Apparatus and method for preventing collision of vehicle

• US 9,031,774 B2
• Filed: 05/13/2010
• Issued: 05/12/2015
• Est. Priority Date: 12/14/2009
• Status: Active Grant

• Current Assignee: Andong National University Industry Academic Cooperation Foundation, Electronics and Telecommunications Research Institute
• Original Assignee: Andong National University Industry Academic Cooperation Foundation, Electronics and Telecommunications Research Institute
• Inventors: Suk, Jung Hee, Chun, Ik Jae, Lyuh, Chun Gi, Yeo, Soon Il, Chung, Wook Jin, Lee, Jeong Hwan, Shim, Jae Chang, Roh, Tae Moon
• Primary Examiner(s): Phongsvirajati, Sind
• Application Number:
  US12/779,221
• Publication Number:
  US 20110144859A1
• Time in Patent Office: 1,825 Days
• Field of Search: 701300-301
• US Class Current: 701/301
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: B62D 15/0265 Automatic obstacle avoidance by steering
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
• CPC Class Codes: G08G 1/16 Anti-collision systems road vehicle drive control systems for predicting or avoiding probable or impending collision otherwise than by control of a particular sub-unit B60W30/08
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection
• CPC Class Codes: Y02T 10/84 Data processing systems or methods, management, administration

Abstract

The present invention provides an apparatus and method for predicting a moving direction of another vehicle running on a carriageway adjacent to a user'"'"'s vehicle using periodically acquired image information around the user'"'"'s vehicle, and performing a control process of preventing collision of the user'"'"'s vehicle when a moving direction of the user'"'"'s vehicle crosses the moving direction of the other vehicle.

Claims

1. An apparatus for preventing collision of a vehicle, comprising:

an image data acquisition part including at least one external camera installed outside a user'"'"'s vehicle and configured to photograph surroundings of the user'"'"'s vehicle to acquire external image data including images for portions of (i) the user'"'"'s vehicle, (ii) a painted lane at one or more sides of the user'"'"'s vehicle, and (iii) another vehicle running in an adjacent carriageway, at predetermined time intervals, and including an internal camera installed inside the user'"'"'s vehicle and configured to photograph a driver of the user'"'"'s vehicle to acquire driver state image data;

an image recognition part configured to analyze the external image data and recognize (i) the user'"'"'s vehicle, (ii) the painted lane, and (iii) the other vehicle;

a running information determination part configured to calculate (i) a first distance between the user'"'"'s vehicle and the painted lane and (ii) a second distance between the other vehicle and the painted lane on the basis of the recognized external image data, predict a running direction of the user'"'"'s vehicle and a running direction of the other vehicle, and determine whether a collision point is expected based on the predicted running direction of the user'"'"'s vehicle and the predicted running direction of the other vehicle,

wherein the first distance between the user'"'"'s vehicle and the painted lane is calculated as a distance from a specific position at a side surface of the user'"'"'s vehicle to a position at which a straight line perpendicular to the side surface of the user'"'"'s vehicle meets the painted lane,

wherein the running information determination part is configured to determine whether the user'"'"'s vehicle leaves the carriageway in which the user'"'"'s vehicle is running,

wherein when it is determined that the user'"'"'s vehicle leaves the carriageway, the image data acquisition acquires the driver state image data using the internal camera in response to a request from a controller,

wherein the image recognition part is configured to analyze the driver state image data to determine whether the driver of the user'"'"'s vehicle is drowsy; and

the controller configured to initiate a cruise driving mode on the user'"'"'s vehicle when the running information determination part determines that the user'"'"'s vehicle leaves the carriageway and when it is determined that the driver of the user'"'"'s vehicle is drowsy.

2. The apparatus according to claim 1, wherein the running information determination part is configured to obtain (i) first disposition information of the user'"'"'s vehicle in the carriageway on the basis of the first distance and (ii) second disposition information of the other vehicle in the adjacent carriageway on the basis of the second distance, and predict the running direction of the user'"'"'s vehicle and the running direction of the other vehicle on the basis of the painted lane and the first and the second disposition information.

3. The apparatus according to claim 1, wherein the painted lane includes (i) a front lane in front of the user'"'"'s vehicle or (ii) a rear lane in rear of the user'"'"'s vehicle.

4. The apparatus according to claim 1, wherein, when there are two or more other vehicles in the adjacent carriageway, the image recognition part assigns numbers to the respective vehicles to distinguish the other vehicles from each other.

5. The apparatus according to claim 1, wherein the first distance is the shortest distance between a given point of the side surface of the user'"'"'s vehicle and the painted lane.

