| CPC G06T 7/246 (2017.01) [G01C 21/165 (2013.01); G01C 21/28 (2013.01); G06F 18/253 (2023.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G06V 20/584 (2022.01); G06V 20/588 (2022.01); G06T 2207/30252 (2013.01)] | 26 Claims |
|
1. A processor-implemented motion information estimating method, comprising:
estimating motion information of a vehicle based on at least one set of initial motion information of the vehicle that is obtained from at least one non-image sensor;
predicting a plurality of sets of image feature information corresponding to a periphery of the vehicle based on the estimated motion information from the at least one non-image sensor;
obtaining a plurality of sets of detected image feature information detected from an input image obtained from an image sensor and an accuracy of each of the sets of the detected image feature information using a neural network;
evaluating a reliability of each of the sets of the detected image feature information, based on a difference between the sets of the predicted image feature information and the sets of the detected image feature information, by comparing the sets of the predicted image feature information from the at least one non-image sensor and the sets of the detected image feature information from the image sensor;
selecting at least one set of the sets of the detected image feature information based on a result of the evaluating of the reliability and on the accuracy; and
correcting the estimated motion information of the vehicle based on the at least one set of the sets of the detected image feature information being selected, including selectively fusing the estimated motion information from the at least one non-image sensor and the plurality of sets of the detected image feature information obtained from the image sensor based on the result of the evaluating of the reliability and on the accuracy,
wherein the evaluating a reliability further includes, when the evaluated reliability is less than or equal to a predetermined threshold value, determining that a malfunction occurs in an image processing process on at least one of the sets of the detected image feature information from the image sensor and/or excluding at least one of the sets of the detected image feature information from the correcting the estimated motion information of the vehicle.
|