WGANVO:敵対的生成ネットワークに基づく単眼視覚オドメトリ
WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks
GANを用いた半教師あり学習で画像ペアからカメラ姿勢を推定し、事前知識なしに絶対スケールを復元できる単眼視覚オドメトリ手法を提案。KITTIでリアルタイム動作と精度を検証した。
著者: Javier Cremona, Lucas Uzal, Taihú Pire
分類: cs.CV, cs.RO
原文アブストラクト
In this work we present WGANVO, a Deep Learning based monocular Visual Odometry method. In particular, a neural network is trained to regress a pose estimate from an image pair. The training is performed using a semi-supervised approach. Unlike geometry based monocular methods, the proposed method can recover the absolute scale of the scene without neither prior knowledge nor extra information. The evaluation of the system is carried out on the well-known KITTI dataset where it is shown to work in real time and the accuracy obtained is encouraging to continue the development of Deep Learning based methods.
