KR102470770B1 - System and method for recognition of vehicle turn indicator - Google Patents

Abstract

A vehicle turn signal recognition system according to an embodiment of the present invention recognizes the position of a magnet that is disposed on the back side of a turn indicator lever and continuously forms a magnetic field, and the position of the magnetic according to the change in the position of the turn indicator lever, thereby detecting the direction indicator lever. A detector that detects movement, forms a first movement signal when the direction indicator lever moves downward, and forms a second movement signal when the direction indicator lever moves upward, and captures the lane in which the vehicle is driving in real time A photographing unit that forms a vehicle driving image by using the vehicle driving image determines whether the vehicle is moving to the left or right of the driving lane, and if the vehicle moves to the left of the driving lane, the first movement signal from the sensing unit and a control device that determines whether or not a second movement signal is formed in the sensing unit when the vehicle moves to the right side of the driving lane, and forms a mismatch signal when mismatch occurs.

Description

Vehicle turn signal recognition system and method {SYSTEM AND METHOD FOR RECOGNITION OF VEHICLE TURN INDICATOR}

The present invention relates to a system and method for recognizing vehicle turn indicators, and more particularly, detects the moving direction of vehicle turn indicators using a Hall sensor and a magnet, and notifies the vehicle in conjunction with a lane change. It relates to a system and method for recognizing vehicle turn indicators capable of generating signals.

In general, the Lane Departure Warning System (LDWS) detects the lane through a camera located in front of the vehicle to determine the location of the vehicle in motion, and when an unintended lane change occurs, the vehicle leaves the lane It is a system that informs the driver that it has been done.

At this time, the lane departure warning to the driver may operate the LDWS display unit that the driver can visually check or vibrate the steering wheel so that the driver can feel it tactfully, and the driver can use a haptic function to tighten the seat belt or generate an alarm sound. Various means for recognizing lane departure have been used.

Such a lane departure warning system is a type of in-vehicle convenience device that recognizes the lane ahead using a camera image and sounds a warning when a danger of lane departure is predicted while driving. Driving is determined through on/off, and the vehicle speed is designed to operate only at a set speed or higher, and when the left/right direction indicators are operated, it is determined that the driver intends to leave the lane and does not give an alarm.

However, even in vehicles shipped without a lane departure warning system, a means capable of performing the same function as the lane departure warning system is required as a matter directly related to safety.

Accordingly, the present invention provides a vehicle turn signal recognition system and method capable of detecting a moving direction of a vehicle turn indicator using a Hall sensor and a magnet and generating a notification signal in conjunction with a vehicle lane change.

A vehicle turn indicator recognition system according to an embodiment of the present invention includes a magnet disposed on the back or side of a turn indicator lever to continuously form a magnetic field; The movement of the direction indicator lever is sensed by recognizing the position of the magnetic according to the position change of the direction indicator lever, and when the direction indicator lever moves downward, a first movement signal is formed, and the direction indicator lamp lever moves upward. a detector configured to form a second movement signal when moving in the direction; a photographing unit that captures a lane in which the vehicle is driving in real time to form a vehicle driving image; and determining whether the vehicle moves to the left or right of the driving lane by using the vehicle driving image, and whether the first movement signal is generated by the sensor when the vehicle moves to the left of the driving lane. or a control device determining whether or not the second movement signal is formed in the sensing unit when the vehicle moves to the right side of the driving lane, and generating a discrepancy signal when discrepant.

In addition, the sensing unit senses that when the direction indicator lever in which the magnet is installed moves downward, the magnetic field in the direction where the magnet was located is dissipated and the magnetic field in the downward direction of the sensing unit becomes denser, so that the direction indicator lamp lever A downward movement is sensed to form the first movement signal, and when the direction indicator lamp lever on which the magnet is installed moves upward, the magnetic field in the direction where the magnet was located is eliminated, and the magnetic field in the upward direction of the sensing unit is removed. The second movement signal may be formed by detecting that the direction indicator lamp lever moves upward by detecting that the direction indicator lamp becomes denser.

In addition, the sensing unit may be spaced apart from the magnetic and a vehicle instrument panel within an effective recognition distance or a supporting means mounted with a handle.

