KR102482359B1 - System and method of diffusing perfume based on black box of vehicle - Google Patents

Abstract

According to a diffuser system and a diffuser method based on a black box image of a vehicle according to embodiments of the present invention, the system includes a photographing unit for photographing the inside and outside of a vehicle, an image analysis unit for analyzing an image received from the photographing unit, and an image analysis unit. and a diffuser unit for injecting the selected fragrance in the form of a mist based on the analysis result in the unit. Therefore, according to the present invention, fragrance is selectively sprayed based on the black box image taken inside and outside of the vehicle to arouse the driver's attention while driving for a long time or spray the fragrance to suit the driver who wants to feel the external environment from the inside of the vehicle. can do.

Description

System and method of diffusing perfume based on black box of vehicle {System and method of diffusing perfume based on black box of vehicle}

The present invention relates to a diffuser system and a diffusing method, and more particularly, to a diffuser system based on a black box image of a vehicle and a diffuser method for selectively dispensing a scent matching the image based on the black box image of the vehicle. will be.

Various car air freshener products to ventilate the scent and smell in the car have been released for a long time. However, air freshener products for vehicles have been developed focusing on the function of maintaining the scent for a long time or easily replacing the product.

In addition, the market for vehicle air purifiers and portable air purifiers for purifying vehicle air in order to improve the driver's driving environment is growing significantly. Such vehicle air purifiers have been developed focusing on implementing various air purifying methods, diversifying structures that can be installed in vehicles, and implementing customized air purifying functions according to external temperature and humidity.

A product that implements both an air cleaning function and a fragrance function by combining such a vehicle air purifier with a fragrance has recently been released.

However, even these combined products do not spray fragrance suitable for the external environment, and are limited to the level of spraying only the fragrance selected by the user or the fragrance installed in the product.

Korean Patent Publication No. 2019-0125814 (2019.11.07) Korean Patent Publication No. 2019-0014363 (2019.02.12)

The present invention has taken this problem into account, and the present invention selectively sprays fragrance based on the black box image taken inside and outside of the vehicle to arouse the attention of drivers who drive for a long time or who want to feel the external environment from the inside of the vehicle. It is to provide a diffuser system based on a black box image of a vehicle that sprays fragrance according to the driver.

The present invention provides a diffuser method based on a black box image of a vehicle for refreshing the driver's mood by injecting a scent matching the external environment to the driver through the diffuser system as described above.

A diffuser system based on a black box image of a vehicle according to embodiments of the present invention is based on a photographing unit that photographs the interior and exterior of a vehicle, an image analysis unit that analyzes an image received from the photographing unit, and an analysis result from the image analysis unit. and a diffuser unit for spraying the selected fragrance in the form of a mist.

In embodiments of the present invention, the photographing unit includes a first photographing unit for photographing the exterior of the vehicle, a second photographing unit for photographing the interior of the vehicle, and photographs taken by the first photographing unit and the second photographing unit. It consists of an image delivery unit that generates images as still cuts and transmits them to the image analysis unit. At this time, in the case of a streaming image captured by the first photographing unit while the vehicle is moving, the image transmission unit generates a still cut through screen capture according to a preset cycle and transmits it to the image analysis unit. to be

In embodiments of the present invention, when the image transfer unit generates a still cut of a streaming image captured by the first capture unit while the vehicle is moving, the screen capture cycle of the streaming image is changed according to the speed of the vehicle You can create still cuts.

In embodiments of the present invention, the image analysis unit analyzes an external still cut of an external image captured by the first capturing unit and an internal still cut of an internal image captured by the second capturing unit.

In embodiments of the present invention, the image analysis unit receives an illuminance value from an illuminance sensor provided in a vehicle, and when the received illuminance value is greater than or equal to a previously set illuminance value, the external image of the first capturing unit is received. The image is analyzed by assigning a weight to the still cut, and if the received illuminance value is less than a preset illuminance value, the image is analyzed by assigning a weight to the internal still cut for the internal image of the second photographing unit. do. In this case, when the image analyzer assigns a weight to an internal still cut of the internal image of the second photographing unit because the illuminance value received from the illuminance sensor provided in the vehicle is less than or equal to a preset illuminance value, the vehicle is boarded. The video can be analyzed considering the number of people, passenger information, and time information.

In the embodiments of the present invention, the image analysis unit selects a scent related to a specific still cut by learning the still cut received from the image delivery unit with a convolutional neural network (CNN).

