CN112498338A - Stock level determination method and device and electronic equipment - Google Patents
Stock level determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN112498338A CN112498338A CN202011418207.2A CN202011418207A CN112498338A CN 112498338 A CN112498338 A CN 112498338A CN 202011418207 A CN202011418207 A CN 202011418207A CN 112498338 A CN112498338 A CN 112498338A
- Authority
- CN
- China
- Prior art keywords
- edge
- image
- passable
- determining
- detection result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/06—Automatic manoeuvring for parking
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
Abstract
The invention provides a parking space determining method, a parking space determining device and electronic equipment.A processor responds to a parking instruction input by a user after receiving the parking instruction, and then performs acquisition of a peripheral image set of a vehicle and a parking available area determined by map information; carrying out edge detection on the image to obtain an edge detection result of the image; determining passable detection results of all reference areas around the vehicle according to a preset passable detection rule and an edge detection result of the image; and determining the position of the reference area which can pass the parking area and has a passable detection result as a target position. By the method and the device, the accuracy of library position identification can be improved on the basis of avoiding human-computer interaction.
Description
Technical Field
The invention relates to the field of parking, in particular to a parking space determining method and device and electronic equipment.
Background
At present, in the process of parking the smart card, an automatic parking processor needs to identify a passable parking space, and then automatic parking is carried out through an automatic parking function.
When the automatic parking processor identifies the passable parking spaces, map information stored in the automatic parking processor is usually used for positioning the passable parking spaces, a plurality of parking spaces are arranged in the passable parking spaces, corresponding parking space information is displayed on a display interface of the processor, the parking spaces needing parking are manually selected in an interface operation mode, the processor responds to the parking space selection instruction, and the passable parking spaces are automatically parked to the parking spaces selected by a user.
However, the above-mentioned library bit selection method requires manual participation, and also requires the processor to respond to the library bit selection instruction of the user, which complicates the human-computer interaction operation.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for determining a library position, and an electronic device, so as to solve the problem that the existing library position selection method is complex in man-machine interaction operation.
In order to solve the technical problems, the invention adopts the following technical scheme:
a library bit determination method is applied to a processor and comprises the following steps:
responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
carrying out edge detection on the image to obtain an edge detection result of the image;
determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and determining a library position of the reference area which can pass the detection result in the parking area as a passable target library position.
Optionally, performing edge detection on the image to obtain an edge detection result of the image, including:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
Optionally, determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image, including:
performing fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
selecting an image to be processed from the target image according to an image selection rule, and deleting an edge of which the edge type in the image to be processed is the target edge type to obtain an intermediate image;
and carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
Optionally, performing passable detection on each reference region in the intermediate image to obtain a passable detection result of each reference region around the vehicle, including:
determining a polar coordinate parameter of each edge in the intermediate image according to edge coordinate information of each edge;
determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
performing equal-interval point-taking operation on the edge between the maximum included angle and the minimum included angle to obtain different edge sections;
and determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
Optionally, determining, as a target garage position, a garage position where the reference area is located, where the passable detection result in the passable parking area is passable, includes:
performing integration operation on the passable detection results of the parkable area and each reference area around the vehicle according to the corresponding coordinate system origin to obtain an integration result;
and determining a passable target area in the integration result as a passable target area, and determining a parking space including the target area in the passable parking area as a target parking space.
A bin position determining device applied to a processor, the bin position determining device comprising:
the data acquisition module is used for responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
the edge detection module is used for carrying out edge detection on the image to obtain an edge detection result of the image;
the passing detection module is used for determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and the storage position determining module is used for determining the storage position of the reference area with the passable detection result in the passable parking area as a target storage position.
