KR102005956B1 - Image recognition apparatus in the inside of vehicle - Google Patents

Image recognition apparatus in the inside of vehicle Download PDF

Info

Publication number
KR102005956B1
KR102005956B1 KR1020180031498A KR20180031498A KR102005956B1 KR 102005956 B1 KR102005956 B1 KR 102005956B1 KR 1020180031498 A KR1020180031498 A KR 1020180031498A KR 20180031498 A KR20180031498 A KR 20180031498A KR 102005956 B1 KR102005956 B1 KR 102005956B1
Authority
KR
South Korea
Prior art keywords
vehicle
image
module
camera
unit
Prior art date
Application number
KR1020180031498A
Other languages
Korean (ko)
Inventor
김대훈
Original Assignee
김대훈
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 김대훈 filed Critical 김대훈
Priority to KR1020180031498A priority Critical patent/KR102005956B1/en
Application granted granted Critical
Publication of KR102005956B1 publication Critical patent/KR102005956B1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/30Transportation; Communications
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00832Recognising scenes inside a vehicle, e.g. related to occupancy, driver state, inner lighting conditions
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • G06K9/4652Extraction of features or characteristics of the image related to colour
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62Methods or arrangements for recognition using electronic means
    • G06K9/6201Matching; Proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/225Television cameras ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, camcorders, webcams, camera modules specially adapted for being embedded in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/2259Means for changing the camera field of view without moving the camera body, e.g. nutating or panning optics or image-sensors
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/222Studio circuitry; Studio devices; Studio equipment ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, TV cameras, video cameras, camcorders, webcams, camera modules for embedding in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/225Television cameras ; Cameras comprising an electronic image sensor, e.g. digital cameras, video cameras, camcorders, webcams, camera modules specially adapted for being embedded in other devices, e.g. mobile phones, computers or vehicles
    • H04N5/232Devices for controlling television cameras, e.g. remote control ; Control of cameras comprising an electronic image sensor
    • H04N5/23203Remote-control signaling for television cameras, cameras comprising an electronic image sensor or for parts thereof, e.g. between main body and another part of camera
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00Details of television systems
    • H04N5/76Television signal recording
    • H04N5/765Interface circuits between an apparatus for recording and another apparatus
    • H04N5/77Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera

Abstract

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an in-vehicle image recognition apparatus, An image analyzer for comparing and analyzing a captured image photographed by the vehicle photographing unit and a preset image set in the vehicle; A state evaluating unit for evaluating a state of use of the vehicle according to an analysis result of the image analyzing unit; And a status transmission unit for transmitting the shot image photographed by the vehicle photographing unit and the evaluation result evaluated by the state evaluation unit to the manager server.

Description

[0001] IMAGE RECOGNITION APPARATUS IN THE INSIDE OF VEHICLE [0002]

The present invention relates to an in-vehicle image recognition apparatus, and more particularly, to an in-vehicle image recognition apparatus, which can compare an image taken inside a vehicle after use of a vehicle with an image taken inside a vehicle before use of the vehicle, To a vehicle interior image recognition device.

The car rental service provides information to the car rental company or the car available to the rental store, and the customer who wants to use the rental car rents and pays the car directly provided at the rental car company or rental store.

Conventionally, when the customer completes the use of the vehicle and returns the vehicle to the garage, the vehicle manager directly checks the interior of the vehicle after use to evaluate the state of use of the vehicle. Thus, the presence or absence of the car wash There was a hassle to do.

In addition, there is a problem that it is impossible to confirm the state of the vehicle because there is no staff in charge at all the garages at the time of using the car sharing as well as the rental car.

In order to solve such a problem, the present applicant has proposed a method of automatically evaluating the state of use of a vehicle after use by image recognition, imposing a discount benefit and a penalty on the customer according to the state of use of the vehicle, , And invented an in-vehicle image recognition device that minimizes the dispute between the customer and the company through monitoring of the damage inside the vehicle.

Korean Registered Patent No. 10-1115944 (Feb. 23, 2012)

An object of the present invention is to provide an in-vehicle image recognition device capable of comparing a captured image captured inside a vehicle after use of a vehicle with a set image captured inside the vehicle before use of the vehicle, have.

