New energy vehicle charging port positioning method and device based on structured light positioning

Abstract

The invention provides a new energy vehicle charging port positioning method and device based on structured light positioning, and relates to the technical field of new energy automatic charging, and the method comprises charging port primary positioning and charging port secondary positioning. According to the invention, the charging port is positioned by combining the charging port position information acquired by the 3D structured light camera and the position information output by the deep learning recognition model for the recognition of the charging port, so that the accuracy and reliability of positioning can be realized, and the accuracy of the recognition of the charging port can be ensured in a severe environment. The positions of different charging ports can be identified, the shape and size information can be identified, reference is provided for selecting the matched charging gun, the identification speed is high, the accuracy is high, and it is guaranteed that the charging gun and the charging port are automatically and accurately connected in a follow-up mode. Meanwhile, secondary positioning of the charging port is carried out after the insertion gun is butted, so that whether the charging gun is inserted or not and whether the charging gun is inserted in place or not are detected, and reliability and safety of automatic charging are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy automatic charging, and in particular to a method and device for locating a charging port of a new energy vehicle based on structured light positioning. Background Art

[0002] At present, there are not enough charging stations for new energy vehicles, charging time is long, and charging positions are occupied for a long time. As a result, electric car owners often face charging anxiety. Through automatic charging technology, car owners can automatically complete charging when the car is idle, reduce waiting time, and thus alleviate charging anxiety. Not only that, automated charging can greatly improve charging efficiency and reduce errors and delays in human operation. Therefore, with the popularization of new energy vehicles, the demand for automatic charging facilities for cars is growing. In order to improve charging efficiency and safety, the automatic charging system for car charging ports came into being. To achieve automatic charging, charging port identification is a very critical link. Moreover, due to different car companies and technical standards, there are various types of charging interfaces. To this end, a precise charging port positioning technology is needed.

[0003] Based on this, the present invention is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for locating a charging port of a new energy vehicle based on structured light positioning, so as to improve the accuracy and speed of charging port recognition.

[0005] To achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for locating a charging port of a new energy vehicle based on structured light positioning, including: S100 charging port primary positioning: photographing the charging port with a 3D structured light camera to obtain charging port image data, and using structured light projection to obtain charging port position information 1; establishing and training a deep learning recognition model for the charging port, inputting the acquired charging port image data into the trained deep learning recognition model for detection and recognition, outputting charging port position information 2, shape information and size information, and comparing and judging whether the charging port position information 1 is consistent with the charging port position information 2. When the two are consistent, the charging port primary positioning is completed; S200 charging port secondary positioning: detecting whether the charging gun is inserted, and after detecting that the charging gun has been inserted into the charging port, detecting whether the charging gun is in place, and completing the charging port secondary positioning after detecting that the charging gun is in place.

[0006] In the first aspect, the present invention provides a preferred solution. In order to reduce interference factors and ensure the accuracy of positioning, in step S100, the acquisition of the charging port position information 1 specifically includes the following: S110 obtains the charging port image data by photographing the charging port with a 3D structured light camera; S120 preprocesses the image data; S130 uses structured light projection on the preprocessed image data and calculates the three-dimensional coordinate data of the charging port through the principle of triangulation; S140 filters the acquired three-dimensional coordinate data.

[0007] In the first aspect, the present invention provides a preferred solution. To ensure the safety and reliability of the charging process, the positioning method also includes S300 charging port confirmation: sending charging parameters to the charging gun, and the charging pile determines whether the charging gun meets the charging requirements based on the charging status information fed back by the charging gun. When the charging gun meets the requirements, a secondary confirmation request is sent to the charging gun. After the charging pile receives the confirmation operation information fed back by the charging gun, the charging port confirmation is completed and charging begins.

[0008] In a second aspect, the present invention provides a new energy vehicle charging port positioning device based on structured light positioning, which adopts the above-mentioned positioning method, including: a charging port primary positioning module, which is used to obtain charging port image data by photographing the charging port with a 3D structured light camera, and obtain charging port position information one by using structured light projection; establish and train a deep learning recognition model of the charging port, input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, output charging port position information two, shape information and size information, compare and determine whether the charging port position information one is consistent with the charging port position information two, and when the two are consistent, complete the primary positioning of the charging port; a charging port secondary positioning module, which is used to detect whether a charging gun is inserted, and after detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place, and complete the secondary positioning of the charging port after detecting that the charging gun is in place.

[0009] Compared with the prior art, the above technical solution has the following advantages: The present invention locates the charging port by combining the charging port position information obtained by a 3D structured light camera and the position information output by the deep learning recognition model. This can achieve the accuracy and reliability of one-time positioning of the charging port, and can also ensure the accuracy of charging port recognition in harsh environments. And by identifying the charging port through a 3D structured light camera and a deep learning recognition model, not only can the positions of different charging ports be identified, but also the shape and size information can be identified, providing a reference for selecting a matching charging gun. The recognition speed is fast and the accuracy is high, ensuring that the charging gun and the charging port are automatically and accurately docked in the future. At the same time, after the gun is docked, the charging port is also positioned twice to detect whether the charging gun is inserted and whether the insertion is in place, to ensure the reliability and safety of automatic charging. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0011] Figure 1 A flow chart of a method for positioning a charging port of a new energy vehicle based on structured light positioning provided in Example 1 of the present invention; Figure 2 This is a module diagram of a new energy vehicle charging port positioning device based on structured light positioning provided in Example 1 of the present invention; Figure 3 This is a flow chart of one-time positioning of a charging port in a method for positioning a charging port of a new energy vehicle based on structured light positioning provided in Example 2 of the present invention; Figure 4 This is a composition diagram of a charging port primary positioning module in a new energy vehicle charging port positioning device based on structured light positioning provided in Example 2 of the present invention; Figure 5 A flow chart of a method for positioning a charging port of a new energy vehicle based on structured light positioning provided in Example 3 of the present invention; Figure 6 This is a module diagram of a new energy vehicle charging port positioning device based on structured light positioning provided in Example 3 of the present invention.

[0012] Figure numerals: charging port primary positioning module 100, image acquisition submodule 110, preprocessing submodule 120, coordinate calculation submodule 130, filtering submodule 140, model recognition submodule 160, model building and training submodule 150, data comparison submodule 170, positioning result acquisition submodule 180, verification submodule 190, charging port secondary positioning module 200, charging gun insertion detection submodule 210, charging gun in place detection submodule 220. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] The technology commonly used in the market for charging port identification currently relies mainly on image processing and pattern recognition technology, which usually includes steps such as image preprocessing, feature extraction, and classifier design. The purpose of image preprocessing is to remove noise and enhance image features for subsequent processing. The feature extraction stage focuses on extracting key information that can represent the charging port from the image. Classifier design is responsible for determining the location of the charging port based on the extracted features. Although these methods can meet the needs of automatic charging to a certain extent, they still need to be improved in terms of processing speed and accuracy. Especially when facing different models and different environmental conditions, the generalization ability and adaptability of the algorithm become problems that need to be solved urgently. To this end, the present invention provides a new energy vehicle charging port positioning method based on structured light positioning, which can solve the above problems, and gives the following preferred embodiments.

[0015] Example 1

[0016] Please refer to Figure 1 This embodiment provides a method for positioning a charging port of a new energy vehicle based on structured light positioning, which is mainly implemented through the following steps: S100 charging port one-time positioning: Use a 3D structured light camera to photograph the charging port to obtain the charging port image data, and use structured light projection to obtain the charging port position information 1; establish and train the deep learning recognition model of the charging port, input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, output the charging port position information 2, shape information and size information, compare and determine whether the charging port position information 1 is consistent with the charging port position information 2, and when the two are consistent, complete the charging port one-time positioning, and then output the position information, shape information and size information as the positioning result, providing accurate reference data for subsequent charging port docking and charging operations. After this step is completed, the charging gun can be automatically docked and inserted into the charging port by the automatic charging device according to the final charging port position information, shape information and size information.

[0017] S200 charging port secondary positioning: detect whether the charging gun is inserted. After detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place. After detecting that the charging gun is in place, complete the secondary positioning of the charging port.

[0018] Please refer to Figure 2The present embodiment provides a new energy vehicle charging port positioning device based on structured light positioning, which adopts the above-mentioned positioning method of Example 1 and is mainly composed of the following parts: a charging port primary positioning module 100, which is used to obtain charging port image data by photographing the charging port through a 3D structured light camera, and obtain charging port position information 1 by using structured light projection; establish and train a deep learning recognition model of the charging port, input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, output charging port position information 2, shape information and size information, compare and determine whether the charging port position information 1 is consistent with the charging port position information 2, and when the two are consistent, complete the charging port primary positioning; a charging port secondary positioning module 200, which is used to detect whether the charging gun is inserted, and after detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place, and complete the charging port secondary positioning after detecting that the charging gun is in place.

