CN111259709A - Elastic polygon-based parking space structure detection model training method - Google Patents
Elastic polygon-based parking space structure detection model training method Download PDFInfo
- Publication number
- CN111259709A CN111259709A CN201811468760.XA CN201811468760A CN111259709A CN 111259709 A CN111259709 A CN 111259709A CN 201811468760 A CN201811468760 A CN 201811468760A CN 111259709 A CN111259709 A CN 111259709A
- Authority
- CN
- China
- Prior art keywords
- parking space
- parking
- neural network
- network model
- information
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the field of intelligent driving, in particular to a training method of a parking space structure detection model based on an elastic polygon. The method for training the parking space structure model comprises the following steps of 101: acquiring a road sample image, wherein the road sample image is marked with parking space area information; step 102: inputting the road sample image into a pre-established initial neural network model; step 103: training the neural network model by using the sample image to obtain a parking space structure detection model; according to the invention, the independent parking space area represented by the elastic polygon is obtained by fusing the information of the independent parking space area and the information of the points forming the independent parking space area, and the parking operation is carried out based on the parking space structure detection model.
Description
Technical Field
The invention relates to the field of intelligent driving, in particular to a parking space structure detection model training method.
Background
With the development of science and technology, new concepts such as automatic driving, unmanned vehicles and the like are developed. The automatic parking system is an indispensable part in the automatic driving technology, the interest of the automobile industry for developing the automatic parking system is gradually promoted, and the parking space detection is one of the core perception tasks in the automatic parking problem. Specifically, a camera of the vehicle or a sensor such as ultrasonic waves can sense the current environment of the vehicle, and the parking space detection technology is adopted to process the surrounding environment information of the vehicle acquired by the sensor, so that nearby parking spaces can be obtained, and parking of the vehicle is guided.
How to accurately and effectively detect and locate the parking space defined by the conventional line segments is a key and unsolved problem for such a system. In fact, adverse factors such as ground materials, changes in lighting conditions, shadows of nearby objects, etc., also increase the difficulty of vision-based parking space detection methods.
The existing parking space detection methods generally utilize bottom layer edge and corner features and extract parking space frames based on manual construction rules, feature expression capability of the existing parking space detection methods is weak, and the existing parking space detection methods are difficult to extend to various parking space forms. Another method is based on an object detection technology, and uses a box to detect and extract parking spaces, and the method is difficult to process inclined parking spaces and has inaccurate positioning of parking space bounding boxes. In another method, the position of a parking space is found by integrating detection information of separation points and separation lines of the parking space, and the method cannot directly provide complete structure information of one parking space and is difficult to give information about whether the parking space can be stopped or not.
Disclosure of Invention
In view of this, the present application provides a method for training a parking space structure detection model, which is used for an end-to-end parking space structured detection method, and the parking method identifies a current road image shot by a vehicle by using a pre-trained parking space structured detection model based on a deep convolutional neural network, and extracts complete parking space structured information, including whether a parking space can be parked, a position of the parking space, and geometric information corresponding to the position. Specifically, an independent parking space is formed into an elastic polygonal area, specific method steps are designed and proposed, and the independent parking space area capable of stopping in the current road image and the point coordinate information forming the area are obtained through a deep neural network model.
Specifically, in a first aspect of the present invention, a method for training a parking space structure detection model is provided, which includes the following steps:
step 101: acquiring a road sample image, wherein the road sample image is marked with parking space area information;
step 102: inputting the road sample image into a pre-established initial neural network model;
step 103: training the neural network model by using the sample image to obtain a parking space structure detection model; in step 101, the independent parking space region represented by the elastic polygon is obtained by fusing the information of the independent parking space region and the information of the points forming the independent parking space region; the training of the preliminary neural network model in step 103 includes the characteristics of convolutional layer local connection and weight sharing in the convolutional neural network model.
Preferably, in the step 101, the parking space area is labeled by using an example mask, and in the labeling, a parking space capable of being parked and a parking space incapable of being parked are distinguished.
