Parking position identification method, parking position learning method, parking position identification system, parking position learning device, and non-transitory recording medium for recording program

1. A parking space identification method in which at least one computer identifies a first parking space of a target vehicle, the parking space identification method comprising:

acquiring input data of an image that is generated by photographing a parking area by a camera which is installed in the target vehicle; and

identifying the first parking space of the target vehicle in the photographed parking area by inputting the input data to a learning model that indicates a relationship between a parking region which has a width in which parking of at least one vehicle is feasible and a second parking space for one vehicle in the parking region,

wherein the learning model identifies the first parking space of the target vehicle in the photographed parking area without identifying lines that serve as marks for parking vehicles in the parking region, and

the learning model is constructed by:

acquiring training data, in which a first annotation as information which indicates the second parking space for the one vehicle in the parking region is added to a second image which indicates the parking region which has the width in which parking of the least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the second image which indicates the parking region; and

learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to identify whether or not a second parking obstacle is present in the first parking space of the target vehicle.

2. The parking space identification method according to claim 1 , wherein

the first annotation indicates the second parking space for the one vehicle by coordinates.

3. The parking space identification method according to claim 1 , wherein

second annotation indicates whether or not the first parking obstacle that is the obstacle to parking is present in the second parking space for the one vehicle as a first parking state in the second parking space for the one vehicle, and

in the identifying of the first parking space of the target vehicle, the learning model identifies whether or not the second parking obstacle is present in the first parking space of the target as a second parking state in the first parking space of the target vehicle.

4. The parking space identification method according to claim 3 , wherein

in a case where a first doorway obstacle that is the first parking obstacle to getting in and out of the one vehicle is present in a periphery of the second parking space for the one vehicle in the second image that indicates the parking region, the second annotation indicates a first distance between the second parking space for the one vehicle and the first doorway obstacle as the first parking state, and

in the identifying of the first parking space of the target vehicle, in the case, the input data are input to the learning model to identify the first parking space of the target vehicle in a periphery of a second doorway obstacle that is imaged in the input data, a second distance between the second doorway obstacle that is imaged in the input data and the first parking space of the target vehicle is identified as the second parking state in the first parking space of the target vehicle.

5. The parking space identification method according to claim 4 , wherein

the first doorway obstacle is a vehicle that is parked next to the second parking space for the one vehicle in the second image that indicates the parking region.

6. The parking space identification method according to claim 5 , wherein

the second annotation further indicates parallel parking or side-by-side parking as the first parking state in the second parking space for the one vehicle, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to further identify parallel parking or side-by-side parking as the second parking state in the first parking space of the target vehicle.

7. The parking space identification method according to claim 3 , wherein

the second annotation further indicates forward entrance or rearward entrance as the first parking state in the second parking space for the one vehicle, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to further identify forward entrance or rearward entrance as the second parking state in the first parking space of the target vehicle.

8. The parking space identification method according to claim 3 , wherein

the second annotation further indicates whether or not parking is prohibited as the first parking state in the second parking space for the one vehicle, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to further identify whether or not parking is prohibited as the second parking state in the first parking space of the target vehicle.

9. The parking space identification method according to claim 1 , wherein

the learning model is a neural network model.

10. A parking space learning method in which a computer learns a first parking space of a target vehicle, the parking space learning method comprising:

acquiring training data, in which a first annotation as information which indicates a second parking space for one vehicle in a parking region is added to an image which indicates the parking region which has a width in which parking of at least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the image which indicates the parking region; and

constructing a learning model by learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data,

wherein the learning model identifies the first parking space of the target vehicle without identifying lines that serve as marks for parking vehicles in the parking region, and

the learning model identifies whether or not a second parking obstacle is present in the first parking space of the target vehicle.

11. A parking space identification device that identifies a first parking space of a target vehicle, the parking space identification device comprising:

a processor; and

a memory that stores at least one program that, when executed by the processor, causes the processor to perform operations including:

acquiring input data of an image which is generated by photographing a parking area by a camera which is installed in the target vehicle; and

identifying the first parking space of the target vehicle in the photographed parking area by inputting the input data to a learning model which indicates a relationship between a parking region which has a width in which parking of at least one vehicle is feasible and a second parking space for one vehicle in the parking region,

wherein the learning model identifies the first parking space of the target vehicle in the photographed parking area without identifying lines that serve as marks for parking vehicles in the parking region, and

the learning model is constructed by:

acquiring training data, in which a first annotation as information which indicates the second parking space for the one vehicle in the parking region is added to a second image which indicates the parking region which has the width in which parking of the at least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the second image which indicates the parking region; and

learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to identify whether or not a second parking obstacle is present in the first parking space of the target vehicle.

12. A parking space identification system that identifies a first parking space of a target vehicle, the parking space identification system comprising:

a processor; and

a memory that stores at least one program that, when executed by the processor, causes the processor to perform operations including:

acquiring training data, in which a first annotation as information which indicates a second parking space for one vehicle in a parking region is added to a second image which indicates the parking region which has a width in which parking of at least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the second image which indicates the parking region;

constructing a learning model by learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data;

acquiring input data of a first image which is generated by photographing a parking area by a camera which is installed in the target vehicle; and

identifying the first parking space of the target vehicle in the photographed parking area by inputting the input data to the learning model,

wherein the learning model identifies the first parking space of the target vehicle in the photographed parking area without identifying lines that serve as marks for parking vehicles in the parking region, and

in the identifying of the first parking space of the target vehicle, the input data are input to the learning model to identify whether or not a second parking obstacle is present in the first parking space of the target vehicle.

13. A parking space learning device that learns a first parking space of a target vehicle, the parking space learning device comprising:

a processor; and

a memory that stores at least one program that, when executed by the processor, causes the processor to perform operations including:

acquiring training data, in which a first annotation as information which indicates a second parking space for one vehicle in a parking region is added to an image which indicates the parking region which has a width in which parking of at least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the image which indicates the parking region; and

constructing a learning model by learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data,

wherein the learning model identifies the first parking space of the target vehicle without identifying lines that serve as marks for parking vehicles in the parking region, and

the learning model identifies whether or not a second parking obstacle is present in the first parking space of the target vehicle.

14. A computer-readable non-transitory recording medium that records a program of learning a first parking space of a target vehicle,

the program being executable by a computer and causing the computer to execute a method, the method comprising:

acquiring training data, in which a first annotation as information which indicates a second parking space for one vehicle in a parking region is added to an image which indicates the parking region which has a width in which parking of at least one vehicle is feasible, and in which a second annotation as information which indicates whether or not a first parking obstacle that is an obstacle to parking is present in the second parking space for the one vehicle is further added to the image which indicates the parking region; and

constructing a learning model by learning the second parking space for the one vehicle in the parking region by using the training data, and by further learning whether or not the first parking obstacle is present in the second parking space for the one vehicle by using the training data,

wherein the learning model identifies the first parking space of the target vehicle without identifying lines that serve as marks for parking vehicles in the parking region, and

the learning model identifies whether or not a second parking obstacle is present in the first parking space of the target vehicle.