Disclosure of Invention
In view of the above problems, embodiments of the present invention are provided to provide a parking space recognition accuracy detection method, a parking space recognition accuracy detection apparatus, an electronic device, and a storage medium that overcome or at least partially solve the above problems.
In order to solve the above problems, the embodiment of the invention discloses a parking space identification precision detection method, which is applied to a detection system, wherein the vehicle detection system comprises an optical positioning system, a vehicle, a look-around visual detection system (AVM) installed on the vehicle and an entity parking space; the method comprises the following steps:
acquiring a first coordinate value of an AVM (automatic vehicle model) for a virtual parking space corresponding to the angular point identification, wherein the AVM is generated by detecting an entity parking space when the vehicle passes through the entity parking space under a preset working condition;
acquiring a second coordinate value of the optical positioning system for identifying the corresponding angular point of the entity parking space;
and comparing the first coordinate value with the second coordinate value to determine the parking space identification precision.
Optionally, the AVM includes a panoramic electronic control unit, a camera, and an intelligent controller, and the first coordinate value is generated as follows:
when the camera detects an entity parking space, the panoramic electronic control unit generates a virtual parking space and determines the corresponding angular point of the virtual parking space;
and the intelligent controller determines a coordinate point of the corresponding angular point of the virtual parking space under a vehicle coordinate system to generate a first coordinate value.
Optionally, the optical positioning system includes an optical base station, a parking space positioner, and a parking space receiving sensor installed on the parking space positioner, and the second coordinate value is generated as follows:
the optical base station sends out optical signals;
when the parking space receiving sensor receives the optical signal, the parking space positioner determines a coordinate point of the parking space receiving sensor in the optical system coordinate to generate a second coordinate value.
Optionally, the first coordinate value is a coordinate value of a vehicle coordinate system; the second coordinate value is a coordinate value of a coordinate system of the optical system, and the step of comparing the first coordinate value with the second coordinate value to determine the parking space recognition accuracy includes:
converting the first coordinate value into a third coordinate value under the optical system coordinate system;
and comparing the third coordinate value with the second coordinate value to determine the parking space identification precision.
Optionally, a vehicle locator and a vehicle receiving sensor mounted on the vehicle locator are further mounted on the vehicle, and when the vehicle receiving sensor receives the optical signal, the vehicle locator determines a coordinate point of the parking space receiving sensor in the optical system coordinates to generate a fourth coordinate value; the step of converting the first coordinate value into a third coordinate value in the optical system coordinate system includes:
determining the acquisition time of the fourth coordinate value and the first coordinate value;
synchronizing the fourth coordinate value and the first coordinate value according to the acquisition time to generate a coordinate conversion matrix;
and converting the first coordinate value into a third coordinate value under the optical system coordinate system through the coordinate conversion matrix.
Optionally, the step of comparing the third coordinate value with the second coordinate value to determine the parking space recognition accuracy includes:
and calculating the difference value of the third coordinate value and the second coordinate value to determine the parking space identification precision.
Optionally, the preset operating condition includes: the speed and the distance between the vehicle and the physical parking space are measured.
The embodiment of the invention also discloses a parking space identification precision detection device which is applied to a detection system, wherein the vehicle detection system comprises an optical positioning system, a vehicle, a look-around visual detection system AVM installed on the vehicle and an entity parking space; the device comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a first coordinate value of an AVM (automatic vehicle model) for a virtual parking space corresponding to an angle point identification, and the AVM is generated by detecting an entity parking space when a vehicle passes through the entity parking space under a preset working condition;
the second acquisition module is used for acquiring a second coordinate value of the optical positioning system for identifying the corresponding angular point of the entity parking space;
and the comparison module is used for comparing the first coordinate value with the second coordinate value to determine the parking space identification precision.
The embodiment of the invention also discloses an electronic device, which comprises: the parking space recognition accuracy detection method comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein the computer program realizes the steps of the parking space recognition accuracy detection method when being executed by the processor.
The embodiment of the invention also discloses a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program is executed by a processor to realize the steps of the parking space identification precision detection method.
