Exploiting temporal information for 3D pose estimation

11/23/2017
by   Mir Rayat Imtiaz Hossain, et al.
0

In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses. Although the recent success of deep networks has led many state-of-the-art methods for 3D pose estimation to train deep networks end-to-end to predict from images directly, the top-performing approaches have shown the effectiveness of dividing the task of 3D pose estimation into two steps: using a state-of-the-art 2D pose estimator to estimate the 2D pose from images and then mapping them into 3D space. They also showed that a low-dimensional representation like 2D locations of a set of joints can be discriminative enough to estimate 3D pose with high accuracy. However, estimation of 3D pose for individual frames leads to temporally incoherent estimates due to independent error in each frame causing jitter. Therefore, in this work we utilize the temporal information across a sequence of 2D joint locations to estimate a sequence of 3D poses. We designed a simple sequence-to-sequence network composed of layer-normalized LSTM units with shortcut connections connecting the input to the output on the decoder side and imposed temporal smoothness constraint during training. We found that the knowledge of temporal consistency improves the best reported result by approximately 17.5% and helps our network to recover temporally consistent 3D poses over a sequence of images even when the 2D pose detector fails.

READ FULL TEXT

page 7

page 8

research
11/04/2020

Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video

The effectiveness of the approaches to predict 3D poses from 2D poses es...
research
03/31/2017

Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

Deep ConvNets have been shown to be effective for the task of human pose...
research
05/23/2019

Pose estimator and tracker using temporal flow maps for limbs

For human pose estimation in videos, it is significant how to use tempor...
research
07/10/2020

SeqHAND:RGB-Sequence-Based 3D Hand Pose and Shape Estimation

3D hand pose estimation based on RGB images has been studied for a long ...
research
12/13/2018

Nrityantar: Pose oblivious Indian classical dance sequence classification system

In this paper, we attempt to advance the research work done in human act...
research
06/10/2021

Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation

Hand pose estimation is difficult due to different environmental conditi...
research
02/24/2020

Anatomy-aware 3D Human Pose Estimation in Videos

In this work, we propose a new solution for 3D human pose estimation in ...

Please sign up or login with your details

Forgot password? Click here to reset