In addition, when the control device determines that the vehicle is moving from the driving lane to the left lane using the vehicle driving image, the second movement signal is formed in the sensor or no movement signal is formed in the sensing unit. A mismatch signal may be formed, and when it is determined that the vehicle moves from the driving lane to the right lane, the sensor may generate the first movement signal or generate the mismatch signal when no movement signal is formed.

In addition, the control device may determine whether the vehicle is moving to the left or right of the driving lane using the vehicle driving image formed by the photographing unit by a machine learning algorithm.

Also, the sensing unit may be a hall sensor.

The controller may further include a speaker generating an alarm sound when receiving the mismatch signal from the control device and/or a vibration unit generating vibration for warning when receiving the mismatch signal from the control device.

In addition, the vibration unit may be installed on a steering wheel or a driver's seat of the vehicle.

In addition, the control device may form the inconsistency signal when the speed of the vehicle is greater than or equal to a preset speed.

A method for recognizing a vehicle turn indicator lamp according to an embodiment of the present invention includes recognizing a position of a magnet according to a position change of a turn indicator lever by a sensing unit and detecting a movement of the turn indicator lever; forming a first movement signal when the direction indicator lever moves in a downward direction and forming a second movement signal when the direction indicator lever moves in an upward direction; forming a vehicle driving image by capturing a lane in which the vehicle is driving in real time; determining whether the vehicle is moving to the left or right of the driving lane by using the vehicle driving image; and determining whether the first movement signal is formed when the vehicle moves to the left side of the driving lane or whether the second movement signal is formed when the vehicle moves to the right side of the driving lane; Forming a mismatch signal.

In addition, the step of detecting the movement of the direction indicator lamp lever, when the direction indicator lamp lever in which the magnet is installed moves downward, it detects that the magnetic field in the direction where the magnet was located decreases and the magnetic field in the downward direction becomes denser. The first movement signal is formed by detecting that the direction indicator lever moves in a downward direction, and when the direction indicator lamp lever in which the magnet is installed moves upward, the magnetic field in the direction where the magnet was located is dissipated, and the upward direction The method may include forming the second movement signal by sensing that the direction indicator lamp lever moves upward by detecting that the magnetic field of the direction becomes denser.

In addition, in the forming of the mismatch signal, when it is determined that the vehicle is moving from the driving lane to the left lane using the vehicle driving image, the second movement signal is formed in the detector or any movement signal is formed. If not, the inconsistency signal is formed, and if it is determined that the vehicle is moving from the driving lane to the right lane, the first movement signal is formed in the sensing unit or if no movement signal is formed, the inconsistency signal is formed. steps may be included.

Also, generating an alarm sound when receiving the inconsistency signal; and generating a warning vibration when the mismatch signal is received.

The forming of the inconsistency signal may include forming the inconsistency signal when the speed of the vehicle is greater than or equal to a preset speed.

According to the present invention, a system capable of recognizing the lane in which the vehicle is running and interlocking with the direction indicator lever to generate an alarm sound or warning vibration when there is movement of the direction indicator lever that is different from the lane change direction can be conveniently installed in the vehicle. Therefore, the driving stability of the vehicle can be economically and easily improved.

In addition, when the vehicle recognizes the lane in which it is running and interlocks with the direction indicator lever to match the direction of the lane change, unnecessary warning sound or vibration for warning can be prevented.

1 is an exemplary view showing the configuration of a vehicle direction indicator recognition system according to an embodiment of the present invention.
2 is an exemplary view showing the configuration of a control device according to an embodiment of the present invention.
3 is a flowchart showing a procedure of a method for recognizing a vehicle turn signal lamp according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. This invention may be embodied in many different forms and is not limited to the embodiments set forth herein.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

1 is an exemplary view showing the configuration of a vehicle direction indicator recognition system according to an embodiment of the present invention.

As shown in FIG. 1 , the vehicle direction indicator recognition system may include a magnet 110, a sensing unit 120, a photographing unit 130, a control device 140, a speaker, a vibration unit, and a database. According to an embodiment, the magnetic 110, the sensing unit 120, the photographing unit 130, the control device 140, the speaker, the vibration unit, and the database may be connected to communicate with each other through a system bus or the like. .

The vehicle VE may include a handle HD for adjusting a running direction and a turn signal lever TS for blinking a left or right direction indicator lamp.

