JP6558234B2 - Destination estimation device - Google Patents

Description

  The present invention relates to a technical field of a destination estimation device that estimates a destination set in an in-vehicle device.

  As this type of device, for example, based on identification information relating to an article loaded on a vehicle or an article carried by a user, and a carrying article database in which a carrying article relating to a destination or a genre is described, a destination is set. An apparatus for supporting the above has been proposed.

JP 2006-145494 A

  There is room for improvement in the technique described in Patent Document 1.

  This invention is made | formed in view of the said fact, and makes it a subject to provide the destination estimation apparatus which can estimate a destination suitably.

  In order to solve the above problems, a destination estimation device according to the present invention is a destination estimation device mounted on a vehicle, and includes an imaging unit that images at least a part of the periphery of the vehicle, and two or more of the vehicles. A storage unit that stores user image information including face images of each of the users in advance, an image captured by the imaging unit, and a recognition unit that recognizes the user of the vehicle by comparing the user image information; When a plurality of users are recognized by the recognition unit, an estimation unit that estimates one or a plurality of destinations according to a combination of the recognized plurality of users, and the estimation among the plurality of recognized users And a proposing unit that proposes at least a part of the estimated destination according to a user who has boarded the vehicle after the destination is estimated by the unit.

  When there is a passenger in addition to the driver, the range of options for the destination of the vehicle is wider than when there is no passenger. Here, the “destination” according to the present invention is a concept including not only the final destination but also a waypoint. Specifically, if the driver goes to the company after sending the passenger to the school, the school and the company are the destinations. Alternatively, when the passenger is sent from his / her home to the nearest station and then returns to his / her home, the nearest station / home is the destination.

  In the present invention, the estimation unit estimates one or a plurality of destinations according to a combination of a plurality of users. That is, the estimation unit estimates, for example, a destination when only one of the plurality of users gets on and a destination when the one user and another user get on. As described above, in the present invention, since the destination is estimated in consideration of not only the driver but also the passenger, the destination can be estimated appropriately.

  For example, not all of the users recognized by the recognition unit may get on, such as when another user is around the vehicle to see off one user. Therefore, in the present invention, the proposing unit proposes at least a part of the estimated destination according to the user who gets on the vehicle after the estimating unit estimates the destination.

  If comprised in this way, the proposal precision of the destination to the boarded user can be improved, and it is very advantageous practically. In addition, since the destination is estimated by the estimation unit before the user gets on, the time until the destination is proposed after the user gets on can be shortened.

  The effect | action and other gain of this invention are clarified from the form for implementing demonstrated below.

It is a block diagram which shows the structure of the destination estimation apparatus which concerns on embodiment. It is a flowchart which shows a part of process which ECU which concerns on embodiment performs. It is a flowchart which shows the destination estimation process which concerns on embodiment.

  An embodiment according to a destination estimation apparatus of the present invention will be described with reference to FIGS. 1 to 3. Since the destination estimation apparatus according to the present embodiment estimates the destination in consideration of not only the driver but also the passenger, the destination can be suitably estimated. In the following, first, the configuration of the vehicle on which the destination estimation apparatus is mounted and the destination estimation apparatus will be described, and then the operation of the vehicle and the destination estimation process will be described.

(Vehicle configuration)
The configuration of the vehicle according to the embodiment will be described with reference to FIG. Note that the vehicle according to the present embodiment may be a vehicle (so-called conventional vehicle) that includes only an engine as a drive source, a hybrid vehicle, or an electric vehicle.

  In FIG. 1, a vehicle 1 includes a vehicle control ECU (Electronic Control Unit) 20 and reception units 21 a to 21 d that receive radio signals transmitted from an electronic key 30 corresponding to the vehicle 1. It is prepared for. The mounting positions of the receiving units 21a to 21d are arbitrary, but are arranged so that the position of the electronic key 30 can be specified based on the radio signals received by the receiving units 21a to 21d.

  The vehicle 1 is configured to automatically travel a predetermined distance from the parking position even if the driver is not on the vehicle 1 (hereinafter referred to as “automatic delivery” as appropriate). For example, the technology described in Japanese Patent Application Laid-Open No. 2013-177128 can be applied to this automatic delivery, and the detailed description thereof is omitted.

(Configuration of destination estimation device)
The configuration of the destination estimation apparatus according to the embodiment will be described with reference to FIG. In FIG. 1, a destination estimation device 10 includes a navigation ECU (hereinafter referred to as “navigation ECU” as appropriate) 11, a recognition personal computer (hereinafter referred to as “recognition PC” as appropriate) 12, and the vicinity of the vehicle 1. A camera 13 that captures at least a part of the vehicle, a camera 14 that captures at least a part of the inside of the vehicle 1, and a DCM (Data Communication Module) 15 that is, for example, a radio or a mobile phone. Yes.