Optionally, the edge detection module is specifically configured to:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
Optionally, the passage detection module includes:
the fusion submodule is used for carrying out fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
the image processing submodule is used for selecting an image to be processed from the target image according to an image selection rule, deleting an edge of which the edge type in the image to be processed is the target edge type, and obtaining an intermediate image;
and the detection submodule is used for carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
Optionally, the detection submodule includes:
the parameter determining unit is used for determining the polar coordinate parameters of each edge in the intermediate image according to the edge coordinate information of each edge;
the included angle determining unit is used for determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
an edge segment determining unit, configured to perform equidistant point fetching on an edge between the maximum included angle and the minimum included angle to obtain different edge segments;
and the result determining unit is used for determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
carrying out edge detection on the image to obtain an edge detection result of the image;
determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and determining a library position of the reference area which can pass the detection result in the parking area as a passable target library position.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a parking space determining method, a parking space determining device and electronic equipment.A processor responds to a parking instruction input by a user after receiving the parking instruction, and then performs acquisition of a peripheral image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle; carrying out edge detection on the image to obtain an edge detection result of the image; determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image; and determining a library position where the reference area which can pass through the parking area and has a passable detection result as a target library position. According to the invention, the parking available area is positioned through the map information, then whether the reference area can pass or not is determined by using the obtained edge detection result of the image in the peripheral image set, and the library position of the reference area with the passable detection result in the parking available area is determined as the target library position.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for determining a bin position according to an embodiment of the present invention;
fig. 2 is a scene schematic diagram of an edge detection result according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method of another library position determination method according to an embodiment of the present invention;
fig. 4 is a schematic view of a scene of a region of interest according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for determining a library position according to another embodiment of the present invention;
fig. 6 is a schematic view of a passable detection scenario according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a library position determining apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
When the automatic parking processor identifies the passable parking spaces, map information stored in the automatic parking processor is usually used for positioning the passable parking spaces, a plurality of parking spaces are arranged in the passable parking spaces, corresponding parking space information is displayed on a display interface of the processor, the parking spaces needing parking are manually selected in an interface operation mode, the processor responds to the parking space selection instruction, and the passable parking spaces are automatically parked to the parking spaces selected by a user.
However, the above-mentioned library bit selection method requires manual participation, and also requires the processor to respond to the library bit selection instruction of the user, which complicates the human-computer interaction operation. In addition, in the process of parking, the driver is required to intervene, the intelligent degree is not high, and the intelligent driving of the whole parking process cannot be realized. In addition, only single map information is used for searching the database, verification information is lacked, and the detection stability is poor.
The inventor finds that if the passable reference areas around the vehicle can be detected after the parkable areas are determined according to the map information, the storage position where the passable reference areas are located in the parkable areas is determined as the target storage position, the parkable areas can be automatically determined without manual reference, and man-machine interaction is avoided. In addition, the passable reference area in the parking available area is set as the target storage position, so that the selected storage position is ensured to be a barrier-free storage position, and the accuracy and the reliability of the parking storage position selection are ensured.
On the basis of the above, an embodiment of the present invention provides a parking space determining method applied to a processor, where the processor may be a parking control processor, and referring to fig. 1, the parking space determining method may include:
and S11, responding to the parking instruction input by the user, acquiring a surrounding image set of the vehicle and the parking available area determined by the map information.
In practical application, a hardware parking button or a software parking button is arranged on the processor, and when a user presses the parking button, the processor receives a parking instruction, and at the moment, the processor acquires a peripheral image set of the vehicle. The set of surrounding images comprises images of different reference areas around the vehicle;
specifically, cameras or cameras are arranged on the side surfaces of the vehicle, such as front, back, left and right sides, each camera or camera can acquire images of an acquisition area of the camera, the acquisition areas of the cameras or cameras on the front, back, left and right sides of the vehicle can be called reference areas, and each camera or camera acquires images of the corresponding reference area.
In addition, in the invention, the processor can acquire the parking available area determined by the map information, and when determining the parking available area according to the map information, a conventional means can be adopted.
And S12, carrying out edge detection on the image to obtain an edge detection result of the image.
In practical application, a preset edge detection model can be called to process the image so as to obtain an edge detection result of the image.