Preferably, the initial neural network model in step 102 is a convolutional neural network model, a convolutional layer in the initial neural network model learns parking space region information in the road sample image, and the obtaining of the parking space structure detection model in step 103 specifically includes: and mapping the relevant features according to the learned relevant features of the road sample image and a full connection layer in the initial neural network model to obtain a recognition result of a parking space area, comparing the recognition result of the parking space area with the parking space area labeled in advance by the road sample image, optimizing parameters of the initial neural network model, and obtaining a parking space structure detection model after the initial neural network model is subjected to iterative training of a plurality of training samples.
In a second aspect of the present invention, a parking space structure detecting method is provided, including the following steps:
step 201: acquiring a current road image;
step 202: inputting the current road image into a parking space structure detection model trained by the training method to obtain parking space structural information including an independent parking space area represented by an elastic polygon;
step 203: and carrying out post-processing on the structured information output by the model, fusing the information, and determining the final parking space area information capable of parking.
In a third aspect of the present invention, there is provided a parking space parking method, including:
step 301: detecting whether the vehicle is in a state of waiting for parking space;
step 302: when the vehicle is detected not to be in the parking space state, returning to the step 301, and continuing the detection of the step 301; when the vehicle is detected to be in a state of waiting for parking space, executing the parking space structure detection method;
step 303: when the detection of the parking space structure in step 302 is completed, a vehicle driving unit performs a parking operation according to the calculated parking space structure.
The fourth aspect of the present invention provides an application of the above training method for a parking space structure detection model in parking.
In a fifth aspect of the present invention, a parking system is provided, which includes a parking space structure detection model trained by the above training method.
In a sixth aspect of the present invention, a parking system is provided to perform the parking method for parking in a parking space.
Compared with the prior art, the invention has the following advantages and beneficial effects, but is not limited to the following points:
(1) through the integration of the regional information of independent parking stall and the information of the regional point of constituteing independent parking stall, thereby obtain the complete structural information that can extract an independent parking stall with the independent parking stall region that elastic polygon represented, included whether the parking stall can stop and its geometrical information that corresponds the parking stall, can train on this basis and obtain parking stall structure detection model. The characteristic expressive force of the model in the prior art is weak, and the complete structural information of the parking space cannot be provided. Compared with the prior art, the parking space information provided by the invention is more detailed and accurate, and the obtained parking space structure detection model is more accurate.
(2) The elastic polygon is adopted to represent the parking space information, the parking space structure in any form can be extracted, the rotation consistency is achieved, and the information of the inclined parking space can be extracted. The application scene of the application is greatly expanded by the characteristics. The parking space structured detection model can extract the characteristics of the current road image in an end-to-end mode and learn the characteristics, and can exert the effect of big data to the maximum extent. This is one of the points of the present invention.
(3) The detection of the parking spaces in the prior art does not have universality, is usually only suitable for the most common conventional parking spaces, and greatly reduces the detection accuracy when the parking spaces of special types are met. The invention utilizes the independent parking space area represented by the elastic polygon and optimizes the convolutional neural network model on the basis, and has good adaptation to the parking space structure, particularly the special parking space structure from the practical result, and the detection result meets the precision requirement. The invention combines the elastic polygon representation parking space area and the optimization convolutional neural network, which is one of the invention points of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a flowchart illustrating a method for training a parking space structured detection model according to an embodiment of the present disclosure;
FIG. 2A is a schematic view of an elastic polygon;
FIG. 2B is a schematic diagram of an elastic polygon that structurally represents an independent parking space area;
FIG. 3 is a schematic view of a road image being labeled;
fig. 4 is a flowchart of a parking space structured detection method according to an embodiment of the present application;
fig. 5 is a schematic diagram of regression of eight direction points for points constituting a parking space region.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The application example provides a training method of a parking space structured detection model and a parking space structured detection method based on the parking space structured detection model. The parking space structured detection model and the parking space structured detection method can be applied to a terminal, a server or the combination of the terminal and the server. Wherein a terminal may be any user device now known, developing or developed in the future that is capable of interacting with a server via any form of wired and/or wireless connection (e.g., Wi-Fi, LAN, cellular, coaxial, etc.), including but not limited to: existing, developing, or future developing smartphones, non-smartphones, tablets, laptop personal computers, desktop personal computers, minicomputers, midrange computers, mainframe computers, and the like. The server in the embodiment of the present application may be an example of an existing device, a device under development, or a device developed in the future, which is capable of providing an application service for information recommendation to a user. The embodiments of the present application are not limited in any way in this respect.