In embodiments of the present invention, the image analysis unit includes an image input unit for receiving an image from a photographing unit, an image analysis unit for interpreting the image input to the image input unit, and an image for classifying the image analyzed by the image analysis unit. It includes a classification unit and a fragrance selection unit that selects a scent that matches the image classified by the image classification unit.

In embodiments of the present invention, the diffuser unit includes a control unit that receives the analysis result of the image analyzer and selects a fragrance, and a dispensing unit that injects at least one fragrance selected by the controller into the interior of the vehicle. At this time, the injection unit is characterized in that the liquid discharged from the incense storage unit separately stored in a liquid state for each incense is sprayed in the form of a mist through an ultrasonic vibrator.

According to the diffusing method based on the black box image of the vehicle according to other embodiments of the present invention, the step of photographing the inside and outside of the vehicle by the photographing unit, the step of analyzing the image received from the photographing unit by the image analysis unit, and the step of and spraying the selected scent in the form of a mist based on the analysis result of the image analyzer.

In embodiments of the present invention, after the step of photographing the interior and exterior of the vehicle by the photographing unit, still cut images are generated by the image transmission unit provided in the photographing unit and transmitted to the image analysis unit. do.

In the embodiments of the present invention, when the video transmission unit generates a still cut of an external streaming image captured while the vehicle is moving, the still cut is generated by changing the screen capture cycle of the streaming image according to the speed of the vehicle. do.

In embodiments of the present invention, in the step of analyzing the image received from the image capturing unit by the image analysis unit, if the received illuminance value is greater than or equal to a preset illuminance value, a weight is applied to the external still cut of the external image. If the received illuminance value is less than or equal to a preset illuminance value, the image is analyzed by assigning a weight to an internal still cut of the internal image. At this time, when the illuminance value transmitted from the illuminance sensor provided in the vehicle is less than or equal to the previously set illuminance value, so that a weight is given to the internal still cut for the internal image, the image analyzer determines the number of occupants of the vehicle and the occupant information. , the image can be analyzed considering the time information.

In the embodiments of the present invention, in the step of analyzing the image delivered by the image analysis unit from the photographing unit, the image analysis unit learns the still cut received from the image delivery unit with a convolutional neural network (CNN) to obtain a specific still image. Select the scent related to the cut.

According to the diffuser system and the diffuser method based on the black box image of the vehicle as described above, the following effects are obtained.

First, the present invention is a system for injecting fragrance into the interior of a vehicle based on an image taken of the exterior of the vehicle, and not only awakens the driver's attention, but also allows the driver to feel the external environment from the inside of the vehicle.

Second, by injecting fragrance into the vehicle based on the image of the interior of the vehicle according to the present invention, the driver can focus on driving in a comfortable environment.

Third, it is possible to improve the analysis result of the captured image by changing the period of interpreting or classifying the captured image according to the moving speed of the vehicle and the degree of change in the captured image, and changing the image analysis method.

Fourth, by analyzing and classifying the car's black box image with a convolutional neural network (CNN), the accuracy of the image analysis result can be increased over time.

1 and 2 are configuration and conceptual diagrams for explaining a diffuser system based on a black box image of a vehicle according to embodiments of the present invention.
Figure 3 is a configuration diagram for explaining the photographing unit of Figure 1
Figure 4 is a configuration diagram for explaining the image analysis unit of Figure 1
5 is a configuration diagram for explaining the diffuser unit of FIG. 1
6 is a flowchart for explaining a diffusing method based on a black box image of a vehicle according to embodiments of the present invention.

A diffuser system and a diffuser method based on a black box image of a vehicle according to embodiments of the present invention will be described in detail with reference to the accompanying drawings. Since the present invention can have various changes and various forms, specific embodiments will be illustrated in the drawings and described in detail in the text. However, this is not intended to limit the present invention to a specific form disclosed, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. Like reference numerals have been used for like elements throughout the description of each figure. In the accompanying drawings, the dimensions of the structures are shown enlarged than actual for clarity of the present invention, or reduced than actual in order to understand the schematic configuration.

Also, terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. Meanwhile, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

1 and 2 are configuration and conceptual diagrams for explaining a diffuser system based on a black box image of a vehicle according to embodiments of the present invention. 3 is a configuration diagram for explaining the photographing unit of FIG. 1 , FIG. 4 is a configuration diagram for explaining the image analysis unit of FIG. 1 , and FIG. 5 is a configuration diagram for explaining the diffuser unit of FIG. 1 .

