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.

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 Real-Time Energy Efficient Hand Pose Estimation: A Case Study

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2828
Author(s):  
Mhd Rashed Al Koutayni ◽  
Vladimir Rybalkin ◽  
Jameel Malik ◽  
Ahmed Elhayek ◽  
Christian Weis ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Pose Estimation ◽  
Energy Efficient ◽  
Graphics Processing Units ◽  
Estimation Algorithm ◽  
High Energy ◽  
Estimation Methods ◽  
Hand Pose Estimation ◽  
Hand Pose

The estimation of human hand pose has become the basis for many vital applications where the user depends mainly on the hand pose as a system input. Virtual reality (VR) headset, shadow dexterous hand and in-air signature verification are a few examples of applications that require to track the hand movements in real-time. The state-of-the-art 3D hand pose estimation methods are based on the Convolutional Neural Network (CNN). These methods are implemented on Graphics Processing Units (GPUs) mainly due to their extensive computational requirements. However, GPUs are not suitable for the practical application scenarios, where the low power consumption is crucial. Furthermore, the difficulty of embedding a bulky GPU into a small device prevents the portability of such applications on mobile devices. The goal of this work is to provide an energy efficient solution for an existing depth camera based hand pose estimation algorithm. First, we compress the deep neural network model by applying the dynamic quantization techniques on different layers to achieve maximum compression without compromising accuracy. Afterwards, we design a custom hardware architecture. For our device we selected the FPGA as a target platform because FPGAs provide high energy efficiency and can be integrated in portable devices. Our solution implemented on Xilinx UltraScale+ MPSoC FPGA is 4.2× faster and 577.3× more energy efficient than the original implementation of the hand pose estimation algorithm on NVIDIA GeForce GTX 1070.

scholarly journals Low-Cost Sensors State Estimation Algorithm for a Small Hand-Launched Solar-Powered UAV

Sensors ◽  
2019 ◽  
Vol 19 (21) ◽  
pp. 4627 ◽  
Author(s):  
Guo ◽  
Zhou ◽  
Zhu ◽  
Bai
Keyword(s):  
State Estimation ◽  
Low Cost ◽  
Estimation Algorithm ◽  
Position Estimation ◽  
Parameters Estimation ◽  
Estimation Accuracy ◽  
Estimation Algorithms ◽  
Full State ◽  
Small Hand ◽  
Solar Powered

In order to reduce the cost of the flight controller and improve the control accuracy of solar-powered unmanned aerial vehicle (UAV), three state estimation algorithms based on the extended Kalman filter (EKF) with different structures are proposed: Three-stage series, full-state direct and indirect state estimation algorithms. A small hand-launched solar-powered UAV without ailerons is used as the object with which to compare the algorithm structure, estimation accuracy, and platform requirements and application. The three-stage estimation algorithm has a position accuracy of 6 m and is suitable for low-cost small, low control precision UAVs. The precision of full-state direct algorithm is 3.4 m, which is suitable for platforms with low-cost and high-trajectory tracking accuracy. The precision of the full-state indirect method is similar to the direct, but it is more stable for state switching, overall parameters estimation, and can be applied to large platforms. A full-scaled electric hand-launched UAV loaded with the three-stage series algorithm was used for the field test. Results verified the feasibility of the estimation algorithm and it obtained a position estimation accuracy of 23 m.

Sign in / Sign up

Export Citation Format

Share Document