CN117429413A - Empty space detection method and device, intelligent automobile and readable storage medium - Google Patents

Abstract

The invention relates to the field of automatic driving, and discloses a method and a device for detecting an empty space, an intelligent automobile and a readable storage medium. The method comprises the following steps: acquiring original distance data returned by the detection devices in all directions on the vehicle to obtain dynamic coordinates of all detected objects; determining a real-time boundary distance between the vehicle and each detected object according to the dynamic coordinates; determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value; and determining the contour width and the contour depth according to the generated detection contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values. The vehicle can determine the parking space through the outline, and the vehicle is more accurate.

Description

Empty space detection method and device, intelligent automobile and readable storage medium

Technical Field

The invention relates to the field of automatic driving, in particular to a method and a device for detecting an empty space, an intelligent automobile and a readable storage medium.

Background

The APA parking system is an automatic parking auxiliary system, and detects the environment around the vehicle through sensors such as a camera, ultrasonic waves and the like of the vehicle, automatically searches for a proper parking space and automatically completes the parking operation.

In APA parking, an ultrasonic sensor is usually used for assisting in visual recognition of an empty parking space, when an automobile runs at a low speed and passes through the empty parking space, an ultrasonic sensor arranged on the side face of the automobile can conduct distance detection, when obstacles or vehicles are arranged on two sides of the empty parking space, the detection distance of the ultrasonic sensor can be firstly reduced, then is increased and then is reduced, the system obtains empty parking space information according to vehicle positioning information through detecting the process, and the obtained empty parking space is delivered to a follow-up planning module to conduct automatic parking control.

At present, certain errors exist in the distance information returned by the ultrasonic sensor, and the influence of the surrounding environment is larger: the ultrasonic sensor has a beam angle, and has the condition of unstable echo jump, which leads to advanced echo or delayed echo, thereby generating obstacle positioning error, inaccurate parking space obtained by detection, or generating erroneous judgment or missed judgment.

Disclosure of Invention

In a first aspect, the present application provides a method for detecting an empty space, including:

acquiring original distance data returned by the detection devices in all directions on the vehicle to obtain dynamic coordinates of all detected objects;

determining a real-time boundary distance between the vehicle and each detected object according to the dynamic coordinates;

determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value;

and determining the contour width and the contour depth according to the generated detection contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values.

Further, the determining whether to generate the detection profile according to the distance mutation value includes:

determining a change interval of the distance mutation value, wherein each change interval has a set weight value;

if the mutation direction of the distance mutation value is the same as the mutation direction in the last detection, accumulating the weight value corresponding to the change interval according to the change interval where the distance mutation value is located, and if the accumulated weight value reaches a preset threshold, determining to generate a detection contour.

Further, the method further comprises:

if the mutation direction of the distance mutation value is different from the mutation direction in the last detection, resetting the weight value;

returning to the step of determining the real-time boundary distance between the vehicle and each detected object.

Further, determining a contour width and a contour depth according to the currently generated detection contour, and determining that an empty car is detected if the contour width and the contour depth reach preset values, including:

calculating the distance between adjacent contours to obtain contour distances;

if the contour distance is larger than a first preset distance, taking the boundary distance of the areas between the adjacent contours as the contour depth;

and if the contour depth is larger than a second preset distance, determining that the empty vehicle position is detected.

Further, the determining whether to generate the detection profile according to the distance mutation value includes:

determining the mutation direction of the current distance mutation value, and determining to generate a new contour if the mutation direction is different from the mutation direction in the last detection.

Further, the acquiring the original distance data returned by the detection device in each direction of the vehicle includes:

and acquiring object coordinates detected by the detection devices in the four directions of the front left, the front right, the rear left and the rear right of the vehicle.

Further, the method further comprises:

fusing outlines generated by different detection devices in the same area, and determining that an empty parking space exists in the current area if any one detection device recognizes that the empty parking space exists in the current area.