1 to 5, the diffuser system 10 based on the black box image of the vehicle according to the embodiments of the present invention selectively sprays fragrance based on the black box image taken inside and outside of the vehicle to drive for a long time. It is to arouse the driver's attention or to inject fragrance to suit the driver who wants to feel the external environment from the inside of the vehicle.

To this end, the system 10 includes a photographing unit 100, an image analysis unit 200, and a diffuser unit 300.

The photographing unit 100 photographs the inside and outside of the vehicle. For example, the photographing unit 100 may be a black box provided in a vehicle, or may be a camera mounted in a vehicle separately from the black box.

The photographing unit 100 includes a first photographing unit 110 for photographing the exterior of the vehicle, a second photographing unit 120 for photographing the interior of the vehicle, the first photographing unit 110 and the second photographing unit 120 ) It consists of an image transmission unit 130 that generates still cuts of images taken in and transmits them to the image analysis unit 200 .

In embodiments of the present invention, the image delivery unit 130 provided in or connected to the black box for a vehicle captures images taken inside and outside of the vehicle and generates still cuts. Accordingly, the image analysis unit 200 may reduce the time required to analyze the video by transmitting the still cut to the image analysis unit 200 without transmitting the streaming video or the recorded video from the photographing unit 100 .

In particular, in the case of a streaming image captured by the first capture unit 110 while the vehicle is moving, the image delivery unit 130 creates a still cut through screen capture according to a pre-set cycle to the image analysis unit. (200). In particular, when generating a still cut of a streaming image captured by the first capture unit 110 while the vehicle is moving, the image transfer unit 130 changes the screen capture period of the streaming image according to the speed of the vehicle to capture the still image. cuts can be made. That is, when the speed of the vehicle is high, the image transfer unit 130 captures the external image at a shorter cycle to generate a still cut.

On the other hand, the image transfer unit 130 generates still cuts according to a preset cycle of the interior image captured by the second capture unit 120 that takes pictures of the interior of a vehicle that does not change significantly, and the capture cycle has a large change. It will be said that it is free even if there is not.

The image analysis unit 200 analyzes the image transmitted from the photographing unit 100 . At this time, the image analysis unit 200 analyzes an external still cut of an external image captured by the first capture unit 110 and an internal still cut of an internal image captured by the second capture unit 120 . At this time, the image analysis unit 200 may apply a little more weight to the external image of the first screen capture unit 110 for analysis.

Meanwhile, the image analyzer 200 receives an illuminance value from an illuminance sensor provided in the vehicle, and if the received illuminance value is greater than or equal to a preset illuminance value, the external still cut of the external image of the first capture unit 110 If the received illuminance value is less than or equal to a preset illuminance value, the image may be analyzed by assigning a weight to an internal still cut of the internal image of the second capture unit 120. .

That is, the image analyzer 200 performs analysis by focusing on the external image during the day when the illuminance value is high, and analyzes the image by focusing on the internal image at night when the illuminance value is low. At this time, when the illuminance value transmitted from the illuminance sensor provided in the vehicle is less than or equal to the previously set illuminance value, and weight is given to the internal still cut for the internal image of the second photographing unit 120, the image analyzer 200 ) may analyze the image in consideration of the number of occupants of the vehicle, occupant information, and time information. For example, in the case of night when the illumination value is low, when there are a plurality of passengers in the internal image captured by the second photographing unit 120, whether the passengers are adults, gender information, and time information (night, dawn) It is to analyze the image taking into account.

In embodiments of the present invention, the image analyzer 200 selects a scent related to a specific still cut by learning the still cut received from the image delivery unit 130 with a convolutional neural network (CNN).

To this end, the image analysis unit 200 includes an image input unit 210 for receiving an image from the photographing unit 100, an image analysis unit 220 for analyzing an image input to the image input unit 210, and an image analysis unit ( An image classification unit 230 that classifies the image analyzed in 220) and a fragrance selection unit 240 that selects a fragrance matching the image classified by the image classification unit 230.

In other embodiments of the present invention, the image analysis unit 200 sets an image corresponding to a specific environment, for example, a mountain and the sea, among image information from the photographing unit 100 as an object, and when the mountain and the sea appear, The photographing unit 100 is controlled in such a way as to capture an image, or the image analysis unit 200 analyzes and determines an image based on a reference image or input information such as color, size, and appearance based on an input image. You may.