  The navigation ECU 11 constitutes a part of a car navigation system mounted on the vehicle 1. For this reason, for example, the navigation ECU 11 can access a map database (not shown) and has history data related to past destinations, travel routes, and the like.

  The recognition PC 12 has a storage unit (not shown) such as a hard disk or a nonvolatile memory that stores user image information including the face image of the user of the vehicle 1 in advance. Particularly in the present embodiment, it is assumed that user image information including face images of two or more users is stored in advance in the storage unit.

  In addition to the face image, the user image information includes information for specifying a user ID and an individual (for example, name, age, sex, address, etc.). It should be noted that the existing technique can be applied to the user image information storage (registration) method, and the detailed description thereof will be omitted.

  Each of the cameras 13 and 14 is not limited to one camera, and may be composed of a plurality of cameras.

(Operation of ECU for vehicle control)
Next, processing executed by the vehicle control ECU 20 when the vehicle 1 is parked in the parking space will be described with reference to the flowchart of FIG. The vehicle control ECU 20 and the receivers 21a to 21d are supplied with minute electric power from a battery (not shown) even when the vehicle 1 is parked (that is, when the ignition is off).

  2A, the vehicle control ECU 20 detects the approach of the driver of the vehicle 1 (here, the person holding the electronic key 30) (step S101). Specifically, the vehicle control ECU 20 estimates the distance between the vehicle 1 and the driver based on the reception intensity of the radio signal transmitted from the electronic key 30 in at least one of the reception units 21a to 21d. . The vehicle control ECU 20 determines that the approach of the driver has been detected when the estimated distance is within a predetermined distance.

  The vehicle control ECU 20 obtains the moving speed of the driver based on the time change of the reception intensity of the radio signal transmitted from the electronic key 30. If the obtained moving speed is equal to or higher than the predetermined speed, the vehicle control ECU 20 It may be determined that the vehicle is not approaching (in this case, the driver is likely to pass around the vehicle 1).

  When the approach of the driver is not detected in the process of step S101 (step S101: No), the vehicle control ECU 20 once ends the process, and executes the process of step S101 again after a predetermined time.

  On the other hand, when the approach of the driver is detected in the process of step S101 (step S101: Yes), the vehicle control ECU 20 turns on the power of the vehicle 1 (step S102). Here, “turning on the power” means a state in which main electrical components can be started and the engine can be started in a so-called conventional vehicle, and in a hybrid vehicle or an electric vehicle, the vehicle can be driven. (So-called ready state).

  In FIG.2 (b), after the vehicle 1 is turned on by the process of step S102, the vehicle control ECU 20 determines whether or not there is a delivery request (step S111). Specifically, for example, the vehicle control ECU 20 determines that there is a delivery request when a signal indicating execution of the automatic delivery control is received, and executes the automatic delivery control within a predetermined time from the start of the processing in step S111. If a signal indicating “No” is not received, it is determined that there is no delivery request.

  In the process of step S111, when it is determined that there is a delivery request (step S111: Yes), the vehicle control ECU 20 executes predetermined automatic delivery control (step S112). On the other hand, if it is determined in step S111 that there is no exit request (step S111: No), the vehicle control ECU 20 once ends the process, and again executes step S111 after a predetermined time.

(Destination estimation processing)
Next, the destination estimation process according to the present embodiment that is executed in parallel with the process shown in the flowchart of FIG. 2B will be described with reference to the flowchart of FIG.

  The destination estimation processing according to the present embodiment includes (i) that a database relating to clothes and a database relating to carry-on items are built in advance in the cloud (that is, a server on the Internet), and (ii) storing in the recognition PC 12 For example, it is assumed that personal information such as destination history, search history, mail information, schedule information, and the like for each user indicated by the user image information stored in advance in the section can be used. An existing technique can be applied to the technique that realizes the premises of (i) and (ii).

1. Recognition PC operation (1):
In FIG. 3, the recognition PC 12 is based on the reception intensity of the radio wave signal transmitted from the electronic key 30 received by each of the receiving units 21 a to 21 d after the vehicle 1 is turned on by the process of step S <b> 102 described above. Then, the position of the electronic key 30 (for example, a direction around the vehicle 1, a distance from the vehicle 1, etc.) is specified (step S211). Since the existing technique can be applied to the method for specifying the position of the electronic key 30, the detailed description thereof is omitted.

