Vision-based human motion analysis: An overview

R Poppe - Computer vision and image understanding, 2007 - Elsevier
Markerless vision-based human motion analysis has the potential to provide an
inexpensive, non-obtrusive solution for the estimation of body poses. The significant …

Hand modeling, analysis and recognition

Y Wu, TS Huang - IEEE Signal Processing Magazine, 2001 - ieeexplore.ieee.org
Analyzing hand gestures is a comprehensive task involving motion modeling, motion
analysis, pattern recognition, machine learning and even psycholinguistic studies. A …

Multimodal deep autoencoder for human pose recovery

C Hong, J Yu, J Wan, D Tao… - IEEE transactions on …, 2015 - ieeexplore.ieee.org
Video-based human pose recovery is usually conducted by retrieving relevant poses using
image features. In the retrieving process, the map** between 2D images and 3D poses is …

Learning to fuse 2d and 3d image cues for monocular body pose estimation

B Tekin, P Márquez-Neila… - Proceedings of the …, 2017 - openaccess.thecvf.com
Most recent approaches to monocular 3D human pose estimation rely on Deep Learning.
They typically involve regressing from an image to either 3D joint coordinates directly or 2D …

[KNIHA][B] Computer vision: algorithms and applications

R Szeliski - 2022 - books.google.com
Humans perceive the three-dimensional structure of the world with apparent ease. However,
despite all of the recent advances in computer vision research, the dream of having a …

A survey of vision-based methods for action representation, segmentation and recognition

D Weinland, R Ronfard, E Boyer - Computer vision and image …, 2011 - Elsevier
Action recognition has become a very important topic in computer vision, with many
fundamental applications, in robotics, video surveillance, human–computer interaction, and …

HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

L Sigal, AO Balan, MJ Black - International journal of computer vision, 2010 - Springer
While research on articulated human motion and pose estimation has progressed rapidly in
the last few years, there has been no systematic quantitative evaluation of competing …

Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval

C Hong, J Yu, D Tao, M Wang - IEEE transactions on industrial …, 2014 - ieeexplore.ieee.org
Image-based 3-D human pose recovery is usually conducted by retrieving relevant poses
with image features. However, it suffers from the high dimensionality of image features and …

Recovering 3D human pose from monocular images

A Agarwal, B Triggs - IEEE transactions on pattern analysis …, 2005 - ieeexplore.ieee.org
We describe a learning-based method for recovering 3D human body pose from single
images and monocular image sequences. Our approach requires neither an explicit body …

A data-driven approach for real-time full body pose reconstruction from a depth camera

A Baak, M Müller, G Bharaj, HP Seidel… - … Depth Cameras for …, 2013 - Springer
The 3D reconstruction of complex human motions from 2D color images is a challenging
and sometimes intractable problem. The pose estimation problem becomes more feasible …