The following describes a specific implementation of the embodiments of the present application with reference to the drawings.
First, a specific implementation manner of the training method for the parking space structured detection model provided in the embodiment of the present application is introduced.
Fig. 1 is a flowchart illustrating a training method for a parking space structured detection model, which is applied to the field of automatic driving and is provided by an example of the present application, and referring to fig. 1, the method includes:
step 101: and acquiring a road sample image, wherein the road sample image is marked with parking space area information.
The road sample image may be regarded as a sample image for training a parking space structured detection model. In the embodiment of the application, the training model adopts a supervised training mode, so that parking space area information is marked in the road sample image.
The parking space area refers to an area which is divided by a parking space identification line and can be used for parking. A parking space area is mathematically understood to be a range that can be characterized in various ways. For a range, it can be represented generally by boundaries, contours, etc., for example, by functions, coordinates, etc. In order to flexibly represent various parking space shapes in the image, an independent parking space area can be represented by using an elastic polygon. An elastic polygon is composed of n polygon vertices connected in order, as shown in fig. 2, which is a representation with rotational consistency. The independent parking space area represented by the elastic polygon can be obtained by fusing the information of the independent parking space area and the information of the points forming the independent parking space area, so that in some possible implementation manners of the embodiment of the application, the parking space area can be marked by marking the information of the independent parking space area and the information of the points forming the independent parking space area, which is one of the invention points of the invention, and a model for representing the independent parking space area by using the elastic polygon is not found in the prior art.
In some possible implementations of the embodiment of the present application, the processed image may be a ring view obtained by stitching images acquired by cameras located at the front, left, rear, right, and the like of the vehicle body, where the center of the image is the position of the vehicle and the rest positions are potential parking areas, as shown in fig. 3. In some possible implementation manners of the example of the application, the independent parking space area can be marked in a manner of example mask, and parking spaces which cannot be parked are distinguished in the marking, namely, the parking spaces are used as two categories. The points forming the independent parking space area can be directly represented by using the coordinates of the points in the image. The parking spaces are divided into the parking spaces which can be used for parking and the parking spaces which cannot be used for parking, although the calculation steps are added, the accuracy of later training is facilitated, and the parking spaces are integrated to achieve high-efficiency and accurate unification. As shown in fig. 3, the parking space region information labeling diagram is shown, wherein a part of the parking space region information labeling diagram represents an independent parking space region and is divided into the independent parking space region. The points at the four vertex positions in the region form the points of the independent parking space region, namely the vertexes of the elastic polygon. Some possible implementations of the embodiments of the present application may also be labeled in other ways.
In the embodiment of the present application, a sample library may be established in advance, and a sample image may be obtained from the sample library. The sample library can adopt public images in a data set, and can also acquire images collected by a camera of the vehicle from storage equipment of the vehicle, and mark parking space areas in the images, so that the sample library is established. In some cases, the sample image may also be directly obtained, for example, an image collected by a camera of the vehicle in real time is directly obtained, the parking space area of the image is labeled, and the labeled image is used as the sample image.
Step 102: and inputting the road image into a pre-established initial neural network model.
After the road sample image is acquired, the road sample image may be input to a pre-established initial neural network model, so that the initial neural network model is trained by using the road sample image.
In some possible implementations of the embodiments of the present application, the road sample image may be further scaled to a preset size before being input into the pre-established initial neural network model. Therefore, the initial neural network model can learn the road sample images with the same size, so that the road samples can be processed more quickly and accurately, and the training efficiency of the model is improved.
Step 103: and training the neural network model by using the sample image to obtain a parking space structured detection model.
