Self-Supervised Map-Segmentation by Mining Minimal-Map-Segments
Self-Supervised Map-Segmentation by Mining Minimal-Map-Segments
复制标题
DOI：
10.1109/iv47402.2020.9304724
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Tanaka Kanji
中科院分区：
文献类型：
--
作者：
Tanaka Kanji
在视觉地点识别 (VPR) 中，地图分割 (MS) 是一种预处理技术，用于将给定的视图序列地图划分为地点类别（即地图片段），以便每个类别都为视觉地点分类器 (VPC) 提供良好的特定地点训练图像。现有的 MS 方法隐式/显式地假设图片段具有一定的大小，或者各个图片段的大小是平衡的。然而，最近的VPR系统表明，非常小的重要地图片段（最小地图片段）通常足以满足VPC的需求，并且应该丢弃地图的剩余大的不重要部分以最小化地图维护成本。这里提出了一种新的 MS 算法，可以从大视图序列图中挖掘最小的地图片段。为了解决固有的 NP 难题，MS 被表述为视频分割问题，并使用最近开发的基于高效点轨迹的视频分割范例。所提出的地图表示是通过三种类型的 VPC 实现的：深度卷积神经网络、词袋和对象类检测器，并且每种类型都集成到拓扑 VPR 框架内的蒙特卡罗定位算法 (MCL) 中。使用公开的 NCLT 数据集进行的实验彻底研究了 MS 在 VPR 性能方面的功效。
In visual place recognition (VPR), map segmentation (MS) is a preprocessing technique used to partition a given view-sequence map into place classes (i.e., map segments) so that each class has good place-specific training images for a visual place classifier (VPC). Existing approaches to MS implicitly/explicitly suppose that map segments have a certain size, or individual map segments are balanced in size. However, recent VPR systems showed that very small important map segments (minimal map segments) often suffice for VPC, and the remaining large unimportant portion of the map should be discarded to minimize map maintenance cost. Here, a new MS algorithm that can mine minimal map segments from a large view-sequence map is presented. To solve the inherently NP hard problem, MS is formulated as a video-segmentation problem and the recently-developed efficient point-trajectory based paradigm of video segmentation is used. The proposed map representation was implemented with three types of VPC: deep convolutional neural network, bag-of-words, and object class detector, and each was integrated into a Monte Carlo localization algorithm (MCL) within a topometric VPR framework. Experiments using the publicly available NCLT dataset thoroughly investigate the efficacy of MS in terms of VPR performance.