KR102179995B1 - Method for detection driver violence - Google Patents

Abstract

The present invention includes a photographing apparatus that photographs objects to generate object data, and a determination server that detects objects from the object data and determines whether a driver is violent by using the detected objects.

Description

How to detect driver violence{METHOD FOR DETECTION DRIVER VIOLENCE}

The present invention relates to a driver violence detection system and a driver violence detection method, and more particularly, to a driver violence detection system and a driver violence detection method for determining whether or not a violence situation is performed using the overlapping degree of objects and facial expressions of the objects.

The interior space of the vehicle is usually formed as a single open space consisting of a driver's seat and a passenger's seat.

The safety of drivers who drive vehicles is very important. However, since the driver's seat and the passenger seat are open inside the vehicle, driving may be disturbed by the occupants who board the passenger seat.

In particular, even if the driver is intentionally assaulted or threatened with a weapon, the driver is bound to be unprotected and unilaterally attacked, and there are cases in which the driver is actually injured or killed due to such a violent act.

In addition, due to the violent behavior of the occupant, the driver cannot concentrate on driving, which is likely to lead to a secondary traffic accident.

However, in the past, it is not possible to accurately recognize the violent situation in which a violent act is applied, and there is a problem that the amount of computation increases in order to accurately recognize it.

Republic of Korea Patent Publication No. 10-2017-0117901 (published on October 24, 2017)

The present invention was invented to solve the above problems, and an object thereof is to provide a driver violence detection system and a driver violence detection method capable of accurately determining whether a driver violence situation exists.

In addition, another object of the present invention is to provide a driver violence detection system and a driver violence detection method having a low computational burden.

In addition, another object of the present invention is to provide a driver violence detection system and a driver violence detection method capable of outputting a driver violence situation to a preset contact information.

In order to solve the above-described problems, the present invention provides a photographing apparatus for generating object data by photographing objects, and a determination server for detecting objects from the object data and determining whether a driver is violent using the detected objects. Includes.

In addition, the determination server, an object detection device for detecting objects in the object data, an overlap data generation module for generating object overlap data by determining an overlap degree of the detected objects, and recognizing the facial expressions of the objects, and the recognition An expression data generation module that generates facial expression data using the facial expressions of one object, and a violence situation determination module that determines whether or not a violence situation is performed using the object overlapping data and the facial expression data.

In addition, the objects may be detected from the object data using a YOLO object detection algorithm.

In addition, the overlapping data may be generated by using an algorithm for measuring the Euclidean distance between objects.

According to another aspect of the present invention, the driver violence detection system photographs objects to generate object data, the driver violence detection system detects objects from the object data, and the driver violence detection system overlaps the detected objects. Determining a degree to generate object overlap data, the driver violence detection system recognizing the expressions of the objects, generating facial expression data using the recognized expressions of the objects, and the driver violence detection system the object overlapping data And determining whether there is a violent situation using the facial expression data.

According to the present invention, there is an effect of accurately determining whether or not a driver's violence situation exists.

In addition, there is an effect of providing a driver violence detection system and a driver violence detection method with low computational burden.

In addition, there is an effect of outputting the driver's violence situation to a preset contact information.

1 is a diagram showing a driver violence detection system according to an embodiment of the present invention.
2 is a diagram showing a configuration of a photographing apparatus.
3 is a diagram showing the configuration of a decision server.
4 is a flowchart schematically illustrating a method for detecting driver violence according to an embodiment of the present invention.

Specific structural or functional descriptions of the embodiments according to the concept of the present invention disclosed in the present specification are exemplified only for the purpose of describing the embodiments according to the concept of the present invention, and the embodiments according to the concept of the present invention are It may be implemented in various forms and is not limited to the embodiments described herein.

Since the embodiments according to the concept of the present invention can apply various changes and have various forms, the embodiments will be illustrated in the drawings and described in detail in the present specification. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes all changes, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first or second may be used to describe various elements, but the elements should not be limited by the terms. The terms are only for the purpose of distinguishing one component from other components, for example, without departing from the scope of the rights according to the concept of the present invention, the first component may be referred to as the second component, and similarly The second component may also be referred to as a first component.

When a component is referred to as being "connected" or "connected" to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in the middle. Should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle. Other expressions describing the relationship between components, such as "between" and "just between" or "adjacent to" and "directly adjacent to" should be interpreted as well.

The terms used in this specification are used only to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise.

In the present specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, action, component, part, or combination thereof is present, but one or more other features or numbers It is to be understood that the possibility of addition or presence of, steps, actions, components, parts, or combinations thereof is not preliminarily excluded.

Unless otherwise defined, all terms including technical or scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

Terms as defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted as an ideal or excessively formal meaning unless explicitly defined in this specification. Does not.

In the following description, the same identification symbols mean the same configuration, and unnecessary redundant descriptions and descriptions of known technologies will be omitted.

In an embodiment of the present invention,'communication','communication network', and'network' may be used with the same meaning. The three terms refer to wired/wireless local and wide area data transmission/reception networks capable of transmitting and receiving files between a user terminal, a terminal of other users, and a download server.

Hereinafter, the present invention will be described in detail by describing a preferred embodiment of the present invention with reference to the accompanying drawings.

1 is a diagram illustrating a driver violence detection system according to an embodiment of the present invention, FIG. 2 is a diagram illustrating a configuration of a photographing apparatus, and FIG. 3 is a diagram illustrating a configuration of a decision server.

Referring to FIG. 1, a driver violence detection system according to an embodiment of the present invention includes a photographing apparatus 100 and a decision server 200.

1 and 2, the photographing apparatus 100 includes a first control module 110, a first communication module 120, an image acquisition module 130, an object data generation module 140, and a first database ( 150).

The first control module 110, the first communication module 120, the image acquisition module 130, the object data generation module 140 and the first database 150 constituting the photographing apparatus 100 are interconnected. , It is possible to transmit data to each other.

The first control module 110 manages information on the photographing apparatus 100 or an operation of the photographing apparatus 100.

The first control module 110 manages the operation of the image acquisition module 130.

The first control module 110 manages the operation of the object data generation module 140.

The first control module 110 may set an image acquisition condition of the image acquisition module 130.

The first control module 110 may include a memory (not shown) in which programs are stored and a processor (not shown) for executing the program stored in the memory (not shown).

In this case, an operation program (eg, OS) for operating the photographing apparatus 100 may be stored in the memory (not shown).

The first communication module 120 is connected to the decision server 200 through a network.

The first communication module 120 transmits the image acquired by the image acquisition module 130 to the determination server 200.

The first communication module 120 transmits the object data generated by the object data generation module 140 to the determination server 200.

The first communication module 120 receives an image retransmission signal transmitted from the determination server 200.

The first communication module 120 transmits an image corresponding to the image retransmission signal to the determination server 200.

The image acquisition module 130 photographs objects.

The image acquisition module 130 may photograph the driver as an object.

The image acquisition module 130 may photograph a passenger as an object.

In this case, the occupant refers to a person who has boarded the boarding seat on the right side of the driver's seat.

The image acquisition module 130 may photograph a driver and a passenger.

The image acquisition module 130 may acquire an image only when both the driver and the occupant enter the photographing screen.

The image acquisition module 130 may take an image based on the driver's seat.

The object data generation module 140 generates object data by using the image captured by the image acquisition module 130.

The object data generation module 140 may generate object data only when both the driver and the occupant are photographed in the image.

The object data generation module 140 may generate object data based on a driver's seat.

The object data generation module 140 may generate object data even when only the driver is photographed in the image.

The object data generation module 140 may generate object data even when only the passenger is photographed in the image.

The first database 150 stores an image acquisition condition of the image acquisition module 130.

The first database 150 stores an image acquired by the image acquisition module 130.

The first database 150 stores object data generated by the object data generation module 140.

The first database 150 stores the image transmitted to the decision server 200.

The first database 150 stores object data transmitted to the decision server 200.

1 and 3, the determination server 200 includes a second control module 210, a second communication module 220, an object detection module 230, an overlap data generation module 240, and an expression data generation module. 250, a violence situation determination module 260, an output module 270, and a second database 280.

The second control module 210 constituting the decision server 200, the second communication module 220, the object detection module 230, the overlap data generation module 240, the facial expression data generation module 250, the violence situation determination The module 260, the output module 270, and the second database 280 are interconnected, and data can be transmitted to each other.

The second control module 210 manages information on the decision server 200 or an operation of the decision server 200.

The second control module 210 manages the operation of the object detection module 230.

