Direct current charging pile charging method, system and device based on face recognition and medium

Abstract

The invention provides a direct current charging pile charging method, system and device based on face recognition and a medium, and belongs to the technical field of charging piles. According to the scheme, the camera module is installed in the charging pile, the face image is collected in real time, and the main control module carries out face recognition through the YOLOv4 model. In the charging starting stage, the recognized face features are recorded, the charging pile is locked, face information is continuously detected during charging, and unlocking is conducted if the face information is matched with the face information. After charging is finished, charging is stopped, and unlocking is conducted. In addition, a charging abnormity detection function is introduced in the scheme, and charging abnormity is monitored in real time and processing measures are taken by collecting BMS and CCS data of the electric vehicle. Meanwhile, a face detection algorithm is optimized, an improved CSPDarkNet-53 is adopted as a backbone network, features are extracted through a CSPLayer2Conv convolution block, a PANet is replaced with an MFPN, and CCAM is introduced to enhance feature attention, so that the accuracy and robustness of the algorithm are improved, and the safety and convenience of the charging process are improved.

Description

Technical Field

[0001] The present invention relates to a direct current charging pile charging method, system, device and medium based on face recognition, belonging to the technical field of charging piles. Background Art

[0002] With the popularity of electric vehicles and the rapid development of charging infrastructure, DC charging piles, as the main charging equipment for electric vehicles, have become the focus of attention for their safety and convenience. Traditional DC charging pile charging methods often rely on physical keys or RFID cards for identity authentication and charging control. These methods are not only cumbersome to operate, but also have the risk of loss or theft. In order to improve the safety of the charging process and user experience, charging methods based on biometric technology have gradually gained attention.

[0003] As an advanced biometric technology, face recognition technology has the advantages of non-contact, fast recognition speed and high accuracy, so it has been widely used in various fields. Applying face recognition technology to the DC charging pile charging method can realize the rapid verification of user identity and intelligent control of the charging process, thereby improving the safety and convenience of the charging process.

[0004] However, there are still some problems with the existing DC charging pile charging method based on face recognition. First, the efficiency of the camera module's image acquisition and face recognition algorithm directly affects the response speed and accuracy of the charging process. Traditional image processing and face recognition algorithms often have high computational complexity and are difficult to meet real-time requirements. Secondly, abnormality detection and processing during the charging process is also a major challenge. Traditional charging methods often rely on hardware sensors and simple threshold judgments, and cannot accurately detect and process various complex charging abnormalities. Summary of the invention

[0005] The purpose of the present invention is to provide a DC charging pile charging method, system, device and medium based on face recognition to solve the above problems and significantly improve the safety of the charging process and user experience.

[0006] In order to achieve the above object, the present invention is implemented through the following technical solutions: A DC charging pile charging method based on face recognition, comprising: A camera module is set inside the DC charging pile to collect facial images, and the camera module is controlled by the charging pile main control module; The camera module collects images in real time and sends the collected images to the charging pile main control module, and the charging pile main control module performs face recognition on the images through a face detection algorithm, and the face detection algorithm is based on the YOLOv4 model; At the beginning of charging, the charging pile main control module records the recognized facial features, locks the charging pile, and starts charging. During the charging phase, the charging pile main control module detects the facial information in the current image in real time. If the facial features recorded at the beginning of charging are detected, the charging pile is unlocked; At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

[0007] Preferably, the human figure detection algorithm uses an improved CSPDarkNet-53 as the backbone network of the model, extracts image features through the CSPLayer_2Conv convolution block, uses MFPN to replace the original PANet in the Neck network, and introduces CCAM to enhance attention to important features.

[0008] Preferably, image preprocessing is performed on an image before face recognition is performed using a face detection algorithm, including: normalizing and graying the image, using a first-order or second-order differential operator to calculate the gradient of the image, dividing the image into multiple local blocks, calculating the gradient direction and gradient amplitude of the pixels in each image block, and projecting them into a gradient direction histogram to generate a feature vector for classification and recognition.

[0009] Preferably, the method also includes charging anomaly detection, which includes: collecting BMS data through the CAN bus interface of the DC charging pile; detecting the battery health status of the electric vehicle through the BMS data and CCS data of the electric vehicle; updating the face detection algorithm database in real time, and detecting current / voltage anomalies, DC charging pile anomalies, and vehicle anomalies based on the updated face detection algorithm.

