個別研究テーマ編集

三田誠一シニア研究スカラ
助教 ジョン ヴィジャイ コーネリウス キルバカラン

掲載年度

2019

個別研究テーマ
(日本語)

深層学習によるレーン検出(Deep Learning-based Lane Estimation)

個別研究テーマ
(英語)

研究者 ジョン ヴィジャイ コーネリウス キルバカラン
研究概要

In this research, we present a robust real-time lane estimation algorithm by adopting a learning framework using the convolutional neural network and extra trees. By utilising the learning framework, the proposed algorithm predicts the ego-lane location in the given image even under conditions of lane marker occlusion or absence. In the algorithm, the convolutional neural network is trained to extract robust features from the road images. While the extra trees regression model is trained to predict the ego-lane location from the extracted road features. The extra trees are trained with input-output pairs of road features and egolane image points. The ego-lane image points correspond to Bezier spline control points used to define the left and right lane markers of the egolane.

close

ページのトップへ戻る