The second control module 210 manages the operation of the overlapping data generation module 240.

The second control module 210 manages the operation of the facial expression data generation module 250.

The second control module 210 manages the operation of the violence situation determination module 260.

The second control module 210 manages the operation of the output module 270.

The second control module 210 may include a memory (not shown) in which programs are stored and a processor (not shown) for executing the program stored in the memory (not shown).

In this case, an operation program (eg, OS) for operating the decision server 200 may be stored in the memory (not shown).

The second communication module 220 is connected to the photographing device 100 through a network.

The second communication module 220 receives an image transmitted by the photographing device 100.

The second communication module 220 receives object data transmitted by the photographing device 100.

The second communication module 220 may transmit the result of determining whether the violence situation is present to a preset contact information.

In this case, the preset contact information is preferably one of contact information of a police station, an insurance company, a family member, a friend, or an acquaintance, but is not limited thereto.

The object detection module 230 detects a driver object from an image transmitted by the photographing device 100.

The object detection module 230 detects a driver object from object data transmitted from the photographing device 100.

The object detection module 230 detects an external object from an image transmitted by the photographing device 100.

The object detection module 230 detects an external object from object data transmitted by the photographing device 100.

The object detection module 230 may detect the objects using a YOLO object detection algorithm.

The overlapping data generation module 240 determines the degree of overlap of objects detected by the object detection module 230 to generate object overlapping data.

The overlapping data generation module 240 may use an algorithm for measuring an Euclidean distance between coordinates of the driver object and the external object in order to determine the degree of overlap.

The overlapping data generation module 240 may determine the degree of overlap using the following [Equation 1].

When it is determined that there is an overlap between the driver object and the external object, the overlap data generation module 240 generates object overlap data.

When it is determined that there is no overlap between the driver object and the external object, the overlap data generation module 240 may not generate object overlap data.

The facial expression data generation module 250 recognizes the facial expressions of the objects, and generates facial expression data by using the facial expressions of the recognized objects.

The facial expression data generation module 250 may pre-process the image transmitted by the photographing apparatus 100 by using a binary Hartley transform or a Fourier-related transform.

The facial expression data generation module 250 may extract a lip region by applying a lip detection algorithm to the preprocessed image, and compare the extracted lip region with a pre-stored lip image template to recognize facial expressions of the objects.

In this case, the lip detection algorithm is a method of emphasizing the driver's lip part using a threshold using a feature that the part of the driver's face with the strongest red color is the lip.

In addition, the pre-stored lip image templates include Neutral, Happiness, Grief, Surprized, and Anger.

The facial expression data generation module 250 may generate facial expression data from facial expressions of the recognized objects.

The violence situation determination module 260 determines whether there is a violence situation using the object overlap data and the facial expression data.

The violence situation determination module 260 may determine whether the violence situation exists by assigning a weight to each of the object overlapping data and the facial expression data.

The violence situation determination module 260 may determine whether the violence situation is present by assigning a weight to the object overlapping data.

The violence situation determination module 260 may determine whether the violence situation is present by assigning a weight to the facial expression data.

The output module 270 outputs whether the violence situation is determined by the violence situation determination module 260.

The output module 270 may transmit a result of determining whether there is a violence situation to a preset contact information through the second communication module 220.

In this case, the preset contact information is preferably one of contact information of a police station, an insurance company, a family member, a friend, or an acquaintance, but is not limited thereto.

The second database 280 stores an image transmitted from the photographing device 100.

The second database 280 stores object data transmitted from the photographing device 100.

The second database 280 stores preset contact information.

The second database 280 stores object overlap data generated by the overlap data generation module 240.

The second database 280 stores facial expression data generated by the facial expression data generation module 250.

The second database 280 stores a lip image template.

The second database 280 stores the violence situation determined by the violence situation determination module 260.

The second database 280 stores the result of determining whether there is a violence situation output by the output module 270.

The term'server' used herein denotes a logical structural unit, and it is obvious to those skilled in the art that the present invention is not necessarily a physically classified component.

The term'module' as used herein denotes a logical structural unit, and it is obvious to those skilled in the art that the present invention is not necessarily a physically classified component.

4 is a flowchart schematically illustrating a method for detecting driver violence according to an embodiment of the present invention.

