IEEE Trans Pattern Anal Mach Intell. 2018 Feb;40(2):257-271. doi: 10.1109/TPAMI.2017.2667665. Epub 2017 Feb 13.
We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings being built or destroyed. Such situations represent a major challenge for current large-scale place recognition methods. This work has the following three principal contributions. First, we demonstrate that matching across large changes in the scene appearance becomes much easier when both the query image and the database image depict the scene from approximately the same viewpoint. Second, based on this observation, we develop a new place recognition approach that combines (i) an efficient synthesis of novel views with (ii) a compact indexable image representation. Third, we introduce a new challenging dataset of 1,125 camera-phone query images of Tokyo that contain major changes in illumination (day, sunset, night) as well as structural changes in the scene. We demonstrate that the proposed approach significantly outperforms other large-scale place recognition techniques on this challenging data.
我们解决了在场景外观发生重大变化的情况下进行大规模视觉场所识别的问题，例如，由于光照（白天/黑夜）、季节变化、老化，或者随着时间的推移建筑物的建造或破坏等结构上的修改。这种情况对当前的大规模场所识别方法提出了重大挑战。这项工作有以下三个主要贡献。首先，我们证明了当查询图像和数据库图像从大致相同的视角描绘场景时，跨场景外观的大变化进行匹配变得容易得多。其次，基于这一观察结果，我们开发了一种新的场所识别方法，该方法结合了（i）高效的新视图合成和（ii）紧凑的可索引图像表示。第三，我们引入了一个新的具有挑战性的数据集，包含东京的 1125 个摄像手机查询图像，其中包含光照（白天、日落、夜晚）的重大变化以及场景的结构变化。我们证明，在所提出的方法在这个具有挑战性的数据集上显著优于其他大规模场所识别技术。
