SMPLR: Deep learning based SMPL reverse for 3D human pose and shape recovery

2020 ◽  
Vol 106 ◽  
pp. 107472 ◽  
Author(s):  
Meysam Madadi ◽  
Hugo Bertiche ◽  
Sergio Escalera
Keyword(s):  
Deep Learning ◽  
Shape Recovery ◽  
Human Pose

In-Cabin vehicle synthetic data to test Deep Learning based human pose estimation models

2021 ◽  
Author(s):  
Luis Gustavo Tomal Ribas ◽  
Marta Pereira Cocron ◽  
Joed Lopes Da Silva ◽  
Alessandro Zimmer ◽  
Thomas Brandmeier
Keyword(s):  
Deep Learning ◽  
Pose Estimation ◽  
Synthetic Data ◽  
Human Pose Estimation ◽  
Human Pose ◽  
Estimation Models

scholarly journals Analysis and Best Parameters Selection for Person Recognition based on Gait model using CNN algorithm and Image Augmentation

2020 ◽  
Author(s):  
Abeer Saleh ◽  
Talal Hamoud
Keyword(s):  
Deep Learning ◽  
Learning Algorithms ◽  
Person Recognition ◽  
Critical Issues ◽  
Dataset Size ◽  
Deep Convolution Neural Network ◽  
Human Pose ◽  
Improved Model ◽  
Pose Variation ◽  
Best Parameters

Abstract Person recognition based on gait model and motion print is indeed a challenging and novel task due to its usages and to the critical issues of human pose variation, human body occlusion, camera view variation, etc. In this project, a deep convolution neural network (CNN) was modified and adapted for person recognition with image augmentation technique. CNN is best algorithm of deep learning algorithms. Adaptation aims to get best values for CNN parameters to get best CNN model. In Addition to the CNN parameters, the design of CNN model itself was adapted to get best model design; number of layers and normalization between them. After choosing best parameters and best design, Image augmentation was used to increase train dataset with many copies of the image to boost the number of different images that will be used to train Deep learning algorithms. The tests were achieved using known dataset (Market dataset). The dataset contains sequential pictures of people in different gait status. The image in CNN model as matrix is extracted to many images or matrices, so dataset size may be bigger by hundred times to make the problem a big data problem, in this project Results show that adaptation has improved the accuracy of person recognition using gait model, that is represented in many successive images for the same person. In addition, dataset contains images of person carrying things. The improved model of CNN is robust to image dimensions (quality and resolution) and to carried things by persons.

scholarly journals A Deep Learning and Computer Vision Based Multi-Player Tracker for Squash

2020 ◽  
Vol 10 (24) ◽  
pp. 8793
Author(s):  
Maria Martine Baclig ◽  
Noah Ergezinger ◽  
Qipei Mei ◽  
Mustafa Gül ◽  
Samer Adeeb ◽  
...  
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
High Speed ◽  
Motion Tracking ◽  
Estimation Algorithm ◽  
Video Tracking ◽  
Unique Challenge ◽  
Player Tracking ◽  
Elite Level ◽  
Human Pose

Sports pose a unique challenge for high-speed, unobtrusive, uninterrupted motion tracking due to speed of movement and player occlusion, especially in the fast and competitive sport of squash. The objective of this study is to use video tracking techniques to quantify kinematics in elite-level squash. With the increasing availability and quality of elite tournament matches filmed for entertainment purposes, a new methodology of multi-player tracking for squash that only requires broadcast video as an input is proposed. This paper introduces and evaluates a markerless motion capture technique using an autonomous deep learning based human pose estimation algorithm and computer vision to detect and identify players. Inverse perspective mapping is utilized to convert pixel coordinates to court coordinates and distance traveled, court position, ‘T’ dominance, and average speeds of elite players in squash is determined. The method was validated using results from a previous study using manual tracking where the proposed method (filtered coordinates) displayed an average absolute percent error to the manual approach of 3.73% in total distance traveled, 3.52% and 1.26% in average speeds <9 m/s with and without speeds <1 m/s, respectively. The method has proven to be the most effective in collecting kinematic data of elite players in squash in a timely manner with no special camera setup and limited manual intervention.

scholarly journals Deep Learning for Computer Vision: A Brief Review

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Athanasios Voulodimos ◽  
Nikolaos Doulamis ◽  
Anastasios Doulamis ◽  
Eftychios Protopapadakis
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Review Paper ◽  
Machine Learning Techniques ◽  
Future Directions ◽  
Boltzmann Machines ◽  
Learning Techniques ◽  
Previous State ◽  
Human Pose ◽  
Learning Schemes

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein.

Sign in / Sign up

Export Citation Format

Share Document