When the direction indicator lever (TS) is moved downward (direction 1), the left direction indicator lamp located in the front and rear of the vehicle (VE) flickers, and the direction indicator lever (TS) is moved upward (direction 2). If so, the right direction indicator lamp located in the front and rear of the vehicle VE flickers. In normal times, the direction indicator lever TS may be disposed at a preset position 3.

The magnet 110 is disposed behind (facing the instrument panel of the vehicle) or on the side of the direction indicator lever TS, and can continuously form a magnetic field. According to one embodiment, the magnet 110 and the sensing unit 120 may be disposed to be located within an effective distance. For example, when the direction indicator lever TS is located at 3, the effective linear distance between the magnetic 110 and the sensing unit 120 is 2.5 cm, and when the direction indicator lever TS is located at 1, the direction indicator lever ( TS) is located at 3, the straight line effective distance is 2.5 cm, and when the turn signal lamp lever (TS) is located at 2, the straight line effective distance from the turn indicator lever (TS) is located at 3 can be 2.5 cm. have. In addition, the distance between the magnet 110 and the sensing unit 120 should be arranged such that it does not deviate from the maximum effective distance. For example, when the direction indicator lever TS is located at 3, the maximum effective distance between the magnetic 110 and the sensing unit 120 is 5 cm, and when the direction indicator lever TS is located at 1, the direction indicator lever TS ) is located at 3, the maximum effective distance is 5 cm, and when the direction indicator lever (TS) is located at 2, the maximum effective distance with the direction indicator lever (TS) is located at 3 may be 5 cm. If the distance between the magnet 110 and the sensing unit 120 is out of the maximum effective distance, the recognition rate of the sensing unit 120 may decrease.

The sensing unit 120 may be disposed on the instrument panel facing the vehicle when the direction indicator lever TS is positioned at position 3. According to one embodiment, the sensing unit 120 may include a hall sensor capable of sensing the magnetic field of the magnet 110, but is not limited thereto. The sensor 120 may detect the movement of the direction indicator lever TS by recognizing the position of the magnet 110 according to the position change of the direction indicator lever TS. According to one embodiment, the sensor 120 recognizes the position of the turn signal lever TS at 1, 2, and 3 in advance to form a first movement signal when the turn indicator lever TS is located at 1, , When the direction indicator lever TS is located at 2, a second movement signal is formed, and when the direction indicator lever TS is located at 3, no movement signal may be formed. For example, the sensor 120, after calibrating the position of the turn signal lever TS in the state at position 3, lowers the turn indicator lever TS downward (direction 1), and then After performing calibration, on the contrary, after raising the direction indicator lever TS upward (direction 2), the positions of the direction indicator lever TS 1, 2, and 3 may be recognized in advance by performing calibration.

According to another embodiment, the detector 120 may detect the movement of the direction indicator lever TS by detecting a change in the density of the magnetic field generated by the magnet 110 . For example, in the sensing unit 120, when the direction indicator lever TS moves in one direction, the magnetic field in the direction 3 in which the magnet 110 was originally located is dissipated, and the sensing unit 120 moves in the downward direction ( By detecting that the magnetic field of 1) becomes dense, it is possible to detect that the direction indicator lever TS has moved in one direction. When detecting that the direction indicator lever TS moves in one direction, the detector 120 may form a first movement signal. In addition, the sensing unit 120, when the direction indicator lever TS moves in two directions, the magnetic field in the direction (3) where the magnet 110 was originally located is eliminated, and the upward direction (2) of the sensing unit 120 It is possible to sense that the direction indicator lever (TS) has moved in two directions by sensing that the magnetic field is getting denser. When detecting that the direction indicator lever TS moves in two directions, the detector 120 may form a second movement signal. According to one embodiment, the sensing unit 120 may be spaced apart from the magnetic 110 and the side of the supporting means on which the vehicle instrument panel or handle HD is mounted within an effective recognition distance, but is not limited thereto.

The photographing unit 130 may form a vehicle driving image by capturing a lane in which the vehicle VE is driving in real time. According to one embodiment, the photographing unit 130 may include, but is not limited to, a black box, a camera, and a LiDAR (Light Detection And Ranging) sensor.