[0019] This embodiment locates the charging port by combining the charging port position information obtained by the 3D structured light camera and the position information output by the deep learning recognition model. This can achieve the accuracy and reliability of the one-time positioning of the charging port, and can also ensure the accuracy of the charging port recognition in harsh environments (poor field of view). In addition, by using the 3D structured light camera and the deep learning recognition model to identify the charging port, not only can the positions of different charging ports be identified, but also the shape and size information can be identified, providing a reference for selecting a matching charging gun. The recognition speed is fast and the accuracy is high, ensuring that the charging gun and the charging port are automatically and accurately docked in the future. At the same time, after the gun is docked, the charging port is also positioned twice to detect whether the charging gun is inserted and whether it is inserted in place, to ensure the reliability and safety of automatic charging.

[0020] Example 2

[0021] This embodiment provides a more preferred implementation method, and adds the following technical solutions on the basis of Embodiment 1: This embodiment provides a method for positioning a charging port of a new energy vehicle based on structured light positioning. In this embodiment, based on the technical solution of positioning the charging port once in step S100 of embodiment 1, the following more specific and more preferred implementation method is adopted for acquiring the first position information of the charging port, and the following steps are specifically adopted: S100 charging port one-time positioning: Use a 3D structured light camera to capture the charging port image data, and use structured light projection to obtain the charging port location information. Figure 3 The acquisition of the charging port location information 1 is specifically implemented through the following steps: S110 uses a 3D structured light camera to shoot the charging port to obtain image data of the charging port. In this step, the structured light camera needs to be initialized and a preliminary environmental scan needs to be performed to ensure that the camera and the charging port are in the same coordinate system. When obtaining the image data captured by the camera, the image must be clear and unobstructed.

[0022] S120 performs preprocessing on the image data, including denoising, grayscale conversion, binarization, etc., to improve the accuracy of subsequent processing.

[0023] S130 uses structured light projection and triangulation principle to calculate the three-dimensional coordinate data of the charging port for the pre-processed image data; this step uses the principle of 3D structured light camera to obtain the target position, that is, the principle of structured light projection and triangulation. 3D structured light camera is a device that uses structured light technology to obtain three-dimensional information of objects. It projects light of a specific pattern (such as stripes or dots) onto the target object, and uses one or more cameras to capture the pattern deformation formed by these lights on the surface of the object, thereby obtaining the three-dimensional coordinates of the target object. The following are the detailed steps: 1. Projecting structured light: The 3D structured light camera first projects a specific pattern of light (usually stripes or dots) onto the target object. These lights can be red or green laser light sources, or invisible infrared lasers of a specific wavelength. These lights are projected onto the object after a certain encoding, forming a series of light spots or light strips. 2. Capturing deformed patterns: The camera captures the patterns formed by these lights on the surface of the object through the lens. Due to the different shapes and depths of the surface of the object, the light will deform on the surface of the object to form a unique pattern. 3. Calculate three-dimensional coordinates: Based on the captured deformation pattern and the known relative position relationship between the light source and the camera, the 3D structured light camera will calculate the spatial coordinates of each point on the surface of the object through the principle of triangulation. Triangulation is a measurement method based on geometric principles. It uses the known relative position relationship between the light source and the camera, as well as the deformation of the pattern formed by the light on the surface of the object, to calculate the spatial coordinates of each point on the surface of the object. The position of the camera and the light source is known. When the light is projected onto the surface of the object and reflected back to the camera, the camera can capture the position of the reflected light. By comparing the angular change between the reflected light and the original light (i.e., the "angular offset" in triangulation), and using the known distance between the camera and the light source, the distance from each point on the surface of the object to the camera can be calculated, and the three-dimensional coordinates of the object can be obtained.

[0024] S140 performs filtering processing on the acquired three-dimensional coordinate data to remove abnormal values ​​caused by environmental interference or equipment errors.

