Automatic tracking collision avoidance system and method thereof

• US 9,399,463 B2
• Filed: 12/24/2014
• Issued: 07/26/2016
• Est. Priority Date: 11/07/2014
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Chen, Long-Der, Huang, Dau-Chen, Cheng, Pai-Wei, Lai, Shin-Chi, Kao, Kuo-Chen, Chen, Ke-Horng, Lei, Sheau-Fang
• Primary Examiner(s): ARTHUR JEANGLAUD, GERTRUDE
• Application Number:
  US14/582,596
• Publication Number:
  US 20160129906A1
• Time in Patent Office: 580 Days
• Field of Search: 701/36, 701/70, 340/438, 340/425.5
• US Class Current: 1/1
• CPC Class Codes: B60T 2201/022 Collision avoidance systems
• CPC Class Codes: B60T 2210/32 Vehicle surroundings
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60W 10/18 including control of braking systems
• CPC Class Codes: B60W 2050/143 Alarm means
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 2554/804 Relative longitudinal speed
• CPC Class Codes: B60W 30/08 Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention

Abstract

An automatic tracking collision avoidance method has following steps: taking images in front of an origin vehicle by at least two photograph units; the images delivering to a calculation assembly, to transform the images from three primary colors images to grey images; having a relative vehicle speed of the front vehicle corresponded to the original vehicle according to the grey images; and according to the grey images the calculation assembly having a relative vehicle speed that the front vehicle corresponded to the original vehicle; the calculation assembly having a safe distance according to the relative vehicle speed, if the safe distance is great than a distance that between the original vehicle and the front vehicle, an alarm module generating an alert signal.

Claims

1. An automatic tracking collision avoidance method, comprising the steps of:

taking images in front of an origin vehicle by at least two photograph units;

delivering the images to a calculation assembly for transforming the images from images of three primary colors to grey-level images;

obtaining a relative vehicle speed of the front vehicle corresponded to the original vehicle according to the grey-level images; and

enabling the calculation assembly to calculate and obtain a safe distance according to the relative vehicle speed, while making an evaluation to determining whether the safe distance is great than a distance between the original vehicle and the front vehicle, if so, enabling an alarm module to generate an alert signal;

wherein the images are transmitted to a grey-level processing unit where the images are transformed from images of three primary colors into grey-level images, while an alignment unit is enabled to perform a level calibration process and a background light calibration process upon the image of three primary colors, and thereafter, the calibrated images of three primary colors are transmitted back to the grey-level processing unit to be transformed into the grey-level images.

2. The method of claim 1, wherein an edge detection unit is provided for detecting and obtaining edges of the images, while a depth calculation unit is provided for calculating and thus obtaining a depth value and a disparity according to the detected edges of the images.

3. The method of claim 2, wherein the depth value is obtained using a semi-global block matching (SGBM) algorithm.

4. The method of claim 2, wherein the semi-global block matching (SGBM) algorithm includes the following calculations:

a matching cost calculation;

a path calculation;

a calculation of sum over paths in all directions; and

a calculation of choose minimum path and get disparity.

5. The method of claim 2, wherein a tail-light detection unit is used for obtaining a front-vehicle-tail-light depth value according to the depth value;

and a distance conversion unit is used for calculating and thus obtaining an actual distance and a vehicle speed according to the front-vehicle-tail-light depth value.

6. The method of claim 5, wherein a front-vehicle distance measurement unit is used for detecting and thus obtaining a front-vehicle distance between the origin vehicle and a vehicle in front of the origin vehicle;

a front-vehicle distortion calibration unit is used for receiving the front-vehicle distance to be used in a distance calibration process so as to obtained a calibrated front-vehicle distance to be transmitted to the distance conversion unit, while enabling the distance conversion unit to perform a calculation according to the calibrated front-vehicle distance for obtaining an initial value, and thus obtaining the actual distance and the vehicle speed according to the initial value and the front-vehicle-tail-light depth value.

7. The method of claim 1, wherein a distance conversion unit is used for comparing the safe distance to an actual distance so as to issue an alert signal to an alarm module when the safe distance is larger than the actual distance;

and the alert signal is used for enabling one procedure selected from the group consisting of;

enabling an audio unit to generate an alarming sound, and enabling a display unit to display the alert signal.

8. The method of claim 1, further comprising the step of:

making an evaluation to determining whether the actual distance is increasing, if so, stopping the alarm module from generating the alert signal;

otherwise, enabling a brake signal to be generate for enabling the origin vehicle to brake when the origin vehicle is not braking during a specific period of time.

9. An automatic tracking collision avoidance system, comprising:

an on-board module; and

a calculation assembly, connected to the on-board module for signal transmission, further comprising;

an image capturing module, having at least two photograph units;

an image processing module, connected to the image capturing module for signal transmission, and further comprising;

a grey-level processing unit, connected to the image capturing module for transforming an image of three primary colors that is received from the image capturing module into a grey-level image;

an alignment unit, connected to the grey-level processing unit for performing a level calibration process and a background light calibration process upon the image of three primary colors while transmitting the calibrated image of three primary colors to the grey-level processing unit; and

an edge detection unit, connected to the grey-level processing unit for detecting and obtaining image edges according to the grey-level image;

a calculation module, connected to the on-board module and the image processing module, and further comprising;

a depth calculation unit, connected to the edge detection unit for calculating and thus obtaining a depth value and a disparity according to the detected image edges;

a tail-light detection unit, connected to the depth calculation unit for calculating and thus obtaining a front-vehicle-tail-light depth value according to the depth value; and

a distance conversion unit, connected to the tail-light detection unit for calculating and thus obtaining an actual distance and a vehicle speed according to the front-vehicle-tail-light depth value; and

an alarm module, connected to the calculation module for generating an alarm signal in a condition when the actual distance is smaller than a safe distance.

10. The system of claim 9, wherein the on-board module further comprises:

a data collector, connected to a trip computer for signal transmission; and

a data transceiver, connected to a data collector for signal transmission.

11. The system of claim 10, wherein the data transceiver is a device selected from the group consisting of:

a blue-tooth device and a WiFi device.

12. The system of claim 9, wherein the calculation module further comprising:

a front-vehicle distance measurement unit and a front-vehicle distortion calibration unit, and the front-vehicle distance measurement unit is connected to the front-vehicle distortion calibration unit and is used for detecting and thus obtaining a front-vehicle distance between the origin vehicle and a vehicle in front of the origin vehicle while transmitting the front-vehicle distance to the front-vehicle distortion calibration unit; and

the front-vehicle distortion calibration unit is used for performing a distance calibration process upon the front-vehicle distance so as to obtained a calibrated front-vehicle distance while transmitting the same to the calculation module to be used in a calculation process for obtaining an initial value.

13. The system of claim 12, wherein the front-vehicle distance measurement unit is a device selected from the group consisting of:

an ultrasonic ranger finder and a laser range finder.

14. The system of claim 9, wherein the alarm module further comprises:

an audio unit and a display unit.

15. The system of claim 9, further comprising:

a memory module, connected to the image capturing module and the calculation module for signal transmission.

16. The system of claim 15, wherein the memory module is a device selected from the group consisting of:

a memory, a hard disk drive and a memory card.

17. The system of claim 9, wherein the calculation assembly further comprises:

a brake control module, connected to the calculation module for signal transmission.

18. The system of claim 9, wherein the image capturing module further comprises:

a temporary storage unit, connected to the at least two photograph units for signal transmission.