The control device 140 determines whether the vehicle VE is moving to the left or the right side of the driving lane by using the vehicle driving image formed by the photographing unit 130, and determines whether the vehicle VE is moving to the left side of the driving lane. When the vehicle VE moves to the left side of the lane in which the vehicle VE is driving, it is determined whether a first movement signal is generated by the detector 120 when the vehicle moves to VE, or whether a second movement signal is generated by the detector 120 when the vehicle VE moves to the left. In this case, a mismatch signal may be formed. According to an embodiment, when the control device 140 determines that the vehicle VE is moving from the driving lane to the left lane using the vehicle driving image, the second movement signal is formed in the detector 120 or When the movement signal is also not formed, a mismatch signal may be formed. According to another embodiment, when the control device 140 determines that the vehicle VE is moving from the driving lane to the right lane using the vehicle driving image, the first movement signal is generated by the sensor 120 or When the movement signal is also not formed, a mismatch signal may be formed. In addition, the control device 140 may be configured to generate a mismatch signal only when the speed of the vehicle VE is equal to or greater than a predetermined speed (eg, 60 km/h, 80 km/h, or 100 km/h).

The control device 140 may determine whether the vehicle VE is moving to the left or right of the driving lane by using the vehicle driving image formed by the photographing unit 130 using a machine learning algorithm. For example, the control device 140 controls the lane in which the vehicle VE is driving, when the vehicle VE moves to the left in the driving lane, and when the vehicle VE moves to the right in the driving lane. A vehicle driving image may be received as input data of an artificial intelligence learning model or neural network model, and a movement direction (left or right) may be output as output data of the artificial intelligence learning model or neural network model.

The speaker may sound an alarm when receiving a mismatch signal from the control device 140 . According to an embodiment, the speaker may include a vehicle speaker previously installed in a vehicle, but the vehicle turn signal recognition system may include a dedicated speaker separately.

The vibration unit may generate warning vibration when receiving a mismatch signal from the control device 140 . According to an embodiment, the vibrating unit includes a dedicated motor for generating vibration and is installed on the steering wheel HD or the driver's seat SE where the driver sits, and when a mismatch signal is received from the control device 140, the steering wheel HD ) or by vibrating the driver's seat SE to generate warning vibration.

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as recognition and judgment, using machine learning algorithms, can also be understood as artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model derives a correlation between data by extracting and analyzing features from given data, and optimizing the parameters of the neural network model by repeating this process can be referred to as machine learning. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving a regularity between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons that transmit and receive signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can send and receive data according to a convolutional connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, reinforcement learning, and ensemble learning. Machine learning algorithms for performing machine learning include a K-Nearest Neighbor (KNN) algorithm, a decision tree, a Bayesian network, a support vector machine, Artificial Neural Network, Ada-boost, Perceptron, Genetic Programming, Clustering, etc. may be used.

Among them, the KNN algorithm is a type of instance-based learning or delayed learning, in which functions are only approximated locally and all computations can be deferred until function evaluation. Since KNN algorithms rely on distance for classification, normalizing the training data can greatly improve accuracy. A useful technique for both classification and regression is to assign weights to the contributions of neighbors so that closer neighbors contribute more to the mean than more distant neighbors. For example, a common weighting scheme could consist of giving each neighbor a weight of 1/d. where d is the distance to a neighbor. Neighbors can come from a set of objects whose class (in the case of KNN classification) or object property values (in the case of KNN regression) are known. This does not require an explicit training step, but can be thought of as a training set for the algorithm. A characteristic of the KNN algorithm is that it is sensitive to the local structure of the data.

CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. A CNN consists of one or several convolution layers and general artificial neural network layers on top, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

The database may store various data for implementing the vehicle turn signal recognition system. Data stored in the database is data acquired, processed, or used by at least one component of the vehicle turn signal recognition system, and may include software (eg, a program). The database may include volatile and/or non-volatile memory. The database may include various systems with high availability and high scalability based on cloud infrastructure and managed services. As an embodiment, the database may store the vehicle driving image formed by the photographing unit 130, the first and second movement signals formed by the control device 140, and the inconsistency signal, but is not limited thereto.

