region position after movement determined by the determination unit 32 and the movement amount calculated by the calculation unit 33 are stored in the tracking region information storage unit 82. However, if the correlation value with the new image is less than the threshold th3, it cannot be determined that the same part in the image has moved, so the information regarding the corresponding tracking area is initialized. Also, when the start point position (start point coordinates) of the tracking area deviates from a predetermined range (horizontal direction x, vertical direction y), information on the corresponding tracking area is initialized. This is because the detection target moving in a direction different from the moving direction of the stationary object or the host vehicle on the image moves from the vanishing point (center of the captured image) to the peripheral direction (outside of the captured image) with the movement of the host vehicle. This is because the camera goes out of the imaging range as time passes. With respect to the initialized tracking area, the determination process by the determination means 6 described later is not performed.

  The “imaging means movement amount calculation means 4” calculates the movement amount of the imaging means 1. Since the imaging means 1 of this embodiment is mounted on a moving body, in this embodiment, the movement amount of the imaging means 1 is calculated by calculating the movement amount of a vehicle (moving body) on which the imaging means 1 is mounted. Specifically, the number of rotations of the wheel is measured at an imaging cycle (time interval Δt), and is calculated by multiplying the measured number of rotations and the outer circumferential length of the tire. If a plurality of trigger positions with respect to the sensor are set at equal angles, the number of rotations can be measured with a resolution of one rotation or less.

  The “obstacle index value calculation means 5” calculates an index value related to the relative position of the obstacle from the image coordinate value of the tracking area before and after the movement in the two images taken at different timings and the moving amount of the imaging means 1. calculate. As the image coordinate values of the tracking area before and after the movement, those calculated by the area movement amount calculation means 3 can be used.

  In this embodiment, the index value L related to the relative position of the obstacle is calculated using the following equation.

(Equation 1) L = f + ΔL * x1 / (x2-x1) = f + ΔL * x1 / Δx
However,
L is an index value relating to the relative position of the obstacle (if the obstacle is a stationary object, the distance from the lens center to the tracking area after the movement of the imaging means)
f is the lens focal length
ΔL is the amount of movement of the imaging means
x1 is an x-coordinate value on the image coordinates of the tracking area before the imaging unit is moved (the optical axis direction of the imaging unit is the y-axis).
x2 is an x-coordinate value on the image coordinates of the tracking area after the movement of the image pickup means (the optical axis direction of the image pickup means is the y-axis)
Δx is the amount of movement in the x-axis direction on the image coordinates of the tracking area (the optical axis direction of the imaging means is the y-axis) before and after the movement of the imaging means.
In addition to the image coordinate value of the tracking region, the light receiving surface coordinate value of the image sensor of the imaging unit 1 may be used as the image coordinate value of the tracking region.

  The index value L obtained by the above equation (1) is the distance L from the imaging means 1 to the tracking area when the imaging means 1 (camera) mounted on the vehicle moves ΔL in the optical axis direction during the time Δt. It corresponds to. The geometrical relationship of the index value L (distance from the imaging means to the tracking target) is shown in FIG. The x coordinate axis orthogonal to the optical axis direction (y coordinate axis) takes a negative value below the optical axis position and a positive value above the optical axis position.

  FIG. 5A shows a case where the imaging means 1 (camera) that images a stationary obstacle moves ΔL along the optical axis direction during the time Δt. As shown in FIG. 5A, the projected image of the stationary obstacle tracking area moves outward (in the direction in which the absolute value of x increases) from the optical axis position. That is, the x coordinate value x2 on the image coordinates (α2) of the tracking area after the movement of the imaging means 1 is larger than the x coordinate value x1 on the image coordinates (α1) of the tracking area before the movement of the imaging means 1. Takes a larger value. Therefore, Δx = x2−x1 is a positive value, and the index value L calculated by Equation (1) is the distance to the tracking area. Similarly, Δx = x2−x1 is a positive value when the obstacle is away from the camera on which the imaging unit 1 is mounted.

