scholarly journals 3D Hand Pose Estimation in Point Cloud Using 3D Convolutional Neural Network on Egocentric Datasets

2021 ◽  
Vol 2020 (2) ◽  
pp. 87-97
Author(s):  
Lê Văn Hùng
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Color Image ◽  
Point Cloud Data ◽  
Complex Scene ◽  
Cloud Data ◽  
Hand Pose Estimation ◽  
Processing Step ◽  
Egocentric Vision ◽  
Hand Pose

3D hand pose estimation from egocentric vision is an important study in the construction of assistance systems and modeling of robot hand in robotics. In this paper, we propose a complete method for estimating 3D hand posefrom the complex scene data obtained from the egocentric sensor. In which we propose a simple yet highly efficient pre-processing step for hand segmentation. In the estimation process, we used the Hand PointNet (HPN), V2V-PoseNet(V2V), Point-to-Point Regression PointNet (PtoP) for finetuning to estimate the 3D hand pose from the collected data obtained from the egocentric sensor, such as CVRA, FPHA (First-Person Hand Action) datasets. HPN, V2V, PtoP are thedeep networks/Convolutional Neural Networks (CNNs) for estimating 3D hand pose that uses the point cloud data of the hand. We evaluate the estimation results using the preprocessing step and do not use the pre-processing step to see the effectiveness of the proposed method. The results show that 3D distance error is increased many times compared to estimates on the hand datasets are not obstructed (the hand data obtained from surveillance cameras, are viewed from top view, front view, sides view) such as MSRA, NYU, ICVL datasets. The results are quantified, analyzed, shown on the point cloud data of CVAR dataset and projected on the color image of FPHA dataset.

scholarly journals Semi-Supervised Joint Learning for Hand Gesture Recognition from a Single Color Image

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 1007
Author(s):  
Chi Xu ◽  
Yunkai Jiang ◽  
Jun Zhou ◽  
Yi Liu
Keyword(s):  
Gesture Recognition ◽  
Pose Estimation ◽  
Color Image ◽  
Recognition Performance ◽  
Recognition Task ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Estimation Task ◽  
Hand Pose Estimation ◽  
Hand Pose

Hand gesture recognition and hand pose estimation are two closely correlated tasks. In this paper, we propose a deep-learning based approach which jointly learns an intermediate level shared feature for these two tasks, so that the hand gesture recognition task can be benefited from the hand pose estimation task. In the training process, a semi-supervised training scheme is designed to solve the problem of lacking proper annotation. Our approach detects the foreground hand, recognizes the hand gesture, and estimates the corresponding 3D hand pose simultaneously. To evaluate the hand gesture recognition performance of the state-of-the-arts, we propose a challenging hand gesture recognition dataset collected in unconstrained environments. Experimental results show that, the gesture recognition accuracy of ours is significantly boosted by leveraging the knowledge learned from the hand pose estimation task.

Model-free pose estimation using point cloud data

2019 ◽  
Vol 165 ◽  
pp. 298-311 ◽  
Author(s):  
Tae W. Lim ◽  
Charles E. Oestreich
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Point Cloud Data ◽  
Cloud Data ◽  
Model Free

LPPM-Net: Local-aware point processing module based 3D hand pose estimation for point cloud

2021 ◽  
Vol 90 ◽  
pp. 116036
Author(s):  
Jian Yang ◽  
Xiaohong Ma ◽  
Yi Sun ◽  
Xiangbo Lin
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Hand Pose Estimation ◽  
Processing Module ◽  
Hand Pose

scholarly journals Maximum Sum of Evidence—An Evidence-Based Solution to Object Pose Estimation in Point Cloud Data

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6473
Author(s):  
Tyson Phillips ◽  
Tim D’Adamo ◽  
Peter McAree
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Joint Space ◽  
Object Identification ◽  
Sensor Calibration ◽  
Evidence Based ◽  
Point Cloud Data ◽  
Cloud Data ◽  
Object Pose Estimation ◽  
2D And 3D

The capability to estimate the pose of known geometry from point cloud data is a frequently arising requirement in robotics and automation applications. This problem is directly addressed by Iterative Closest Point (ICP), however, this method has several limitations and lacks robustness. This paper makes the case for an alternative method that seeks to find the most likely solution based on available evidence. Specifically, an evidence-based metric is described that seeks to find the pose of the object that would maximise the conditional likelihood of reproducing the observed range measurements. A seedless search heuristic is also provided to find the most likely pose estimate in light of these measurements. The method is demonstrated to provide for pose estimation (2D and 3D shape poses as well as joint-space searches), object identification/classification, and platform localisation. Furthermore, the method is shown to be robust in cluttered or non-segmented point cloud data as well as being robust to measurement uncertainty and extrinsic sensor calibration.

scholarly journals 3-D Hand Pose Estimation from Kinect’s Point Cloud Using Appearance Matching

2016 ◽  
pp. 37-45 ◽  
Author(s):  
Pasquale Coscia ◽  
Francesco A. N. Palmieri ◽  
Francesco Castaldo ◽  
Alberto Cavallo
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Hand Pose Estimation ◽  
Appearance Matching ◽  
Hand Pose

scholarly journals 3D Modeling of Lane Marks Using a Combination of Images and Mobile Mapping Data

2018 ◽  
Vol 12 (3) ◽  
pp. 386-394 ◽  
Author(s):  
Jingxin Su ◽  
Ryuji Miyazaki ◽  
Toru Tamaki ◽  
Kazufumi Kaneda ◽  
◽  
...  
Keyword(s):  
Point Cloud ◽  
Color Image ◽  
Region Growing ◽  
Surface Region ◽  
Point Cloud Data ◽  
Mobile Mapping ◽  
Cloud Data ◽  
The Road ◽  
Boundary Points ◽  
Scan Line

When we drive a car, the white lines on the road show us where the lanes are. The lane marks act as a reference for where to steer the vehicle. Naturally, in the field of advanced driver-assistance systems and autonomous driving, lane-line detection has become a critical issue. In this research, we propose a fast and precise method that can create a three-dimensional point cloud model of lane marks. Our datasets are obtained by a vehicle-mounted mobile mapping system (MMS). The input datasets include point cloud data and color images generated by laser scanner and CCD camera. A line-based point cloud region growing method and image-based scan-line method are used to extract lane marks from the input. Given a set of mobile mapping data outputs, our approach takes advantage of all important clues from both the color image and point cloud data. The line-based point cloud region growing is used to identify boundary points, which guarantees a precise road surface region segmentation and boundary points extraction. The boundary points are converted into 2D geometry. The image-based scan line algorithm is designed specifically for environments where it is difficult to clearly identify lane marks. Therefore, we use the boundary points acquired previously to find the road surface region from the color image. The experiments show that the proposed approach is capable of precisely modeling lane marks using information from both images and point cloud data.

Sign in / Sign up

Export Citation Format

Share Document