Gesture-World Environment Technology for Mobile Manipulation – Remote Control System of a Robot with Hand Pose Estimation –

2012 ◽  
Vol 24 (1) ◽  
pp. 180-190 ◽  
Author(s):  
Kiyoshi Hoshino ◽  
◽  
Takuya Kasahara ◽  
Motomasa Tomida ◽  
Takanobu Tanimoto ◽  
...  
Keyword(s):  
Remote Control ◽  
High Precision ◽  
Pose Estimation ◽  
High Speed ◽  
High Performance ◽  
Vision System ◽  
Hand Pose Estimation ◽  
Hand Region ◽  
Detailed Search ◽  
Hand Pose

The purpose of this paper is to propose a remotecontrolled robot system capable of accurate highspeed performance of the same operation strictly conforming to human operator movement without sensors or special control means. We specifically intend to implement high-precision high-speed 3D hand pose estimation enabling a remote-controlled robot to be operated using two cameras installed loosely orthogonally using one ordinary PC. The two cameras have their own database. Once sequential hand images are shot at high speed, the system starts selecting one database with bigger size of hand region in each recorded image. Coarse screening then proceeds based on proportional hand image information roughly corresponding to wrist rotation or thumb or finger extension. Finally, a detailed search is done for similarity among selected candidates. Experiments show that mean and standard deviation scores of errors in estimated angles at the proximal interphalangeal (PIP) index are 0.45 ± 14.57 and at the carpometacarpal (CM) thumb 4.7 ± 10.82, respectively, indicating it as a high-precision 3D hand pose estimation. Remote control of a robot with the proposed vision system shows high performance as well.

Vision-Controlled Robot Using Hand Pose Estimation without Marker Loading Requirement

2012 ◽  
Vol 162 ◽  
pp. 358-367
Author(s):  
Kiyoshi Hoshino
Keyword(s):  
Pose Estimation ◽  
High Speed ◽  
Visual Servoing ◽  
Hand Pose Estimation ◽  
Orthogonal Relationship ◽  
Time Operation ◽  
Real Time Operation ◽  
Hand Region ◽  
Detailed Search ◽  
Hand Pose

The author proposes a visual-servoing and vision-controlled robot. It claims no sensors installed or special control means used, instead of that a high-precision and high-speed 3D hand pose estimation permits real time operation with two cameras installed at positions of loosely orthogonal relationship, using one PC of the normal specifications. Two cameras have their own database. Once sequential hand images are recorded with these two high-speed cameras, the system first selects one database with bigger size of hand region in each recorded image. Second, a coarse screening is carried out according to the proportional information on the hand image which roughly correspond to wrist rotation, or thumb or finger extension. Third, a detailed search is performed for similarity among the selected candidates. The estimated results are transmitted to a robot so that the same motions of an operator is reconstructed in the robot without time delay.

scholarly journals 3D Hand Pose Estimation Using a Single Camera for Unspecified Users

2009 ◽  
Vol 21 (6) ◽  
pp. 749-757 ◽  
Author(s):  
Kiyoshi Hoshino ◽  
◽  
Motomasa Tomida
Keyword(s):  
Pose Estimation ◽  
High Speed ◽  
Estimation Error ◽  
Three Dimensional ◽  
Single Camera ◽  
Hand Pose Estimation ◽  
Hand Size ◽  
Flexion Extension ◽  
Detailed Search ◽  
Hand Pose

The three-dimensional hand pose estimation this paper proposes uses a single camera to search a large database for the hand image most similar to the data input. It starts with coarse screening of proportional information on hand images roughly corresponding to forearm or hand rotation, or thumb or finger bending. Next, a detailed search is made for similarity among selected candidates. No separate processes were used to estimate corresponding joint angles when describing wrist’s rotation, flexion/extension, and abduction/adduction motions. By estimating sequential hand images this way, we estimated joint angle estimation error within several degrees - even when the wrist was freely rotating - within 80 fps using only a Notebook PC and high-speed camera, regardless of hand size and shape.

Wearable Device for High-Speed Hand Pose Estimation with a Ultrasmall Camera

2015 ◽  
Vol 27 (2) ◽  
pp. 167-173 ◽  
Author(s):  
Motomasa Tomida ◽  
◽  
Kiyoshi Hoshino
Keyword(s):  
Pose Estimation ◽  
High Speed ◽  
Computational Cost ◽  
Wearable Device ◽  
Estimation Accuracy ◽  
Hand Pose Estimation ◽  
Data Matching ◽  
Pip Joint ◽  
Image Characteristic ◽  
Hand Pose

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270002/06.jpg"" width=""300"" /> Hand pose estimation with ultrasmall camera</div> Operating a robot intentionally by using various complex motions of the hands and fingers requires a system that accurately detects hand and finger motions at high speed. This study uses an ultrasmall camera and compact computer for development of a wearable device of hand pose estimation, also called a hand-capture device. The accurate estimations, however, require data matching with a large database. But a compact computer usually has only limited memory and low machine power. We avoided this problem by reducing frequently used image characteristics from 1,600 dimensions to 64 dimensions of characteristic quantities. This saved on memory and lowered computational cost while achieving high accuracy and speed. To enable an operator to wear the device comfortably, the camera was placed as close to the back of the hand as possible to enable hand pose estimation from hand images without fingertips. A prototype device with a compact computer used to evaluate performance indicated that the device achieved high-speed estimation. Estimation accuracy was 2.32°±14.61° at the PIP joint of the index finger and 3.06°±10.56° at the CM joint of the thumb – as accurate as obtained using previous methods. This indicated that dimensional compression of image-characteristic quantities is important for realizing a compact hand-capture device. </span>

scholarly journals Hand Pose Estimation in the Task of Egocentric Actions

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 10533-10547
Author(s):  
Marek Hruz ◽  
Jakub Kanis ◽  
Zdenek Krnoul
Keyword(s):  
Pose Estimation ◽  
Hand Pose Estimation ◽  
Hand Pose

scholarly journals 3D Hand Pose Estimation via Graph-Based Reasoning

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 35824-35833
Author(s):  
Jae-Hun Song ◽  
Suk-Ju Kang
Keyword(s):  
Pose Estimation ◽  
Hand Pose Estimation ◽  
Hand Pose

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.

Sign in / Sign up

Export Citation Format

Share Document