  Next, the PC for recognition 12 is included in the image corresponding to the position of the electronic key 30 specified in the process of step S211 among the images captured by the camera 13 and the user image information stored in advance in the storage unit. The face image to be checked is collated (step S212).

  Next, the recognition PC 12 determines whether or not a driver (here, a user who possesses the electronic key 30) has been identified (step S213). Specifically, the recognition PC 21 compares the image captured by the camera 13 with the face image included in the user image information (that is, performs face authentication based on the face image), and there is a corresponding person. It is determined that the driver has been identified. On the other hand, when there is no corresponding person, the recognition PC 12 determines that the driver is not specified. Note that “there is no corresponding person” is not limited to the case where there is no user indicated by the user image information. For example, the user cannot be clearly imaged due to some obstacle such as another person or a building, and face authentication cannot be performed. Including cases.

  If it is determined in step S212 that the driver has not been identified (step S212: No), the recognition PC 21 once ends the process, and again executes step S211 after a predetermined time.

  On the other hand, if it is determined in step S212 that the driver has been identified (step S212: Yes), the recognition PC 12 recognizes the identified driver's preferences, belongings, and clothes from the image captured by the camera 13. (Step S214). Specifically, the recognition PC 21 refers to a database relating to clothes and a database relating to personal belongings that are built in advance in the cloud, and recognizes the preferences of the identified driver from the image captured by the camera 13.

  For example, if the bag is recognized as a bag in the process of step S214, at least a genre (in this case, “business”, “travel”, “golf”) such as a business bag, a travel bag, and a golf bag can be distinguished. Any degree is acceptable. The same applies to the processing in step S216 described later.

  After the processing in step S214, the recognition PC 12 navigates information related to the identified driver (for example, information related to the user ID and the individual included in the user image information, information related to the recognized appearance, etc.). It transmits to ECU11.

  After the processing in step S214, the recognition PC 12 further identifies the driver by comparing the image captured by the camera 13 with the face image included in the user image information stored in advance in the storage unit. It is determined whether or not the user other than the user (step S215). Specifically, when the person A in FIG. 1 is specified as a driver, the recognition PC 21 determines whether the person B and the person C are users.

  In the process of step S215, when it is determined that there is another user (step S215: Yes), the recognition PC 12 recognizes the preferences of other users (step S216) in the same manner as the process of step S214 described above. ). Thereafter, information related to other users is transmitted to the navigation ECU 11, and a process of step S217 described later is executed.

  On the other hand, if it is determined in step S215 that there is no other user (step S215: No), the recognition PC 12 transmits information indicating that there is no other user to the navigation ECU 11, and will be described later in step S217. Execute the process.

2. Operation of the navigation ECU (1):
In parallel with the processing in step S215 described above, the navigation ECU 11 performs, for example, a destination related to the identified driver from the cloud via the DCM 15 based on the information related to the identified driver transmitted from the recognition PC 12. Personal information such as history, search history, mail information, schedule information is acquired (step S221).

  Next, the navigation ECU 11 determines whether there is another user (step S222). Specifically, when the navigation ECU 11 receives information related to another user from the recognition PC 12, the navigation ECU 11 determines that there is another user, and receives information indicating that there is no other user from the recognition PC 12. In this case, it is determined that there is no other user.

  When it is determined in the process of step 222 that there is another user (step S222: Yes), the navigation ECU 11 sends the individual related to the other user from the cloud via the DCM 15 based on the information related to the other user. Information is acquired (step S223).

  Next, the navigation ECU 11 determines only the driver based on the information related to the identified driver and the personal information acquired from the cloud, the information related to other users and the personal information acquired from the cloud, and the date and day of the week. A destination for boarding the vehicle 1 and a destination for a driver and other users to board the vehicle 1 are estimated (step S224).

  For example, when person A (see FIG. 1) is specified as a driver and person B and person C (see FIG. 1) are specified as other users, the navigation ECU 11 (i) only person A gets on the vehicle 1 (Ii) a destination when people A and B get on the vehicle 1, (iii) a destination when people A and C get on the vehicle 1, (iv) a person A, A destination when the person B and the person C get on the vehicle 1 is estimated.

  Specifically, on the morning of a weekday, when the person A has a business bag and the persons B and C who are children of the person A are around the person A, the navigation ECU 11 determines that the person B and the person C It is presumed that the person A goes to the workplace via the school where the school goes, and the school and the workplace are estimated as the destination.

  After step S224, the navigation ECU 11 executes a process of step S226 described later.

  On the other hand, if it is determined in step S222 that there is no other user (step S222: No), the navigation ECU 11 determines the information related to the identified driver and the personal information acquired from the cloud, as well as the date and day of the week. The destination is estimated based on (Step S225). Thereafter, the navigation ECU 11 performs a process of step S226 described later.

