Method and apparatus for collecting traffic information from big data of outside image of vehicle

• US 10,223,910 B2
• Filed: 03/22/2017
• Issued: 03/05/2019
• Est. Priority Date: 03/22/2016
• Status: Active Grant

• Current Assignee: Korea University Research and Business Foundation
• Original Assignee: Korea University Research and Business Foundation
• Inventors: Ko, Han Seok, Park, Du Bok, Yang, Cheol Jong
• Primary Examiner(s): Dunn, Alex C
• Application Number:
  US15/465,819
• Publication Number:
  US 20170278386A1
• Time in Patent Office: 713 Days
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 20/10 using kernel methods, e.g. support vector machines [SVM]
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/0141 for traffic information dissemination
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors
• CPC Class Codes: G08G 1/096827 where the route is computed onboard
• CPC Class Codes: G08G 1/142 external to the vehicles
• CPC Class Codes: G08G 1/147 where the parking area is within an open public zone, e.g. city centre

Abstract

Provided is a traffic information collecting method using big data of an outside image of a vehicle. According to the present disclosure, a traffic information collecting method using big data of an outside image of a vehicle includes: generating object classification information indicating information on at least one of a position, a type, and a status of at least one object included in an image obtained by photographing an external situation of a vehicle; generating situation analysis information which is information obtained by analyzing the external situation of the vehicle, based on the object classification information; and selectively transmitting the situation analysis information to a server based on whether the situation analysis information corresponds to a passage interruption event which is an incident interrupting passage of the vehicle.

Claims

1. A traffic information collecting method using big data of an outside image of a vehicle, the method comprising:

performing, by a computer, image processing to transform an image obtained by photographing an external situation of a vehicle into an enhanced image with an improved quality;

generating, by a computer, object classification information indicating information on at least one of a position, a type, and a status of at least one object included in the enhanced image;

generating, by the computer, situation analysis information which is information obtained by analyzing the external situation of the vehicle, based on the object classification information; and

selectively transmitting, by the computer, the situation analysis information to a server based on whether the situation analysis information corresponds to a passage interruption event which is an incident interrupting passage of the vehicle;

wherein when in the generating of situation analysis information, a lane interruption ratio which is a ratio between the number of lanes on which the passage of the vehicle is interrupted due to the external situation and the total number of lanes and an expected duration until the external situation is settled are included in the situation analysis information,

in the selectively transmitting of the situation analysis information to a server, it is determined whether the situation analysis information corresponds to the passage interruption event based on at least one of the lane interruption ratio and the expected duration included in the situation analysis information.

2. The traffic information collecting method according to claim 1, wherein the generating of object classification information is performed based on a deep learning algorithm.

3. The traffic information collecting method according to claim 1, wherein the situation analysis information includes information on at least one of a type, a cause, contents, an image, an expected duration, and a place of occurrence of the external situation.

4. The traffic information collecting method according to claim 1, further comprising:

obtaining the image obtained by photographing an external situation of the vehicle from a camera mounted in the vehicle.

5. The traffic information collecting method according to claim 1, wherein the transmitted situation analysis information is relayed to a plurality of clients registered in the server to be used to search for a route of a navigation interlocked with each of the plurality of clients.

6. The traffic information collecting method according to claim 5, wherein with regard to the situation analysis information, a reliability of the situation analysis information is determined based on the number of times that the situation analysis information for the same external situation occurring at the same place is transmitted to the server.

7. The traffic information collecting method according to claim 1, wherein when in the generating of object classification information, facility sales information indicating real-time sales information of at least one driver'"'"'s convenience facility included in the image is further generated and in the generating of situation analysis information, the situation analysis information which further includes the facility sales information is generated,

in the selectively transmitting of the situation analysis information to a server, when the situation analysis information includes the facility sales information, the situation analysis information is transmitted to the server regardless of whether the situation analysis information corresponds to the passage interruption event.

8. A traffic information collecting apparatus using big data of an outside image of a vehicle, the apparatus comprising:

a computer; and

a computer-executable program causing the computer to execute the steps of;

performing image processing to transform an image obtained by photographing an external situation of a vehicle into an enhanced image with an improved quality;

generating object classification information indicating information on at least one of a position, a type, and a status of at least one object included in the enhanced image;

generating situation analysis information which is information obtained by analyzing the external situation of the vehicle, based on the object classification information;

determining whether the situation analysis information corresponds to a passage interruption event which is an incident interrupting passage of the vehicle; and

selectively communicating the situation analysis information to a server based on a determination result;

wherein when in the generating situation analysis information, a lane interruption ratio which is a ratio between the number of lanes that the passage of the vehicle is interrupted due to the external situation and the total number of lanes and an expected duration until the external situation is settled in the situation analysis information, the computer determines whether the situation analysis information corresponds to the passage interruption event based on at least one of the lane interruption ratio and the expected duration included in the situation analysis information.

9. The traffic information collecting apparatus according to claim 8, wherein the computer-executable program further causes the computer to generate the object classification information based on a deep learning algorithm.

10. The traffic information collecting apparatus according to claim 8, wherein the situation analysis information includes information on at least one of a type, a cause, details, an image, an expected duration, and a place of occurrence of the external situation.

11. The traffic information collecting apparatus according to claim 8, wherein the computer-executable program further causes the computer to:

obtain the image obtained by photographing an external situation of the vehicle from a camera mounted in the vehicle.

12. The traffic information collecting apparatus according to claim 8, wherein the transmitted situation analysis information is relayed to a plurality of clients registered in the server to be used to search for a route of a navigation interlocked with each of the plurality of clients.

13. The traffic information collecting apparatus according to claim 8, wherein when the computer-executable program further causes the computer to

generate facility sales information indicating real-time sales information of at least one driver'"'"'s convenience facility included in the image,

generate the situation analysis information which further includes the facility sales information,

determine whether the situation analysis information includes the facility sales information,

communicate the situation analysis information to the server regardless of the determination result on whether the situation analysis information corresponds to the passage interruption event, according to the determination result on whether the facility sales information is included.