In the present invention, a program is software stored in a database, and provides various functions to an operating system, an application, and/or an application to utilize resources of a vehicle turn signal recognition system for controlling resources of a vehicle turn signal recognition system. Middleware, etc. may be included.

2 is an exemplary view showing the configuration of a control device according to an embodiment of the present invention.

As shown in FIG. 2, the control device 140 may include a receiver 141, a processor 142, a transmitter 143, a system bus 144, a digital packet 145, and a database (DB). . As an embodiment, the receiver 141, the processor 142, the transmitter 143, the digital packet 145, and the database (DB) may be connected to each other so as to be communicable using the system bus 144, and the control device ( At least one of these components of 140) may be omitted or another component may be added to the control device 140. In addition, additionally or alternatively, some components may be integrated and implemented, or may be implemented as a singular or plural entity.

The receiving unit 141 may receive the first and second movement signals from the sensing unit 120 through the network N in the form of a digital packet 145 and transmit them to the processor 142 and the database DB. In addition, the receiving unit 141 may receive the vehicle driving image in the form of a digital packet 145 from the photographing unit 130 through the network N and transmit it to the processor 142 and the database DB.

The processor 142 may use the received first and second movement signals and the vehicle driving image to determine whether or not the direction change error of the vehicle VE occurs. According to an embodiment, when the processor 142 determines that the vehicle VE moves from the driving lane to the left lane using the vehicle driving image, the second movement signal is formed and received from the sensor 120 or When no movement signal is formed and received, a mismatch signal may be formed, and when it is determined that the vehicle VE is moving from the driving lane to the right lane using the vehicle driving image, the detector 120 first moves When a signal is formed and received or no movement signal is formed and received, a mismatch signal may be formed in the form of a digital packet 145 .

The transmission unit 143 may transmit the mismatch signal formed in the form of the digital packet 145 by the processor 142 to the speaker and/or the vibration unit through the network N.

The network N may perform wireless or wired communication between components of the control device 140 . For example, the network N may include long-term evolution (LTE), LTE Advanced (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), wireless broadband (WiBro), wireless fidelity (WiFi) , Bluetooth, near field communication (NFC), global positioning system (GPS), or global navigation satellite system (GNSS). For example, the network N may perform wired communication according to a method such as universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 122 (RS-122), or plain old telephone service (POTS). may be

3 is a flowchart showing a procedure of a method for recognizing a vehicle turn signal lamp according to an embodiment of the present invention. Although process steps, method steps, algorithms, etc. are described in a sequential order in the flowchart of FIG. 3, such processes, methods and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods and algorithms described in the various embodiments of the invention need not be performed in the order described herein. Also, although some steps are described as being performed asynchronously, in other embodiments some of these steps may be performed concurrently. Further, illustration of a process by depiction in the drawings does not mean that the illustrated process is exclusive of other changes and modifications thereto, and that any of the illustrated process or steps thereof may be one of various embodiments of the present invention. It is not meant to be essential to one or more, and it does not imply that the illustrated process is preferred.

As shown in FIG. 3, in step S310, the movement of the direction indicator lever is sensed by recognizing the position of the magnet according to the position change of the direction indicator lever. For example, referring to FIGS. 1 and 2 , the detector 120 of the vehicle turn signal recognition system recognizes the position of the magnetic 110 according to the change in the position of the turn indicator lever TS, and then the indicator lever ( TS) can be detected.

In step S320, a first movement signal is generated when the direction indicator lever moves downward, and a second movement signal is generated when the direction indicator lever moves upward. For example, referring to FIGS. 1 and 2 , the detector 120 of the vehicle turn indicator recognition system forms a first movement signal when the turn indicator lever TS moves in a downward direction (1), and When the indicator lever TS moves in the upward direction (2), a second movement signal may be generated.

In step S330, a vehicle driving image is formed by capturing the lane in which the vehicle is driving in real time. For example, referring to FIGS. 1 and 2 , the photographing unit 130 of the vehicle turn signal recognition system may form a vehicle driving image by capturing a lane in which the vehicle VE is driving in real time. According to one embodiment, the photographing unit 130 may include, but is not limited to, a black box, a camera, and a LiDAR (Light Detection And Ranging) sensor.