In a second aspect, the present application further provides an empty space detection device, including:

the detection module is used for acquiring original distance data returned by the detection device in each direction on the vehicle to obtain dynamic coordinates of each detected object;

the ranging module is used for determining the real-time boundary distance between the vehicle and each detected object according to the dynamic coordinates;

the contour generation module is used for determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value;

and the judging module is used for determining the contour width and the contour depth according to the generated detection contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values.

In a third aspect, the present application further provides a smart car, including a processor and a memory, where the memory stores a computer program, and the computer program executes the empty space detection method when running on the processor.

In a fourth aspect, the present application also provides a readable storage medium storing a computer program which, when run on a processor, performs the empty space detection method.

The invention discloses an empty space detection method and device, an intelligent automobile and a readable storage medium. The method comprises the following steps: acquiring original distance data returned by the vehicle and the detection devices in all directions, and obtaining dynamic coordinates of all detected objects; determining a boundary distance between the vehicle and each detected object according to the dynamic coordinates; determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value; and determining the contour width and the contour depth according to the currently generated contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values. The vehicle can determine the parking space through the outline, and the vehicle is more accurate.

Drawings

In order to more clearly illustrate the technical solutions of the present invention, the drawings that are required for the embodiments will be briefly described, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope of the present invention. Like elements are numbered alike in the various figures.

Fig. 1 shows a schematic flow chart of an empty space detection method according to an embodiment of the present application;

FIG. 2 illustrates a schematic view of a parking scenario according to an embodiment of the present application;

FIG. 3 is a schematic view of a world coordinate system of a vehicle in accordance with an embodiment of the present application;

FIG. 4 illustrates a schematic diagram of a detection profile according to an embodiment of the present application;

fig. 5 shows a schematic structural diagram of an empty space detection device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.

The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.

The terms "comprises," "comprising," "including," or any other variation thereof, are intended to cover a specific feature, number, step, operation, element, component, or combination of the foregoing, which may be used in various embodiments of the present invention, and are not intended to first exclude the presence of or increase the likelihood of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.

Furthermore, the terms "first," "second," "third," and the like are used merely to distinguish between descriptions and should not be construed as indicating or implying relative importance.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the invention belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having a meaning that is the same as the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in connection with the various embodiments of the invention.

When the application is applied to parking of the vehicle, the application scene of the empty space position is acquired through automatic detection of the detection device, and the dynamic coordinates of each detection object are obtained mainly through acquisition of the vehicle and the original distance data returned by the detection device in each direction; determining a boundary distance between the vehicle and each detected object according to the dynamic coordinates; determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value; and after the detection contour is generated, determining the contour width and the contour depth, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values. The position of the empty parking space is determined through the outline, and detection is achieved.

The technical scheme of the application is described in the following specific embodiments.

Example 1

As shown in fig. 1, the empty space detection method of the present embodiment includes:

step S100, acquiring original distance data returned by the vehicle and the detection devices in all directions, and obtaining dynamic coordinates of all detected objects;

the empty space detection method of the embodiment is obviously applied to a parking process, wherein a plurality of detection devices are arranged on a vehicle, the detection devices are mainly used for detecting the distance between the surrounding obstacles of the vehicle and the vehicle, and the detection devices can be ultrasonic radars, visual sensors and the like.

The devices are disposed around the vehicle in a certain distribution, as shown in fig. 2, in this parking scenario, the vehicle 100 is driven from right to left, and the detection devices 200 are disposed at four positions of the front left, rear left, front right and rear right of the vehicle 100, and the arrangement and number of the detection devices 200 in fig. 2 are one possible manner, and instead of preventing the four corners of the vehicle, the corresponding detection devices may be disposed on the four sides of the vehicle.

At the same time, a parking space exists on the right side of the vehicle 100 and the vehicle parked in the parking space can be obtained by the layout mode of the detection device as shown in the figure.

It can be seen that the vehicle 100 can detect the coordinate positions of the surrounding obstacles by the four detection devices described above. Since the vehicle is moving, the coordinates of the surrounding obstacle are dynamically updated by the movement of the vehicle, and the obtained coordinates are dynamic coordinates. And it will be appreciated that by concatenating the coordinates, one profile can be obtained with more than one object and more than one coordinate.

