Device for determining lane type and method thereof
A device for determining lane type and method thereof are provided. The device for determining lane type according to an embodiment of the present disclosure includes a camera for acquiring an around view image around a vehicle, a GPS receiver for receiving GPS information, and a controller communicatively connected to the camera and the GPS receiver. Here, the controller is configured to recognize a scene of the image acquired by the camera, detect lanes and road markings from the recognized scene, comprise a classifier adapted based on the GPS information, classify the detected lanes and road markings by the classifier, and confirm a type of the classified lanes.
1. A device for determining lane type, comprising:
a camera for acquiring an around view image around a vehicle;
a GPS receiver for receiving GPS information; and
a controller communicatively connected to the camera and the GPS receiver,
wherein the controller is configured to:
recognize a scene of the image acquired by the camera,
detect lanes and road markings from the recognized scene,
adapt a classifier, by autonomously determining a country and a region in which the vehicle is currently located, based on the GPS information and the detected lanes and road markings,
classify, by using the adapted classifier, the detected lanes and road markings, and
confirm a type of the classified lanes.
2. The device of claim 1 , wherein the controller is configured to adapt the classifier based on the GPS information by inputting the detected lanes and road markings.
3. The device of claim 1 , wherein the controller is configured to transmit a braking signal and an acceleration signal to a corresponding ECU based on the type of lanes and road markings.
4. The device of claim 1 , wherein the controller is configured to search for a color of the detected lanes.
5. The device of claim 1 , wherein the controller is configured to detect roads and other objects from the image.
6. The device of claim 5 , wherein the controller is configured to recognize whether the road is a highway or a downtown road according to the detected roads and other objects.
7. The device of claim 5 , wherein the controller is configured to:
determine whether a road is contained in the recognized scene, and
if the recognized scene contains a road, detect a condition of the road.
8. The device of claim 7 , wherein the controller is configured to detect at least one of snow, water, fallen leaves, and mud on the road.
9. The device of claim 1 , wherein the camera is a fisheye camera.
10. A method for determining lane type, comprising:
acquiring, by a camera, an around view image around a vehicle;
receiving by a GPS receiver, GPS information,
recognizing a scene of the acquired image;
detecting lanes and road markings from the recognized scene;
adapting a classifier, by autonomously determining a country and a region in which the vehicle is currently located, based on the GPS information and the detected lanes and road markings;
classifying, by using the adapted classifier, the detected lanes and road markings;
confirming a type of the classified lanes.
11. The method of claim 10 , further comprising:
receiving GPS information; and
adapting the classifier based on the GPS information by inputting the detected lanes and road markings.
12. The method of claim 10 , further comprising transmitting a braking signal and an acceleration signal to a corresponding ECU based on the type of lanes and road markings.
13. The method of claim 10 , wherein the confirming the type of the lanes comprises searching for a color of the detected lanes.
14. The method of claim 10 , wherein the recognizing the scene comprises detecting roads and other objects from the image.
15. The method of claim 14 , wherein the recognizing the scene comprises recognizing whether the road is a highway or a downtown road according to the detected road and other objects.
16. The method of claim 14 , further comprising:
determining whether a road is contained in the recognized scene; and
if the recognized scene contains a road, detecting a condition of the road.
17. The method of claim 16 , wherein the detecting the condition of the road comprises detecting at least one of snow, water, fallen leaves, and mud on the road.
18. The method of claim 10 , wherein the acquiring the image comprises acquiring the image by using a fisheye camera.
19. The device of claim 1 ,
wherein the controller is configured to classify, by using the adapted classifier, the detected lanes into one of a plurality of lane types, the plurality of lane types including a first lane type being a dotted line, a second lane type being a solid line, and third lane type being a combination of a dotted line and a solid line.
20. The method of claim 10 ,
wherein the detected lanes are classified, by using the adapted classifier, into one of a plurality of lane types, the plurality of lane types including a first lane type being a dotted line, a second lane type being a solid line, and third lane type being a combination of a dotted line and a solid line.