| CPC G06V 20/588 (2022.01) [G06V 10/454 (2022.01); G06V 10/82 (2022.01)] | 20 Claims |

|
1. A lane detection system for a vehicle for determining a current lane of a multi-lane road which the vehicle is driving on, wherein the system comprises:
a processor; and
a memory coupled to the processor and having processor-executable instructions stored thereon, which are executed by the processor and cause the processor to:
obtain a current image of the multi-lane road;
determine a first candidate current lane by using a leftmost lane in the current image of the multi-lane road as a first reference lane;
determine a second candidate current lane by using a rightmost lane in the current image of the multi-lane road as a second reference lane;
determine, for the first candidate current lane, a first set of likelihood measure values, and for the second candidate current lane, a second set of likelihood measure values, wherein the first set of likelihood measure values comprises a respective likelihood measure value for each lane of the multi-lane road that the vehicle is driving on the respective lane, and wherein the second set of likelihood measure values comprises a respective likelihood measure value for each lane of the multi-lane road that the vehicle is driving on the respective lane;
determine the first candidate current lane as the lane associated with the largest likelihood measure value of the first set of likelihood measure values;
determine the second candidate current lane as the lane associated with the largest likelihood measure value of the second set of likelihood measure values; and
determine either the first candidate current lane or the second candidate current lane to be the current lane of the vehicle in the current image by comparing a first difference between the largest likelihood measure value and an average likelihood measure value of the first set of likelihood measure values with a second difference between the largest likelihood measure value and an average likelihood measure value of the second set of likelihood measure values.
|