In other embodiments of the present invention, the image transmission unit 130 of the photographing unit 100 uses a specific color based on a pre-input threshold value or a threshold value, boundary value, etc. input through learning, When it is determined that the image corresponds to the mountain and the sea, the corresponding image may be captured and generated as a still cut. At this time, the image analysis unit 200 compares the image received from the photographing unit 100 with a reference image to determine the degree of similarity of the corresponding image, and may spray incense when the degree of similarity is greater than or equal to a threshold value. there is.

In still other embodiments of the present invention, the video analyzer 200 comprehensively interprets information received from the outside, including vehicle location information (GPS, etc.), season, and weather information, together with the analysis result to select a direction. can For example, even if the image analyzer 200 interprets the image as an image of the sea, different fragrances may be sprayed according to the corresponding season. Similarly, even if the image captured by the black box of the vehicle is the sea, if the location of the vehicle is on a road around a mountain near the sea, the direction may be selected by considering location information as well as image information.

The diffuser unit 300 sprays the selected fragrance in the form of a mist based on the analysis result of the image analyzer 200 . At this time, the diffuser unit 300 may be connected to and communicate with the image analyzer 200 through short-range communication.

The diffuser unit 300 includes a controller 310 that receives the analysis result of the image analyzer 200 and selects a fragrance, and a spray unit 320 that sprays at least one fragrance selected by the controller 310 into the vehicle. do.

The injection unit 320 is characterized in that the liquid discharged from the fragrance storage unit (not shown) separately stored in a liquid state for each fragrance is sprayed in the form of a mist through an ultrasonic vibrator.

6 is a flowchart illustrating a diffusing method based on a black box image of a vehicle according to embodiments of the present invention.

Referring to FIG. 6 , in the diffusing method based on a black box image of a vehicle according to embodiments of the present invention, a photographing unit photographs the interior and exterior of a vehicle (S10), and an image analysis unit analyzes an image received from the photographing unit. A step (S20) and a step (S30) of the spraying unit dispensing the selected scent in the form of a mist based on the analysis result of the image analyzing unit.

In the embodiments of the present invention, after the step of photographing the interior and exterior of the vehicle by the photographing unit, still cut images are generated by the image transmission unit provided in the photographing unit and transmitted to the image analysis unit characterized by In this case, when the video delivery unit generates a still cut of an external streaming image captured while the vehicle is moving, the still cut may be generated by changing a screen capture cycle of the streaming image according to the speed of the vehicle.

In embodiments of the present invention, in the step of analyzing the image received from the image capturing unit by the image analysis unit, if the received illuminance value is equal to or greater than a previously set illuminance value, the external still cut for the external image has a weighted value. If the received illuminance value is less than or equal to a previously set illuminance value, the image may be analyzed by assigning a weight to the internal still cut for the internal image. Further, when the illuminance value transmitted from the illuminance sensor provided in the vehicle is less than or equal to the preset illuminance value, so that a weight is given to the internal still cut for the internal image, the image analyzer determines the number of occupants of the vehicle, occupant information, time It is characterized in that the image is analyzed in consideration of the information.

In the step of analyzing the image received from the image capturing unit by the image analysis unit, the image analysis unit learns the still cut received from the image delivery unit with a convolutional neural network (CNN) and selects a scent related to a specific still cut.

The diffuser unit receives the analysis result of the image analysis unit and injects at least one selected fragrance into the vehicle. At this time, the diffuser unit may spray the liquid discharged from the incense storage unit (not shown) that separates and stores each incense in a liquid state in the form of a mist through an ultrasonic vibrator.

Although the detailed description of the present invention described above has been described with reference to preferred embodiments of the present invention, those skilled in the art or those having ordinary knowledge in the art will find the spirit of the present invention described in the claims to be described later. And it will be understood that the present invention can be variously modified and changed without departing from the technical scope.

