Search

KR-102962347-B1 - Method for determining which pedal is pressed and System for providing notification Thereof

KR102962347B1KR 102962347 B1KR102962347 B1KR 102962347B1KR-102962347-B1

Abstract

A method for determining which pedal among the accelerator pedal and the brake pedal of a vehicle is pressed according to the technical concept of the present invention comprises: receiving information capturing the pedal of the vehicle and the pedal area where the lower body of the driver driving the vehicle is located; recognizing the position of the driver's lower body and the movement of the driver's lower body in the information capturing the pedal area through a machine learning model; determining which pedal among the pedals of the vehicle is pressed through the machine learning model based on the recognized information of the driver's lower body; and after determining which pedal among the pedals of the vehicle is pressed, notifying the driver of the result of the determination.

Inventors

  • 조형래
  • 정미랑

Assignees

  • 주식회사 모어다임

Dates

Publication Date
20260508
Application Date
20240912

Claims (11)

  1. A method for determining which pedal is pressed, between the accelerator and brake pedals of a vehicle, is: A step of receiving information capturing the pedal of the above vehicle and the pedal area where the lower body of the driver operating the above vehicle is located; A step of recognizing the position of the driver's lower body and the movement of the driver's lower body from the information in which the pedal area is captured, through a machine learning model; A step of determining which of the pedals of the vehicle is pressed through the machine learning model based on the recognized lower body information of the driver; A step of determining, through the machine learning model above, whether the driver's lower body position and movement are in a state of accelerator pedal operation error based on the normal operating state of the accelerator pedal; and After determining whether the above accelerator pedal operation error state exists, if the above accelerator pedal operation error state is determined, a step of transmitting the determination result to an alarm device; Includes, In the step of recognizing the position and movement of the driver's lower body, the machine learning model learns the position and movement of the driver's lower body when the driver presses the accelerator pedal of the vehicle, stores the learned position and movement of the driver's lower body in the normal operating state of the accelerator pedal, and learns the position and movement of the driver's lower body when the driver presses the brake pedal of the vehicle, and stores the learned position and movement of the driver's lower body in the normal operating state of the brake pedal. In the step of determining whether there is an error in operating the accelerator pedal, the machine learning model determines whether the recognized position and movement of the driver's lower body are normal based on the position and movement of the driver's lower body stored in the normal operating state of the accelerator pedal, and The processor determines that the lower body position and movement of the driver recognized through the imaging device are the lower body position and movement of the normal operating state of the brake pedal learned through the machine learning model, but determines the accelerator pedal operation error state when the driver actually presses the accelerator pedal. Method for determining pressed pedal.
  2. delete
  3. In Article 1, After determining which of the pedals of the above vehicle is pressed, a step of transmitting the determination result to an alarm device; and The alarm device that receives the above judgment result further includes the step of emitting light; and In the step of emitting the light, the wavelength of light emitted by the alarm device when the accelerator pedal of the vehicle is pressed is different from the wavelength of light emitted by the alarm device when the brake pedal of the vehicle is pressed. Method for determining pressed pedal.
  4. In Paragraph 3, The above alarm device is installed on the outer edge of the camera that photographs the pedal area. Method for determining pressed pedal.
  5. In Article 1, The machine learning model determines the accelerator pedal operation error state when it determines that the driver's lower body has pressed the accelerator pedal four or more times per second. Method for determining pressed pedal.
  6. In Article 1, The machine learning model determines the accelerator pedal operation error state when the recognized position of the driver's lower body is the position when the accelerator pedal of the learned vehicle is pressed, and the recognized movement of the driver's lower body is the movement of the driver's lower body when the brake pedal of the learned vehicle is pressed. How to determine if a pedal is pressed..
  7. In Article 1, In the step of recognizing the position and movement of the driver's lower body, the machine learning model learns the driver's lower body movement when the driver presses the brake pedal of the vehicle, and In the step of determining which pedal among the pedals of the vehicle is pressed, the learned machine learning model determines whether the accelerator pedal of the vehicle is pressed or whether the brake pedal of the vehicle is pressed, and In the step of determining which of the pedals of the above vehicle is pressed, if it is determined that the accelerator pedal of the above vehicle is pressed, the step of determining whether there is an accelerator pedal operation error is performed. Method for determining pressed pedal.
  8. In Article 7, The method further includes the step of transmitting the judgment result of the machine learning model to an alarm device, and the alarm device notifying the driver through at least one of light and sound. The step of notifying the driver above provides the driver with a normal acceleration alarm, a normal braking alarm, and an abnormal acceleration alarm, and The above normal acceleration alarm is provided to the driver when it is determined that the accelerator pedal is pressed in the step of determining which of the pedals of the vehicle is pressed, and The above normal braking alarm is provided to the driver when it is determined that the brake pedal is pressed in the step of determining which of the pedals of the vehicle is pressed, and The above abnormal acceleration alarm is provided to the driver when, in the step of determining whether there is an accelerator pedal operation error state, the movement of the driver's lower body is determined to be in the accelerator pedal operation error state. Method for determining pressed pedal.
  9. In Article 1, The machine learning model further comprises the step of learning the driver's lower body movement, determined to be an accelerator pedal operation error state, as the driver's normal accelerator pedal operation state when feedback is received as such. Method for determining pressed pedal.
  10. A computer program stored on a computer-readable record medium to execute the method according to claim 1 on a computer.
  11. delete

Description

Method for determining which pedal is pressed and System for providing notification Thereof The technical concept of the present invention relates to a method for determining which pedal is pressed and a system for indicating this, and more specifically, to a method, program, and system for determining and indicating which pedal among the pedals of a vehicle is pressed. Recently, as the importance of safety has been emphasized in the automotive industry, various technologies are being developed to protect the lives of drivers and passengers. Among these, the phenomenon of sudden acceleration, or unintended acceleration, is recognized as a serious safety threat. When unintended acceleration occurs, it becomes difficult for the driver to control the vehicle, which can lead to a major accident. In particular, sudden acceleration issues can occur not only due to malfunctions in the electronic control system but also due to driver errors in pedal operation. For instance, if a driver mistakenly presses the accelerator pedal instead of the brake, the vehicle may accelerate rapidly, which can lead to extremely dangerous consequences in sudden situations. Since such driver pedal errors frequently occur among novice drivers with limited experience or elderly drivers, there is a growing need for technology to prevent them. FIG. 1 is a conceptual diagram schematically illustrating an automobile according to exemplary embodiments. FIG. 2 is a layout schematically illustrating a system according to exemplary embodiments. FIG. 3 is a flowchart schematically illustrating a method for determining a pressed pedal according to exemplary embodiments. FIGS. 4 and 5 are cross-sectional views schematically showing a semiconductor package according to exemplary embodiments by cutting a portion of it. Exemplary embodiments of the present invention are provided to more fully explain the invention to those skilled in the art to which the concept of the invention pertains, and the following embodiments may be modified in various different forms, and the scope of the invention is not limited to the following embodiments. Rather, these embodiments are provided to make the disclosure more faithful and complete and to fully convey the spirit of the invention to those skilled in the art. Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by those skilled in the art to which the concept of the present invention pertains. Furthermore, it will be understood that commonly used terms, such as those defined in advance, should be interpreted in a meaning consistent with their intent in the context of the relevant technology, and should not be interpreted in an overly formal sense unless explicitly defined herein. In the following, variations of the depicted shapes may be expected in the attached drawings depending on manufacturing techniques and/or tolerances. Accordingly, embodiments of the present invention should not be interpreted as being limited to specific shapes of the areas depicted in this specification, and should include, for example, variations in shape resulting from the manufacturing process. FIG. 1 is a conceptual diagram schematically illustrating a vehicle (1000) according to exemplary embodiments. FIG. 2 is a layout schematically illustrating a system (100) according to exemplary embodiments. FIG. 3 is a flowchart schematically illustrating a pressed pedal determination method (S100) according to exemplary embodiments. FIG. 4 and FIG. 5 are conceptual diagrams schematically illustrating a pressed pedal determination method (S100) according to exemplary embodiments. Referring to FIG. 1, the vehicle (1000) may include a plurality of imaging devices (200), a system (100), and an alarm device (300). Referring to FIG. 4 together with FIG. 1, the plurality of imaging devices (200) may include a first imaging device (200a) that images the pedal area (PA) of the vehicle (1000). In FIG. 1, the first imaging device (200a), the system (100), and the alarm device (300) are shown as being composed of separate devices, but are not limited thereto and may be composed of a single device. For example, the system (100) may be installed inside the first imaging device (200a), and the alarm device (300) may be installed outside the first imaging device (200a). Referring to FIG. 2, the system (100) may include memory (120), a processor (130), and a communication module (110). The communication module (110) may include a communication module that supports one of various wired and wireless communication methods. For example, the communication module (110) may be in the form of a chipset, or may be a sticker/barcode containing information necessary for communication (e.g., a sticker containing an NFC tag). Additionally, the communication module (110) may be a short-range communication module or a wired communication module. For example, the communication module (110)