scholarly journals Can Markerless Pose Estimation Algorithms Estimate 3D Mass Centre Positions and Velocities during Linear Sprinting Activities?

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2889
Author(s):  
Laurie Needham ◽  
Murray Evans ◽  
Darren P. Cosker ◽  
Steffi L. Colyer
Keyword(s):  
Pose Estimation ◽  
Poor Performance ◽  
Estimation Algorithm ◽  
Specific Data ◽  
Estimation Algorithms ◽  
Mass Centre ◽  
Kalman Smoothing ◽  
The Mean ◽  
Human Pose ◽  
Signal Processing Methods

The ability to accurately and non-invasively measure 3D mass centre positions and their derivatives can provide rich insight into the physical demands of sports training and competition. This study examines a method for non-invasively measuring mass centre velocities using markerless human pose estimation and Kalman smoothing. Marker (Qualysis) and markerless (OpenPose) motion capture data were captured synchronously for sprinting and skeleton push starts. Mass centre positions and velocities derived from raw markerless pose estimation data contained large errors for both sprinting and skeleton pushing (mean ± SD = 0.127 ± 0.943 and −0.197 ± 1.549 m·s−1, respectively). Signal processing methods such as Kalman smoothing substantially reduced the mean error (±SD) in horizontal mass centre velocities (0.041 ± 0.257 m·s−1) during sprinting but the precision remained poor. Applying pose estimation to activities which exhibit unusual body poses (e.g., skeleton pushing) appears to elicit more erroneous results due to poor performance of the pose estimation algorithm. Researchers and practitioners should apply these methods with caution to activities beyond sprinting as pose estimation algorithms may not generalise well to the activity of interest. Retraining the model using activity specific data to produce more specialised networks is therefore recommended.

Addressing pose estimation issues for machine vision based UAV autonomous serial refuelling

2007 ◽  
Vol 111 (1120) ◽  
pp. 389-396 ◽  
Author(s):  
G. Campa ◽  
M. R. Napolitano ◽  
M. Perhinschi ◽  
M. L. Fravolini ◽  
L. Pollini ◽  
...  
Keyword(s):  
Machine Vision ◽  
Pose Estimation ◽  
Estimation Algorithm ◽  
Computational Effort ◽  
Unmanned Aircraft ◽  
Light Sources ◽  
Estimation Algorithms ◽  
Trade Offs ◽  
Labeling Algorithms ◽  
Selection Of

Abstract This paper describes the results of an effort on the analysis of the performance of specific ‘pose estimation’ algorithms within a Machine Vision-based approach for the problem of aerial refuelling for unmanned aerial vehicles. The approach assumes the availability of a camera on the unmanned aircraft for acquiring images of the refuelling tanker; also, it assumes that a number of active or passive light sources – the ‘markers’ – are installed at specific known locations on the tanker. A sequence of machine vision algorithms on the on-board computer of the unmanned aircraft is tasked with the processing of the images of the tanker. Specifically, detection and labeling algorithms are used to detect and identify the markers and a ‘pose estimation’ algorithm is used to estimate the relative position and orientation between the two aircraft. Detailed closed-loop simulation studies have been performed to compare the performance of two ‘pose estimation’ algorithms within a simulation environment that was specifically developed for the study of aerial refuelling problems. Special emphasis is placed on the analysis of the required computational effort as well as on the accuracy and the error propagation characteristics of the two methods. The general trade offs involved in the selection of the pose estimation algorithm are discussed. Finally, simulation results are presented and analysed.

scholarly journals Model-Based 3D Pose Estimation of a Single RGB Image Using a Deep Viewpoint Classification Neural Network

2019 ◽  
Vol 9 (12) ◽  
pp. 2478 ◽  
Author(s):  
Jui-Yuan Su ◽  
Shyi-Chyi Cheng ◽  
Chin-Chun Chang ◽  
Jing-Ming Chen
Keyword(s):  
Neural Network ◽  
Pose Estimation ◽  
Low Cost ◽  
Estimation Algorithm ◽  
Training Dataset ◽  
3D Pose Estimation ◽  
Estimation Algorithms ◽  
Model Based ◽  
3D Scene ◽  
Rgb Image

This paper presents a model-based approach for 3D pose estimation of a single RGB image to keep the 3D scene model up-to-date using a low-cost camera. A prelearned image model of the target scene is first reconstructed using a training RGB-D video. Next, the model is analyzed using the proposed multiple principal analysis to label the viewpoint class of each training RGB image and construct a training dataset for training a deep learning viewpoint classification neural network (DVCNN). For all training images in a viewpoint class, the DVCNN estimates their membership probabilities and defines the template of the class as the one of the highest probability. To achieve the goal of scene reconstruction in a 3D space using a camera, using the information of templates, a pose estimation algorithm follows to estimate the pose parameters and depth map of a single RGB image captured by navigating the camera to a specific viewpoint. Obviously, the pose estimation algorithm is the key to success for updating the status of the 3D scene. To compare with conventional pose estimation algorithms which use sparse features for pose estimation, our approach enhances the quality of reconstructing the 3D scene point cloud using the template-to-frame registration. Finally, we verify the ability of the established reconstruction system on publicly available benchmark datasets and compare it with the state-of-the-art pose estimation algorithms. The results indicate that our approach outperforms the compared methods in terms of the accuracy of pose estimation.