10: Diffuser system based on vehicle's black box image
100: photographing unit 110: first photographing unit
120: second capture unit 130: image transfer unit
200: video segmentation unit 210: video input unit
220: image analysis unit 230: image classification unit
240: fragrance selection unit 300: diffuser unit
310: control unit 320: injection unit

Claims (16)

A photographing unit that photographs the inside and outside of the vehicle;
an image analysis unit that analyzes the image received from the photographing unit;
Including a diffuser unit for injecting a selected fragrance in the form of a mist based on the analysis result of the image analysis unit,
The filming department
a first photographing unit for photographing the exterior of the vehicle;
a second photographing unit for photographing the interior of the vehicle;
It consists of an image transfer unit that generates images captured by the first and second capture units as still cuts and transmits them to the image analysis unit;
The video delivery unit
In the case of a streaming image captured by the first photographing unit while the vehicle is moving, still cuts are generated through screen capture according to a preset cycle and transmitted to the image analysis unit,
The video analysis unit
Receiving an illuminance value from an illuminance sensor provided in the vehicle,
If the received illuminance value is greater than or equal to a previously set illuminance value, the external still cut for the external image of the first capturing unit is weighted and the image is analyzed;
A diffuser system based on a black box image of a vehicle, characterized in that for analyzing the image by assigning a weight to an internal still cut for the internal image of the second photographing unit when the received illuminance value is less than or equal to the preset illuminance value. delete The method of claim 1, wherein the image transfer unit
When the first photographing unit generates a still cut of a streaming image captured while the vehicle is moving, the still cut is generated by changing a screen capture cycle of the streaming image according to the speed of the vehicle. A diffuser system based on imaging. According to claim 1,
The video analysis unit
The diffuser system based on the black box image of the vehicle, characterized in that for analyzing the external still cut of the external image captured by the first photographing unit and the internal still cut of the internal image captured by the second photographing unit. delete The method of claim 1, wherein the image analysis unit
When the illuminance value transmitted from the illuminance sensor provided in the vehicle is less than or equal to the preset illuminance value, so that a weight is given to the internal still cut for the internal image of the second photographing unit, the number of occupants of the vehicle, occupant information, and time information A diffuser system based on a black box image of a vehicle, characterized in that for analyzing the image in consideration of. The method of claim 1, wherein the image analysis unit
A diffuser system based on a black box image of a vehicle, characterized in that the still cut received from the image transmission unit is learned with a convolutional neural network (CNN) to select a scent related to a specific still cut. The method of claim 1, wherein the image analysis unit
an image input unit for receiving an image from the photographing unit;
an image analysis unit that analyzes the image input to the image input unit;
an image classification unit that classifies the image analyzed by the image analysis unit; and
A diffuser system based on a black box image of a vehicle, characterized in that it comprises a fragrance selection unit for selecting a fragrance matching the image classified by the image classification unit. The method of claim 1, wherein the diffuser unit
a control unit receiving the analysis result of the image analysis unit and selecting a fragrance; and
A diffuser system based on a black box image of a vehicle, characterized in that it comprises a spraying unit for spraying at least one fragrance selected by the control unit into the interior of the vehicle. The method of claim 9, wherein the injection unit
A diffuser system based on a black box image of a vehicle, characterized in that the liquid discharged from the fragrance storage unit, which is separated and stored in a liquid state for each fragrance, is sprayed in the form of mist through an ultrasonic vibrator. Photographing the inside and outside of the vehicle by the photographing unit;
Analyzing the image transmitted from the photographing unit by an image analysis unit; and
Including the step of spraying the selected scent based on the analysis result of the image analyzer in the form of a mist by the spraying unit,
After the step of photographing the inside and outside of the vehicle by the photographing unit
An image transmission unit provided in the photographing unit
The captured images are generated as still cuts and transmitted to the image analysis unit;
In the step of analyzing the image received from the image analysis unit by the image analysis unit
If the received illuminance value is greater than or equal to a preset illuminance value, the image is analyzed by assigning a weight to an external still cut of the external image;
The diffusing method based on the black box image of a vehicle, characterized in that for analyzing the image by assigning a weight to an internal still cut for the internal image when the received illuminance value is less than or equal to a preset illuminance value. delete According to claim 11,
The video delivery unit
In the case of generating a still cut of an external streaming image taken while the vehicle is moving, the still cut is generated by changing the screen capture cycle of the streaming image according to the speed of the vehicle. fusing method. delete According to claim 11,
When the illuminance value transmitted from the illuminance sensor provided in the vehicle is less than or equal to the preset illuminance value, weight is given to the internal still cut for the internal image.
The diffusing method based on the black box image of the vehicle, characterized in that the image analysis unit analyzes the image in consideration of the number of occupants of the vehicle, occupant information, and time information. According to claim 11,
In the step of analyzing the image transmitted by the image analysis unit from the photographing unit
The diffusing method based on the black box image of the vehicle, characterized in that the image analysis unit selects a scent related to a specific still cut by learning the still cut received from the image delivery unit with a convolutional neural network (CNN).

Images