The embodiment of the invention has the following advantages:
according to the embodiment of the invention, a first coordinate value of an AVM (automatic vehicle model) for identifying the corresponding angle point of a virtual parking space is obtained, wherein the AVM is generated by detecting the entity parking space when the vehicle passes through the entity parking space under a preset working condition; acquiring a second coordinate value of the optical positioning system for identifying the corresponding angular point of the entity parking space; and comparing the first coordinate value with the second coordinate value to determine the parking space identification precision. And carrying out accurate control on the posture of the vehicle body when the vehicle is parked into the parking space during automatic parking based on the identification precision.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a parking space recognition accuracy detection method according to the present invention is shown, and the method is applied to a detection system, where the vehicle detection system includes an optical positioning system, a vehicle, a look-around visual detection system AVM installed on the vehicle, and an entity parking space;
it should be noted that, referring to fig. 2, a schematic structural diagram of an optical system in an embodiment of the present invention is shown; the optical system adopts 850 nm eye safe infrared light, the optical base station sends out optical signals with unique codes, and the radius of a circle of a coverage area is 2.5 times of the height from the base station to the ground.
The AVM is a system which shoots images through a plurality of super-large wide-angle fisheye lenses, and performs distortion correction and splicing on the shot images through a special algorithm to form a panoramic image around an object.
The method may specifically comprise the steps of:
step 101, acquiring a first coordinate value of an AVM for identifying a corresponding angle point of a virtual parking space, wherein the AVM is generated by detecting an entity parking space when a vehicle passes through the entity parking space under a preset working condition;
a plurality of parking spaces can be divided in an area in the detection system, the parking spaces on the ground are determined to be entity parking spaces, the entity parking spaces are provided with parking lines, the entity parking spaces are formed by the envelope of the parking lines, and the intersection points of the parking lines are the corner points corresponding to the entity parking spaces. The virtual parking space is a virtual object corresponding to the entity parking space and is displayed in a digital image mode.
When the vehicle runs in the area containing the entity parking space under the preset working condition, the AVM can acquire the environmental information of the position where the vehicle is located, and the environmental information contains the image data of the entity parking space.
And obtaining a first coordinate value for identifying the corresponding angular point of the virtual parking space by carrying out corresponding processing on the image data, including but not limited to parking space feature extraction.
Fig. 3 can be seen to show an example diagram of an angle point corresponding to a virtual parking space detected by an AVM in the embodiment of the present invention;
in a preferred embodiment of the present invention, the first coordinate value includes four angular points, and among the four angular points of the same parking space, two of the four angular points close to the vehicle in a direction perpendicular to a direction of the vehicle are near angular points, and two of the angular points far from the vehicle are far angular points, and two of the four angular points near the front and two of the points far from the vehicle in a driving direction are rear angular points, and the four angular points are sequentially obtained as a near front angular point, a far front angular point, a near rear angular point, and a far rear angular point. Accordingly, the first coordinate value may include a Near Front (NF) coordinate, a Far Front (FF) coordinate, a Near Rear (NR) coordinate, and a Far Rear (FR) coordinate.
In a preferred embodiment of the present invention, the preset operation condition includes: the speed and the distance between the vehicle and the physical parking space are measured.
In practical application, different vehicle speeds and different entity parking space side distances can be combined to form different working conditions to detect the recognition accuracy of the entity parking spaces under different working conditions of the vehicle. Wherein, the different vehicle speeds include but are not limited to 3KM/H, 5KM/H, 7KM/H, 12KM/H, and the vehicle-to-physical parking space side distance includes but is not limited to 0.5M, 1M, 1.5M. Those skilled in the art may set other vehicle speeds and distances between the vehicle and the physical parking space according to requirements, which is not limited in the embodiment of the present invention.
In a preferred embodiment of the present invention, the AVM includes a panoramic electronic control unit, a camera, and an intelligent controller, and the first coordinate value is generated as follows:
when the camera detects an entity parking space, the panoramic electronic control unit generates a virtual parking space and determines the corresponding angular point of the virtual parking space;
and the intelligent controller determines a coordinate point of the corresponding angular point of the virtual parking space under a vehicle coordinate system to generate a first coordinate value.