It is another object of the present invention to provide a vehicle interior image recognition apparatus capable of providing a discount benefit to a customer who uses the vehicle cleanly according to the state of use of the vehicle.

In addition, the present invention provides an in-vehicle image recognition apparatus that imposes a penalty on a customer who does not use the vehicle cleanly according to the state of use of the vehicle, but can apply various penalties according to the cleanliness degree in connection with the cleanliness rating system It has its purpose.

It is another object of the present invention to provide an in-vehicle image recognition apparatus capable of selecting a car class according to the state of use of the vehicle and reducing the car wash cost by allowing optimal car wash according to the class to proceed.

Another object of the present invention is to provide an in-vehicle image recognition apparatus capable of notifying a customer of a lost item by checking the corresponding lost item in the event that the lost vehicle exists in the vehicle after use.

It is another object of the present invention to provide an in-vehicle image recognition device which can compare a set image before use of a vehicle, a taken image after using a vehicle, a washed image,

In addition, the present invention minimizes the dispute between the customer and the company through the monitoring of the damage inside the vehicle, and when the autonomous vehicle is commercialized and the shared car culture is further activated, the internal inspection of the vehicle is carried out from time to time, The present invention is directed to a vehicle interior image recognition apparatus capable of positively utilizing information on monitoring of a vehicle.

According to an aspect of the present invention, there is provided an apparatus for recognizing an internal image of a vehicle, including: a vehicle photographing unit for photographing an interior of the vehicle; An image analyzer for comparing and analyzing a captured image photographed by the vehicle photographing unit and a preset image set in the vehicle; A state evaluating unit for evaluating a state of use of the vehicle according to an analysis result of the image analyzing unit; And a status transmission unit for transmitting the shot image photographed by the vehicle photographing unit and the evaluation result evaluated by the state evaluation unit to the manager server.

The vehicle photographing unit may further include: a movement guide member including a rail installed on a ceiling of the vehicle; And a camera installed on the rail and photographing the interior of the vehicle while moving the rail. The camera may be a black box installed in the vehicle, a camera separately installed in the vehicle, or a depth recognition sensor.

The vehicle photographing unit may further include: a tilt member installed between the rail and the camera and tilting and rotating the camera to change the photographing angle of the camera; And a control member connected to the camera and the tilt member to drive the camera and the tilt member, respectively.

In addition, the vehicle photographing unit may further include a sensing member installed in the camera for sensing the illuminance and the lightness of the interior of the vehicle, and the control member may control illumination installed inside the vehicle according to a sensed result value from the sensing member .

The image analysis unit may further include: a storage module for storing the setting image; An input module for receiving a captured image captured by the camera and a set image stored in the storage module, respectively; A comparison module for comparing the shot image and the set image input to the input module with each other to search for a mismatch area between the shot image and the set image; A calculation module for calculating a mismatch ratio between the photographed image and the set image according to the mismatch area searched by the comparison module; And an output module outputting the inconsistency rate calculated in the calculating module.

In addition, the comparison module may compare the colors of the photographed image and the set image to each other to search for the region where the color or depth difference has occurred in the entire region of the photographed image, as the mismatch region.

The calculation module may calculate the mismatch ratio by a ratio occupied by the mismatch area in the entire area of the captured image.

The calculation module may calculate the mismatch rate by the number of mismatch areas displayed in the entire area of the captured image.

In addition, the calculation module may calculate the discordance rate using an object recognition technique including an image recognition technique by deep-running the disparity area displayed in the entire area of the captured image.

The condition evaluation unit may include a customer evaluation module that evaluates a customer's use state with respect to the vehicle according to the mismatch ratio output from the output module; And a car selection module for selecting a car grade for the vehicle according to the mismatch ratio output from the output module.

The customer evaluation module may provide the customer with a discount for the use of the vehicle when the mismatch rate output from the output module is less than or equal to a predetermined value and if the mismatch rate exceeds the preset value, Can be imposed.

In addition, the car wash selection module selects a car wash grade corresponding to the section in which the discordance rate output from the output module belongs, after selecting the discordance rate section for the shot image and the set image and the car wash grade matched to each section, And can be provided to the vehicle manager.