[0010] Preferably, the charging pile main control module performs face recognition on the image through a face recognition algorithm, including: Preset the detection target in the charging image; predict each charging image to obtain candidate frames; perform non-maximum suppression processing on the candidate frames to obtain valid candidate frames, and retain valid candidate frames within a set number range; classify the obtained valid candidate frames to obtain the final recognition result.

[0011] A DC charging pile system based on face recognition, comprising: Camera module: configured to collect facial images, the camera module collects images in real time and sends the collected images to the charging pile main control module; Charging pile master control module: configured to perform face recognition on images through a face detection algorithm, wherein the face detection algorithm is based on the YOLOv4 model; charging control methods include: At the beginning of charging, a command is sent to the charging pile main control module to record the recognized facial features, lock the charging pile, and start charging. During the charging phase, the charging pile main control module detects the facial information in the current image in real time. If the facial features recorded at the beginning of charging are detected, the charging pile is unlocked; At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

[0012] A novel grid-building type renewable energy transient reactive support strategy and setting device comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the novel grid-building type renewable energy transient reactive support strategy and setting method when running the program instructions.

[0013] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the novel grid-building type renewable energy transient reactive support strategy and setting method.

[0014] The advantages of the present invention are: the present invention collects face images in real time by setting a camera module inside the DC charging pile, and performs face recognition through an efficient face detection algorithm. At the same time, the method also introduces a charging anomaly detection function, which monitors abnormal conditions in the charging process in real time by collecting and analyzing the battery management system (BMS) data and charging control system (CCS) data of the electric vehicle, and takes corresponding treatment measures.

[0015] In addition, the present invention also improves and optimizes the face detection algorithm. The improved CSPDarkNet-53 is used as the backbone network of the model, and the image features are extracted through the CSPLayer_2Conv convolution block, which improves the accuracy and robustness of the algorithm. At the same time, MFPN is used to replace the original PANet in the Neck network, and CCAM is introduced to enhance the focus on important features, further improving the recognition performance of the algorithm.

[0016] In summary, the present invention proposes a DC charging pile charging method based on face recognition, which has the advantages of high efficiency, safety, convenience, etc., and can significantly improve the safety of the charging process and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0018] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] Example 1 like Figure 1 As shown, a DC charging pile charging method based on face recognition includes: S1: A camera module is installed inside the DC charging pile to collect facial images, and the camera module is controlled by the charging pile main control module; S2: The camera module collects images in real time and sends the collected images to the charging pile main control module. The charging pile main control module performs face recognition on the images through a face detection algorithm, and the face detection algorithm is based on the YOLOv4 model; S3: At the beginning of charging, the charging pile main control module records the recognized facial features, locks the charging pile, and starts charging. S4: During the charging phase, the charging pile main control module detects the face information in the current image in real time. If the face features recorded at the beginning of charging are detected, the charging pile is unlocked; S5: At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

[0021] As a refinement of the above embodiment, the human figure detection algorithm adopts the improved CSP DarkNet-53 as the backbone network of the model, extracts image features through the CSPLayer_2Conv convolution block, uses MFPN to replace the original PANet in the Neck network, and introduces CCAM to enhance the focus on important features.

[0022] As a refinement of the above embodiment, image preprocessing is first performed on an image for face recognition using a face detection algorithm, including: normalizing and graying the image, performing gradient calculation on the image using a first-order or second-order differential operator, dividing the image into multiple local blocks, calculating the gradient direction and gradient amplitude of the pixels in each image block, and projecting them into a gradient direction histogram to generate a feature vector for classification and recognition.

[0023] As a refinement of the above embodiment, the method also includes charging abnormality detection, which includes: collecting BMS data through the CAN bus interface of the DC charging pile; detecting the battery health status of the electric vehicle through the BMS data and CCS data of the electric vehicle; updating the face detection algorithm database in real time, and detecting current / voltage abnormalities, DC charging pile abnormalities, and vehicle abnormalities based on the updated face detection algorithm.

[0024] As a refinement of the above embodiment, the charging pile main control module performs face recognition on the image through the face recognition algorithm, including: Preset the detection target in the charging image; predict each charging image to obtain candidate frames; perform non-maximum suppression on the candidate frames to obtain valid candidate frames, and retain valid candidate frames within a set number range; classify the obtained valid candidate frames to obtain the final recognition result.

