Vehicle classification system and method

• US 9,984,704 B2
• Filed: 08/04/2017
• Issued: 05/29/2018
• Est. Priority Date: 08/05/2016
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Kwon, Young Jin, Kim, Do Hyun, Lee, Seung Jun
• Primary Examiner(s): King, Simon
• Application Number:
  US15/669,375
• Publication Number:
  US 20180040337A1
• Time in Patent Office: 298 Days
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G08G 1/0133 for classifying traffic situation
• CPC Class Codes: G08G 1/017 identifying vehicles G08G1/015, G08G1/054 take precedence
• CPC Class Codes: G08G 1/02 using treadles built into the road pads or other sensitive devices responsive to passage of vehicles E01F11/00
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: H04R 2410/00 Microphones
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308

Abstract

Disclosed is vehicle classification technology. A vehicle classification system includes a sound generation module configured to generate a sound caused by friction with a wheel of a passing vehicle and a sensor node configured to collect the sound generated by the sound generation module, analyze the collected sound to acquire axle information, and classify a model of the vehicle on the basis of the acquired axle information.

Claims

1. A vehicle classification system comprising:

a sound generation module configured to generate a sound caused by friction with a wheel of a passing vehicle; and

a sensor node configured to collect the sound generated by the sound generation module, analyze the collected sound to acquire axle information, and classify a model of the vehicle on the basis of the acquired axle information.

2. The vehicle classification system of claim 1, wherein the sound generation module is implemented in the form of a bar or a groove.

3. The vehicle classification system of claim 1, wherein the sound generation module is disposed behind the sensor node with respect to a vehicle traveling direction.

4. The vehicle classification system of claim 1, wherein the sensor node comprises:

a sensor module comprising a first sensor configured to collect the sound generated by the sound generation module and a second sensor configured to detect the vehicle; and

a control unit configured to analyze the sound collected by the first sensor to acquire the axle information and classify the model of the vehicle on the basis of the acquired axle information.

5. The vehicle classification system of claim 4, wherein the control unit activates the first sensor after receiving a vehicle detection signal from the second sensor and analyzes the sound transmitted from the first sensor to acquire the axle information.

6. The vehicle classification system of claim 4, wherein the control unit periodically acquires noise from a current road environment and removes an area corresponding to the acquired noise from the sound collected by the first sensor.

7. The vehicle classification system of claim 6, wherein the control unit determines that a sound transmitted from the first sensor after the vehicle detection signal is received from the second sensor is the sound used to acquire the axle information when the noise is acquired from the first sensor, and determines whether the second sensor detects a vehicle and then determines that sounds transmitted from the first sensor during a certain time when there is no vehicle are noise.

8. A vehicle classification method performed by a control unit, the vehicle classification method comprising:

acquiring a vehicle detection signal from a second sensor;

acquiring a sound transmitted from a first sensor;

storing the acquired sound in association with the vehicle detection signal;

determining whether the vehicle detection signal is acquired from the second sensor within a predetermined time; and

classifying a model of each vehicle on the basis of a result of analyzing a sound stored for each vehicle detection signal when a result of the determination is that the vehicle detection signal is not acquired.

9. The vehicle classification method of claim 8, wherein the vehicle detection signal is transmitted by the second sensor to the control unit when the vehicle enters a detection area.

10. The vehicle classification method of claim 8, wherein the sound is generated by friction between a sound generation module and a wheel of the vehicle while the vehicle is passing on the sound generation module.

11. The vehicle classification method of claim 8, wherein when a result of the determination is that the vehicle detection signal is acquired, the control unit performs the acquisition of the sound.

12. The vehicle classification method of claim 8, wherein the classifying of a vehicle model comprises:

analyzing a pattern of the sound for each vehicle detection signal to acquire axle information;

comparing the acquired axle information with prestored axle information for each vehicle model; and

identifying a vehicle model corresponding to the acquired axle information and classifying a current vehicle as the identified vehicle model.

13. The vehicle classification method of claim 8, further comprising:

periodically acquiring and storing noise in a current road environment; and

removing an area corresponding to the stored noise from the acquired sound.

14. The vehicle classification method of claim 13, wherein the periodically acquiring and storing of the noise comprises determining that a sound transmitted from the first sensor after the vehicle detection signal is received from the second sensor is the sound used to classify a vehicle model, and determining whether the second sensor detects a vehicle and then determining that sounds transmitted from the first sensor during a certain time when there is no vehicle are noise.