使用生成对抗网络处理具有挑战性的场景识别任务

每天一分钟，带你读遍机器人顶级会议文章

标题：Addressing Challenging Place Recognition Tasks using Generative Adversarial Networks

作者：Yasir Latif, Ravi Garg, Michael Milford and Ian Reid

来源：2018 IEEE International Conference on Robotics and Automation (ICRA)

编译：明煜航

审核：颜青松，陈世浪

欢迎个人转发朋友圈；其他机构或自媒体如需转载，后台留言申请授权

摘要

场景识别是同时定位与建图（SLAM）中十分重要的一个部分。在发生巨大的外表变化的时候，可靠的场景识别是一个十分困难的感知任务。这是因为同样的场景在早上、晚上以及各个季节的时候会看起来十分不一样。本文将以域翻译任务的形式来处场景识别。作者展示了在不需要跨域的图像间匹配的情况下，使用一对对偶生成对抗网络（GANs）从一个域（比如冬天的图像）生成另一个域（比如夏天的图像）的可能性。

通过执行循环一致性限制，域之间的映射关系可以在不需要知道示例匹配的情况下，从每个域中的图像集里学习。在这个过程中，也同样学习了每个域的有意义的特征空间。其中特征空间里的距离可以用来执行场景识别任务。实验表明学习到的特征对应了视觉相似度，并且可以有效的用来实现跨季节的场景识别。

Abstract

Place recognition is an essential component of Simultaneous Localization And Mapping (SLAM). Under se- vere appearance change, reliable place recognition is a difficult perception task since the same place is perceptually very different in the morning, at night, or over different seasons. This work addresses place recognition as a domain translation task. Using a pair of coupled Generative Adversarial Networks (GANs), we show that it is possible to generate the appear- ance of one domain (such as summer) from another (such as winter) without requiring image-to-image correspondences across the domains. Mapping between domains is learned from sets of images in each domain without knowing the instance- to-instance correspondence by enforcing a cyclic consistency constraint. In the process, meaningful feature spaces are learned for each domain, the distances in which can be used for the task of place recognition. Experiments show that learned features correspond to visual similarity and can be effectively used for place recognition across seasons.