3. Recognition PC operation (2):
After the process of step S216 described above, the recognition PC 12 determines whether a person has boarded the vehicle 1 (step S217). In addition, when the automatic leaving control (see FIG. 2B) of step S112 described above is performed, the process of step S217 is performed after the vehicle 1 is stopped. Since various existing aspects can be applied to the boarding determination, a detailed description thereof is omitted.

  If it is determined in step S217 that the vehicle is not on board (step S217: No), the recognition PC 12 executes the process of step S217 again after a predetermined time (that is, enters a standby state).

  On the other hand, if it is determined in step S217 that the vehicle has been boarded (step S217: Yes), the recognition PC 12 corresponds to the image captured by the camera 14 (that is, the image inside the vehicle) and the identified driver. The face image included in the user image information (when there is another user, the face image included in the user image information corresponding to the other user) is further collated, and the person who gets on the vehicle 1 is specified. (Step S218). Thereafter, the recognition PC 12 transmits information indicating the identified person to the navigation ECU 11.

4). Operation of the navigation ECU (2):
After the process of step S224 or the process of step S226 described above, the navigation ECU 11 is the only driver who has boarded the vehicle 1 based on the information indicating the specified person transmitted from the recognition PC 12. It is determined whether or not (step S226).

  In the process of step S226, when it is determined that only the identified driver has boarded the vehicle 1 (step S226: Yes), the navigation ECU 11 determines the destination when only the driver gets on among the estimated destinations. Is proposed, for example, by displaying it on a display (not shown) of the navigation system (step S227).

  On the other hand, in the process of step S226, when it is determined that the identified driver and another user have boarded the vehicle 1 (step S226: No), the navigation ECU 11 determines that the driver and other users out of the estimated destinations. A destination for the user to get on is proposed (step S228).

  Specifically, when it is determined that the person A and the person B get on the vehicle 1, the navigation ECU 11 selects the destination when the person A and the person B get on the vehicle 1 among the estimated destinations. suggest. When it is determined that the person A and the person C get on the vehicle 1, the navigation ECU 11 proposes a destination when the person A and the person C get on the vehicle 1 among the estimated destinations. When it is determined that the person A, the person B, and the person C get on the vehicle 1, the navigation ECU 11 determines the destination when the person A, the person B, and the person C get on the vehicle 1 among the estimated destinations. Propose.

(Effect of destination estimation processing according to the embodiment)
As described above, when a plurality of users are recognized by the recognition PC 12, the navigation ECU 11 estimates one or a plurality of destinations according to the combination of the plurality of users. In the present embodiment, since the destination is estimated in consideration of not only the person specified as the driver but also the person who is estimated to ride in the vehicle 1, the destination can be suitably estimated.

  Further, the navigation ECU 11 proposes a destination according to a person who actually gets on the vehicle 1 among the estimated destinations. Therefore, it is possible to improve the destination proposal accuracy. In addition, since the estimation of the destination is started before the user gets on the vehicle 1, it is possible to shorten the time until the destination is proposed after the user gets on the vehicle 1.

  The “navi ECU 11” according to the embodiment is an example of the “estimating unit” and the “proposing unit” according to the present invention. The “recognition PC 12” according to the embodiment is an example of the “storage unit” and the “recognition unit” according to the present invention. The “camera 13” according to the embodiment is an example of the “imaging unit” according to the present invention.

  The present invention is not limited to the above-described embodiments, and can be appropriately changed without departing from the gist or concept of the invention that can be read from the claims and the entire specification. The apparatus is also included in the technical scope of the present invention.

  DESCRIPTION OF SYMBOLS 1 ... Vehicle, 10 ... Destination estimation apparatus, 11 ... Navigation ECU, 12 ... Recognition personal computer, 13, 14 ... Camera, 15 ... DCM, 20 ... Vehicle control ECU, 21a, 21b, 21c, 21d ... Receiver 30 ... Electronic key

Claims (1)

A destination estimation device mounted on a vehicle,
An imaging unit for imaging at least a part of the periphery of the vehicle;
A storage unit that stores in advance user image information including face images of two or more users of the vehicle;
A recognition unit for recognizing a user of the vehicle by comparing the image captured by the imaging unit with the user image information;
When a plurality of users are recognized by the recognition unit, an estimation unit that estimates one or a plurality of destinations according to a combination of the recognized plurality of users;
Among the plurality of recognized users, a proposal unit that proposes at least a part of the estimated destination according to a user who has boarded the vehicle after the destination is estimated by the estimation unit;
A destination estimation apparatus comprising: