地面テクスチャに基づく自己位置推定のための特徴量サーベイ
Features for Ground Texture Based Localization -- A Survey
地面テクスチャを用いた車両の自己位置推定において、各種特徴抽出法を実画像ペアと合成変換で比較評価し、AKAZE・SURF・CenSurEが優れた検出器であること、増分推定にはCenSurEとORB/BRIEF/LATCHの組合せ、絶対推定にはSIFTが有効であることを示した。
著者: Jan Fabian Schmid, Stephan F. Simon, Rudolf Mester
分類: cs.CV, cs.RO
原文アブストラクト
Ground texture based vehicle localization using feature-based methods is a promising approach to achieve infrastructure-free high-accuracy localization. In this paper, we provide the first extensive evaluation of available feature extraction methods for this task, using separately taken image pairs as well as synthetic transformations. We identify AKAZE, SURF and CenSurE as best performing keypoint detectors, and find pairings of CenSurE with the ORB, BRIEF and LATCH feature descriptors to achieve greatest success rates for incremental localization, while SIFT stands out when considering severe synthetic transformations as they might occur during absolute localization.
