Articulated motion discovery using pairs of trajectories

Luca Del Pero, Susanna Ricco, Rahul Sukthankar, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages10
Publication statusPublished - 2015


Dive into the research topics of 'Articulated motion discovery using pairs of trajectories'. Together they form a unique fingerprint.

Cite this