Robust Human Face Tracking in Eigenspace for Perceptual Human-Robot Interaction

Author(s):  
Richard Jiang ◽  
Abdul Sadka

This chapter introduces a robust human face tracking scheme for vision-based human-robot interaction, where the detected face-like regions in the video sequence are tracked using unscented Kalman filter (UKF), and face occlusion are tackled by using an online appearance-based scheme using principle component analysis (PCA). The experiment is carried out with the standard test video, which validates that the proposed PCA-based face tracking can attain robust performance in tackling face occlusions.

Sensor Review ◽  
2015 ◽  
Vol 35 (3) ◽  
pp. 244-250 ◽  
Author(s):  
Pedro Neto ◽  
Nuno Mendes ◽  
A. Paulo Moreira

Purpose – The purpose of this paper is to achieve reliable estimation of yaw angles by fusing data from low-cost inertial and magnetic sensing. Design/methodology/approach – In this paper, yaw angle is estimated by fusing inertial and magnetic sensing from a digital compass and a gyroscope, respectively. A Kalman filter estimates the error produced by the gyroscope. Findings – Drift effect produced by the gyroscope is significantly reduced and, at the same time, the system has the ability to react quickly to orientation changes. The system combines the best of each sensor, the stability of the magnetic sensor and the fast response of the inertial sensor. Research limitations/implications – The system does not present a stable behavior in the presence of large vibrations. Considerable calibration efforts are needed. Practical implications – Today, most of human–robot interaction technologies need to have the ability to estimate orientation, especially yaw angle, from small-sized and low-cost sensors. Originality/value – Existing methods for inertial and magnetic sensor fusion are combined to achieve reliable estimation of yaw angle. Experimental tests in a human–robot interaction scenario show the performance of the system.


Author(s):  
Thathupara Subramanyan Kavya ◽  
Tao Peng ◽  
Young-Min Jang ◽  
Erdenetuya Tsogtbaatar ◽  
Sang-Bock Cho

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4586 ◽  
Author(s):  
Chunxu Li ◽  
Ashraf Fahmy ◽  
Johann Sienz

In this paper, the application of Augmented Reality (AR) for the control and adjustment of robots has been developed, with the aim of making interaction and adjustment of robots easier and more accurate from a remote location. A LeapMotion sensor based controller has been investigated to track the movement of the operator hands. The data from the controller allows gestures and the position of the hand palm’s central point to be detected and tracked. A Kinect V2 camera is able to measure the corresponding motion velocities in x, y, z directions after our investigated post-processing algorithm is fulfilled. Unreal Engine 4 is used to create an AR environment for the user to monitor the control process immersively. Kalman filtering (KF) algorithm is employed to fuse the position signals from the LeapMotion sensor with the velocity signals from the Kinect camera sensor, respectively. The fused/optimal data are sent to teleoperate a Baxter robot in real-time by User Datagram Protocol (UDP). Several experiments have been conducted to test the validation of the proposed method.


Respati ◽  
2018 ◽  
Vol 13 (2) ◽  
Author(s):  
Mepa Kurniasih ◽  
Syaiful Akbar

INTISARI Wajah pada manusia merupakan salah satu ukuran fisiologis yang dapat mengenali ataupun yang akan menjadi pembeda antara individu yang satu dengan individu yang lainnya. Manusia mengenali seseorang lebih cepat dengan melihat pola wajah, yang akhirnya pengenalan pola wajah manusia merupakan suatu hal yang menarik untuk banyak orang ataupun para peneliti yang akan melalukan penelitian terhadapa pola wajah yang terdapat pada fisiologis manusia, terlebih pada setiap perusahaan. Aplikasi pengenalan pola wajah manusia dapat di aplikasikan untuk kehadiran karyawan di perusahaan, agar perusahaan tersebut mendapatkan data yang akurat dan dapat di percaya. Pada aplikasi yang dibuat ini, yang berjudul Identifikasi Kemiripan Wajah Untuk Kehadiran Karyawan yaitu menggunakan metode Algoritma Eigenface. Eigenface adalah salah satu algoritma pengenalan wajah yang didasarkan pada Principle Component Analysis (PCA ). Untuk mencocokan wajah setiap masing-masing karyawan terlebih dahulu karyawan yang akan diidentifikasi wajahnya. Wajah karyawan mempunyai master datanya yang terlebih dahulu melakukan registrasi karyawan setelah itu akan di capture menggunakan webcam. Untuk mencocokkan citra wajah master dengan citra wajah masukan yaitu dengan mengkonversi citra wajah masukan menjadi .jpg, kemudian dinormalisasi dengan menurunkan kualitas warna menjadi tipe grayscale. Ukuran dari citra wajah juga diseragamkan dengan ukuran 80 x 80 pixel. Setelah didapatkan citra wajah yang ternormalisasi, maka akan ditentukan eigenface dari citra wajah tersebut. Apabila citra wajah masukan cocok dengan citra wajah master, maka aplikasi akan menampilkan citra wajah master dan citra wajah masukan, kemudian karyawan dinyatakan hadir pada saat itu.Kata Kunci : algortima eigenface, PCA, identifikasi wajah, kehadiran karyawan, webcam, citra wajahABSTRACTThe face in humans is one of the physiological measures that can perceive or that will be the contrast between a person with each other. People perceive a man speedier by taking a gander at facial patterns, which at last the acknowledgment of human facial patterns is a fascinating thing for some individuals or analysts who will do inquire about on facial patterns contained in human physiology, particularly in each organization. Human face design acknowledgment application can be connected for the nearness of workers in the organization, with the goal that the organization gets exact and solid information. In this made application, entitled Identification of Face Similarity For Employee Presence is utilizing Eigenface Algorithm technique. Eigenface is one of the facial acknowledgment calculations in view of Principle Component Analysis (PCA). To coordinate every worker's face first the representative to be distinguished his face. The representative's face has its lord information initially to enroll the worker after it will be caught utilizing the webcam. To coordinate the face image of the ace with the image of the info confront is to change over the information confront image to .jpg, at that point standardized by diminishing the nature of the shading into grayscale type. The span of the face image is additionally formally dressed with the extent of 80 x 80 pixels. Having acquired a standardized face image, it will be resolved eigenface of the face image. On the off chance that the face image of the information coordinates the ace face image, at that point the application will show the face image of the ace and the information confront image, at that point the representative is proclaimed present around then.Keywords : eigenface algorithm, PCA, face identification, employee presence, webcam, face image


Sign in / Sign up

Export Citation Format

Share Document