Multi-view 3D Human Pose Estimation in Complex Environment

By Michael Hofmann, Dariu M. Gavrila. 2011

106 citations recorded by the source corpus.

We introduce a framework for unconstrained 3D human upper body pose estimation from multiple camera views in complex environment. Its main novelty lies in the integration of three components: single-frame pose recovery, temporal integration and model texture adaptation. Single-frame pose recovery consists of a hypothesis generation stage, in which candidate 3D poses are generated, based on probabilistic hierarchical shape matching in each camera view. In the subsequent hypothesis verification stage, the candidate 3D poses are re-projected into the other camera views and ranked according to a multi-view likelihood measure. Temporal integration consists of computing K-best trajectories combining a motion model and observations in a Viterbi-style maximum-likelihood approach. Poses that lie on the best trajectories are used to generate and adapt a texture model, which in turn enriches the shape likelihood measure used for pose recovery. The multiple trajectory hypotheses are used to generate pose predictions, augmenting the 3D pose candidates generated at the next time step.We demonstrate that our approach outperforms the state-of-the-art in experiments with large and challenging real-world data from an outdoor setting.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Feature Boosting Network For 3D Pose Estimation (2019, background): “Most of the existing works make use of highly constrained configurations [2], such as multi-view systems [3] and depth sensors [4], to infer the 3D poses.”
3D Pictorial Structures for Multiple Human Pose Estimation (2014, background): “silhouettes, edges) or depth observations and 3D human body poses is learned [1, 14, 16, 20, 26, 28, 30].”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “In general, background subtraction methods are employed as a pre-processing step to isolate humans from the background [159].”
Monocular 3D Human Pose Estimation by Predicting Depth on Joints (2017, background): “ages [40, 26] or RGB images captured simultaneously at multiple viewpoints [2, 10].”
3D Human Pose Estimation = 2D Pose Estimation + Matching (2016, background): “Previous approaches often make use of a highly sensored environment, including video streams [37, 30], multiview cameras [3, 10], depth images [23, 36, 27].”
Panoptic Studio: A Massively Multiview System for Social Motion Capture (2015, background): “Recently, other approaches consider markerless motion capture in more general setups with simpler model assumptions [20, 8, 5].”