In this embodiment, the preset edge detection model may be a deep learning network for performing edge detection, and the deep learning network is used to perform a semantic segmentation algorithm on the above-mentioned image to determine the type of the edge (which refers to any place protruding from the road surface), including the edges of vehicles, pedestrians, road edges, general obstacles, backgrounds, and the like, and output the x/y coordinates (edge coordinate information in the image coordinate system) and the edge type of the discrete boundary point. Referring to fig. 2, different lines in fig. 2 are detected edges, and in practical applications, different edges may be identified by using lines with different colors.
And S13, determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image.
In practical applications, there may be an obstacle around the vehicle, such as a vehicle parked at a certain parking space, or a parked vehicle or a vehicle leaving a garage at the parking space, or a pedestrian moving around the parking space, etc., which may cause at least one obstacle around the vehicle. Furthermore, the passable detection results of the reference areas around the vehicle can be analyzed, the passable detection results are divided into passable and impassable results, the passable results indicate that no barrier exists in the area, the impassable results indicate that the barrier exists in the area, and then the passable detection results of the reference areas determine the parking space.
S14, determining the position of the reference area where the passable detection result in the parking-capable area is passable as a target position.
In practical applications, step S14 may include:
1) and integrating the passable detection results of the parking areas and the reference areas around the vehicle according to the corresponding coordinate system origin to obtain an integrated result.
Specifically, the result of the parking available area is displayed in the form of a coordinate system with the center of the rear axle of the vehicle as the origin of the coordinate system, the accessible detection result of each reference area around the vehicle is also displayed in the form of a coordinate system with the center of the rear axle of the vehicle as the origin of the coordinate system, the origins of the two coordinate systems are overlapped, or data on one coordinate system is transferred to the other coordinate system, the data of the two coordinate systems are integrated, and the integrated result is obtained.
2) And determining a passable target area in the integration result as a passable target area, and determining a parking space including the target area in the passable parking area as a target parking space.
In practical application, a plurality of storage positions are arranged in the parking available area, but each storage position is not a free storage position, so in the embodiment, the passable detection result of each reference area is determined, if passable, the storage position is definitely a free storage position, and the storage position including the target area in which the passable detection result is passable in the parking available area can be determined as the target storage position.
If the number of the storage positions including the target area is multiple, one storage position can be randomly selected as a parking storage position, and if the number of the storage positions including the target area is only one, the target storage position is determined as the parking storage position. And after the parking garage position is determined, directly carrying out parking operation according to the garage position.
In this embodiment, it is determined whether the storage location within the field of view of the camera is a passable storage location based on the boundary in the polar coordinate system, and if the road edges on both sides of the storage location can be detected and no vehicle is present in the storage/in front of the storage location, it is determined that the storage location is passable. And integrating the map information and the passable storage position information to provide a storage position for parking for the intelligent heavy card. And then locking the target parking space, and sending the target parking space to an intelligent driving program to finish the parking process. The parking system can be started during parking, whether barriers exist in front of and inside the target parking space or not is checked, and a passable area range is given.
In the embodiment, after receiving a parking instruction, the processor responds to the parking instruction input by a user, and then acquires a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle; carrying out edge detection on the image to obtain an edge detection result of the image; determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image; and determining a library position where the reference area which can pass through the parking area and has a passable detection result as a target library position. According to the invention, the parking available area is positioned through the map information, then whether the reference area can pass or not is determined by using the obtained edge detection result of the image in the peripheral image set, and the library position of the reference area with the passable detection result in the parking available area is determined as the target library position.
The above embodiment describes "determining the passable detection result of each of the reference areas around the vehicle according to a preset passable detection rule and the edge detection result of the image", and a specific implementation process thereof is described, specifically, referring to fig. 3, "determining the passable detection result of each of the reference areas around the vehicle according to the preset passable detection rule and the edge detection result of the image" may include:
and S21, performing fusion operation on all the images to obtain a target image with the center of the rear axle of the vehicle as the origin of the coordinate system.
In practical application, the acquired images are images in four directions of the front, the back, the left and the right of the vehicle, and the images in the four directions are integrated or fused for realizing the overall analysis of the images around the vehicle. Specifically, firstly, each camera or camera segmentation boundary point set is traversed row by row and column by column, the boundary point set is converted into a world coordinate system by means of a camera parameter matrix, and the boundary point set is converted into a vehicle coordinate system by combining vehicle parameters (the center of a rear axle of the vehicle is selected by a coordinate origin). And obtaining a target image with the center of the rear axle of the vehicle as the origin of the coordinate system, namely the aerial view.
S22, selecting an image to be processed from the target image according to an image selection rule, and deleting an edge of which the edge type in the image to be processed is the target edge type to obtain an intermediate image.
Specifically, in order to reduce the data processing amount, an image to be processed may be selected from the target image according to an image selection rule, for example, a range of x, y, left, and right z of the vehicle is selected as an area of interest, where the range is set according to an actually required vehicle range and an optimal detection distance of the camera (for example, 30m, left, and right 30m of a vehicle 30m after 60m of the vehicle in front of the vehicle, refer to fig. 4).
And then screening boundary points, namely edge points, which fall in the image, and filtering out points with the edge type being background to obtain an intermediate image.
S23, carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
In practical applications, referring to fig. 5, step S23 may include:
and S31, determining the polar coordinate parameters of each edge in the intermediate image according to the edge coordinate information of each edge.
In the above embodiment, for each edge, the edge coordinate information and the edge type of each point on the edge are given, and at this time, the coordinates of each point are converted according to the edge coordinate information of the point, and the vehicle coordinate system is converted into the polar coordinate system, so as to obtain the corresponding polar coordinate parameters.
And S32, determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of the edges.
And converting the overlooking point under the Cartesian coordinate system into a polar coordinate system, and traversing to find the maximum and minimum value of theta, wherein the center of the rear axle of the vehicle is still the origin of coordinates of the polar coordinate system, the maximum value is the maximum included angle between the vehicle and the edge, and the minimum value is the minimum included angle between the vehicle and the edge.
And S33, performing equal-interval point-taking operation on the edge between the maximum included angle and the minimum included angle to obtain different edge sections.
And giving a target output point number N, and taking N points at equal intervals in the range between the maximum included angle and the minimum included angle as key points, wherein the points taken at equal intervals can ensure that most edges can be analyzed when edge analysis is carried out.
After the keypoints are determined, the edge is divided into a plurality of edge segments. Specifically, referring to fig. 6, in fig. 6, points are not taken at equal intervals, but are taken at random, but in order to improve the detection effect, points are preferably taken at equal intervals.
S34, determining the passable detection result of the reference area corresponding to each edge segment according to the edge type corresponding to the boundary point of the edge segment.
Specifically, the edge types of the connecting line of two adjacent key points are determined, all the key points are arranged according to a theta angle descending order, when the categories of the two points are different and the distance between the two points is too far, the two points are judged to be passable, the other points are judged to be undrivable, and the (rho, theta) information of the target point is output.
For example, if the edge type of point a is road and the edge type of point B is road, it means that the section AB is road section and is not passable, and if the edge type of point a is road and the edge type of point B is pedestrian, it means that there is no obstacle in the middle of the section AB and is passable. By the detection method, the passable detection result of each edge segment can be detected, and the result is determined as the passable detection result of the reference area corresponding to the edge segment. And determining a target parking space capable of parking through the passable detection result of the reference area and the parking available area.
Optionally, on the basis of the above embodiment of the library position determining method, another embodiment of the present invention provides a library position determining apparatus applied to a processor, and referring to fig. 7, the library position determining apparatus may include:
the data acquisition module 11 is configured to acquire a surrounding image set of a vehicle and a parking available area determined by map information in response to a parking instruction input by a user; the set of surrounding images comprises images of different reference areas around the vehicle;
an edge detection module 12, configured to perform edge detection on the image to obtain an edge detection result of the image;
a passing detection module 13, configured to determine a passable detection result of each reference area around the vehicle according to a preset passable detection rule and an edge detection result of the image;
a storage location determining module 14, configured to determine a storage location where the reference area is located in the parking available area, where the passable detection result is passable, as a target storage location.
Further, the edge detection module is specifically configured to:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
Further, the passage detection module comprises:
the fusion submodule is used for carrying out fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
the image processing submodule is used for selecting an image to be processed from the target image according to an image selection rule, deleting an edge of which the edge type in the image to be processed is the target edge type, and obtaining an intermediate image;
and the detection submodule is used for carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
Further, the detection submodule includes:
the parameter determining unit is used for determining the polar coordinate parameters of each edge in the intermediate image according to the edge coordinate information of each edge;
the included angle determining unit is used for determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
an edge segment determining unit, configured to perform equidistant point fetching on an edge between the maximum included angle and the minimum included angle to obtain different edge segments;
and the result determining unit is used for determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
Further, the library position determining module is specifically configured to:
and performing integration operation on the passable detection results of the parkable area and the reference areas around the vehicle according to the corresponding coordinate system origin to obtain an integration result, determining the passable detection result in the integration result as a passable target area, and determining a parking space including the target area in the parkable area as a target parking space.
In the embodiment, after receiving a parking instruction, the processor responds to the parking instruction input by a user, and then acquires a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle; carrying out edge detection on the image to obtain an edge detection result of the image; determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image; and determining a library position where the reference area which can pass through the parking area and has a passable detection result as a target library position. According to the invention, the parking available area is positioned through the map information, then whether the reference area can pass or not is determined by using the obtained edge detection result of the image in the peripheral image set, and the library position of the reference area with the passable detection result in the parking available area is determined as the target library position.
It should be noted that, for the working processes of each module, sub-module, and unit in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the embodiments of the library position determining method and apparatus, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
carrying out edge detection on the image to obtain an edge detection result of the image;
determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and determining a library position of the reference area which can pass the detection result in the parking area as a passable target library position.
Further, performing edge detection on the image to obtain an edge detection result of the image, including:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
Further, determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image, including:
performing fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
selecting an image to be processed from the target image according to an image selection rule, and deleting an edge of which the edge type in the image to be processed is the target edge type to obtain an intermediate image;
and carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
Further, the detecting the passability of each reference area in the intermediate image to obtain the passability detection result of each reference area around the vehicle includes:
determining a polar coordinate parameter of each edge in the intermediate image according to edge coordinate information of each edge;
determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
performing equal-interval point-taking operation on the edge between the maximum included angle and the minimum included angle to obtain different edge sections;
and determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
Further, determining a library position where the reference area is located, the passable detection result of which is passable in the parking available area, as a target library position, includes:
performing integration operation on the passable detection results of the parkable area and each reference area around the vehicle according to the corresponding coordinate system origin to obtain an integration result;
and determining a passable target area in the integration result as a passable target area, and determining a parking space including the target area in the passable parking area as a target parking space.
In the embodiment, after receiving a parking instruction, the processor responds to the parking instruction input by a user, and then acquires a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle; carrying out edge detection on the image to obtain an edge detection result of the image; determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image; and determining a library position where the reference area which can pass through the parking area and has a passable detection result as a target library position. According to the invention, the parking available area is positioned through the map information, then whether the reference area can pass or not is determined by using the obtained edge detection result of the image in the peripheral image set, and the library position of the reference area with the passable detection result in the parking available area is determined as the target library position.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A library bit determination method applied to a processor is characterized by comprising the following steps:
responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
carrying out edge detection on the image to obtain an edge detection result of the image;
determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and determining a library position of the reference area which can pass the detection result in the parking area as a passable target library position.
2. The method for determining the library position according to claim 1, wherein performing edge detection on the image to obtain an edge detection result of the image comprises:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
3. The library level determination method according to claim 2, wherein determining the passable detection result for each of the reference areas around the vehicle in accordance with a preset passable detection rule and the edge detection result of the image comprises:
performing fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
selecting an image to be processed from the target image according to an image selection rule, and deleting an edge of which the edge type in the image to be processed is the target edge type to obtain an intermediate image;
and carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
4. The library level determining method according to claim 3, wherein the passable detection is performed on each of the reference areas in the intermediate image, and a passable detection result of each of the reference areas around the vehicle is obtained, and the method comprises:
determining a polar coordinate parameter of each edge in the intermediate image according to edge coordinate information of each edge;
determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
performing equal-interval point-taking operation on the edge between the maximum included angle and the minimum included angle to obtain different edge sections;
and determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
5. The library level determination method according to claim 1, wherein determining, as a target library level, a library level where the reference area in the parkable area where the passable detection result is passable, includes:
performing integration operation on the passable detection results of the parkable area and each reference area around the vehicle according to the corresponding coordinate system origin to obtain an integration result;
and determining a passable target area in the integration result as a passable target area, and determining a parking space including the target area in the passable parking area as a target parking space.
6. A bin position determining apparatus applied to a processor, the bin position determining apparatus comprising:
the data acquisition module is used for responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
the edge detection module is used for carrying out edge detection on the image to obtain an edge detection result of the image;
the passing detection module is used for determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and the storage position determining module is used for determining the storage position of the reference area with the passable detection result in the passable parking area as a target storage position.
7. The library position determining apparatus of claim 6, wherein the edge detecting module is specifically configured to:
calling a preset edge detection model to process the image so as to obtain an edge detection result of the image; the edge detection result includes edge types and edge coordinate information of the respective edges.
8. The library level determining apparatus of claim 7, wherein the passage detection module comprises:
the fusion submodule is used for carrying out fusion operation on all the images to obtain a target image taking the center of the rear axle of the vehicle as the origin of a coordinate system;
the image processing submodule is used for selecting an image to be processed from the target image according to an image selection rule, deleting an edge of which the edge type in the image to be processed is the target edge type, and obtaining an intermediate image;
and the detection submodule is used for carrying out passable detection on each reference area in the intermediate image to obtain passable detection results of each reference area around the vehicle.
9. The library position determination device of claim 8, wherein the detection submodule comprises:
the parameter determining unit is used for determining the polar coordinate parameters of each edge in the intermediate image according to the edge coordinate information of each edge;
the included angle determining unit is used for determining the maximum included angle and the minimum included angle between the vehicle and all the edges according to the polar coordinate parameters of all the edges;
an edge segment determining unit, configured to perform equidistant point fetching on an edge between the maximum included angle and the minimum included angle to obtain different edge segments;
and the result determining unit is used for determining the passable detection result of the reference area corresponding to each edge section according to the edge type corresponding to the boundary point of each edge section.
10. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
responding to a parking instruction input by a user, acquiring a surrounding image set of a vehicle and a parking available area determined by map information; the set of surrounding images comprises images of different reference areas around the vehicle;
carrying out edge detection on the image to obtain an edge detection result of the image;
determining the passable detection result of each reference area around the vehicle according to a preset passable detection rule and the edge detection result of the image;
and determining a library position of the reference area which can pass the detection result in the parking area as a passable target library position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418207.2A CN112498338B (en) | 2020-12-07 | 2020-12-07 | Stock level determination method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011418207.2A CN112498338B (en) | 2020-12-07 | 2020-12-07 | Stock level determination method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112498338A true CN112498338A (en) | 2021-03-16 |
| CN112498338B CN112498338B (en) | 2022-04-12 |
Family
ID=74970918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011418207.2A Active CN112498338B (en) | 2020-12-07 | 2020-12-07 | Stock level determination method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112498338B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366601A (en) * | 2012-04-04 | 2013-10-23 | 现代自动车株式会社 | Apparatus and method of setting parking position based on around-view image |
| CN110598512A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
| CN110826364A (en) * | 2018-08-09 | 2020-02-21 | 上海汽车集团股份有限公司 | Stock position identification method and device |
| CN110861639A (en) * | 2019-11-28 | 2020-03-06 | 安徽江淮汽车集团股份有限公司 | Parking information fusion method and device, electronic equipment and storage medium |
| CN111062285A (en) * | 2019-12-06 | 2020-04-24 | 合肥学院 | Parking lot intelligent monitoring and recognizing system based on deep learning algorithm |
| CN111160172A (en) * | 2019-12-19 | 2020-05-15 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
| JP2020177568A (en) * | 2019-04-22 | 2020-10-29 | クラリオン株式会社 | Image processing apparatus and image processing method |
-
2020
- 2020-12-07 CN CN202011418207.2A patent/CN112498338B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366601A (en) * | 2012-04-04 | 2013-10-23 | 现代自动车株式会社 | Apparatus and method of setting parking position based on around-view image |
| CN110598512A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Parking space detection method and device |
| CN110826364A (en) * | 2018-08-09 | 2020-02-21 | 上海汽车集团股份有限公司 | Stock position identification method and device |
| JP2020177568A (en) * | 2019-04-22 | 2020-10-29 | クラリオン株式会社 | Image processing apparatus and image processing method |
| CN110861639A (en) * | 2019-11-28 | 2020-03-06 | 安徽江淮汽车集团股份有限公司 | Parking information fusion method and device, electronic equipment and storage medium |
| CN111062285A (en) * | 2019-12-06 | 2020-04-24 | 合肥学院 | Parking lot intelligent monitoring and recognizing system based on deep learning algorithm |
| CN111160172A (en) * | 2019-12-19 | 2020-05-15 | 深圳佑驾创新科技有限公司 | Parking space detection method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 朱强: "基于全景相机的自动泊车系统设计与实现", 《中国优秀硕士论文全文数据库（电子期刊）》 * |
| 李瑾泽: "基于全自动泊车与对数变换的轨迹图像边缘信息细节化检测", 《科学技术与工程》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112498338B (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN108629292B (en) | Curved lane line detection method and device and terminal | |
| CN111376895B (en) | Around-looking parking sensing method and device, automatic parking system and vehicle | |
| US20130265429A1 (en) | System and method for recognizing parking space line markings for vehicle | |
| US20140112542A1 (en) | System and method for recognizing parking space line markings for vehicle | |
| CN110929655B (en) | Lane line identification method in driving process, terminal device and storage medium | |
| CN110751012B (en) | Target detection evaluation method and device, electronic equipment and storage medium | |
| CN113269163B (en) | Stereo parking space detection method and device based on fisheye image | |
| CN111860219B (en) | High-speed channel occupation judging method and device and electronic equipment | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN111488808A (en) | Lane line detection method based on traffic violation image data | |
| CN107766847B (en) | Lane line detection method and device | |
| CN108052921B (en) | Lane line detection method, device and terminal | |
| CN113065427A (en) | Vehicle parking state determination method, device, equipment and storage medium | |
| CN111739333B (en) | Empty parking space identification method | |
| CN112115939A (en) | Vehicle license plate recognition method and device | |
| KR20120098292A (en) | Method for detecting traffic lane | |
| CN114120254A (en) | Road information identification method, device and storage medium | |
| CN112498338B (en) | Stock level determination method and device and electronic equipment | |
| CN114973752B (en) | License plate and parking space number association method and device, intelligent vehicle and readable storage medium | |
| CN115240150A (en) | Lane departure warning method, system, device and medium based on monocular camera | |
| CN111739332A (en) | Parking lot management system | |
| CN111746521B (en) | Parking route planning method, device, equipment and storage medium | |
| CN114972731A (en) | Traffic light detection and identification method and device, moving tool and storage medium | |
| Bubeníková et al. | The ways of streamlining digital image processing algorithms used for detection of lines in transport scenes video recording |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220512 Address after: No. 203, Shanghai Songjiang Road, No. 201563, Pudong New Area Patentee after: SAIC Motor Corp.,Ltd. Patentee after: Shanghai automobile industry (Group) Co., Ltd Address before: Room 509, building 1, 563 Songtao Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 201203 Patentee before: SAIC Motor Corp.,Ltd. |