The AVM comprises a panoramic electronic control unit, a camera and an intelligent controller; when a vehicle enters the detection system, the camera performs environment detection to obtain an environment image, and when the vehicle passes through an entity parking space, a complete entity parking space appears in the environment image, such as a complete rectangular parking space frame is detected; and the panoramic electronic control unit generates a virtual parking space according to the image, and the corner point of the parking space frame corresponding to the virtual parking space. And then, determining coordinate points of the corner points of the parking space frames corresponding to the virtual parking spaces under the vehicle coordinate system through the intelligent controller, and generating a first coordinate value. The vehicle coordinate system may be a three-dimensional rectangular coordinate system established by the intelligent controller for the origin. The intelligent controller may be a vehicle odometer.
102, acquiring a second coordinate value of the optical positioning system for identifying the corresponding angular point of the entity parking space;
and acquiring a second coordinate value of the angular point of each entity parking space determined by the optical positioning system, and taking the second coordinate value as a true value (also called as a standard value) of the angular point position of the entity parking space.
Similarly, the second coordinate value also includes four corner points, two corner points close to the vehicle in the direction perpendicular to the vehicle direction are near corner points, two corner points far away from the vehicle are far corner points, two front corner points near the front in the vehicle driving direction and two rear corner points near the rear in the vehicle driving direction are rear corner points, and the four corner points are sequentially obtained as a near front corner point, a first far front corner point, a near rear corner point and a far rear corner point. Accordingly, the second coordinate value may include a Near Front (NF) coordinate, a Far Front (FF) coordinate, a Near Rear (NR) coordinate, and a Far Rear (FR) coordinate.
In a preferred embodiment of the present invention, the optical positioning system includes an optical base station, a parking space positioner, and a parking space receiving sensor installed on the parking space positioner, and the second coordinate value is generated as follows:
the optical base station sends out optical signals;
when the parking space receiving sensor receives the optical signal, the parking space positioner determines a coordinate point of the parking space receiving sensor in the optical system coordinate to generate a second coordinate value.
The optical positioning system includes: the angle points of the entity parking spaces are provided with parking space locators, parking space receiving sensors arranged on the parking space locators and optical base stations capable of communicating with the optical locators of the entity parking spaces. When light rays of the optical base station irradiate the parking space receiving sensor on the parking space positioner, the optical base station and the optical positioner are communicated with each other to obtain the relative position of each optical positioner and each optical base station, the position of the entity parking space angular point relative to the optical base station is determined through the relative positions of the optical positioners and the optical base stations, and the position of the entity parking space angular point is identified through the optical positioning coordinate system to obtain a second coordinate value.
And 103, comparing the first coordinate value with the second coordinate value to determine the parking space identification precision.
And comparing and calculating the first coordinate data and the second coordinate data, determining the difference of the virtual parking space relative to the entity parking space, and determining the parking space identification precision.
When the detection precision of the virtual parking space meets the preset requirement, the virtual parking space generated in the vehicle can be close to the actual situation of the physical parking space, and the vehicle posture can be controlled.
When the detection precision of the virtual parking space cannot meet the preset requirement, the detection error between the visual parking space and the physical parking space is large, the virtual parking space identified by the vehicle cannot accurately perform corresponding attitude control on the vehicle, or when the vehicle is correspondingly controlled based on the virtual parking space, the actual effect and the expected effect have large difference.
In a preferred embodiment of the present invention, the first coordinate values are coordinate values of a vehicle coordinate system; the second coordinate value is a coordinate value of a coordinate system of the optical system, and the step of comparing the first coordinate value with the second coordinate value to determine the parking space recognition accuracy includes:
substep S1031, converting the first coordinate value into a third coordinate value in the optical system coordinate system;
when the first coordinate value detected by the AVM is the coordinate value of the vehicle coordinate system and the second coordinate value detected by the optical positioning system is the coordinate value of the optical system coordinate system, the two coordinate values cannot be directly compared because the coordinate values are in different coordinate systems, so that the first coordinate value corresponding to the virtual parking space detected by the AVM can be converted into the third coordinate value in the optical system coordinate system.
