CVROFeb 27, 2020

Features for Ground Texture Based Localization -- A Survey

arXiv:2002.11948v213 citations
AI Analysis

This survey addresses the problem of achieving infrastructure-free, high-accuracy localization for vehicles, but it is incremental as it evaluates existing methods rather than proposing new ones.

The paper conducted the first extensive evaluation of feature extraction methods for ground texture-based vehicle localization, identifying AKAZE, SURF, and CenSurE as top keypoint detectors and specific pairings like CenSurE with ORB, BRIEF, and LATCH for high success rates in incremental localization, with SIFT performing best under severe synthetic transformations.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes