JP7262184B2 - fence detector - Google Patents

Description

The present invention relates to a fence detection device.

2. Description of the Related Art Conventionally, when performing automatic parking or the like, there is a technique of detecting obstacles existing around a vehicle using sonar. Specifically, there is known a technique for detecting the distance to an object by radiating ultrasonic waves around a vehicle using sonar and detecting the reflected waves (see, for example, Patent Document 1).

Japanese Patent Application Laid-Open No. 2005-306301

However, in the case of a fence formed like a net so that the background can be seen through, it may not be possible to detect the distance to the fence using sonar.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a fence detection device capable of detecting fences that are difficult to detect with sonar.

A fence detection device according to the present invention includes an image acquisition unit that acquires an image obtained by capturing an image around the vehicle with an imaging unit mounted on the vehicle, and based on a plurality of images acquired by the image acquisition unit. an obstacle detection unit that detects an obstacle existing around the vehicle; an obstacle determination unit that determines whether the obstacle detected by the obstacle detection unit is a rod-shaped object; a feature point extracting unit for extracting feature points in an image region between the plurality of rod-shaped objects that are determined to be the plurality of rod-shaped objects; and A fence determination unit that determines that there is a fence between the rod-shaped objects when the plurality of characteristic points extracted by the extraction unit satisfies a predetermined condition.

According to this invention, it is possible to detect fences that are difficult to detect with sonar.

BRIEF DESCRIPTION OF THE DRAWINGS It is a schematic diagram which shows the structure of the parking lot to which the fence detection apparatus 100 which concerns on an Example is applied (part 1). FIG. 2 is a schematic diagram showing the configuration of a parking lot to which the fence detection device 100 according to the embodiment is applied (No. 2); It is a hardware block diagram showing hardware elements constituting a fence detection system to which a fence detection device is applied. It is a flowchart which shows the flow of a series of processes performed with a fence detection apparatus. It is explanatory drawing for demonstrating the detection process of a fence (part 1). It is an explanatory view for explaining detection processing of a fence (part 2). It is an explanatory view for explaining a predetermined condition in judging processing of a fence.

Hereinafter, specific embodiments of the fence detection device according to the present invention will be described with reference to the drawings.

The fence detection device 100 according to the first embodiment is applied to a vehicle 1 traveling in a parking lot with a fence provided at the boundary of a parking space.

(Description of the application scene of the fence detection device)
First, an outline of a parking lot to which the fence detection device 100 (FIG. 3) according to the first embodiment is applied will be described with reference to FIGS. 1 and 2. FIG.

In FIG. 1, a schematic diagram of a parking lot is shown on the left side, and an example of an image captured by the front camera 50 is shown on the right side.

In FIG. 1, of the image captured by the front camera 50, the left half portion is omitted because it is unnecessary, and only the right half portion will be used for explanation.

The image shown in the upper right of FIG. 1 is an image captured by front camera 50 at time t0. The image shown in the lower right of FIG. 1 is an image captured by front camera 50 at time t1.

1 and 2 are schematic diagrams showing the configuration of a parking lot to which the fence detection device 100 according to the first embodiment is applied. Pillars P (rod-shaped members) are erected at predetermined intervals on the boundary separating the parking lot from another parking lot. Between the pillars P that are adjacent to each other, a net-like fence F is provided, which is made up of, for example, wire-like metal, synthetic resin, or the like.

The vehicle 1 is traveling upward in the plane of FIG. 1 (the direction indicated by the white arrow in FIG. 1). A front camera 50 (imaging unit) that captures an image of the periphery of the vehicle 1 including the front end of the vehicle 1 is mounted on the front portion of the vehicle 1 . The asterisks shown in FIGS. 1 and 2 indicate the position of the post P on which the front camera 50 is focused.

The fence detection device 100 executes fence detection processing, which will be described later, based on the image captured by the front camera 50 . FIG. 1 shows a state in which no obstacles other than the pillars P and the fence F exist in the parking lot. A detection device 100 is applied.

As shown in FIG. 2 , even if another vehicle 2 exists in the parking lot, the fence detection device 100 detects only the post P and the fence F from the image captured by the front camera 50 .

(Description of system configuration to which fence detection device is applied)
FIG. 3 is a hardware block diagram showing hardware elements forming fence detection system 10 to which fence detection device 100 is applied.

A fence detection system 10 is installed in a vehicle 1 . The fence detection system 10 has a front camera 50 , a wheel speed sensor 60 , a steering angle sensor 70 and a fence detection device 100 .

Wheel speed sensor 60 detects the wheel speed of vehicle 1 . Information detected by the wheel speed sensor 60 is output to the fence detection device 100 and used in arithmetic processing in the fence detection device 100 .

The steering angle sensor 70 measures the steering angle of the steering of the vehicle 1 . Information detected by the steering angle sensor 70 is output to the fence detection device 100 and used in arithmetic processing in the fence detection device 100 .

(Description of the configuration of the fence detection device)
As shown in FIG. 3, the fence detection device 100 includes an image acquisition unit 101, an obstacle detection unit 102, an obstacle determination unit 103, a feature point extraction unit 104, a fence determination unit 105, and a movement detection unit 106. , and a storage unit 107 .

Inside the fence detection device 100, for example, a microprocessor and programs including peripheral devices, a RAM (Random Access Memory) for storing necessary data, a ROM (Read Only Memory), a dedicated ASIC for image processing and signal processing (Application Specific Integrated Circuit) and other modules are mounted.

The image acquisition unit 101 acquires an image obtained by imaging the surroundings of the vehicle 1 ( FIG. 1 ) with the front camera 50 .

The obstacle detection unit 102 detects obstacles existing around the vehicle 1 based on the plurality of images acquired by the image acquisition unit 101 .

The obstacle determination unit 103 determines whether or not the obstacle detected by the obstacle detection unit 102 is the support P.

The feature point extracting unit 104 extracts feature points FP in an image region between the plurality of determined pillars P when the obstacle determining unit 103 determines that a plurality of the obstacles are the pillars P. .

The fence determination unit 105 determines that there is a fence F between the pillars P when the plurality of feature points FP extracted by the feature point extraction unit 104 satisfy a predetermined condition.

The predetermined condition is that the plurality of feature points FP are arranged substantially in a straight line in the vertical and horizontal directions, the intervals between the feature points FP are substantially the same, and the number of feature points FP is equal to or greater than a predetermined number within a predetermined area. condition that it exists.

Here, the predetermined value is a preset value, and is preferably set to 5 cm, for example (FIG. 7). The predetermined area is a preset area, and is preferably set to 750 cm ² , for example (FIG. 7). The predetermined number is a preset number, and is preferably set to 8, for example.

The movement detection unit 106 detects that the vehicle 1 is moving based on information about the behavior of the vehicle 1 (FIG. 1). Information about the behavior of the vehicle 1 includes the wheel speed detected by the wheel speed sensor 60 and the steering angle detected by the steering angle sensor 70 .

(Flow of a series of processes performed by the fence detection device 100)
Next, the flow of a series of processes performed by the fence detection device 100 will be described with reference to the flowchart shown in FIG. 4 and explanatory diagrams shown in FIGS.

The series of processes shown in FIG. 4 is started, for example, when an input instructing the start of execution of the fence detection process is sent to the fence detection device 100 by the driver's switch operation.

(Step S1)
First, the image acquisition unit 101 acquires an image obtained by imaging the surroundings of the vehicle 1 with the front camera 50 .

(Step S2)
Next, the obstacle detection unit 102 detects obstacles existing around the vehicle 1 using known motion stereo technology. By using motion stereo technology, the obstacle detection unit 102 can obtain a three-dimensional point cloud of obstacles.

Specifically, as shown in FIG. 1, the motion stereo technology utilizes a plurality of images I0 and I1 captured from different viewpoints at different times t0 and t1 by a single front camera 50, and detects obstacles on a plurality of images. This technology calculates the three-dimensional coordinate position of an obstacle based on the movement amount (parallax) of the object.

(Step S3)
Next, the obstacle determination unit 103 determines whether or not the obstacle detected by the obstacle detection unit 102 is the support P. Specifically, the obstacle determination unit 103 determines that the obstacle is the post P when the height of the obstacle is equal to or greater than a predetermined height and the width of the obstacle is equal to or less than a predetermined length. judge.

Here, the predetermined height is a preset height, and is preferably set to 0.5 m, for example. The predetermined length is a preset length, preferably set to 3 cm.

The obstacle determination unit 103 removes noise by detecting obstacles other than the support P, such as vehicles and people that are lower than the support P. Thereby, the support P can be detected more accurately.

If it is determined that the obstacle is the post P (YES in step S3), the process proceeds to step S4. If the obstacle is not determined to be the post P (NO in step S3), the process returns to step S2.

(Step S4)
Next, the feature point extraction unit 104 determines whether or not the obstacle determination unit 103 has determined that a plurality of the obstacles are the pillars P or not. If a plurality of determinations are made (YES in step S4), the process proceeds to step S5. If multiple determinations are not made (NO in step S4), the process returns to step S2.

(Step S5)
A feature point extraction unit 104 extracts feature points FP in an image region between the plurality of supports P. FIG. Here, the feature point FP is a portion where the linear members intersect. Specifically, the feature point FP is a portion where wire-like metal, thin synthetic resin, or the like that constitutes the grid-like fence F crosses and intersects. It is indicated by the intersection marked with an X in FIG. Here, the term “lattice” refers to a state in which a plurality of vertical lines and horizontal lines intersect, and includes not only a rectangular lattice but also a repeating shape such as a regular hexagonal lattice (honeycomb shape).

The feature point extracting unit 104 scans an area occupying a predetermined area of the image area between the plurality of pillars P in a substantially straight line in the vertical and horizontal directions, and extracts a luminance change point. This extracted portion becomes a portion where the wire-like metal, thin synthetic resin, or the like crosses and intersects. The feature point extraction unit 104 extracts, as feature points FP, points of change where the respective intervals are substantially the same. After that, the process proceeds to step S6.

(Step S6)
Next, the fence determination unit 105 compares the feature points FP stored in advance in the storage unit 107 with the feature points FP by pattern recognition, template matching, or the like, and calculates a correlation value between the two. The fence determination unit 105 determines whether or not there is a feature point FP whose calculated correlation value is equal to or greater than a predetermined threshold.

If there is a feature point FP whose correlation value is greater than or equal to the threshold (YES in step S6), the process proceeds to step S7. If there is no feature point FP whose correlation value is equal to or greater than the threshold (NO in step S6), the process returns to step S5.

(Step S7)
Next, the fence determination unit 105 determines whether or not the number of feature points FP whose correlation values are equal to or greater than the threshold is equal to or greater than a predetermined number. If the number of feature points FP is equal to or greater than the predetermined number (YES in step S7), the fence determination unit 105 determines that there is a fence between the pillars P (step S8). If the number of feature points FP is less than the predetermined number (NO in step S7), the process proceeds to step S9.
(Step S9)
Next, the fence determination unit 105 determines whether or not the determination has been completed for all the columns. When the determination has been completed for all the pillars (YES in step S9), a series of processing performed by the fence detection device 100 is completed. On the other hand, if the determination has not been completed for all strut spaces, the process returns to step S5.

In Example 1 described above, the fence determination unit 105 determines that there is a fence F between the pillars P when the plurality of feature points FP extracted by the feature point extraction unit 104 satisfy a predetermined condition. This makes it possible to detect the fence F, which is difficult to detect with sonar.

Although the embodiments of the present invention have been described above in detail with reference to the drawings, the embodiments are merely illustrative of the present invention, and the present invention is not limited only to the configurations of the embodiments. It goes without saying that even if there is a change in design within the scope of the gist of the invention, it is included in the present invention.

In the first embodiment described above, an example was described in which an obstacle is detected based on a plurality of images captured by the single front camera 50 at different times t0 and t1 while the vehicle 1 is moving. The present invention is not limited to this aspect, and for example, a plurality of cameras installed at positions different from the front of the vehicle 1 may detect obstacles based on a plurality of images taken simultaneously at a specific time. Objects may be detected.

In addition, in the first embodiment described above, an example in which the front camera 50 attached to the front portion of the vehicle 1 configures the imaging unit has been described. The present invention is not limited to this aspect. may be configured.

In addition, in the first embodiment described above, an example was explained in which the characteristic point FP is a portion where the linear members intersect each other. The present invention is not limited to this aspect, and for example, feature points FP may be portions having substantially the same contour shape.

1... vehicle 2... other vehicle (obstacle)
10 Fence detection system 50 Front camera (imaging unit)
Reference Signs List 100 Fence detection device 101 Image acquisition unit 102 Obstacle detection unit 103 Obstacle determination unit 104 Feature point extraction unit 105 Fence determination unit 106 Movement Detection unit F... Fence FP... Characteristic points I0, I1... Image P... Post (bar-shaped member)

Claims (4)

an image acquisition unit that acquires an image obtained by imaging the surroundings of the vehicle with an imaging unit mounted on the vehicle;
an obstacle detection unit that detects obstacles existing around the vehicle based on the plurality of images acquired by the image acquisition unit;
an obstacle determination unit that determines whether the obstacle detected by the obstacle detection unit is a rod-shaped object;
When the obstacle determination unit determines that a plurality of the obstacles are the rod-shaped objects, extracting feature points in an image region between the plurality of the determined rod-shaped objects, a feature point extracting unit that does not extract the feature points if a plurality of the rod-shaped objects are not determined;
a fence determination unit that determines that there is a fence between the rod-shaped objects when the plurality of feature points extracted by the feature point extraction unit satisfies a predetermined condition. . The fence detection device according to claim 1,
The fence detection device, wherein the feature point is an intersecting portion. In the fence detection device according to claim 1 or claim 2,
The predetermined condition is that the plurality of feature points are arranged in a substantially straight line in the vertical direction and the horizontal direction, the intervals between the feature points are substantially the same, and a predetermined number or more of the feature points are located within a predetermined area. A fence detection device characterized by being a condition that it exists. In the fence detection device according to any one of claims 1 to 3,
A movement detection unit that detects that the vehicle is moving based on information about the behavior of the vehicle;
The obstacle detection unit detects the obstacle existing in the vicinity based on a plurality of images acquired at different times when it is detected that the vehicle is moving. Fence detector.

Images