For ease of understanding, the concept of a neural network model is first briefly introduced. A neural network is a network system formed by a large number of simple processing units widely interconnected, which is a highly complex nonlinear dynamical learning system with massive parallelism, distributed storage and processing, self-organization, self-adaptation and self-learning capabilities. The neural network model is a mathematical model established based on the neural network, and is widely applied in many fields based on the strong learning capacity of the neural network model.
In the field of image processing and pattern recognition, a convolutional neural network model is often used for pattern recognition. Due to the characteristics of partial connection of convolution layers and weight sharing in the convolutional neural network model, parameters needing to be trained are greatly reduced, the network model is simplified, and the training efficiency is improved. Through rapid development in recent years, convolutional neural networks have a series of achievements in the field of example segmentation at present. The basic idea of instance segmentation can be regarded as a combination of object detection and semantic segmentation. When there are multiple objects of the same type in an image, semantic segmentation predicts all pixels of the multiple objects as the same class, and example segmentation further distinguishes which pixels belong to a certain object example under the class.
Considering the problem of parking space detection, in one road image, there may be a plurality of parking spaces including parkable and unpassible. An example segmentation technique can be used to identify each individual parking space region. Each independent parking space area represents an area for only one vehicle to park, and a plurality of parking spaces are distinguished. With stoppable versus non-stoppable as different categories, the model gives information whether an area is a parking-capable area or not.
Specifically, in this embodiment, a network that obtains a better result in the example segmentation field may be used as an initial neural network model, the number of output classes and the structures of other parts that may need to be modified are modified accordingly, and the neural network model is trained by using a road sample image and using a fine-tuning method. The parking space structured detection method specifically includes the steps that a convolution layer in an initial neural network model fully learns the characteristics of a parking space area in a road sample image, according to the learned relevant characteristics of the road sample image, a full connection layer in the initial neural network model can map the relevant characteristics to obtain the identification result of the parking space area, the identification result of the parking space area is compared with the parking space area marked in advance by the road sample image, the parameters of the initial neural network model can be optimized, and after the initial neural network model is subjected to iterative training of more training samples, the parking space structured detection model can be obtained.
Therefore, the application provides a training method of the parking space structured detection model. The method comprises the steps of obtaining a road sample image, marking a parking space area in the road sample image, inputting the road sample image into an initial neural network model, and finely adjusting the initial neural network model by utilizing the road sample image in a supervised learning mode to obtain a parking space structured detection model. The initial neural network model is trained by adopting the road sample images marked with the parking space areas, and the parking space structured detection model obtained by training has higher accuracy when the parking space areas are predicted by adopting a large amount of road sample images.
Based on the training method for the parking space structured detection model provided in the above embodiment, the embodiment of the present application further provides a parking space structured detection method based on the parking space structured detection model.
Next, a parking space structured detection method provided in the embodiments of the present application is described in detail with reference to the accompanying drawings.
Fig. 4 is a flowchart of a parking space structured detection method provided in an embodiment of the present application, where the method is applied to the field of automatic driving, and referring to fig. 4, the method includes:
step 401: and acquiring a current road image.
The current road image refers to an image of the surroundings of the current location of the vehicle, because in practice this parking space detection method is always used when the vehicle is ready for parking, at which time there should be a parking space around the location of the vehicle. In this embodiment, the current road image is an image of a parking space area that needs to be detected.
It is to be understood that the current road image may be a road image acquired in real time. In some possible implementation manners of the embodiment of the application, distortion removal and splicing operations can be performed on images shot by front-view, left-view, rear-view and right-view cameras of a vehicle, and the obtained all-round-view image is used as a current road image. In some possible implementations, there may be more or fewer cameras, or the road image near the position of the vehicle may be captured by the around-looking camera of the vehicle, so as to obtain the current road image.
In some cases, the current road image may also be a received road image transmitted by another device. For example, when a camera of a vehicle has a fault, a passenger in the vehicle may capture a road image of a current location through a mobile phone or other device, so that the current road image may be obtained from a device of the user, so as to perform parking space area detection through the image.
The above is only some specific examples of obtaining the current road image, and the obtaining of the current road image is not limited in the present application, and different implementation manners may be adopted according to requirements.
Step 402: and inputting the current road image into a parking space structured detection model to obtain an independent parking space area and points forming the independent parking space area.