The state evaluation unit may include: a lost and found item checking module for checking whether a lost or stolen item is present in the vehicle; A lost-material storage module storing a plurality of images of the lost material; And a failure checking module for checking whether the vehicle is damaged. The output module outputs a mismatch area between the photographed image and the set image searched by the comparing module, And the damage confirmation module checks the mismatch area output from the output module by the object recognition technique if the mismatch area is matched with the image of the lost material stored in the lost material storage module, It is possible to determine whether or not the vehicle is used.

In addition, when the state evaluating unit can not evaluate the state of use of the vehicle, the state transfer unit may transmit only the taken image photographed by the vehicle photographing unit to the manager server so that the vehicle manager can directly evaluate the state.

As described above, according to the in-vehicle image recognizing apparatus of the present invention, it is possible to provide an in-vehicle image recognizing apparatus and an in- There is an effect that the use state of the vehicle after the use can be evaluated by comparing the set images photographed inside the vehicle with each other.

In addition, the present invention provides a discount benefit to customers who cleanly use the vehicle according to the use state of the vehicle, and a penalty is paid to the customers who do not use the vehicle cleanly. In accordance with the cleanliness rating system, Thereby providing the customer with the cleanliness of the vehicle to be used, thereby enabling the customer to be actively cleaned and kept clean.

Further, according to the present invention, the car wash cost can be reduced by selecting the car wash grade according to the use state of the vehicle and proceeding the optimum car wash according to the car grade. In other words, it is not an unconditional car wash, but it carries out car washing only at necessary moment, and if it is not so dirty, it carries out car wash using low-cost non-professional carpenters such as part-time manpower In addition, it is possible to reduce the cost by introducing a service that recognizes the status of the dirty car by the next customer and then cleans himself and discounts the car.

In addition, the present invention has an effect that the vehicle manager can notify the customer of the lost item by checking the lost item when the lost vehicle exists in the vehicle after use.

Further, the present invention can compare the setting image before use of the vehicle, the image taken after the vehicle use, the car wash and the image taken after the internal inspection is completed to check the state of the vehicle after use, It is also possible to make aging judgment by changing the state.

In addition, the present invention minimizes the dispute between the customer and the company through the monitoring of the damage inside the vehicle, and when the autonomous vehicle is commercialized and the shared car culture is further activated, the internal inspection of the vehicle is carried out from time to time, And the like can be effectively utilized.

1 is a configuration diagram of an in-vehicle image recognition apparatus according to the present invention.
2 is a configuration diagram of a vehicle photographing section according to the present invention.
3 is a first embodiment of a vehicle photographing unit according to the present invention.
4 is a second embodiment of a vehicle photographing section according to the present invention.
5 is a configuration diagram of an image analysis unit according to the present invention.
6 is a first exemplary view of a shot image and a set image to be compared in the comparison module according to the present invention.
7 is a second exemplary view of a shot image and a set image to be compared in the comparison module according to the present invention.
8 is a configuration diagram of a state evaluation unit according to the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. First, it should be noted that the same components or parts among the drawings denote the same reference numerals whenever possible. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted so as not to obscure the subject matter of the present invention.

1 is a configuration diagram of an in-vehicle image recognition apparatus according to the present invention.

As shown in FIG. 1, an apparatus for recognizing an in-vehicle image according to the present invention includes a vehicle photographing unit 100, an image analyzing unit 200, a state evaluating unit 300, and a status transmitting unit 400.

The present invention can be operated when there is no customer inside the vehicle in a state that the vehicle is returned to the garage.

The vehicle photographing unit 100 may photograph the inside of the vehicle to generate a photographed image inside the vehicle, in order to check the use state of the vehicle after the customer uses the vehicle.

2 is a configuration diagram of a vehicle photographing section according to the present invention.

2, the vehicle photographing unit 100 includes a rail 110, a camera 120, a tilt member 130, a sensing member 140, and a control member 150, which are movement guide members. . ≪ / RTI >

The rails 110 may be installed on the inner ceiling of the vehicle. The rails 110 may be installed along the longitudinal direction of the vehicle to move the camera 120, which will be described later, in the longitudinal direction of the vehicle.