6. The apparatus according to claim 5, wherein the running information determination part is configured to calculate the predicted running direction of the user'"'"'s vehicle on the basis of the first distance detected at two or more points in time.

7. The apparatus according to claim 1,

wherein the running information determination part is configured to calculate (i) a first distance which is the shortest distance between a first given point on the side surface of the user'"'"'s vehicle and the painted lane, and (iii) third and fourth distances between a second given point on the side surface of the user'"'"'s vehicle and a first point and a second point on the painted lane, respectively, and

wherein the third and the fourth distances each have angles ±

θ

(0°

<

θ

<

90°

) with respect to the painted lane.

8. The apparatus according to claim 7, wherein the running information determination part is configured to calculate the predicted running direction of the user'"'"'s vehicle on the basis of the first, the third, and the fourth distances.

9. The apparatus according to claim 1, wherein the running information determination part is configured to determine whether the collision point is expected within a predetermined distance.

10. The apparatus according to claim 1, wherein the running information determination part is configured to determine whether the collision point is expected within a predetermined distance at a current speed of the user'"'"'s vehicle.

11. The apparatus according to claim 1, wherein the control signal is configured to control a steering apparatus or a speed controller of the user'"'"'s vehicle.

12. The apparatus according to claim 11, wherein the controller is further configured to generate and output an alarm signal in a form of any of a sound signal and an image signal.

13. The apparatus according to claim 1, wherein the controller is configured to collect information including a speed of the user'"'"'s vehicle, a distance between the user'"'"'s vehicle and the other vehicle, and position information between the user'"'"'s vehicle and the other vehicle with respect to the painted lane, and store the information in a black box.

14. The apparatus according to claim 1, the apparatus further comprising a driver input part configured to receive a cruise driving request from the driver of the user'"'"'s vehicle,

wherein, when the cruise driving request is received, the controller is configured to initiate a cruise driving mode.

15. The apparatus according to claim 1, wherein the controller is configured to determine whether the user'"'"'s vehicle is in a center of the carriageway when the cruise driving mode is initiated, and generate and output a control signal for controlling a steering apparatus when the user'"'"'s vehicle is not in the center of the carriageway.

16. The apparatus according to claim 15, wherein the controller is configured to calculate a steering angle to move the user'"'"'s vehicle to the center of the carriageway, and generate and output a control signal corresponding to the calculated steering angle.

17. The apparatus according to claim 16, wherein the controller is configured to calculate the steering angle on the basis of a current speed of the user'"'"'s vehicle.

18. The apparatus according to claim 1, wherein the controller is configured to generate and output a sound signal or an image signal to inform that the cruise driving mode has been initiated.

19. A method of preventing collision of a vehicle, comprising:

acquiring external image data, using an external camera installed outside a user'"'"'s vehicle, the external image data including images for portions of (i) the user'"'"'s vehicle running in a carriageway, (ii) a painted lane at one or more sides of the user'"'"'s vehicle, and (iii) another vehicle running in an adjacent carriageway, at predetermined time intervals;

analyzing, by an image recognition part and a running information determination part, the external image data, and recognizing images of the user'"'"'s vehicle, the painted lane, and the other vehicle based on the analyzed external image data;

calculating distances from the user'"'"'s vehicle and the other vehicle to the painted lane on the basis of the recognized images;

obtaining disposition information of the user'"'"'s vehicle in the carriageway and disposition information of the other vehicle in the adjacent carriageway on the basis of the calculated distances;

writing the disposition information of the user'"'"'s vehicle and the disposition information of the other vehicle to a black box;

calculating a predicted running direction of the user'"'"'s vehicle and a predicted running direction of the other vehicle with respect to the painted lane on the basis of the obtained disposition information;

determining whether a collision point is expected based on the predicted running direction of the user'"'"'s vehicle and the predicted running direction of the other vehicle;

determining whether the user'"'"'s vehicle leaves the carriageway in which the user'"'"'s vehicle is running;

acquiring driver state image data by photographing, using an internal camera installed inside the user'"'"'s vehicle, a driver of the user'"'"'s vehicle when it is determined that the user'"'"'s vehicle leaves the carriageway;

analyzing the driver state image data to determine whether the driver of the user'"'"'s vehicle is drowsy; and

generating and initiating a cruise driving mode on the user'"'"'s vehicle when the running information determination part determines that the user'"'"'s vehicle leaves the carriageway and when it is determined that the driver of the user'"'"'s vehicle is drowsy.