Robust Visual Place Recognition with Graph Kernels
Robust Visual Place Recognition with Graph Kernels
复制标题
DOI：
10.1109/cvpr.2016.491
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
E. Stumm;Christopher Mei;S. Lacroix;Juan I. Nieto;Marco Hutter;R. Siegwart
中科院分区：
文献类型：
--
作者：
E. Stumm;Christopher Mei;S. Lacroix;Juan I. Nieto;Marco Hutter;R. Siegwart
介绍了一种新的视觉识别方法，并进行了评估，表现出鲁棒性的感知混淆和观察噪声。这是通过视觉观察的更结构化的表示来增加区分来实现的。观测似然估计是基于图核公式，利用结构和视觉信息编码的共视图。所提出的概率模型是能够规避通常困难和昂贵的后验归一化过程，利用视觉观测中的信息。此外，地点识别的复杂度与地图的大小无关。结果显示，在一组不同的公共数据集和新实验上，该方法比现有技术有所改进，突出了该方法的优点。
A novel method for visual place recognition is introduced and evaluated, demonstrating robustness to perceptual aliasing and observation noise. This is achieved by increasing discrimination through a more structured representation of visual observations. Estimation of observation likelihoods are based on graph kernel formulations, utilizing both the structural and visual information encoded in covisibility graphs. The proposed probabilistic model is able to circumvent the typically difficult and expensive posterior normalization procedure by exploiting the information available in visual observations. Furthermore, the place recognition complexity is independent of the size of the map. Results show improvements over the state-of-theart on a diverse set of both public datasets and novel experiments, highlighting the benefit of the approach.