Here, the rail 110 is installed not only in the longitudinal direction but also in the lateral direction of the vehicle, so that the camera 120 can be moved in the lateral direction of the vehicle. Further, the rail 110 is curved, Can be moved through the rail.

3 is a first embodiment of a vehicle photographing unit according to the present invention.

As shown in FIG. 3, the camera 120 may be installed directly on the rail 110, move along the rail, and photograph the interior of the vehicle to generate the photographed image. At this time, the rail 110 may protrude as shown in FIG. 3 or be inserted into the ceiling.

Specifically, the camera 120 may use a black box installed in the vehicle, or a separate camera may be mounted on the vehicle. The camera 120 may be mounted on the vehicle 120 while moving along the longitudinal and lateral directions of the vehicle. A driver's seat and a passenger seat in one row, and both seats in two rows of the vehicle are sequentially photographed to generate a photographed image matched with the corresponding column.

When the vehicle is, for example, three rows or a trunk in the boarding space, the camera 120 sequentially photographs the seats and trunks of the three rows of the vehicle, Can be generated.

On the other hand, the camera 120 can be moved through the rail 110 installed on the ceiling if there is a sunroof in the vehicle ceiling or other devices.

4 is a second embodiment of a vehicle photographing section according to the present invention.

4, the tilt member 130 is installed between the rail 110 and the camera 120. The tilt member 130 is installed directly on the rail and moves along the rail to move the camera 120 in various directions And rotate. At this time, the rail 110 may be changed according to characteristics of the sunroof mounted vehicle or the vehicle, not a straight line. Such a rail 110 may be a curved shape rather than a straight line, And can be installed in various forms in accordance with the characteristics of the vehicle.

Specifically, the tilt member 130 can change the photographing angle of the camera by tilting the camera at a specific angle on the rail at a certain angle, thereby allowing the camera 120 to photograph the inside of the vehicle at various angles, It is possible to generate various photographed images for the inside.

The sensing member 140 may be installed in the camera to sense the internal environment of the vehicle including the illuminance and contrast of the interior of the vehicle. The sensing member 140 may include various sensors capable of sensing brightness, The control member 150 may be connected to the control member 150 to transmit the sensing result to the control member 150. [

The control member 150 may be connected to the camera and the tilt member to drive the camera and the tilt member, respectively. In this case, the control member 150 may include a sensing member 140 and a vehicle interior (Not shown) provided in the illumination unit (not shown) to control the corresponding illumination according to the resultant value sensed by the sensing member.

For example, when the sensed value of the sensing member 140 belongs to a specific section after setting various intervals of the brightness of the interior of the vehicle, the control member 150 may match the corresponding section It is possible to easily generate the photographed image by controlling the brightness of the inside of the vehicle automatically even when the brightness of the inside of the vehicle is low by controlling the lighting with the brightness.

In addition, the control member 150 can receive the photographed image value of the camera or the position value of the camera from the camera to grasp the exact position of the camera, and move the camera along the rail.

That is, a command for moving the camera along the rails in order to move to a predetermined position and take a photograph is also made in the control member, and a command for tilting and rotating the camera to photograph a specific position can also be performed in the control member.

Thus, the control member 150 can move the position of the camera, change the tilt of the camera, change the illumination, and change the angle through the rotation of the camera.

Meanwhile, in the present invention, a method of moving a camera is used. In the case of a motor fixed type, a method of moving a rail such as a string or a chain in a fixed motor and pulling the camera while moving the camera, And moving it along the rail directly can be used.

The image analyzing unit 200 may compare the captured image captured by the vehicle photographing unit 100 with the preset image set in the vehicle, and calculate the discordance rate between the captured image and the set image.

 Here, the set image is an image taken inside the vehicle before use of the vehicle. Such a set image may be set to a vehicle image in a state where there is no contamination right after the car was washed. As described later, May be stored in the storage module 250 in advance.

In addition, the photographed image may be a still image taken by the camera at a specific position, or may be a stereoscopic image or an image photographed while the camera moves at a constant speed.

5 is a configuration diagram of an image analysis unit according to the present invention.

5, the image analysis unit 200 includes an input module 210, a comparison module 220, a calculation module 230, an output module 240, and a storage module 250 can do.