[0025] Example 2 A DC charging pile system based on face recognition, comprising: Camera module: configured to collect facial images, the camera module collects images in real time and sends the collected images to the charging pile main control module; Charging pile master control module: configured to perform face recognition on images through a face detection algorithm, wherein the face detection algorithm is based on the YOLOv4 model; charging control methods include: At the beginning of charging, a command is sent to the charging pile main control module to record the recognized facial features, lock the charging pile, and start charging. During the charging phase, the charging pile main control module detects the facial information in the current image in real time. If the facial features recorded at the beginning of charging are detected, the charging pile is unlocked; At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

[0026] The embodiment of the present disclosure also provides a DC charging pile device based on face recognition, including a processor and a memory. Optionally, the device may also include a communication interface and a bus. Among them, the processor, the communication interface, and the memory can communicate with each other through the bus. The communication interface can be used for information transmission. The processor can call the logic instructions in the memory to execute the DC charging pile method based on face recognition of the above embodiment.

[0027] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0028] The memory, as a computer-readable storage medium, can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor executes the function application and data processing by running the program instructions / modules stored in the memory, that is, the DC charging pile method based on face recognition in the above embodiment is implemented.

[0029] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory.

[0030] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned DC charging pile method based on face recognition.

[0031] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0032] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0033] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A DC charging pile charging method based on face recognition, characterized in that: include: A camera module is set inside the DC charging pile to collect facial images, and the camera module is controlled by the charging pile main control module; The camera module collects images in real time and sends the collected images to the charging pile main control module, and the charging pile main control module performs face recognition on the images through a face detection algorithm, and the face detection algorithm is based on the YOLOv4 model; At the beginning of charging, the charging pile main control module records the recognized facial features, locks the charging pile, and starts charging. During the charging phase, the charging pile main control module detects the facial information in the current image in real time. If the facial features recorded at the beginning of charging are detected, the charging pile is unlocked; At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

2. The DC charging pile charging method based on face recognition according to claim 1 is characterized in that: The human figure detection algorithm adopts the improved CSPDarkNet-53 as the backbone network of the model, extracts image features through the CSPLayer_2Conv convolution block, uses MFPN to replace the original PANet in the Neck network, and introduces CCAM to enhance the focus on important features.

3. The DC charging pile charging method based on face recognition according to claim 1, characterized in that: When performing face recognition on an image through a face detection algorithm, image preprocessing is first performed, including: normalizing and graying the image, using first-order or second-order differential operators to calculate the gradient of the image, dividing the image into multiple local blocks, calculating the gradient direction and gradient amplitude of the pixels in each image block, and projecting them into the gradient direction histogram to generate a feature vector for classification and recognition.

4. The DC charging pile charging method based on face recognition according to claim 1, characterized in that: The method also includes charging anomaly detection, which includes: collecting BMS data through the CAN bus interface of the DC charging pile; detecting the battery health status of the electric vehicle through the BMS data and CCS data of the electric vehicle; updating the face detection algorithm database in real time, and detecting current / voltage anomalies, DC charging pile anomalies, and vehicle anomalies based on the updated face detection algorithm.

5. The DC charging pile charging method based on face recognition according to claim 2 is characterized in that: The charging pile main control module uses the face recognition algorithm to perform face recognition on the image, including the following steps: Preset the detection target in the charging image; predict each charging image to obtain candidate frames; perform non-maximum suppression on the candidate frames to obtain valid candidate frames, and retain valid candidate frames within a set number range; classify the obtained valid candidate frames to obtain the final recognition result.

6. A DC charging pile system based on face recognition using the method described in any one of claims 1 to 5, characterized in that: include: Camera module: configured to collect facial images, the camera module collects images in real time and sends the collected images to the charging pile main control module; Charging pile master control module: configured to perform face recognition on images through a face detection algorithm, wherein the face detection algorithm is based on the YOLOv4 model; charging control methods include: At the beginning of charging, a command is sent to the charging pile main control module to record the recognized facial features, lock the charging pile, and start charging. During the charging phase, the charging pile main control module detects the facial information in the current image in real time. If the facial features recorded at the beginning of charging are detected, the charging pile is unlocked; At the end of charging, the charging pile master control module stops charging and unlocks the charging pile.

7. A novel grid-building renewable energy transient reactive support strategy and setting device, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the new grid-connected new energy transient reactive support strategy and setting method as described in any one of claims 1-5 when running the program instructions.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, which, when executed by a processor, implements a novel grid-connected new energy transient reactive support strategy and setting method as described in any one of claims 1-5 above.

Images