Step S200, determining a boundary distance between the vehicle and each detected object according to the dynamic coordinates.

In this embodiment, the center point of the rear axle of the vehicle is used as the coordinates of the vehicle, and the boundary distance between each dynamic coordinate and the vehicle is calculated based on the coordinates.

In order to better determine the dynamic coordinates and the boundary distance when the vehicle is parked, the starting point of the vehicle is taken as a far point, the center of the rear axle of the vehicle is taken as the vehicle coordinate, and a world coordinate system is established, wherein the coordinate system is shown in fig. 3.

Wherein, the point P is the center of the rear axle of the vehicle, the position coordinates are (xoc, yoc), the heading angles of the vehicle are theta, FL, RL, FR, RR are respectively left front, left rear, right front and right rear ultrasonic radars, the lateral distances of the left front (right front) and the left rear (right rear) from the center point P of the rear axle of the vehicle are SNS1 and SNS2, and the longitudinal distances of the left front, right front, left rear and right rear from the center point P of the rear axle of the vehicle are SNS_Y.

Through a triangle formula, the coordinates of the 4 ultrasonic radars in the global coordinate system can be obtained as follows:

FLx＝xoc+SNS2·cosθ-SNS_Y·sinθ

FLy＝yoc+SNS2·sinθ+SNS_Y·cosθ

RLx＝xoc-SNS1·cosθ-SNS_Y·sinθ

RLy＝yoc-SNS1·sinθ+SNS_Y·cosθ

FRx＝xoc+SNS2·cosθ+SNS_Y·sinθ

FRy＝yoc+SNS2·sinθ-SNS_Y·cosθ

RRx＝xoc-SNS1·cosθ+SNS_Y·sinθ

RRy＝yoc-SNS1·sinθ-SNS_Y·cosθ

assuming that the distances detected by the ultrasonic radar of the Front Left (FL), the Rear Left (RL), the Front Right (FR) and the Rear Right (RR) are d0, d1, d2 and d3 respectively in the current pose, the coordinates of the currently detected obstacle are:

(FLx-d0·sinθ，FLy+d0·cosθ)，

(RLx-d1·sinθ，RLy+d1·cosθ)，

(FRx+d2·sinθ，FRy-d2·cosθ)，

(RRx+d3·sinθ，RRy-d3·cosθ)。

step S300, determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value.

The abrupt value refers to the difference between the last boundary distance and the last boundary distance.

The boundary distance will change along with the movement of the vehicle, and there are generally 6 states, for example, a first preset distance is set from small to large, a second preset distance and a third preset distance, when the return distance is stable, the detected boundary distance is greater than the third preset distance, and the change range of the abrupt change value is smaller than the first preset distance, and then the state is a vacancy state.

If the returned boundary distance is stable and smaller than the third preset distance, the obstacle state is obtained.

If the boundary distance is obviously increased and the abrupt change value is in the first interval, the state is in a small ascending trend state, and if the abrupt change value is in the second interval, the state is in a large ascending trend state.

If the boundary distance is obviously reduced and the abrupt change value is in the first interval, the state is in a small descending trend, and if the abrupt change value is in the second interval, the state is in a large descending trend.

The first preset distance may be 20 to 40 cm, the second preset distance may be 80 to 100cm, and the third preset distance may be 2000 to 3500 cm, and the first interval may be composed of the first preset value and the second preset value, and the second interval may be composed of the second preset value and the third preset value, and the interval may be changed along with the change of the three preset values, so long as the range of the first interval is smaller than the range of the second interval.

Wherein the four trend states are unstable states.

In the empty and obstacle states, a steady state is assumed in which if a profile has been generated, the profile can continue to extend without the need to generate a detection profile.

For the following four upward trends and downward trends, the distance between the surrounding object and the vehicle is suddenly changed, and a detection profile may need to be generated to determine the surrounding environment.

For this reason, a first weight is set when the abrupt change value is in a first interval, a second weight is set when the abrupt change value is in a second interval, the abrupt change value is calculated after the boundary distance is updated each time, the weights are accumulated according to the interval in which the abrupt change value is located until the weights reach a preset value, and then the detection contour is considered to be required to be generated.

