Computer-readable medium, vehicle control system, and vehicle control method

1. A vehicle control system comprising:

one or more image sensors disposed on a vehicle to have a field of view of an inside of the vehicle; and

a controller connected to the image sensor to perform communication, and configured to:

control the vehicle according to a state of a child existing in the vehicle,

recognize an occupant sensing area on the basis of image data generated by the image sensor,

determine whether an occupant is the child on the basis of the occupant sensing area,

in response to determining that the occupant is the child, determine whether the state of the child is a dangerous situation on the basis of at least one of an existence of the child alone in the vehicle for a predetermined reference time or more and a movement of the child, and

in response to determining that the state of the child is a dangerous situation, control the vehicle according to an indoor state of the vehicle,

wherein the controller is further configured to:

generate at least one of a torso central point of a torso and a head central point of a head of the occupant in the occupant sensing area,

identify a movement of the occupant by calculating an amount of the generated central point moved per unit time, and

determine the state of the child to be a dangerous situation when the amount of the generated central point moved per unit time is less than or equal to a predetermined reference movement amount.

2. The vehicle control system of claim 1 , wherein the controller is configured to:

estimate a size of an upper body of the occupant by calculating an area of the occupant sensing area; and

determining the occupant to be the child when the estimated size of the upper body is below a predetermined reference size value.

3. The vehicle control system of claim 1 , wherein the controller is configured to:

extract a length of an upper body of the occupant from the occupant sensing area; and

determine the occupant to be the child when the length of the upper body of the occupant is below a predetermined reference length value.

4. The vehicle control system of claim 1 , wherein the controller determines the occupant to be the child when a ratio of an area occupied by the occupant sensing area in an image is less than or equal to a predetermined reference ratio.

5. The vehicle control system of claim 1 , wherein the controller is configured to:

extract an upper body length corresponding to an upper body of the occupant and shoulder length corresponding to a shoulder of the occupant from the occupant sensing area;

generate a determination index on which the upper body length and the shoulder length are reflected; and

determine the occupant to be the child when the determination index is less than or equal to a predetermined reference determination index.

6. The vehicle control system of claim 1 , wherein the controller is configured to:

distinguish a head sensing area corresponding to a head of the occupant from a torso sensing area corresponding to the torso of the occupant in the occupant sensing area; and

determine the occupant to be the child when a ratio of the head sensing area to the torso sensing area is greater than or equal to a predetermined reference ratio.

7. The vehicle control system of claim 1 , wherein the controller is configured to:

distinguish a head sensing area corresponding to a head of the occupant from a full body sensing area corresponding to a full body of the occupant in the occupant sensing area; and

determining the occupant to be the child when a ratio of the head sensing area to the full body sensing area is greater than or equal to a predetermined reference ratio.

8. The vehicle control system of claim 1 , wherein the image sensor includes a plurality of image sensors, and the plurality of image sensors are disposed on the vehicle to have fields of view of a plurality of seats installed in the vehicle,

wherein the controller determines whether the child exists alone in the vehicle on the basis of a plurality of pieces of data sensed by the plurality image sensors, respectively.

9. The vehicle control system of claim 8 , wherein the controller generates an alarm signal for performing an alarm operation in the vehicle when the child exits in the vehicle for the predetermined reference time or more, and outputs the generated alarm signal.

10. The vehicle control system of claim 1 , wherein the controller is configured to:

generate the torso central point with respect to the upper body of the occupant in the occupant sensing area; and

detect the head central point with respect to the head sensing area generated in the occupant sensing area.

11. The vehicle control system of claim 1 , wherein the controller is configured to:

set a connecting line connecting the torso central point to the head central point; and

compare a characteristic of the connecting line including at least one of a movement trajectory, a size, and a shape of the connecting line with a previously stored normal model, and in response to mismatch of the characteristic and the previously stored normal model, determine the state of the child to be a dangerous situation.

12. The vehicle control system of claim 1 , further comprising a temperature sensor configured to sense an indoor temperature of the vehicle,

wherein the controller is configured to:

in response to determining the state of the child to be a dangerous situation, control the vehicle to operate an air conditioner disposed in the vehicle when the indoor temperature is higher than or equal to a previously set first reference temperature, and

in response to determining the state of the child to be a dangerous situation, control the vehicle to operate a heater disposed in the vehicle when the indoor temperature is lower than or equal to a previously set second reference temperature.

13. The vehicle control system of claim 1 , further comprising an oxygen concentration sensor configured to sense an indoor oxygen concentration of the vehicle,

wherein the controller is configured to, in response to determining the state of the child to be a dangerous situation, control the vehicle to open at least one of a window and a sunroof of the vehicle when the oxygen concentration sensed by the oxygen concentration sensor is lower than or equal to a previously set reference concentration.

14. The vehicle control system of claim 1 , further comprising a communication module configured to communicate with a rescue center,

wherein the controller is configured to, in response to determining the state of the child to be a dangerous situation, generate a rescue signal for requesting a rescue from the rescue center and output the generated rescue signal.

15. The vehicle control system of claim 1 , further comprising a communication module configured to communicate with a mobile communication terminal of a guardian,

wherein the controller, in response to determining the state of the child to be a dangerous situation, generates a notification signal for providing image data including an image of the child and providing the mobile communication terminal with the generated notification signal.

16. A vehicle control method comprising:

sensing, by one or more image sensors disposed on a vehicle to have a field of view of an inside of the vehicle, sensing an inside of the vehicle;

recognizing, by a controller, an occupant sensing area on the basis of image data generated by the image sensor;

determining, by the controller, whether an occupant is the child on the basis of the occupant sensing area;

determining, by the controller, whether the state of the child is a dangerous situation on the basis of at least one of an existence of the child alone in the vehicle for a predetermined reference time or more and a movement of the child in response to determining that the occupant is the child; and

controlling, by the controller, the vehicle according to the determined dangerous situation,

wherein the determining, by the controller, whether the state of the child is a dangerous situation comprises:

generating at least one of a torso central point of a torso and a head central point of a head of the occupant in the occupant sensing area,

identifying a movement of the occupant by calculating an amount of the generated central point moved per unit time, and

determining the state of the child to be a dangerous situation when the amount of the generated central point moved per unit time is less than or equal to a predetermined reference movement amount.

17. A non-transitory computer readable storage medium that records executable instructions that, when executed by a processor of a computer, controls the computer to execute operations comprising:

recognizing, an occupant sensing area on the basis of image data generated by an image sensor disposed on a vehicle to have a field of view of an inside of the vehicle;

determining, whether an occupant is the child on the basis of the occupant sensing area;

determining, whether the state of the child is a dangerous situation on the basis of at least one of an existence of the child alone in the vehicle for a predetermined reference time or more and a movement of the child in response to determining that the occupant is the child; and

controlling, the vehicle according to the determined dangerous situation,

wherein the operation to determine whether the state of the child is a dangerous situation comprises:

generating at least one of a torso central point of a torso and a head central point of a head of the occupant in the occupant sensing area,

identifying a movement of the occupant by calculating an amount of the generated central point moved per unit time, and

determining the state of the child to be a dangerous situation when the amount of the generated central point moved per unit time is less than or equal to a predetermined reference movement amount.