KR20180107757A - System for counting traffic volume using artificial intelligence - Google Patents

Abstract

The present invention relates to a traffic coefficient system using artificial intelligence. The objective of the present invention is to measure traffic within a desired distance without using manpower or installing a complicated sensor by learning a person and a vehicle by using a deep learning technique rather than using manpower and installing the complicated sensor to use a smartphone and develop an application. The traffic coefficient system comprises: a user terminal; and a traffic coefficient server.

Description

[0001] SYSTEM FOR COUNTING TRAFFIC VOLUME USING ARTIFICIAL INTELLIGENCE [0002]

One embodiment of the invention relates to a traffic counting system using artificial intelligence.

The traffic volume survey is a survey to measure the number of passing vehicles using various roads by type, direction and time zone. Traffic measurement data are widely used for road traffic planning and design, road management and operation, and are frequently used in various fields related to road and traffic.

Such a road traffic measurement method has a conventional method of measuring the traffic volume by using a mechanical counting device while visually checking the vehicle passing through the surveyor. However, this conventional method has a disadvantage that not only the time and cost are required to manually measure the traffic volume by hand, but also all the operations must be manually performed in the case of statistical work. Therefore, there is an increasing need for a system that automatically measures road traffic volume and traffic volume statistics.

As the number of vehicles increases and traffic problems become more serious, the need to count the traffic volume of each vehicle type on various roads is increasing, have. In order to do this, it is necessary not only to collect the traffic volume measured by each time frame and each vehicle type, but also to collect the traffic volume measured by each road in an effective manner.

Japanese Patent Application Laid-Open No. 10-2017-0107782 Japanese Patent Application Laid-Open No. 10-2017-0110424

One embodiment of the present invention teaches people and vehicles by using a deep learning technique rather than installation of complex sensors and manpower, and by making them smart phones and applications, To provide a traffic counting system using artificial intelligence.

The artificial intelligence traffic counting system according to an embodiment of the present invention shoots a distance using a user terminal and identifies an object at a distance photographed through an application that learns a vehicle and a person using a deep learning technique to calculate a number And can be converted into a DB together with the GPS signal.

The artificial intelligence traffic counting system according to an embodiment of the present invention is provided with a traffic count application, captures the distance that the vehicle and the person move by execution of the traffic count application, A user terminal for displaying traffic information of a vehicle and a person at a corresponding distance based on the location information; And a database in which vehicle and person type techniques are stored. The mobile terminal receives the moving object information and the position information of the taken distance from the user terminal, And a traffic amount counting server for generating traffic amount information of the vehicle and the person at the corresponding distance corresponding to the information and transmitting the generated traffic amount information to the user terminal.

The vehicle and person class technique may be previously learned and stored by the deep learning technique, and may be programmed to recognize only the vehicle and the person type of the moving object information of the taken distance.

The artificial intelligence traffic counting system according to an embodiment of the present invention uses a terminal possessed by a person such as a smart phone to photograph distances without using a complicated sensor or the like, The traffic volume information can be acquired by identifying the object at the distance photographed through the application, calculating the number, and converting it into a DB together with the GPS signal.

FIG. 1 and FIG. 2 are views schematically showing an artificial intelligence traffic coefficient system according to an embodiment of the present invention.

The terms used in this specification will be briefly described and the present invention will be described in detail.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. Also, in certain cases, there may be a term selected arbitrarily by the applicant, in which case the meaning thereof will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term, not on the name of a simple term, but on the entire contents of the present invention.

When an element is referred to as "including" an element throughout the specification, it is to be understood that the element may include other elements as well, without departing from the spirit or scope of the present invention. Also, the terms "part," " module, "and the like described in the specification mean units for processing at least one function or operation, which may be implemented in hardware or software or a combination of hardware and software .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

FIG. 1 and FIG. 2 are views schematically showing an artificial intelligence traffic coefficient system according to an embodiment of the present invention.

In order to recover the traffic of the street, a sensor capable of detecting movement of a vehicle or object has been installed or a method of directly repairing the vehicle using manpower has been used.

On the other hand, according to the artificial intelligence traffic counting system according to the embodiment of the present invention, distance is photographed using a terminal possessed by a person such as a smart phone without using a complicated sensor and the like, It is possible to acquire the traffic volume information by calculating the number of the object at the distance taken by the application which has learned the traffic volume and making the DB together with the GPS signal.

The artificial intelligence traffic counting system according to an embodiment of the present invention is provided with a traffic count application, captures the distance that the vehicle and the person move by execution of the traffic count application, A user terminal for displaying traffic information of a vehicle and a person at a corresponding distance based on the location information; And a database in which vehicle and person type techniques are stored. The mobile terminal receives the moving object information and the position information of the taken distance from the user terminal, And a traffic amount counting server for generating traffic amount information of the vehicle and the person at the corresponding distance corresponding to the information and transmitting the generated traffic amount information to the user terminal.

The vehicle and person class technique can be previously learned and stored by the deep learning technique and can be programmed to recognize only the type of vehicle and person in the moving object information of the taken distance

In other words, this artificial intelligence-based traffic counting system enables the user to immediately drive the camera at the current position through a mobile terminal such as a smart phone and take a distance, Only the person can be extracted and the number can be calculated.

In other words, this artificial intelligence-based traffic coefficient system learns people and vehicles by using deep-learning technique rather than installing complicated sensors and manpower, and by making them smartphones and applications, It is possible to install without complicated sensor installation.

Through this, the traffic coefficient system using the artificial intelligence learns only human and vehicle types by the deep learning technique, so the traffic volume of unrecognized objects is not recovered.

This is a great advantage in terms of accuracy, while conventional sensors can not distinguish between animals and other moving objects.

As described above, the present invention is not limited to the above-described embodiment, and it is to be understood that the present invention is not limited to the above- It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention.

Claims (2)

A traffic amount counting application is installed and the vehicle and the person moving distance are photographed by the execution of the traffic amount counting application and the traffic amount information of the vehicle and the person at the distance based on the moving distance information and the position information of the taken distance A user terminal for displaying; And
And a database in which vehicle and person type techniques are stored. The mobile terminal receives information on the moving object and the position information of the taken distance from the user terminal, And a traffic amount counting server for generating traffic amount information of the vehicle and the person at the corresponding distance corresponding to the traffic amount counting server and transmitting the traffic amount information to the user terminal.
The method according to claim 1,
The vehicle and person type techniques may include,
Learning and stored in advance by the deep learning technique,
Wherein the traffic information is programmed to recognize only the type of the vehicle and the person in the moving object information of the taken distance.

Images