  FIG. 5B shows the geometric relationship of the index value L when an obstacle approaches the vehicle, particularly an obstacle that jumps out from the periphery toward the center of the road. The imaging means 1 (camera) moves ΔL along the optical axis direction at time Δt. As shown in FIG. 5B, the projection image of the tracking area of the obstacle approaching the vehicle moves inward from the optical axis position. That is, the x coordinate value x2 on the image coordinates (α2) of the tracking area after the movement of the imaging means 1 is larger than the x coordinate value x1 on the image coordinates (α1) of the tracking area before the movement of the imaging means 1. Takes a smaller value. Therefore, Δx = x2−x1 is a negative value, and the index value L calculated by the equation (1) does not become the distance to the tracking area. In the present invention, attention is paid to the fact that the sign value L corresponds to the behavior of the obstacle, and the behavior of the obstacle is determined using the index value L.

  The “determination unit 6” determines the behavior of the obstacle based on the index value. Specifically, the “determination means 6” determines whether the obstacle is a moving object, whether the obstacle is a stationary object, whether the obstacle is an object approaching the host vehicle, or the obstacle collides with the host vehicle. Determine if this is possible. The determination of the behavior of the obstacle is preferably performed based on the index value L calculated by the above (Equation 1).

  First, the function of the determination means 6 for determining whether the obstacle is a stationary object, whether the obstacle is a moving object, or whether the obstacle is an object approaching the host vehicle will be described. The determination unit 6 of the present embodiment determines the behavior of the obstacle based on the index value L calculated by the obstacle index value calculation unit 5.

  When the index value L of the tracking area imaged in a predetermined cycle calculated by the obstacle index value calculation unit 5 is negative, the determination unit 6 of the present embodiment is a moving object that approaches the vehicle. If the index value L is positive, it is determined that the obstacle is a stationary object or a moving object separated from the vehicle.

  In addition, the determination unit 6 calculates the frequency at which the index value L of the tracking region imaged in a predetermined cycle, which is calculated by the obstacle index value calculation unit 5, is negative, and the calculated frequency is the first threshold value ( If it is equal to or greater than Rths1), it is determined that the object is approaching the imaging unit 1 (the vehicle on which the imaging unit 1 is mounted). On the other hand, when the frequency that the index value L of the tracking area is negative is less than the second threshold value (Rths2), the determination unit 6 is stationary with respect to the imaging unit 1 (the vehicle on which the imaging unit 1 is mounted). It is judged that it is the thing which is doing or is separated. The “frequency” calculated here is calculated as a ratio of the number of times that the index value L calculated for a predetermined number of imaging is positive. The first threshold value (Rths1) and the second threshold value (Rths2) may be different values, but in the present embodiment, they are the same value.

  Next, a function for determining whether an obstacle is a stationary object, an obstacle is a moving object, or an obstacle is an object approaching the host vehicle using another technique will be described. The determination means 6 of the present embodiment calculates the frequency at which the index value L of each tracking area imaged at a predetermined cycle, which is calculated by the obstacle index value calculation means 5, is a negative value, and the calculation is performed. In the case where the frequency is equal to or higher than the first threshold, the difference between the index values L of the tracking area imaged in a predetermined cycle calculated by the obstacle index value calculation unit 5 and the imaging unit movement amount calculation When calculating the difference between the movement amount of the image pickup means 1 calculated by the means 4 and calculating the frequency at which the difference is equal to or greater than the third threshold, and when the calculated frequency is equal to or greater than the fourth threshold, It is determined that the obstacle is an object approaching the imaging unit.

  When the obstacle is a stationary object, the index value L (distance to the tracking area) for each tracking area imaged in a predetermined cycle should be reduced by the moving distance (ΔL) of the imaging means 1 (see FIG. 5 (a)). In other words, the value obtained by subtracting the moving distance ΔL of the imaging means 1 from the difference in the index value L (distance to the tracking area) of the tracking area calculated sequentially with the imaging operation should be zero or less than a predetermined value. . In other words, when the obstacle approaches the vehicle, the difference in the index value L should be larger than ΔL by the amount of movement of the obstacle. In the present embodiment, the frequency at which ΔL is subtracted from the difference between the index values L (corresponding to the approaching movement amount of the obstacle) is equal to or greater than the third threshold thL, and the calculated frequency is the fourth threshold. If it is equal to or greater than RthL, it is determined that the obstacle is an object approaching the imaging means. The third threshold value and the fourth threshold value are preferably determined as appropriate based on experimental results. By the way, the frequency at which ΔL is subtracted from the difference between the index values L is less than a predetermined threshold, and when the calculated frequency is equal to or lower than the predetermined threshold, it is determined that the obstacle is an approaching object. May be. Further, the frequency at which ΔL is subtracted from a difference between the index values L is less than a predetermined threshold value, and when the calculated frequency is equal to or higher than the predetermined threshold value, the obstacle is determined to be a stationary object. You can also

  Next, the function of the determination unit 6 that determines whether an obstacle is a possibility of a rear-end collision will be described. The determination unit 6 of the present embodiment determines the behavior of the obstacle based on the movement amount calculated by the region movement amount calculation unit 3.

  In the present embodiment, the determination unit 6 captures an obstacle in the imaging unit when the movement amount of the tracking area, which is captured in a predetermined cycle, tends to be equal to or less than the fifth threshold (thm). to decide. The reason why it is configured to make this determination will be described. FIG. 6 shows the relative positional relationship when another vehicle (obstacle) located at B approaches the own vehicle located at A at a constant speed and collides at position C. As shown in FIG. 6, the triangle formed by the positions A, B, and C of the host vehicle and other vehicles (obstacles) becomes smaller while maintaining a similar relationship when the host vehicle moves toward the position C. Therefore, when imaging the front with the imaging means 1 (camera) mounted on the host vehicle at the position A, B where the other vehicle (obstacle) is located maintains an angle θ with respect to the optical axis direction y. The x coordinate on the image does not change. As described above, of the obstacles approaching the host vehicle like the other vehicle (B), there is a feature that the amount of movement in the x direction in the image is small in the possibility of collision. In the present invention, paying attention to the relationship between the amount of movement of the tracking region and the possibility of collision, if the amount of movement of the tracking region tends to be less than a predetermined threshold, it is determined that the obstacle is likely to collide It is said. In the present embodiment, when the frequency that the movement amount of the tracking area is less than the fifth threshold (thm) is greater than or equal to the sixth threshold (Rthm), it is determined that there is a possibility that an obstacle may collide with the imaging unit 1. To do.

  As described above, the determination unit 6 according to the present embodiment determines the behavior of the obstacle based on the sign value L of the relative position of the obstacle, the calculation result using the index value L, and the movement amount of the tracking area. Can be judged. An evaluation value based on these three factors can be arbitrarily combined to determine a stationary object, a moving object, an approaching object, and an obstacle with a possibility of collision. FIG. 7 shows an approaching object, an object that may collide, and a stationary object in a coordinate system with three evaluation values as axes.

  The “movement amount evaluation value” in FIG. 7 is the frequency at which the movement amount of the tracking area captured at a predetermined cycle is equal to or less than the fifth threshold value (thm). If this frequency is equal to or greater than the sixth threshold (Rthm), it is determined that the obstacle is an object that may collide with the image pickup means 1 (the vehicle on which the image pickup means 1 is mounted). The “index value positive / negative evaluation value” is the frequency at which the index value L of the tracking area captured in a predetermined cycle is negative. When this frequency is equal to or higher than the first threshold value (Rths), it is determined that the obstacle is an object approaching the imaging unit 1 (the vehicle on which the imaging unit 1 is mounted). The “difference evaluation value” is calculated by calculating the frequency at which a value obtained by subtracting ΔL from the difference between the index values L (corresponding to the approaching movement amount of the obstacle) is less than the third threshold thL, and the calculated frequency is a predetermined value. When it is equal to or greater than the threshold value RthL ′, it is determined that the obstacle is an object that is stationary with respect to the imaging unit 1 (the vehicle on which the imaging unit 1 is mounted). That is, it is determined that an area less than the threshold value RthL ′ is an obstacle approaching the imaging unit 1 (vehicle equipped with the imaging unit 1). By combining these evaluation values as described above, the obstacle to be detected can be accurately detected.

Next, a processing procedure of the obstacle detection apparatus 100 according to the present embodiment will be described.
FIG. 8 is a flowchart showing a processing procedure of the obstacle detection apparatus 100 according to the present embodiment.
The process starting from step S10 starts when an ignition switch (not shown) is turned on. In step S10, the tracking area information stored in the tracking area information storage unit 82 is initialized, and the process proceeds to step S20. In step S20, the imaging means 1 images the periphery of the vehicle, particularly the front of the vehicle, stores the captured image in the image storage unit 81, and proceeds to step S30.

  The tracking area detection unit 2 detects the tracking area based on the image stored in the image storage unit 81 (step S30). Next, the region movement amount calculation means 3 calculates the movement amount of the tracking region corresponding to the moving obstacle based on two images captured at different timings at a predetermined imaging cycle (imaging interval Δt). (Step S40). The imaging unit movement amount calculation unit 4 calculates the movement amount of the imaging unit 1. The obstacle index value calculation means 5 calculates an obstacle index value from the image coordinate value of the tracking area and the moving amount of the imaging means (step S50). The judging means 6 judges the behavior of the obstacle based on the obstacle index value. (Step S60).

  The determination result by the determination unit 6 is output to the warning device 200 and / or the driving support device 300 which are external devices via the output unit 7. Obstacle detection results are as follows: “There is a stationary obstacle” “There is a moving obstacle” “There is an obstacle approaching the own vehicle (vehicle equipped with imaging means)” “Own vehicle (imaging) The vehicle equipped with the means) has an obstacle that may cause a collision. Further, an “obstacle presence position” derived by referring to coordinates associated with the image of the tracking area may be included. Further, information “what is an obstacle” derived by pattern matching processing may be included.

  According to the determination result of the determination means 6, the warning device 200 outputs an alarm to the driver (step S70). The alarm may be a screen display or a voice guidance.

  When the process in step S70 ends, the process returns to step S20. Thereafter, the processing after step S20 is repeatedly performed at a cycle of the imaging interval Δt.

  As described above, according to the obstacle detection apparatus 100 of the present embodiment, it is possible to detect an obstacle by judging the behavior of the obstacle. In other words, the obstacle detection apparatus 100 according to the present embodiment includes “an obstacle that is stationary”, “an obstacle that moves”, and “an obstacle that approaches the host vehicle (a vehicle equipped with an imaging unit)”. It is possible to output an obstacle detection result in which the behavior of the obstacle is judged to the effect that “there is an obstacle with a possibility of collision in the own vehicle (vehicle equipped with the imaging means)”.

  The obstacle detection apparatus 100 according to the present embodiment uses the difference between the index value L obtained by the above equation (1), the movement amount of the tracking area, the difference between the index value L and the movement distance of the imaging apparatus 1. It is possible to accurately determine the behavior of an object.

  In the process of calculating the movement amount of the tracking area, the correlation value between the tracking area and the search area is calculated, and the movement area of the tracking area is accurately calculated by determining the tracking area after movement based on the correlation value. Can do.

  In order to track the movement of obstacles, areas with multiple shade changes are set as tracking areas, and obstacles are detected in areas where obstacles can be detected accurately. Processing can be performed.

  In this embodiment, an obstacle can be detected by one camera, and the behavior of the obstacle can be determined. That is, it is not necessary to provide two or more cameras. For this reason, it is not necessary to provide a device for measuring the distance to the object as in a device having two or more cameras, and the device configuration can be simplified. In addition, it is not necessary to perform precise optical axis alignment between cameras, and costs and man-hours can be reduced.

  In the present embodiment, the obstacle detection apparatus 100 that is mounted on a vehicle and detects obstacles around the vehicle has been described. However, the present invention is not limited to this, and the obstacle detection apparatus 100 can also be used for a robot, a machine tool, or the like.

  The embodiment described above is described for facilitating the understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

It is a block block diagram of the obstacle detection apparatus which concerns on this embodiment. It is a 1st figure for demonstrating the detection process of a tracking area | region. It is a 2nd figure for demonstrating the detection process of a tracking area | region. It is a figure for demonstrating the calculation process of the movement amount of a tracking area | region. 5A and 5B are diagrams for explaining the index value L. FIG. It is a figure for demonstrating the judgment method of the collision possibility based on a moving amount | distance. It is a figure for demonstrating the detection process of an obstruction. It is a flowchart figure which shows the process sequence of the obstruction detection apparatus which concerns on this embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Obstacle detection apparatus 1 ... Imaging means 2 ... Tracking area | region detection means 3 ... Area movement amount calculation means 4 ... Imaging means movement amount calculation means 5 ... Obstacle index value calculation means 6 ... Judgment means 7 ... Output means 8 ... Memory | storage Means 81 ... Image storage unit 82 ... Tracking area information storage unit 83 ... Threshold storage unit 200 ... Warning device 300 ... Driving support device

Claims (10)