In step S340, it is determined whether the vehicle moves to the left or right of the driving lane using the vehicle driving image. For example, referring to FIGS. 1 and 2 , the control device 140 of the vehicle turn signal recognition system uses a machine learning algorithm such as deep learning to form a vehicle driving image formed by the photographing unit 130. It is possible to determine whether the vehicle VE is moving to the left or right of the lane in which it is driving.

In step S350, it is determined whether a first movement signal is formed when the vehicle moves to the left side of the driving lane or whether a second movement signal is formed when the vehicle moves to the right side of the driving lane. signal is formed. For example, referring to FIGS. 1 and 2 , in the control device 140 of the vehicle turn signal recognition system, when the vehicle VE moves to the left side of the driving lane, the sensor 120 receives a first movement signal. When the vehicle VE moves to the right side of the driving lane, the sensing unit 120 determines whether or not the second movement signal is formed, and when there is a discrepancy, a discrepancy signal may be formed.

In the above, the present invention has been described with reference to the embodiments shown in the drawings. However, the present invention is not limited thereto, and various modifications or other embodiments belonging to the scope equivalent to the present invention can be made by those skilled in the art. Therefore, the true scope of protection of the present invention will be defined by the following claims.

110: magnetic 120: detection unit
130: photographing unit 140: control device
141: receiver 142: processor
143: transmission unit 144: system bus
145: digital packet N: network
VE: Vehicle HD: Steering Wheel
TS: vehicle indicator lever SE: driver's seat
DB: database

Claims (14)

As a vehicle direction indicator recognition system,
A magnet disposed on the back or side of the turn signal lever to continuously form a magnetic field;
The movement of the direction indicator lever is sensed by recognizing the position of the magnetic according to the position change of the direction indicator lever, and when the direction indicator lever moves downward, a first movement signal is formed, and the direction indicator lamp lever moves upward. a sensing unit that forms a second movement signal when moving in the direction;
a photographing unit that captures a lane in which the vehicle is driving in real time to form a vehicle driving image; and
It is determined whether the vehicle moves to the left or right of the driving lane by using the vehicle driving image, and whether the first movement signal is formed in the detector when the vehicle moves to the left of the driving lane. or, when the vehicle moves to the right side of the driving lane, the sensor determines whether or not the second movement signal is formed, and when there is a mismatch, a control device is formed to form a mismatch signal;
the sensor,
When the direction indicator lever on which the magnet is installed moves downward, the magnetic field in the direction where the magnet was located is dissipated, and it is sensed that the magnetic field in the downward direction of the sensing unit becomes denser, indicating that the direction indicator lever moves downward. sensing to form the first movement signal;
When the direction indicator lever on which the magnet is installed moves upward, the magnetic field in the direction where the magnet was located disappears, and it is sensed that the magnetic field in the upper direction of the sensing unit is dense, indicating that the direction indicator lever moves upward. It detects and forms the second movement signal, characterized in that it is spaced apart from the side of the support means on which the vehicle instrument panel or handle within an effective recognition distance from the magnet is mounted,
Vehicle turn signal recognition system. delete delete According to claim 1,
The control device,
When it is determined by using the vehicle driving image that the vehicle moves from the driving lane to the left lane, the second movement signal is formed in the sensing unit or when no movement signal is formed, the mismatch signal is formed;
When it is determined that the vehicle is moving from the driving lane to the right lane, the first movement signal is formed in the sensing unit or the inconsistency signal is formed when no movement signal is formed.
Vehicle turn signal recognition system. According to claim 1,
The control device,
Determining whether the vehicle moves to the left or right of the driving lane using the vehicle driving image formed by the photographing unit by a machine learning algorithm,
Vehicle turn signal recognition system. According to claim 1,
The sensing unit is a hall sensor,
Vehicle turn signal recognition system. According to claim 1,
A speaker generating an alarm when receiving the inconsistency signal from the control device, or
Further comprising a vibration unit for generating a warning vibration when receiving the mismatch signal from the control device,
Vehicle turn signal recognition system. According to claim 7,
the vibrator,
Installed on the steering wheel or driver's seat of the vehicle,
Vehicle turn signal recognition system. According to claim 1,
The control device,
Forming the inconsistency signal when the speed of the vehicle is greater than or equal to a preset speed,
Vehicle turn signal recognition system. delete delete delete delete delete

Images