In this work, we consider the multi-image object matching problem in distributed networks of robots. Multi-image feature matching is a keystone of many applications, including Simultaneous Localization and Mapping, homography, object detection, and Structure from Motion. We first review the QuickMatch algorithm for multi-image feature matching. We then present NetMatch, an algorithm for distributing sets of features across computational units (agents) that largely preserves feature match quality and minimizes communication between agents (avoiding, in particular, the need to flood all data to all agents). Finally, we present an experimental application of both QuickMatch and NetMatch on an object matching test with low-quality images. The QuickMatch and NetMatch algorithms are compared with other standard matching algorithms in terms of preservation of match consistency. Our experiments show that QuickMatch and Netmatch can scale to larger numbers of images and features, and match more accurately than standard techniques.

中文翻译：

---

通过 QuickMatch 进行分布式一致的多图像特征匹配

在这项工作中，我们考虑了机器人分布式网络中的多图像对象匹配问题。多图像特征匹配是许多应用的基石，包括同步定位和映射、单应性、对象检测和运动结构。我们首先回顾了用于多图像特征匹配的 QuickMatch 算法。然后，我们介绍了 NetMatch，一种用于跨计算单元（代理）分布特征集的算法，该算法在很大程度上保持了特征匹配质量并最大限度地减少了代理之间的通信（特别是避免了将所有数据泛滥到所有代理的需要）。最后，我们展示了 QuickMatch 和 NetMatch 在低质量图像对象匹配测试中的实验应用。QuickMatch 和 NetMatch 算法与其他标准匹配算法在保持匹配一致性方面进行了比较。我们的实验表明，QuickMatch 和 Netmatch 可以扩展到更多的图像和特征，并且比标准技术更准确地匹配。