arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1605.08359cs.CVcs.RO
收藏

图像序列的成对分解在主动多视点识别中的应用

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

Imperial College London(伦敦帝国理工学院)

Edward Johns, Stefan Leutenegger, Andrew J. Davison

摘要:

多视角图像序列提供了比来自单个图像的更丰富的对象识别能力。然而,大多数现有的多视图识别解决方案通常采用手工制作的基于模型的几何方法,这些方法不容易接受深度学习的最新趋势。我们建议将卷积神经网络用于通用多视图识别,通过将图像序列分解为一组图像对,独立地对每一对进行分类,然后通过加权每一对的贡献来学习对象分类器。这允许在任意相机轨迹上进行识别,而不需要在潜在的无限数量的相机路径和长度上进行显式训练。建立这些成对的关系,然后自然地扩展到下一个最佳视图问题的主动识别框架。为了实现这一点,我们训练第二个卷积神经网络,以直接从观察到的图像映射到下一个视点。最后,我们将其纳入一个轨迹优化任务,从而寻求最佳的识别信心,为一个给定的轨迹长度。我们在ModelNet数据集上展示了引导和非引导多视图识别的最新结果,并展示了我们的方法如何用于深度图像、灰度图像或两者。

英文摘要:

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