An obstacle detection device that is mounted on a mobile body and detects obstacles around the mobile body,
Imaging means for imaging the periphery of the moving body at a predetermined cycle;
A tracking area detecting means for detecting a tracking area corresponding to an image of an obstacle moving at least relatively from the image captured by the imaging means;
Area movement amount calculation means for obtaining image coordinate values before and after movement of the tracking area detected by the tracking area detection means based on two images captured at different timings by the imaging means;
An imaging means movement amount calculating means for detecting a movement amount of the imaging means;
Obstacle index value calculating means for calculating an index value related to the relative position of the obstacle from the image coordinate value of the tracking area before the movement, the image coordinate value of the tracking area after the movement, and the moving amount of the imaging means,
An obstacle detection apparatus comprising: a determination unit that determines the behavior of the obstacle based on the index value. The obstacle detection device according to claim 1, wherein the obstacle index value calculation means calculates the index value using the following equation.
(Equation 1) L = f + ΔL * x1 / (x2-x1)
However,
L is the index value f related to the relative position of the obstacle, the lens focal length ΔL is the moving amount x1 of the imaging means, and the x coordinate value on the image coordinates of the tracking area before the imaging means is moved (of the imaging means). The optical axis direction is the y-axis)
x2 is an x-coordinate value on the image coordinates of the tracking area after the movement of the image pickup means (the optical axis direction of the image pickup means is the y-axis)   When the index value L of each tracking area imaged in the predetermined cycle calculated by the obstacle index value calculating unit is a negative value, the determining unit determines that the obstacle is The obstacle detection apparatus according to claim 2, wherein the obstacle detection apparatus determines that the object is approaching.   The determination means calculates a frequency that is calculated by the obstacle index value calculation means and the index value L of each tracking region imaged in the predetermined cycle is a negative value, and the calculated frequency is a first value. The obstacle detection device according to claim 2, wherein, when the threshold is equal to or greater than 1, the obstacle is determined to be an object approaching the imaging unit.   When the index value L of each tracking area imaged in the predetermined period calculated by the obstacle index value calculating unit is a positive value, the determining unit determines that the obstacle is The obstacle detection apparatus according to claim 2, wherein the obstacle detection apparatus determines that the object is stationary or separated from the imaging unit.   The determination means calculates a frequency that is calculated by the obstacle index value calculation means and the index value L of each tracking region imaged in the predetermined cycle is a negative value, and the calculated frequency is a first value. The obstacle detection device according to claim 2, wherein when it is less than a threshold value of 2, the obstacle is determined to be an object that is stationary relative to the imaging unit or an object that is separated from the imaging unit.   The determining means includes the difference between the index values L for each tracking area imaged in the predetermined period, calculated by the obstacle index value calculating means, and the imaging means detected by the imaging means movement amount calculating means. And calculating the frequency at which the difference is greater than or equal to a third threshold, and when the calculated frequency is greater than or equal to a fourth threshold, the obstacle is The obstacle detection device according to claim 4, wherein the obstacle detection device determines that the object is approaching. The area movement amount calculation means calculates the movement amount of the tracking area from the image coordinate value of the tracking area before movement and the image coordinate value of the tracking area after movement,
The determination means calculates a frequency at which the movement amount of the tracking area calculated by the area movement amount calculation means is less than a fifth threshold, and if the calculated frequency is equal to or more than a sixth threshold, The obstacle detection device according to any one of claims 2 to 7, wherein an object is determined to have a possibility of a rear-end collision with the imaging unit. The area movement amount calculation means includes:
A correlation value calculation unit for calculating a correlation value between the detected tracking region and a search region set with reference to the tracking region;
A determination unit that determines a search region where the correlation value calculated by the correlation value calculation unit is maximum as a tracking region after movement;
The calculation unit that compares the position of the tracking area after movement determined by the determination unit with the position of the tracking area before movement detected by the tracking area detection unit, and calculates a movement amount. The obstacle detection apparatus according to 1. The tracking area detecting means includes
An edge detection unit for detecting an edge of the image;
A variance value calculating unit that calculates a variance value of a ratio of magnitudes of vertical and horizontal components of an edge detected by the edge detecting unit for each predetermined region of the image;
The tracking area determination part which determines the predetermined area | region where the dispersion value calculated by the said dispersion value calculation part is larger than a predetermined value as a tracking area for tracking the movement of the said obstruction. The obstacle detection device according to any one of the above.

Images