Results 41 to 50 of about 4,537,022 (282)

MLE-Loss Driven Robust Hand Pose Estimation

IEEE Access
This paper introduces a novel method for accurately estimating the 2D coordinates of hand keypoints from single static images, utilizing a sequential convolutional neural network optimized with Maximum Likelihood Estimation Loss.
Xudong Lou, Xin Lin, Xiangxian Zhu, Chen Chen   +3 more
doaj   +1 more source

Training a Feedback Loop for Hand Pose Estimation [PDF]

2015 IEEE International Conference on Computer Vision (ICCV), 2015
Presented at ICCV 2015 (oral)
Markus Oberweger, Paul Wohlhart, Vincent Lepetit   +2 more
openaire   +2 more sources

Content based image pose manipulation [PDF]

, 2009
This thesis proposes the application of space-frequency transformations to the domain of pose estimation in images. This idea is explored using the Wavelet Transform with illustrative applications in pose estimation for face images, and images of planar ...
Begley, Seán
core   +2 more sources

A Soft Proposal Segmentation Network (SPS-Net) for Hand Segmentation on Depth Videos

IEEE Access, 2019
Hand segmentation is an important prerequisite for acquiring accurate 3D hand poses on depth images, as it can significantly reduce the complicity of hand pose estimation.
Fan Yang, Yang Wu
doaj   +1 more source

Articulated Hand Pose Estimation Review

CoRR, 2016
With the increase number of companies focusing on commercializing Augmented Reality (AR), Virtual Reality (VR) and wearable devices, the need for a hand based input mechanism is becoming essential in order to make the experience natural, seamless and immersive.
openaire   +3 more sources

Efficient Camera-Based Pose Estimation for Real-Time Applications [PDF]

, 2009
Accurate online localization is crucial for mobile robotics. In this paper, we describe a real-time image-based localization technique, which is based on a single calibrated camera.
Elmar Mair, Klaus H. Strobl, Michael Suppa, Mair, Elmar, Darius Burschka, Strobl, Klaus, Suppa, Michael, Burschka, Darius   +7 more
core   +1 more source

Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations

IEEE Access, 2020
3D hand pose estimation from a single depth image plays an important role in computer vision and human-computer interaction. Although recent hand pose estimation methods using convolution neural network (CNN) have shown notable improvements in accuracy ...
Cheol-Hwan Yoo, Seowon Ji, Yong-Goo Shin, Seung-Wook Kim, Sung-Jea Ko   +4 more
doaj   +1 more source

6D Pose Estimation on Spoons and Hands

CoRR
Accurate dietary monitoring is essential for promoting healthier eating habits. A key area of research is how people interact and consume food using utensils and hands. By tracking their position and orientation, it is possible to estimate the volume of food being consumed, or monitor eating behaviours, highly useful insights into nutritional intake ...
Kevin Tan, Fan Yang, Yuhao Chen
openaire   +3 more sources

L‐aspartate oxidase provides new insights into fumarate reduction in anaerobic darkness in Synechocystis sp. PCC6803

FEBS Letters, EarlyView.
Synechocystis strains deficient in succinate dehydrogenase (SDH) secrete more succinate than the WT under dark anaerobic conditions, supporting that SDH then primarily acts as SDH, not as a fumarate reductase. L‐aspartate oxidase (Laspo) from Synechocystis is functional under anaerobic conditions, reducing fumarate to succinate.
Kateryna Kukil, Jeffrey A. Hawkes, Cecilia Blikstad, Pia Lindberg   +3 more
wiley   +1 more source

Hand and Object Pose Estimation using Self-Supervised Learning [PDF]

, 2021
Hand and object pose estimation is an important topic in robotics and computer vision. State-of-the-art methods typically train a deep neural network on annotated dataset using supervised learning.
Luo, Weiqi
core