Articulated motion discovery using pairs of trajectories
Articulated motion discovery using pairs of trajectories
复制标题
使用轨迹对发现铰接运动
DOI：
--
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
V. Ferrari
中科院分区：
文献类型：
--
作者：
Luca Del Pero;Susanna Ricco;R. Sukthankar;V. Ferrari
我们提出了一种无监督的方法来发现视频中的特征运动模式，这些视频中的物体表现出自然的、无脚本的行为，比如野生老虎。通过分析大量有序轨迹对随时间的相对位移，我们发现了自下而上的一致模式，使得每个轨迹都连接到对象上的不同移动部分。成对的轨迹描述符完全依赖于运动，并且比采用单个轨迹的最新特征更具鉴别力。我们的方法生成时间视频间隔，每个时间视频间隔自动修剪为所发现行为的一个实例，并按类型（例如，跑步、转头、喝水）。我们在两个数据集上进行了实验：来自YouTube对象的狗和国家地理老虎视频的新数据集。结果证实，我们提出的描述符优于现有的基于外观和语义的描述符（例如，HOG和DTFs），使我们能够将不受约束的动物视频分割成包含单个行为的间隔。
We propose an unsupervised approach for discovering characteristic motion patterns in videos of highly articulated objects performing natural, unscripted behaviors, such as tigers in the wild. We discover consistent patterns in a bottom-up manner by analyzing the relative displacements of large numbers of ordered trajectory pairs through time, such that each trajectory is attached to a different moving part on the object. The pairs of trajectories descriptor relies entirely on motion and is more discriminative than state-of-the-art features that employ single trajectories. Our method generates temporal video intervals, each automatically trimmed to one instance of the discovered behavior, and clusters them by type (e.g., running, turning head, drinking water). We present experiments on two datasets: dogs from YouTube-Objects and a new dataset of National Geographic tiger videos. Results confirm that our proposed descriptor outperforms existing appearance- and trajectory-based descriptors (e.g., HOG and DTFs) on both datasets and enables us to segment unconstrained animal video into intervals containing single behaviors.