The input module 210 may be connected to the camera 120 and the storage module 250, respectively, and may receive a captured image captured by the camera and a set image previously stored in the storage module.

The comparison module 220 may compare the captured image and the set image input to the input module with each other and analyze the captured image and the mismatch area between the captured image and the set image.

Specifically, the comparison module 220 may compare the colors of the photographed image and the set image with each other, thereby searching for a region in which the color difference between the photographed image and the set image is generated, as a mismatch area.

In addition, the comparison module 220 can detect the inconsistency and the object recognition information. For example, in the case of a small object such as a cigarette butt, the degree of inconsistency is small, but a large penalty is imposed through object recognition Or the score of the foreign object can be made higher, and the recognition rate of the object can be increased by recognizing the change value in the image by utilizing the 3d sensor (depth recognition sensor) such as the Lada sensor and the infrared sensor.

6 is a first exemplary view of a shot image and a set image to be compared in the comparison module according to the present invention.

As shown in FIG. 6, for example, the comparison module 220 compares the setting image (a) of the first row of the vehicle with the shooting image (b) If a region in which a difference is found is found, the region can be searched as a mismatch region.

7 is a second exemplary view of a shot image and a set image to be compared in the comparison module according to the present invention.

7, the comparison module 220 compares the setting image (a) of the second row of the vehicle with the image of the image (b), and as a result, The central seat front portion, and the left seat portion, the corresponding region can be searched as a mismatch region.

6 and 7, when a specific object is located in a specific area of the photographed image, the comparison module 220 determines the corresponding area as a region where a color or depth difference occurs, You can search.

Meanwhile, the comparison module 220 can be programmed to search for a region of interest in a mismatched region even if a specific object is not located in a specific region of the photographed image.

6 and the right seat of FIG. 7, even when a separate object is not positioned, for example, when a specific area of the seat is contaminated with foreign matter, It is possible to determine such a contaminated area as an area in which a color difference has occurred and search the corresponding area as a non-matching area.

The calculation module 230 may calculate the mismatch ratio between the photographed image and the set image according to the mismatch area searched by the comparison module.

Specifically, the calculation module 230 may calculate the mismatch ratio by the ratio of the mismatch area occupied by the entire area of the photographed image. The mismatch ratio may be a ratio of the total area of the photographed image to the total area of the mismatch area Can be calculated.

For example, when the total area of the photographed image is assumed to be 100, when the total area of the inconsistent areas is 10, the relative area ratio of these two areas of 10% can be calculated as the inconsistency rate.

In addition, the calculation module 230 may calculate an inconsistency rate by the number of inconsistent areas displayed in the entire area of the photographed image. The inconsistency rate may be calculated based on the assumption that the inconsistency rate increases as the number of inconsistent areas increases , The inconsistency rate can be calculated by applying a function to which the principle and various variable conditions are added to the calculation module.

That is, the result of the discordance rate can be calculated by using the discordance area (range), the discordance degree (intensity), the discordance degree of depth recognition, and the discordance evaluation result through object recognition, Position shift, angle change, seatbelt position change, sidebar position change, etc., may not be included in the determination of inconsistency due to the change using the image learning logic. In addition, the inconsistency recognition method may be applied in various ways.

In addition, the calculation module 230 may calculate the mismatch rate by mixing the ratio of the mismatch area occupied by the entire area of the photographed image with the number of the mismatch areas displayed by the entire area of the photographed image.

The output module 240 may output the inconsistency rate calculated by the calculation module and then transmit the inconsistency rate to the state evaluator 300 described later.

In addition, the output module 240 may output a mismatch area between the photographed image and the set image searched by the comparison module, and then transmit the mismatch rate to the state evaluator 300, which will be described later.

As described above, the storage module 250 may store a predetermined setting image in the vehicle and provide the setting image to the input module 210. [

The state evaluation unit 300 may evaluate the state of use of the vehicle after use according to the analysis result of the image analysis unit 200. [

8 is a configuration diagram of a state evaluation unit according to the present invention.

8, the state evaluating unit 300 includes a customer evaluation module 310, a car wash selection module 320, a lost and found item confirmation module 330, a lost and stolen item storage module 340, (350).

The customer evaluation module 310 is connected to the output module 240 and can evaluate the customer's use state of the vehicle according to the mismatch ratio output from the output module 240.

Specifically, the customer evaluation module 310 can provide discounts for vehicle use to the customer when the mismatch ratio output from the output module is less than a predetermined value. So that it is possible to actively clean and maintain cleanliness of the customer.

For example, the customer evaluation module 310 may set the mismatch rate to 5% as a reference set value for providing discount benefits. If the mismatch rate output from the output module is 5% or less, Can be evaluated as "good" and the cost of using the vehicle can be discounted. At this time, the discount rate for the customer can be increased as the inconsistency rate decreases.

On the other hand, the customer evaluation module 310 may not discount the vehicle use cost by evaluating the use state of the customer as "bad " when the inconsistency rate exceeds 5% If it is not very clean, you can charge an additional fee on the basis of the photographic image. At this time, in addition to the inconsistency rate, for example, the cleanliness of the user through object recognition, such as dust-5, food-10, and cigarette butt-20, can be evaluated at the same time.

The car wash selection module 320 may be connected to the output module 240 to select the car grade for the vehicle according to the mismatch ratio output from the output module 240.

Specifically, the car wash selection module 320 may select various inconsistency rate intervals for the photographed image and the set image, and a car wash grade matched to each section. If the inconsistency rate belongs to a specific section among the various inconsistency rate sections, it is possible to provide the vehicle manager with a car class that matches the section, thereby allowing the car manager to carry out the optimal car wash according to the grade to reduce the car wash cost Or if the next user is informed, a discounted system can be used to reduce car wash costs.

The lost material confirmation module 330 can confirm to the vehicle manager whether or not the lost object is lost in the vehicle.

Specifically, when the discrepancy area between the photographed image and the set image output from the output module 240 is matched with the image of the lost item stored in the lost image storage module 340, The user can notify the customer of the lost item if the lost item is present in the vehicle, or the user can judge whether the lost item is a garbage such as a book, a ring, or a mobile phone by recognizing the image through object recognition, for example, If an object exists, it can be judged to be a lost item and notified.

That is, if the matching rate of the mismatch area and the lost article stored in the lost article storage module 340 is equal to or greater than a predetermined matching rate, the lost article confirmation module 330 determines that there is a high possibility that the lost article exists in the vehicle, To the vehicle manager. Here, the matching rate for confirming the presence or absence of the lost item may be variously changed by the vehicle manager.

The damage confirmation module 350 can confirm to the vehicle manager whether the vehicle is damaged or not.

Specifically, the damage confirmation module 350 may notify the vehicle manager of whether the vehicle is damaged through object recognition by detecting a mismatch area between the shot image and the set image output from the output module 240.

Meanwhile, the status transferring unit 400 transmits a shot image photographed by the vehicle photographing unit 100 and an evaluation result evaluated by the state evaluating unit 300 to the manager server, And can provide shot images and evaluation results.

In addition, when the status evaluation unit 300 itself is difficult to evaluate, the status transmission unit 400 may transmit the shot image taken by the vehicle image pickup unit 100 to the manager server so that the vehicle manager can directly evaluate the image .

As described above, according to the present invention, by comparing the photographed image photographed inside the vehicle after use of the vehicle with the set image photographed inside the vehicle before use of the vehicle or the reference image photographed after the car wash, , It is possible to provide the discount benefit by feeding back the cleanliness of the use through the system such as the use cleanliness score to the customer who uses the cleanliness of the vehicle and by selecting the car grade according to the use state of the vehicle, It is possible to reduce the car wash cost and increase the customer satisfaction. Also, when there is a lost item in the vehicle after use, the vehicle manager can identify the lost item by notifying the customer of the lost item. In addition, We can minimize disputes between customers and companies through monitoring, If you come yulju commercialized shared car culture has become more active, you can take advantage of positive information on the monitoring of progress from time to time to check the inside of the car wash, Lost, damage or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It will be understood that various modifications may be made by those skilled in the art.