The parking space structured detection model is generated according to the training method of the parking space regionalization detection model provided in the above embodiment.
After the current road image is input into the parking space structured detection model, the parking space structured detection model can extract the characteristics of the current road image and map the extracted characteristics to obtain an example mask image representing an independent parking space area, the example mask is an output result of the parking space structured detection model, the result is an area which is separated from each other, one area represents an independent parking space area, and the parking space structured detection model can also provide information whether the area is a parking space area or not.
Specifically, adjacent parts between each parking stall and the parking stall can not link to each other, and the model uses such setting can learn out the parking stall region that can distinguish independently. And filtering the noise area through operations such as corrosion expansion and filtering of an oversize or undersize area. By classifying only the parking space available region as the foreground region, in the obtained example segmentation map, all the segmented examples are the parking space available regions. Through the contour extraction and connected domain searching algorithm, all the stoppable independent parking space areas in one picture can be obtained.
And secondly, forming points of the independent parking space area, and obtaining position coordinates of the points forming the complete parking space area by regressing the points on the parking space area. Specifically, in the present invention, for a point on each stoppable region, eight directions are divided into points on the regression full region. As shown in fig. 5, for a point to be regressed, its relative direction and corresponding offset distance amount with respect to the regression point are calculated. The offset coordinates of the points are regressed in the corresponding direction while classifying whether a point is present in that direction. After obtaining the parking independent parking space region information and the regression information of the points through the model, obtaining the regression result of the points on the corresponding positions by using the parking space region information, and finally obtaining the coordinates of the points forming the parking space region through voting, noise filtering, non-maximum value inhibition and other steps.
Step 403: and carrying out post-processing on the structured information output by the model, fusing the information, and determining the final parking space area information capable of parking.
In step 402, the current road image is input into the parking space structured detection model to obtain independent parking space region information, and then points on the independent parking space region are regressed to obtain points forming the independent parking space region.
Here, the information of the points that form the independent parking space area and the independent parking space area are associated, that is, the points have only independent parking space areas to which they belong. And integrating the information of the independent parking space areas and the information forming the independent parking space points, carrying out post-processing on the result, filtering noise, and finally obtaining the independent parking space areas represented by the elastic polygons. The independent parking space area represented by the elastic polygon contains the complete structure information of an independent parking space, can represent parking spaces in any form, and is a scheme with rotation consistency.
Therefore, the parking space area detection method provided in the embodiment of the present application can determine the independent parking space area in the current road image based on the output result of the parking space structured detection model by inputting the current road image into the pre-trained parking space structured detection model. The parking space structured detection method provided by the embodiment of the application can directly learn from end to end and output a structured independent parking space area, which is one of the innovation points of the invention. The model is obtained by training in a mode of combining massive sample road images with deep learning, has higher accuracy and efficiency when predicting the independent parking space area, provides higher accuracy and efficiency, and is one of the innovation points of the invention.
In the above embodiment, the convolutional neural network model is mainly used as the neural network model, training is performed to obtain the parking space structured detection model, and the parking space area in the current road image is detected based on the parking space structured detection model. With the continuous development of machine learning, a convolutional neural network model is also continuously developed. In particular, different types of convolutional neural networks may be employed as the initial neural network based on the function of the model to be trained and the data to be processed by the model. Common convolutional neural networks used in the field of example segmentation include SDS, ISFCN, FCIS, Mask R-CNN, and the like. In some possible implementation manners, Mask R-CNN can be used as an initial neural network model, and after part of the structure of the initial neural network model is modified, the initial neural network model is finely adjusted to obtain a parking space structured detection model.
Therefore, the embodiment of the application provides a training method of a parking space structured detection model and a parking space structured detection method. The method comprises the steps of obtaining a road sample image, marking a parking space area in the road sample image, inputting the road sample image into an initial neural network model, and finely adjusting the initial neural network model by utilizing the road sample image in a supervised learning mode to obtain a parking space structured detection model. The initial neural network model is trained by adopting the road sample images marked with the parking space areas, and the parking space structured detection model obtained by training has higher accuracy when the parking space areas are predicted by adopting a large amount of road sample images. By inputting the current road image into the pre-trained parking space structured detection model, the independent parking space parking area in the current road image can be determined based on the output result of the parking space structured detection model. The parking space structured detection method provided by the embodiment of the application can directly learn end to end, and outputs a structured independent parking space area. In addition, the model is obtained by training in a mode of combining massive sample road images with deep learning, and has higher accuracy and efficiency when the independent parking space area is predicted.
