GODSAC*: ロボット自己位置推定のためのグラフ最適化DSAC*
GODSAC*: Graph Optimized DSAC* for Robot Relocalization
単眼カメラの深層学習による姿勢推定を、ノイズを含むオドメトリとポーズグラフ最適化で補強し、屋外など広い環境でも高精度に自己位置推定する手法を提案した論文。
著者: Alphonsus Adu-Bredu, Noah Del Coro, Tianyi Liu
分類: cs.RO
原文アブストラクト
Deep learning based camera pose estimation from monocular camera images has seen a recent uptake in Visual SLAM research. Even though such pose estimation approaches have excellent results in small confined areas like offices and apartment buildings, they tend to do poorly when applied to larger areas like outdoor settings, mainly because of the scarcity of distinctive features. We propose GODSAC* as a camera pose estimation approach that augments pose predictions from a trained neural network with noisy odometry data through the optimization of a pose graph. GODSAC* outperforms the state-of-the-art approaches in pose estimation accuracy, as we demonstrate in our experiments.