In a preferred embodiment of the present invention, a vehicle locator and a vehicle receiving sensor mounted on the vehicle locator are further mounted on the vehicle, and when the vehicle receiving sensor receives the optical signal, the vehicle locator determines a coordinate point of the parking space receiving sensor in the optical system coordinates to generate a fourth coordinate value; the step of converting the first coordinate value into a third coordinate value in the optical system coordinate system includes:
substep S10311, determining the acquisition time of the fourth coordinate value and the first coordinate value;
the vehicle is also provided with a vehicle locator and a vehicle receiving sensor arranged on the vehicle locator, and when the vehicle receiving sensor receives the optical signal, the vehicle locator determines a coordinate point of the parking space receiving sensor in the optical system coordinate to generate a fourth coordinate value; the position of the vehicle relative to the physical parking space can be determined through parking space receiving sensing, the relative position, the driving distance and the like of the vehicle at each moment in the driving process can be determined through the parking space receiving sensing, and the position of the virtual parking space relative to the vehicle can be determined based on the positioning of the vehicle and the combination of image data. Therefore, the fourth coordinate value, and the acquisition time of the first coordinate value may be determined first.
Substep S10312, synchronizing the fourth coordinate value and the first coordinate value according to the acquisition time, and generating a coordinate transformation matrix;
and synchronizing the fourth coordinate value and the first coordinate value corresponding to each moment through time matching.
And a substep S10313, converting the first coordinate value into a third coordinate value in the optical system coordinate system by the coordinate conversion matrix.
And then converting the first coordinate value into a third coordinate value under the optical system coordinate system according to a coordinate conversion matrix. So that the second coordinate values are re-projected under the optical system coordinate system.
And a substep S1032 of comparing the third coordinate value with the second coordinate value to determine the parking space recognition accuracy.
After the re-projection, the third coordinate value and the second coordinate value are already in the coordinate system corresponding to the optical system, so that the difference between the third coordinate value and the second coordinate value is compared to determine the parking space identification precision.
In a preferred embodiment of the present invention, the step of comparing the third coordinate value with the second coordinate value to determine the parking space recognition accuracy includes:
and a substep S10321 of calculating a difference between the third coordinate value and the second coordinate value to determine the parking space recognition accuracy.
And determining the difference between the virtual parking space detected by the AVM system and the entity vehicle by calculating the difference between the third coordinate value and the second coordinate value, and determining the parking space recognition accuracy.
According to the embodiment of the invention, a first coordinate value of an AVM (automatic vehicle model) for identifying the corresponding angle point of a virtual parking space is obtained, wherein the AVM is generated by detecting the entity parking space when the vehicle passes through the entity parking space under a preset working condition; acquiring a second coordinate value of the optical positioning system for identifying the corresponding angular point of the entity parking space; and comparing the first coordinate value with the second coordinate value to determine the parking space identification precision. And carrying out accurate control on the posture of the vehicle body when the vehicle is parked into the parking space during automatic parking based on the identification precision.
In order to enable those skilled in the art to better understand the embodiments of the present application, the following description is given by way of an example:
referring to fig. 4, a schematic diagram of a detection system in an embodiment of the invention is shown. The entity parking stall is the rectangle, has four angular points. Before testing, the parking space positioner is placed at the angular point of each parking space. A receiving optical base station (not shown) may be utilized to measure a second coordinate value of a true test value (true value) of a visual parking stall angle point within a circle of a coverage area of the optical base station in advance.
And fixing the vehicle receiving sensor and the positioner to a specific position of the top of the test vehicle, connecting the positioner and the CAN network of the whole vehicle, and preparing a CAN tool for testing.
The vehicle vision parking space detection system mainly comprises a panoramic ECU, 4 cameras all around and an intelligent controller. When a vehicle passes through a visual parking space, four angular points NF (near front)/NR (near real)/FF (far front)/FR (far real) of a parking space frame are detected by a left and right sight glass camera, and the x and y coordinates of NF/NR/FF/FR are output through a CAN signal in combination with a vehicle odometer.
Synchronously acquiring CAN signals related to a locator and a whole vehicle under different test working conditions (different vehicle speeds (including but not limited to 3KM/H, 5KM/H, 7KM/H and 12KM/H) and vehicle-to-parking-space side distances (including but not limited to 0.5M, 1M and 1.5M));
and comparing the parking space angular point coordinates of the visual detection with the angular point coordinate truth value of the optical positioning measurement through coordinate conversion to obtain the vehicle visual parking space detection precision.
The embodiment of the invention determines the real value of the parking space angular point by adopting the optical positioning system, outputs the virtual parking space by adopting the AVM, and determines the detection precision of the virtual parking space by comparing the virtual parking space with the real value of the parking space angular point to determine whether the AVM system of the vehicle meets the use requirement or not so as to determine whether the vehicle can accurately control the vehicle body posture.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Referring to fig. 5, a block diagram of a parking space recognition accuracy detecting device according to an embodiment of the present invention is shown, and the parking space recognition accuracy detecting device is applied to a detecting system, where the vehicle detecting system includes an optical positioning system, a vehicle, a look-around visual detection system AVM installed on the vehicle, and a physical parking space; the device is provided. The method specifically comprises the following modules:
a first obtaining module 501, configured to obtain a first coordinate value of an AVM for identifying a corresponding angle point of a virtual parking space, where the AVM is generated by detecting an entity parking space when the vehicle passes through the entity parking space under a preset working condition;
a second obtaining module 502, configured to obtain a second coordinate value of the optical positioning system for identifying the corner point corresponding to the physical parking space;
a comparing module 503, configured to compare the first coordinate value with the second coordinate value to determine the parking space recognition accuracy
In a preferred embodiment of the present invention, the AVM includes a panoramic electronic control unit, a camera, and an intelligent controller, and the first coordinate value is generated as follows:
when the camera detects an entity parking space, the panoramic electronic control unit generates a virtual parking space and determines the corresponding angular point of the virtual parking space;
and the intelligent controller determines a coordinate point of the corresponding angular point of the virtual parking space under a vehicle coordinate system to generate a first coordinate value.
In a preferred embodiment of the present invention, the optical positioning system includes an optical base station, a parking space positioner, and a parking space receiving sensor installed on the parking space positioner, and the second coordinate value is generated as follows:
the optical base station sends out optical signals;
when the parking space receiving sensor receives the optical signal, the parking space positioner determines a coordinate point of the parking space receiving sensor in the optical system coordinate to generate a second coordinate value.
In a preferred embodiment of the present invention, the first coordinate values are coordinate values of a vehicle coordinate system; the second coordinate value is a coordinate value of a coordinate system of the optical system, and the comparing module 503 includes:
the conversion submodule is used for converting the first coordinate value into a third coordinate value under the optical system coordinate system;
and the comparison submodule is used for comparing the third coordinate value with the second coordinate value to determine the parking space identification precision.
In a preferred embodiment of the present invention, a vehicle locator and a vehicle receiving sensor mounted on the vehicle locator are further mounted on the vehicle, and when the vehicle receiving sensor receives the optical signal, the vehicle locator determines a coordinate point of the parking space receiving sensor in the optical system coordinates to generate a fourth coordinate value; the conversion submodule comprises:
an acquisition time determining unit for determining acquisition times of the fourth coordinate value and the first coordinate value;
the synchronization unit is used for synchronizing the fourth coordinate value and the first coordinate value according to the acquisition time and generating a coordinate conversion matrix;
and the conversion unit is used for converting the first coordinate value into a third coordinate value under the optical system coordinate system through the coordinate conversion matrix.
In a preferred embodiment of the present invention, the comparison sub-module includes:
and the precision identification unit is used for calculating the difference value of the third coordinate value and the second coordinate value so as to determine the parking space identification precision.
In a preferred embodiment of the present invention, the preset operation condition includes: the speed and the distance between the vehicle and the physical parking space are measured.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
An embodiment of the present application further provides an electronic device, including: the precision detection method comprises a processor, a memory and a computer program which is stored on the memory and can run on the processor, wherein when the computer program is executed by the processor, each process of the precision detection method embodiment is realized, the same technical effect can be achieved, and in order to avoid repetition, the details are not repeated.
The embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the processes of the foregoing precision detection method embodiment, and can achieve the same technical effects, and in order to avoid repetition, details are not repeated here.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The parking space recognition accuracy detection method, the parking space recognition accuracy detection device, the electronic equipment and the storage medium are introduced in detail, specific examples are applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.