100: vehicle photographing unit 110: rail
120: camera 130: tilt member
140: sensing member 150: control member
200: image analysis unit 210: input module
220: comparison module 230: calculation module
240: output module 250: storage module
300: status evaluation unit 310: customer evaluation module
320: Car wash selection module 330: Lost & Found module
340: Lost and Found Storage Module 350: Failure Verification Module
400:

Claims (14)

  1. A vehicle photographing section photographing the interior of the vehicle;
    An image analyzer for comparing and analyzing a captured image photographed by the vehicle photographing unit and a preset image set in the vehicle;
    A state evaluating unit for evaluating a state of use of the vehicle according to an analysis result of the image analyzing unit; And
    And a status transmission unit for transmitting the shot image photographed by the vehicle photographing unit and the evaluation result evaluated by the state evaluation unit to the manager server,
    The vehicle photographing unit
    A moving guide member including a rail installed on a ceiling of the vehicle; And a camera installed on the rail and photographing the inside of the vehicle while moving the rail,
    The image analysis unit may include:
    A storage module for storing the setting image; An input module for receiving a captured image captured by the camera and a set image stored in the storage module, respectively; A comparison module for comparing the shot image and the set image input to the input module with each other to search for a mismatch area between the shot image and the set image; A calculation module for calculating a mismatch ratio between the photographed image and the set image according to the mismatch area searched by the comparison module; And an output module outputting the inconsistency rate calculated in the calculating module,
    The state evaluating unit may include:
    A customer evaluation module for evaluating a customer's use state of the vehicle according to a mismatch ratio output from the output module; And a car selection module for selecting a car grade for the vehicle according to a mismatch ratio output from the output module.
  2. The method according to claim 1,
    The camera comprises:
    A black box installed in the vehicle, a camera separately mounted on the vehicle, or a depth recognition sensor.
  3. The method according to claim 1,
    The vehicle photographing unit
    A tilt member installed between the rail and the camera for tilting and rotating the camera to change an angle of the camera; And
    Further comprising a control member connected to the camera and the tilt member to drive the camera and the tilt member, respectively.
  4. The method of claim 3,
    The vehicle photographing unit
    Further comprising: a sensing member installed in the camera for sensing illuminance and contrast within the vehicle,
    Wherein the control member controls the illumination installed inside the vehicle according to a result of sensing by the sensing member.
  5. delete
  6. The method according to claim 1,
    Wherein the comparison module comprises:
    Wherein the color matching unit compares the color of the shot image with the color of the set image to search for an area where color or depth difference has occurred in the entire area of the shot image as the unmatch area.
  7. The method according to claim 6,
    Wherein the calculation module comprises:
    And calculates the incoincidence rate by a ratio occupied by the inconsistency area in the entire area of the photographed image.
  8. The method according to claim 6,
    Wherein the calculation module comprises:
    And calculates the incoincidence rate by the number of the inconsistent areas displayed in the entire area of the photographed image.
  9. The method according to claim 6,
    Wherein the calculation module comprises:
    Wherein the inconsistency rate is calculated using an object recognition technique including an image recognition technique by deep-running the disparity area displayed in the entire area of the captured image.
  10. delete
  11. The method according to claim 1,
    The customer evaluation module,
    Providing a discount benefit for vehicle use to the customer when the mismatch rate output from the output module is less than a predetermined value,
    And imposes a penalty when the inconsistency rate exceeds the preset value.
  12. 12. The method of claim 11,
    The car wash selection module,
    A mismatch rate section for the shot image and a set image, and a car class to match each section,
    Wherein the vehicle classifier provides the vehicle class manager with a class of car that matches an interval to which the discordance rate that is output from the output module belongs.
  13. 13. The method of claim 12,
    The state evaluating unit may include:
    A lost material confirmation module for confirming whether the lost vehicle is present in the vehicle;
    A lost-material storage module storing a plurality of images of the lost material; And
    Further comprising a damage check module for checking whether the vehicle is damaged,
    Wherein the output module outputs a mismatch area between the photographed image and the set image retrieved from the comparison module,
    Wherein the lossy confirmation module checks the presence or absence of the lossy material to the vehicle manager when the mismatch area output from the output module matches an image of the lost material stored in the lost material storage module,
    Wherein the damage confirmation module uses the object recognition technique to determine whether the vehicle is in the mismatch area output from the output module.
  14. 14. The method of claim 13,
    Wherein the status transmission unit comprises:
    When the state evaluation unit fails to evaluate the use state of the vehicle,
    Wherein only the captured image photographed by the vehicle photographing section is transmitted to the manager server so that the vehicle manager can directly evaluate the photographed image.
KR1020180031498A 2018-03-19 2018-03-19 Image recognition apparatus in the inside of vehicle KR102005956B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020180031498A KR102005956B1 (en) 2018-03-19 2018-03-19 Image recognition apparatus in the inside of vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020180031498A KR102005956B1 (en) 2018-03-19 2018-03-19 Image recognition apparatus in the inside of vehicle

