Eye Gaze Correction for Video Conferencing Using Kinect v2

被引:4
|
作者
Ko, Eunsang [1 ]
Jang, Woo-Seok [1 ]
Ho, Yo-Sung [1 ]
机构
[1] GIST, Sch Informat & Commun, Gwangju 500712, South Korea
来源
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2015, PT II | 2015年 / 9315卷
关键词
Eye gaze correction; Eye contact; Video conferencing; Kinect v2;
D O I
10.1007/978-3-319-24078-7_58
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In video conferencing, eye gaze correction is beneficial for effective communication. In this era, video conferencing at homes using laptops is straightforward. In this paper, we propose an eye gaze correction method with a low-cost simple setup using Kinect v2. Our method detects an ellipse that connects edge points of the face after identifying several feature points within the face using Kinect v2 SDK. Then, we apply a 3D affine transform that allows eye gaze correction using camera space points that are acquired from depth information. Thus, in the preprocessing step, an ellipse model should be extracted when the user gazes the camera and display, respectively. Also, we fill holes that are caused by the affine transform using color inpainting. As a result, we produced a natural eye gaze-corrected image in real-time.
引用
收藏
页码:571 / 578
页数:8
相关论文
共 50 条
  • [1] Gaze Correction for Home Video Conferencing
    Kuster, Claudia
    Popa, Tiberiu
    Bazin, Jean-Charles
    Gotsman, Craig
    Gross, Markus
    ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (06):
  • [2] Kinect v2 infrared images correction
    Bobovsky, Zdenko
    Krys, Vaclav
    Mostyn, Vladimir
    INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS, 2018, 15 (01):
  • [3] BEAMFORMING WITH KINECT V2
    Gombots, Stefan
    Egner, Felix
    Kaltenbacher, Manfred
    5. TAGUNG INNOVATION MESSTECHNIK, 2017, : 76 - 81
  • [4] Quantifying Facial Paralysis using the Kinect v2
    Gaber, Amira
    Taher, Mona F.
    Wahed, Manal Abdel
    2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2015, : 2497 - 2501
  • [5] Respiratory Motion Tracking Using Kinect V2
    Silverstein, E.
    Snyder, M.
    MEDICAL PHYSICS, 2016, 43 (06) : 3651 - 3651
  • [6] Correction to: depth analysis of kinect v2 sensor in different mediums
    Aditi Bhateja
    Adarsh Shrivastav
    Himanshu Chaudhary
    Brejesh Lall
    Prem K. Kalra
    Multimedia Tools and Applications, 2022, 81 (25) : 35801 - 35801
  • [7] Evaluating the Accuracy of the Azure Kinect and Kinect v2
    Kurillo, Gregorij
    Hemingway, Evan
    Cheng, Mu-Lin
    Cheng, Louis
    SENSORS, 2022, 22 (07)
  • [8] Multiple Kinect V2 Calibration
    Cordova-Esparza, Diana-Margarita
    Terven, Juan R.
    Jimenez-Hernandez, Hugo
    Vazquez-Cervantes, Alberto
    Herrera-Navarro, Ana-Marcela
    Ramirez-Pedraza, Alfonso
    AUTOMATIKA, 2016, 57 (03) : 810 - 821
  • [9] Multispectral Hand Recognition Using the Kinect v2 Sensor
    Samoil, S.
    Yanushkevich, S. N.
    2016 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2016, : 4258 - 4264
  • [10] Evaluation of the Azure Kinect and Its Comparison to Kinect V1 and Kinect V2
    Tolgyessy, Michal
    Dekan, Martin
    Chovanec, Lubos
    Hubinsky, Peter
    SENSORS, 2021, 21 (02) : 1 - 25