And if the mutation direction of the mutation value is different from that of the previous time, resetting the weight value.

It will be appreciated that this is typically the case where the surrounding barrier is complex in its environment, where there are barriers in one area and no barriers in another, so that the detection means will detect abrupt changes with different trends, and in this case no effective profile can be formed.

For example, the first weight is 1, the second weight is 5, and the preset weight value is 20, that is, if the 4 consecutive detection abrupt change values are all within the second interval, the detection contour is considered to be required to be generated. And when the weight value reaches a preset value, the current state is judged to be a stable state. In steady state no new contours are reproduced.

One of the profiles may include start and end coordinates of the profile, and when the detected profile is generated, the coordinates of the obstacle detected at this time are the start coordinates of the detected profile.

Before the detection contour is generated, judging whether the width of the old contour is smaller than a contour width threshold (such as smaller than 5 cm), if so, judging that the old contour is interference data, and deleting the old contour;

before the detected contour is generated, judging whether the current contour and the previous contour have the same characteristics (the distance from the vehicle body is the same), if so, indicating that interference data can be received in the middle, and combining the two contours.

Step S400, after the detection contour is generated, determining the contour width and the contour depth, and if the contour width and the contour depth reach preset values, determining that the empty vehicle is detected.

In generating the detection profile, the profile width and profile depth are also determined.

As shown in fig. 4, a contour image generated by a detection device corresponds to the scene of the parking lot in fig. 2.

The contour is composed of line segments 1, 2, 3, 4 and 5, wherein the line segments 1 and 2 represent the contour formed by the vehicles parked in the parking space in front of the vehicles in fig. 2, the line segments 4 and 5 represent the vehicles parked in the parking space at the rear side of the vehicles, and the line segment 3 represents the limiters such as parking space stops existing in the parking space. It will be appreciated that according to the foregoing profile generation rule, 3 sets of profiles are actually implemented in fig. 4, that is, the line segments 1 and 2 are one set, which is called a first profile, the line segment 3 is a second profile, and the line segments 4 and 5 are a third profile.

It is clear that the first contour and the third contour indicate that there are some physical obstacles in this part of the space, through which the vehicle cannot travel, and that the second contour indicates that no physical obstacle is detected here, through which the vehicle can travel.

Therefore, the contour width in this step refers to the distance between the areas where the first contour and the third contour are determined to be the obstacle, and the area where the second contour is located is determined to be the empty state.

The contour width, i.e. the length represented by the line segment D indicated in fig. 4, and the contour depth, i.e. the boundary distance detected in the space where the contour width is located, i.e. the boundary distance detected by the detecting means 200 in the area where the contours are located.

It will be appreciated that generally the depth of the outline of an empty space will be greater than the width or length of the vehicle and therefore the distance between the sides of the outline and the vehicle. Alternatively, the empty space may correspond to the empty state described above.

Wherein the contour width is at least greater than the width of the vehicle itself to adequately stop the vehicle, and the contour depth is also at least greater than the width of the vehicle. Because the parking space is generally a longitudinal parking space or a transverse parking space, if the parking space is a longitudinal parking space, the contour width can be smaller than the length of the vehicle but is necessarily larger than the width of the vehicle, and meanwhile, the contour depth is necessarily larger than the length of the vehicle, and similarly, if the parking space is a transverse parking space, the contour width is necessarily larger than the length of the vehicle, and meanwhile, the contour depth is also required to be larger than the width of the vehicle. That is, the contour width and contour depth satisfying the above conditions can be determined that the empty parking space is detected.

In addition, as can be seen from the layout and the driving direction of the detecting device 200 in fig. 2, a plurality of detecting devices 200 are often scanned for the same area, and the data of each detecting device can form a contour according to the above steps, so that the contour fusion operation is performed for the contours in this embodiment.

Specifically, according to the scheme of maximizing the contour, the contours formed by the front and rear sides of the same side of the vehicle are combined, so that the interference of the surrounding environment can be further eliminated, and the more accurate parking space contour is obtained. That is, as long as the outline of one detection device is judged to be in a stable vacancy state in a certain section of region, no matter what state the other detection device is judged to be, the region is set to be in the vacancy state; and the same is recorded, all dynamic coordinate points are traversed, and the contours of the same side of the vehicle can be fused.

Specifically, only three cases are used in which the contour obtained by the front detection device a and the contour obtained by the rear detection device B are combined by traversing the area through which the vehicle is traveling, and the three cases are as follows:

no contours exist for a and B in this region: this region is determined to be in a transitional state and is not processed as an unknown contour.

Only one contour exists for a and B in this region: this profile feature is added after merging to make the profile clearer.

Both a and B have contours within this region: after merging, the distance between the contour of the intersection area and the central axis takes the value of the distance from the vehicle body to the far.

For example, in the region of 100cm to 150cm in X coordinate, A and B obtain the following profile information respectively:

profile a: the start point coordinates (100, 130), the end point coordinates (150 ) are located at a distance of 130cm to 150cm from the vehicle center axis.

Profile B: the start point coordinates (100, 150) and the end point coordinates (150, 130) are located at a distance of 150cm to 130cm from the vehicle center axis.

The combined profile is then the start point coordinates (100, 150) and the end point coordinates (150 ) are 150cm from the vehicle center axis.

Meanwhile, for each detection device, the maximum range is often provided, for example, when the parking space boundary is too far away from the vehicle, the range of actual effective detection is too narrow, and the current contour cannot be used for parking space judgment. Firstly, checking the difference value between the depth of the outline and the boundary, judging whether the depth is smaller than the threshold value of the vehicle width, and if so, continuing to wait for the subsequent continuous detection.

For example, if the maximum range of a certain detection device is 4m, and if the parking space boundary distance of a certain contour is greater than 3m, the effective detection depth of the maximum identified empty space is smaller than 1m, and the contour cannot be output as an effective parking space.

After judging that the vehicle has a parking space, the parking space coordinates of the global coordinate system are converted into a vehicle body coordinate system taking the center of the rear wheel of the current vehicle as an origin, so that the vehicle can park conveniently.

If the global coordinate system is parking space (x 0, y 0), (x 1, y 1), (x 2, y 2), (x 3, y 3).

Then calculating the parking space coordinates under the vehicle body coordinate system:

((x 0', y 0'), (x 1', y 1'), (x 2', y 2'), (x 3', y 3')) the method is as follows

x0’＝(x0-xoc)·cos(θ)+(y0-yoc)·sin(θ)

y0’＝(y0-yoc)·cos(θ)-(x0-xoc)·sin(θ)

x1’＝(x1-xoc)·cos(θ)+(y1-yoc)·sin(θ)

y1’＝(y1-yoc)·cos(θ)-(x1-xoc)·sin(θ)

x2’＝(x2-xoc)·cos(θ)+(y2-yoc)·sin(θ)

y2’＝(y2-yoc)·cos(θ)-(x2-xoc)·sin(θ)

x3’＝(x3-xoc)·cos(θ)+(y3-yoc)·sin(θ)

y3’＝(y3-yoc)·cos(θ)-(x3-xoc)·sin(θ)

Where θ in the above equation represents a heading angle when the vehicle is running, yoc and xoc are coordinates of the vehicle position in the global coordinate system.

According to the method, whether the detected contour is generated or not is judged through collecting the detected obstacle distance and through the change of the abrupt change value of the boundary distance, the corresponding contour is generated, and the contour distance and the contour depth are calculated, so that a vehicle is helped to judge whether an idle parking space exists nearby or not. The method of the embodiment enables the formation of the contour to be more stable, the generated contour is basically located at the same distance with the distance of the vehicle in consideration of the influence of the abrupt change value, the generated contour result has more reference significance, and interference signals can be further removed through combination.