Referring to FIG. 4, in the method for detecting driver violence according to an embodiment of the present invention, a driver violence detection system photographs objects to generate object data (S100).

In this case, the driver violence detection system may generate object data based on the driver's seat.

The driver violence detection system detects objects from the object data (S110).

In this case, the driver violence detection system may detect the objects using a YOLO object detection algorithm.

The driver violence detection system determines the degree of overlap of the detected objects to generate object overlap data (S120).

In this case, the driver violence detection system may generate the overlapping data by using an algorithm for measuring the Euclidean distance between objects.

The driver's violence detection system recognizes the facial expressions of the objects, and generates facial expression data using the recognized facial expressions of the objects (S130).

At this time, the driver violence detection system extracts the lip region by applying a lip detection algorithm to the preprocessed image, compares the extracted lip region with a pre-stored lip image template, recognizes the expressions of the objects, and uses the recognized expression. Data can be created.

The driver violence detection system determines whether there is a violence situation using the object overlap data and the facial expression data (S140).

In this case, the driver violence detection system may determine whether or not there is a violence situation by assigning a weight to the object overlapping data.

The driver's violence detection system outputs a result of determining whether there is a violence situation (S150).

In this case, the driver violence detection system may transmit a result of determining whether a violent situation exists to at least one of a police station, an insurance company, a family member, a friend, or an acquaintance.

In the above, even if all the constituent elements constituting the embodiments of the present invention have been described as being combined into one or operating in combination, the present invention is not necessarily limited to these embodiments. That is, within the scope of the object of the present invention, all the constituent elements may be selectively combined and operated with at least one.

In addition, although all of the components may be implemented as one independent hardware, a program module that performs some or all functions combined in one or more hardware by selectively combining some or all of the components. It may be implemented as a computer program having Codes and code segments constituting the computer program may be easily inferred by those skilled in the art of the present invention.

Such a computer program is stored in a computer-readable storage medium, and is read and executed by a computer, thereby implementing an embodiment of the present invention. The computer program storage medium may include a magnetic recording medium, an optical recording medium, and the like.

In addition, the terms such as "include", "consist of" or "have" described above mean that the corresponding component may be embedded unless otherwise stated, excluding other components Rather, it should be interpreted as being able to further include other components.

All terms, including technical or scientific terms, unless otherwise defined, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms generally used, such as terms defined in the dictionary, should be interpreted as being consistent with the meaning in the context of the related technology, and are not interpreted as ideal or excessively formal meanings unless explicitly defined in the present invention.

The above description is merely illustrative of the technical idea of the present invention, and those of ordinary skill in the art to which the present invention pertains will be able to make various modifications and variations without departing from the essential characteristics of the present invention.

Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain the technical idea, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical ideas within the scope equivalent thereto should be interpreted as being included in the scope of the present invention.

100... shooting device 200... decision server

Claims (5)

A photographing device that photographs objects to generate object data; An object detection device for detecting objects in the object data; An overlap data generation module for generating object overlap data by determining an overlap degree of the detected objects; An expression data generation module that recognizes the facial expressions of the objects and generates facial expression data by using the recognized facial expressions of the objects; And a violence situation determination module that determines whether or not a violence situation is made using the object overlap data and the facial expression data, comprising:
Generating object data by photographing objects by a driver violence detection system;
Detecting, by a driver violence detection system, objects in the object data;
Generating object overlap data by determining, by a driver violence detection system, an overlapping degree of the detected objects;
Recognizing, by a driver violence detection system, the facial expressions of the objects, and generating facial expression data using the recognized facial expressions of the objects; And
Including, by the driver violence detection system, determining whether or not a violence situation by using the object overlap data and the facial expression data,
The generating of the facial expression data includes extracting a lip area by applying a lip detection algorithm to the image preprocessed by the driver violence detection system, and comparing the extracted lip area with a pre-stored lip image template to recognize the facial expressions of the objects. And, further comprising the step of generating facial expression data with the recognized facial expression,
The determining of the violence situation further comprises the step of determining, by the driver violence detection system, a violence situation by assigning a weight to the object overlap data. delete The method of claim 1,
A method of detecting driver violence, characterized in that the objects are detected from the object data using a YOLO object detection algorithm. The method of claim 1,
A driver violence detection method for generating the overlapping data by using an algorithm measuring the Euclidean distance between objects. delete

Images