Publications (1)

Publication Number Publication Date
KR102005956B1 true KR102005956B1 (en) 2019-07-31

Family

ID=67473956

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020180031498A KR102005956B1 (en) 2018-03-19 2018-03-19 Image recognition apparatus in the inside of vehicle

Country Status (1)

Country Link
KR (1) KR102005956B1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20100058180A (en) * 2008-11-24 2010-06-03 주식회사 유디코 System and method for detecting disaster occurrence
KR101115944B1 (en) 2004-09-06 2012-02-13 바이에리셰 모토렌 베르케 악티엔게젤샤프트 Device for the detection of an object on a vehicle seat
JP2012069022A (en) * 2010-09-27 2012-04-05 Hitachi Ltd Monitoring system
KR20160043435A (en) * 2014-10-13 2016-04-21 엘지전자 주식회사 Apparatus for providing under vehicle image and vehicle including the same
KR101789690B1 (en) * 2017-07-11 2017-10-25 (주)블루비스 System and method for providing security service based on deep learning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101115944B1 (en) 2004-09-06 2012-02-13 바이에리셰 모토렌 베르케 악티엔게젤샤프트 Device for the detection of an object on a vehicle seat
KR20100058180A (en) * 2008-11-24 2010-06-03 주식회사 유디코 System and method for detecting disaster occurrence
JP2012069022A (en) * 2010-09-27 2012-04-05 Hitachi Ltd Monitoring system
KR20160043435A (en) * 2014-10-13 2016-04-21 엘지전자 주식회사 Apparatus for providing under vehicle image and vehicle including the same
KR101789690B1 (en) * 2017-07-11 2017-10-25 (주)블루비스 System and method for providing security service based on deep learning

Similar Documents

Publication Publication Date Title
CN105022397B (en) For using multiple sensors to carry out the method and system of object detection
US10328932B2 (en) Parking assist system with annotated map generation
CN106461400B (en) Use the vehicle location determination or navigation of linked character pair
US20170203744A1 (en) Systems and methods for braking a vehicle based on a detected object
CN106448260B (en) Driver assistance and vehicle including the driver assistance
CA2967638C (en) System and method for detecting a vehicle event and generating review criteria
CN103879402B (en) For permitting driver assistance system and the method that garage that is autonomous or leading control stops
US8947260B2 (en) Parking assistance system
US10262217B2 (en) Controlling host vehicle based on detected door opening events
KR101924649B1 (en) Determining a pixel classification threshold for vehicle occupancy detection
JP6281492B2 (en) Passenger counting device, method and program
JP6552670B2 (en) Image transmission device
CN103959041B (en) Attachment detector and attachment detection method
CA2599002C (en) Entry control point device, system and method
CN105182535B (en) The method that automobile maintenance is carried out using intelligent glasses
EP1955302B1 (en) Parking control system and method
US20160358474A1 (en) Parking assist method and system
US8855364B2 (en) Apparatus for identification of an object queue, method and computer program
DE102011077173A1 (en) Method for determining a parking trajectory
CN106228835B (en) A kind of parking stall Parking judgment method and system
US8892293B2 (en) Transport facility for autonomous navigation and method for determining damage to a motor vehicle
ES2274597T3 (en) Motor vehicle and its key-card device.
CN103985270A (en) Parking lot control system
CN102551591B (en) Cleaning robot and control method thereof
US20140232852A1 (en) Optical device and method for inspecting tires

Legal Events

Date Code Title Description
GRNT Written decision to grant