Example 2

As shown in fig. 5, the present application further provides an empty space detection device, including:

the detection module 10 is used for acquiring the original distance data returned by the detection device in each direction on the vehicle and obtaining the dynamic coordinates of each detected object;

a ranging module 20 for determining a boundary distance between the vehicle and each detected object according to the dynamic coordinates;

the profile generation module 30 is configured to determine a distance abrupt change value according to a difference between a boundary distance at a current time and a boundary distance at a previous time, and determine whether to generate a detection profile according to the distance abrupt change value;

and the judging module 40 is used for determining the contour width and the contour depth after the detection contour is generated, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values.

The application also provides an intelligent automobile comprising a processor and a memory, wherein the memory stores a computer program, and the computer program executes the empty space detection method when running on the processor.

The present application also provides a readable storage medium storing a computer program which, when run on a processor, performs the empty space detection method.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners as well. The apparatus embodiments described above are merely illustrative, for example, of the flow diagrams and block diagrams in the figures, which illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules or units in various embodiments of the invention may be integrated together to form a single part, or the modules may exist alone, or two or more modules may be integrated to form a single part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a smart phone, a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention.

Claims (10)

1. An empty space detection method, characterized by comprising:

acquiring original distance data returned by the detection devices in all directions on the vehicle, and obtaining dynamic coordinates of all detection objects;

determining a real-time boundary distance between the vehicle and each detected object according to the dynamic coordinates;

determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value;

and determining the contour width and the contour depth according to the generated detection contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values.

2. The empty space detection method according to claim 1, wherein the determining whether to generate a detection profile according to the distance abrupt change value comprises:

determining a change interval of the distance mutation value, wherein each change interval has a set weight value;

if the mutation direction of the distance mutation value is the same as the mutation direction in the last detection, accumulating the weight value corresponding to the change interval according to the change interval where the distance mutation value is located, and if the accumulated weight value reaches a preset threshold, determining to generate a detection contour.

3. The empty space detection method according to claim 2, characterized by further comprising:

if the mutation direction of the distance mutation value is different from the mutation direction in the last detection, resetting the weight value;

returning to the step of determining the real-time boundary distance between the vehicle and each detected object.

4. The empty space detection method according to claim 1, wherein determining a contour width and a contour depth according to the generated detection contour, and determining that an empty space is detected if both the contour width and the contour depth reach preset values comprises:

calculating the distance between adjacent contours to obtain contour distances;

if the contour distance is larger than a first preset distance, taking the boundary distance of the areas between the adjacent contours as the contour depth;

and if the contour depth is larger than a second preset distance, determining that the empty vehicle position is detected.

5. The empty space detection method according to claim 1, wherein the determining whether to generate a detection profile according to the distance abrupt change value comprises:

determining the mutation direction of the current distance mutation value, and determining to generate a new contour if the mutation direction is different from the mutation direction in the last detection.

6. The method for detecting the empty space according to claim 1, wherein the step of acquiring the original distance data returned from the detecting device in each direction of the vehicle comprises the steps of:

and acquiring object coordinates detected by the detection devices in the four directions of the front left, the front right, the rear left and the rear right of the vehicle.

7. The empty space detection method according to claim 1, characterized by further comprising:

fusing outlines generated by different detection devices in the same area, and determining that an empty parking space exists in the current area if any one detection device recognizes that the empty parking space exists in the current area.

8. An empty space detection device, comprising:

the detection module is used for acquiring original distance data returned by the detection device in each direction on the vehicle to obtain dynamic coordinates of each detected object;

the ranging module is used for determining the real-time boundary distance between the vehicle and each detected object according to the dynamic coordinates;

the contour generation module is used for determining a distance mutation value according to the difference value between the boundary distance at the current moment and the boundary distance at the last moment, and determining whether to generate a detection contour according to the distance mutation value;

and the judging module is used for determining the contour width and the contour depth according to the generated detection contour, and determining that the empty vehicle position is detected if the contour width and the contour depth reach preset values.

9. A smart car comprising a processor and a memory, the memory storing a computer program which, when run on the processor, performs the empty space detection method of any of claims 1 to 7.

10. A computer-readable storage medium, characterized in that it stores a computer program which, when run on a processor, performs the empty space detection method of any of claims 1 to 7.