Spatio-temporal Object Detection Proposals
Spatio-temporal Object Detection Proposals
复制标题
DOI：
10.1007/978-3-319-10578-9_48
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
Dan Oneaţă;Jérôme Revaud;J. Verbeek;C. Schmid
中科院分区：
文献类型：
--
作者：
Dan Oneaţă;Jérôme Revaud;J. Verbeek;C. Schmid
视频中动作和事件的时空检测是一个具有挑战性的问题。除了与识别相关的困难之外，视频检测的一个主要挑战是由沿着帧的包围盒序列形成的时空管所定义的搜索空间的大小。近年来，产生无监督检测建议的方法已被证明对于静止图像中的目标检测非常有效。这些方法提供了使用强大但计算昂贵的特征的可能性，因为只需要评估相对较少数量的检测假设。在这篇论文中，我们为开发时空检测问题的检测方案做出了两点贡献。首先，我们扩展了最近的2D对象建议方法，通过随机的超体素合并过程来产生时空建议。我们引入了空间、时间和时空成对的超体素特征来指导合并过程。其次，我们提出了一种新的高效超体素方法。我们结合我们新的超体素方法和现有的方法对我们的检测建议进行了实验评估。这项评估表明，与使用现有最先进的超体素方法相比，我们的超体素可以提供更准确的建议。
Spatio-temporal detection of actions and events in video is a challenging problem. Besides the difficulties related to recognition, a major challenge for detection in video is the size of the search space defined by spatio-temporal tubes formed by sequences of bounding boxes along the frames. Recently methods that generate unsupervised detection proposals have proven to be very effective for object detection in still images. These methods open the possibility to use strong but computationally expensive features since only a relatively small number of detection hypotheses need to be assessed. In this paper we make two contributions towards exploiting detection proposals for spatio-temporal detection problems. First, we extend a recent 2D object proposal method, to produce spatio-temporal proposals by a randomized supervoxel merging process. We introduce spatial, temporal, and spatio-temporal pairwise supervoxel features that are used to guide the merging process. Second, we propose a new efficient supervoxel method. We experimentally evaluate our detection proposals, in combination with our new supervoxel method as well as existing ones. This evaluation shows that our supervoxels lead to more accurate proposals when compared to using existing state-of-the-art supervoxel methods.