scholarly journals Using DeepLabCut for 3D markerless pose estimation across species and behaviors

2018 ◽  
Author(s):  
Tanmay Nath ◽  
Alexander Mathis ◽  
An Chi Chen ◽  
Amir Patel ◽  
Matthias Bethge ◽  
...  
Keyword(s):  
Pose Estimation ◽  
User Interfaces ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Estimation Algorithm ◽  
Graphical User Interfaces ◽  
Training Data ◽  
Behavioral Tracking ◽  
Human Pose ◽  
Python Package

Noninvasive behavioral tracking of animals during experiments is crucial to many scientific pursuits. Extracting the poses of animals without using markers is often essential for measuring behavioral effects in biomechanics, genetics, ethology & neuroscience. Yet, extracting detailed poses without markers in dynamically changing backgrounds has been challenging. We recently introduced an open source toolbox called DeepLabCut that builds on a state-of-the-art human pose estimation algorithm to allow a user to train a deep neural network using limited training data to precisely track user-defined features that matches human labeling accuracy. Here, with this paper we provide an updated toolbox that is self contained within a Python package that includes new features such as graphical user interfaces and active-learning based network refinement. Lastly, we provide a step-by-step guide for using DeepLabCut.

scholarly journals Filling the Joints: Completion and Recovery of Incomplete 3D Human Poses

Technologies ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 97
Author(s):  
Dennis Bautembach ◽  
Iason Oikonomidis ◽  
Antonis Argyros
Keyword(s):  
Pose Estimation ◽  
Gradient Descent ◽  
Estimation Error ◽  
Matrix Completion ◽  
Human Pose Estimation ◽  
Estimation Algorithms ◽  
Post Process ◽  
Recovery Techniques ◽  
Human Pose ◽  
3D Human Pose Estimation

We present a comparative study of three matrix completion and recovery techniques based on matrix inversion, gradient descent, and Lagrange multipliers, applied to the problem of human pose estimation. 3D human pose estimation algorithms may exhibit noise or may completely fail to provide estimates for some joints. A post-process is often employed to recover the missing joints’ locations from the remaining ones, typically by enforcing kinematic constraints or by using a prior learned from a database of natural poses. Matrix completion and recovery techniques fall into the latter category and operate by filling-in missing entries of a matrix whose available/non-missing entries may be additionally corrupted by noise. We compare the performance of three such techniques in terms of the estimation error of their output as well as their runtime, in a series of simulated and real-world experiments. We conclude by recommending use cases for each of the compared techniques.

2D Multi-Person Pose Estimation Combined with Face Detection

2021 ◽  
Author(s):  
Qiming Li ◽  
Lu Xu ◽  
Xiaoyan Yang
Keyword(s):  
Face Detection ◽  
Pose Estimation ◽  
Human Motion ◽  
Two Dimensional ◽  
Estimation Model ◽  
Motion Recognition ◽  
Human Motion Recognition ◽  
The Mean ◽  
Human Pose ◽  
Validation Set

Pose estimation is the basis and key of human motion recognition. In the two-dimensional human pose estimation based on image, in order to reduce the adverse effects of mutual occlusion among multiple people and improve the accuracy of motion recognition, a structurally symmetrical two-dimensional multi-person pose estimation model combined with face detection is proposed in this paper. First, transfer learning is used to initialize each sub-branch network model. Then, MTCNN is used for face detection to predict the number of people in the image. According to the number of people, the image is input into the improved two-branch OpenPose network. What is more, the double judgment algorithm is proposed to correct the false detection of MTCNN. The experimental results show that compared with TensorPose, which is the latest improved method based on OpenPose, the Average Precision (AP) (Intersection over Union [Formula: see text]) on the validation set is 8.8 higher. Furthermore, compared with OpenPose, the mean AP ([Formula: see text]) is 1.7 higher on the validation set and is 1.3 higher on the Test-dev test set.

scholarly journals Drone Detection and Pose Estimation Using Relational Graph Networks

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1479 ◽  
Author(s):  
Ren Jin ◽  
Jiaqi Jiang ◽  
Yuhua Qi ◽  
Defu Lin ◽  
Tao Song
Keyword(s):  
Pose Estimation ◽  
Optical Sensors ◽  
State Of The Art ◽  
Estimation Algorithm ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Estimation Algorithms ◽  
Low Altitude ◽  
Real Scenario ◽  
Keypoints Detection

With the upsurge in use of Unmanned Aerial Vehicles (UAVs), drone detection and pose estimation by using optical sensors becomes an important research subject in cooperative flight and low-altitude security. The existing technology only obtains the position of the target UAV based on object detection methods. To achieve better adaptability and enhanced cooperative performance, the attitude information of the target drone becomes a key message to understand its state and intention, e.g., the acceleration of quadrotors. At present, most of the object 6D pose estimation algorithms depend on accurate pose annotation or a 3D target model, which costs a lot of human resource and is difficult to apply to non-cooperative targets. To overcome these problems, a quadrotor 6D pose estimation algorithm was proposed in this paper. It was based on keypoints detection (only need keypoints annotation), relational graph network and perspective-n-point (PnP) algorithm, which achieves state-of-the-art performance both in simulation and real scenario. In addition, the inference ability of our relational graph network to the keypoints of four motors was also evaluated. The accuracy and speed were improved significantly compared with the state-of-the-art keypoints detection algorithm.

Sign in / Sign up

Export Citation Format

Share Document