[0025] After the charging port location information 1 is obtained, the charging port is identified by establishing a deep learning recognition model to obtain the charging port location information 2 (three-dimensional coordinate data), which is specifically achieved through the following steps: S150 establishes and trains a deep learning recognition model for the charging port. The deep learning recognition model may adopt any one of a convolutional neural network model, a recurrent neural network model, a long short-term memory network model, and a generative adversarial network model. A large amount of image data of the charging port is used when training the model.

[0026] S160 inputs the acquired charging port image data into the trained deep learning recognition model for detection and recognition, and outputs the charging port position information (three-dimensional coordinate data), shape information, and size information.

[0027] S170 compares and determines whether the charging port location information 1 is consistent with the charging port location information 2. When the two are consistent, the charging port is positioned once.

[0028] S180 obtains the central three-dimensional coordinate data and size data of the charging port as the positioning result.

[0029] S190 verifies the positioning results. If there is a deviation, it performs correction processing and finally outputs the final charging port position information, shape information and size information. Real-time and accuracy need to be considered when selecting the correction algorithm. By verifying the positioning results, accurate reference data can be provided for subsequent charging port docking and charging operations. After this step is completed, the charging gun can be automatically docked and inserted into the charging port through the automatic charging device according to the final charging port position information, shape information and size information.

[0030] S200 charging port secondary positioning: The automatic charging device automatically docks and inserts the charging gun into the charging port according to the final charging port position information, shape information and size information. At this time, two steps need to be performed: Charging gun insertion detection: Detect whether the charging gun is inserted through a pressure sensor, photoelectric sensor or visual sensor. Charging gun in place detection: After detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place through a position sensor or proximity sensor. After detecting that the charging gun is in place, the charging port secondary positioning is completed.

[0031] Please refer to Figure 4The present embodiment provides a new energy vehicle charging port positioning device based on structured light positioning, which adopts the positioning method described in Example 2, and is mainly composed of a charging port primary positioning module 100 and a charging port secondary positioning module 200, wherein the charging port primary positioning module 100 is composed of the following submodules: an image acquisition submodule 110, which is used to acquire charging port image data by photographing the charging port with a 3D structured light camera; a preprocessing submodule 120, which is used to preprocess the image data; a coordinate calculation submodule 130, which is used to calculate the three-dimensional coordinate data of the charging port by using structured light projection and triangulation principle for the preprocessed image data; a filtering submodule 140, which is used to filter the acquired three-dimensional coordinate data; a model building and training submodule 1 50, used to establish and train the deep learning recognition model of the charging port; model recognition submodule 160, used to input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, and output the charging port position information 2 (three-dimensional coordinate data), shape information and size information; data comparison submodule 170, used to compare and determine whether the charging port position information 1 is consistent with the charging port position information 2, and when the two are consistent, complete the charging port primary positioning; positioning result acquisition submodule 180, obtains the central three-dimensional coordinate data and size data of the charging port as the positioning result; verification submodule 190, used to verify the positioning result, if there is a deviation, perform deviation correction processing, and finally output the final charging port position information, shape information and size information. The charging port secondary positioning module 200 consists of two submodules, namely: charging gun insertion detection submodule 210, used to detect whether the charging gun is inserted through a pressure sensor, a photoelectric sensor or a visual sensor; charging gun in place detection submodule 220: after detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place through a position sensor or a proximity sensor. After detecting that the charging gun is in place, the secondary positioning of the charging port is completed.

[0032] In the process of positioning the charging port once, this embodiment pre-processes the image data and performs filtering on the acquired three-dimensional coordinate data, so as to further improve the accuracy of positioning the charging port.

[0033] Example 3

[0034] This embodiment provides a more preferred implementation method, and adds the following technical solutions on the basis of Embodiment 1 or 2: Please refer to Figure 5This embodiment provides a method for positioning the charging port of a new energy vehicle based on structured light positioning, wherein, based on the steps S100 for the first positioning of the charging port and S200 for the second positioning of the charging port in Example 1 or Example 2, a step S300 for charging port confirmation is added: charging parameters such as charging current, voltage and charging protocol are sent to the charging gun, and the charging pile determines whether the charging gun meets the charging requirements based on the charging status information fed back by the charging gun, such as the type of charging gun, the charging protocol version, etc. When the charging gun meets the requirements, a second confirmation request is sent to the charging gun. After the charging pile receives the confirmation operation information fed back by the charging gun, the charging port confirmation is completed and charging starts. More specifically, the charging pile sends the charging parameters to the charging gun, and the charging gun feeds back the charging gun status to the charging pile. The charging pile determines whether the charging gun meets the charging requirements based on the information fed back by the charging gun. When the charging gun meets the requirements, the charging pile sends a second confirmation request to the charging gun. After the charging gun receives the second confirmation request, it performs a confirmation operation; after the charging pile receives the confirmation information of the charging gun, the charging process starts. Similarly, please refer to Figure 6 This embodiment provides a new energy vehicle charging port positioning device based on structured light positioning, which adopts the above positioning method of Example 3 and is mainly composed of a charging port primary positioning module 100, a charging port secondary positioning module 200 and a charging port confirmation module 300.