In some embodiments, a parking method for a parking space is provided to apply the above parking space structure detection method and the above training method for the parking space structure detection model. In which a detection unit is used, the function of which is to detect whether the vehicle is in a state in which it is required to be parked. The detection comprises detecting a vehicle control system, including detecting whether the vehicle is in a neutral position, the speed is 0 and other parameters; the parking control unit is used for judging the detection result of the detection unit, and when the detection vehicle is judged not to be in the state of waiting for parking space, the detection unit continues to detect; and when the detected vehicle is judged to be in the state of waiting for the parking space, executing the parking space structure detection. And the vehicle driving unit executes parking operation according to the calculated parking space structure.
In some embodiments, there is provided a parking method for a parking space, including:
step 301: detecting whether the vehicle is in a state of waiting for parking space;
step 302: when the vehicle is detected not to be in the parking space state, returning to the step 301, and continuing the detection of the step 301; when the vehicle is detected to be in a state of waiting for parking space, executing the parking space structure detection;
step 303: when the detection of the parking space structure in step 302 is completed, a vehicle driving unit performs a parking operation according to the calculated parking space structure.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
Claims (8)
1. A training method of a parking space structure detection model comprises the following steps:
step 101: acquiring a road sample image, wherein the road sample image is marked with parking space area information;
step 102: inputting the road sample image into a pre-established initial neural network model;
step 103: training the initial neural network model by using the sample image to obtain a parking space structure detection model; in step 101, the independent parking space region represented by the elastic polygon is obtained by fusing the information of the independent parking space region and the information of the points forming the independent parking space region; the training of the preliminary neural network model in step 103 includes the characteristics of convolutional layer local connection and weight sharing in the convolutional neural network model.
2. The training method according to claim 1, wherein in step 101, a parking space area is labeled by using an instance mask, and in the labeling, a parking space capable and a parking space incapable are distinguished.
3. The training method according to any one of claims 1-2, wherein the initial neural network model in the step 102 is a convolutional neural network model, and a convolutional layer in the initial neural network model learns parking space region information in the road sample image; the obtaining of the parking space structure detection model in step 103 specifically includes: and mapping the relevant features according to the learned relevant features of the road sample image and a full connection layer in the initial neural network model to obtain a recognition result of a parking space area, comparing the recognition result of the parking space area with the parking space area labeled in advance by the road sample image, optimizing parameters of the initial neural network model, and obtaining a parking space structure detection model after the initial neural network model is subjected to iterative training of a plurality of training samples.
4. A parking space structure detection method comprises the following steps:
step 201: acquiring a current road image;
step 202: inputting a current road image into the parking space structure detection model trained by the training method of any one of claims 1-3 to obtain parking space structural information including an independent parking space area represented by the elastic polygon;
step 203: and carrying out post-processing on the structured information output by the model, fusing the information, and determining the final parking space area information capable of parking.
5. A parking space parking method, comprising:
step 301: detecting whether the vehicle is in a state of waiting for parking space;
step 302: when the vehicle is detected not to be in the parking space state, returning to the step 301, and continuing the detection of the step 301; executing the parking space structure detection method of claim 4 when detecting that the vehicle is in a state of waiting for parking space;
step 303: when the detection of the parking space structure in step 302 is completed, a vehicle driving unit performs a parking operation according to the calculated parking space structure.
6. Use of the training method of any one of claims 1-3 for parking.
7. A parking system comprising a parking space structure detection model trained by the training method of any one of claims 1 to 3.