[0035] This embodiment adds a charging port confirmation step to confirm that the charging port and the charging gun's charging current, voltage, and charging protocol fully match, thereby ensuring the matching of the charging gun and the charging port, and further ensuring the reliability and safety of automatic charging.

[0036] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the above-mentioned embodiments of the methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0037] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0038] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A new energy vehicle charging port positioning method based on structured light positioning, characterized in that: include: S100 charging port one-time positioning: Use a 3D structured light camera to photograph the charging port to obtain the charging port image data, and use structured light projection to obtain the charging port position information 1; establish and train the deep learning recognition model of the charging port, input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, output the charging port position information 2, shape information and size information, and compare and determine whether the charging port position information 1 is consistent with the charging port position information 2. When the two are consistent, the charging port is positioned once; S200 charging port secondary positioning: detect whether the charging gun is inserted. After detecting that the charging gun has been inserted into the charging port, detect whether the charging gun is in place. After detecting that the charging gun is in place, complete the secondary positioning of the charging port.

2. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1, characterized in that: In step S100, the acquisition of the charging port location information 1 specifically includes the following steps: S110 uses a 3D structured light camera to capture the charging port image data; S120 pre-processes the image data; S130 uses structured light projection on the preprocessed image data and calculates the three-dimensional coordinate data of the charging port through the triangulation principle; S140 performs filtering processing on the acquired three-dimensional coordinate data.

3. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1, characterized in that: In step S100, after completing the positioning of the charging port once, the three-dimensional coordinate data and size data of the center of the charging port are obtained as the positioning result, and the positioning result is verified. If there is a deviation, a correction process is performed.

4. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1, characterized in that: In the secondary positioning of the charging port in step S200, a pressure sensor, a photoelectric sensor or a visual sensor is used to detect whether the charging gun is inserted.

5. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1 or 4, characterized in that: In the secondary positioning of the charging port in step S200, a position sensor or a proximity sensor is used to detect whether the charging gun is in place.

6. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1, characterized in that: In step S100, the deep learning recognition model adopts any one of a convolutional neural network model, a recurrent neural network model, a long short-term memory network model, and a generative adversarial network model.

7. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 1, characterized in that: It also includes S300 charging port confirmation: charging parameters are sent to the charging gun. The charging pile determines whether the charging gun meets the charging requirements based on the charging status information fed back by the charging gun. When the charging gun meets the requirements, a second confirmation request is sent to the charging gun. After the charging pile receives the confirmation operation information fed back by the charging gun, the charging port confirmation is completed and charging begins.

8. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 7, characterized in that: The charging parameters include charging current, voltage and charging protocol.

9. The method for positioning the charging port of a new energy vehicle based on structured light positioning according to claim 7 or 8, characterized in that: The charging status includes the charging gun type and the charging protocol version.

10. A new energy vehicle charging port positioning device based on structured light positioning, using the positioning method described in any one of claims 1 to 9, characterized in that: include: The charging port one-time positioning module is used to obtain the charging port image data by photographing the charging port with a 3D structured light camera, and obtain the charging port position information 1 by using structured light projection; establish and train the deep learning recognition model of the charging port, input the acquired charging port image data into the trained deep learning recognition model for detection and recognition, output the charging port position information 2, shape information and size information, and compare and determine whether the charging port position information 1 is consistent with the charging port position information 2. When the two are consistent, the charging port one-time positioning is completed; The charging port secondary positioning module is used to detect whether the charging gun is inserted. After detecting that the charging gun has been inserted into the charging port, it is used to detect whether the charging gun is in place. After detecting that the charging gun is in place, the charging port secondary positioning is completed.

Images