8. A parking system that performs the parking space method of claim 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811468760.XA CN111259709B (en) | 2018-12-03 | 2018-12-03 | Elastic polygon-based parking space structure detection model training method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811468760.XA CN111259709B (en) | 2018-12-03 | 2018-12-03 | Elastic polygon-based parking space structure detection model training method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111259709A true CN111259709A (en) | 2020-06-09 |
| CN111259709B CN111259709B (en) | 2022-06-10 |
Family
ID=70952061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811468760.XA Active CN111259709B (en) | 2018-12-03 | 2018-12-03 | Elastic polygon-based parking space structure detection model training method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111259709B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814235A (en) * | 2020-07-01 | 2020-10-23 | 广东博智林机器人有限公司 | Parking space arrangement optimization and polygon simplification method, device, equipment and storage medium |
| CN112733703A (en) * | 2021-01-07 | 2021-04-30 | 深圳市捷顺科技实业股份有限公司 | Vehicle parking state detection method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
-
2018
- 2018-12-03 CN CN201811468760.XA patent/CN111259709B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112370A (en) * | 2014-07-30 | 2014-10-22 | 哈尔滨工业大学深圳研究生院 | Monitoring image based intelligent parking lot parking place identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| VU H T等: "Parking Space Status Inference Upon a Deep CNN and Multi-Task Contrastive Network With Spatial Transform", 《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814235A (en) * | 2020-07-01 | 2020-10-23 | 广东博智林机器人有限公司 | Parking space arrangement optimization and polygon simplification method, device, equipment and storage medium |
| CN112733703A (en) * | 2021-01-07 | 2021-04-30 | 深圳市捷顺科技实业股份有限公司 | Vehicle parking state detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111259709B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110325818B (en) | Joint 3D object detection and orientation estimation via multimodal fusion | |
| CN112991447B (en) | Visual positioning and static map construction method and system in dynamic environment | |
| US9142011B2 (en) | Shadow detection method and device | |
| CN111259710B (en) | Parking space structure detection model training method adopting parking space frame lines and end points | |
| CN111259706B (en) | Lane line pressing judgment method and system for vehicle | |
| CN110781836A (en) | Human body recognition method and device, computer equipment and storage medium | |
| CN108648194B (en) | Three-dimensional target identification segmentation and pose measurement method and device based on CAD model | |
| CN111259704B (en) | Training method of dotted lane line endpoint detection model | |
| CN111169468A (en) | Automatic parking system and method | |
| CN113239726B (en) | Target detection method and device based on coloring point cloud and electronic equipment | |
| KR20170056474A (en) | Method, device and storage medium for calculating building height | |
| CN111098850A (en) | Automatic parking auxiliary system and automatic parking method | |
| CN114179788B (en) | Automatic parking method, system, computer readable storage medium and vehicle terminal | |
| CN111259707B (en) | Training method of special linear lane line detection model | |
| Liang et al. | Image-based positioning of mobile devices in indoor environments | |
| WO2020181426A1 (en) | Lane line detection method and device, mobile platform, and storage medium | |
| CN111260955B (en) | Parking space detection system and method adopting parking space frame lines and end points | |
| CN111259709B (en) | Elastic polygon-based parking space structure detection model training method | |
| US12008743B2 (en) | Hazard detection ensemble architecture system and method | |
| CN114841910A (en) | Vehicle-mounted lens shielding identification method and device | |
| Dimitrievski et al. | Semantically aware multilateral filter for depth upsampling in automotive lidar point clouds | |
| CN110909656A (en) | Pedestrian detection method and system with integration of radar and camera | |
| Ballinas-Hernández et al. | Marked and unmarked speed bump detection for autonomous vehicles using stereo vision | |
| CN112433193B (en) | Multi-sensor-based mold position positioning method and system | |
| JP2023156963A (en) | Object tracking integration method and integration apparatus |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211126 Address after: 215100 floor 23, Tiancheng Times Business Plaza, No. 58, qinglonggang Road, high speed rail new town, Xiangcheng District, Suzhou, Jiangsu Province Applicant after: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. Address before: Room 601-a32, Tiancheng information building, No. 88, South Tiancheng Road, high speed rail new town, Xiangcheng District, Suzhou City, Jiangsu Province Applicant before: MOMENTA (SUZHOU) TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |