Ultrafast Facial Tracker Using Generic Cameras with Applications in Intelligent Lifestyle

The core of Human-Computer Interaction (HCI) is to analyze and understand the user’s intension, which can be mostly manifested from the facial movement and expression of the user. Hence, the stage facial detection and tracking is extremely important in an user-friendly interface between human and computer. In ULSee, we developed an ultrafast markerless facial tracking system which is robust to variation in environmental lighting, pose and occlusion. It can be run at a speed of 10 ms/frame on an iPhone 6S system. With such accuracy and speed, it can be used to support many intelligent HCI applications. In this work, we envision an intelligent lifestyle in the future that can be built upon the basis of the ULSee’s ultrafast markerless facial tracker, ranging from virtual reality, augmented reality, real-time facial recognition and driver drowsiness detection. We believe, that through the joint force between ULSee’s world-class tracker and our clients, more user-awareness HCI application will be invented and a new lifestyle will arise.

[1]  Chih-Hsing Chu,et al.  Human-centric design personalization of 3D glasses frame in markerless augmented reality , 2012, Adv. Eng. Informatics.

[2]  KangKang Yin,et al.  Virtual Try-On Using Kinect and HD Camera , 2012, MIG.

[3]  Simon Lucey,et al.  Real-time avatar animation from a single image , 2011, Face and Gesture 2011.

[4]  Yongli Zhu,et al.  Robust face tracking-by-detection via sparse representation , 2015, 2015 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC).

[5]  Miaolong Yuan,et al.  A mixed reality system for virtual glasses try-on , 2011, VRCAI.

[6]  Tal Hassner,et al.  Effective face frontalization in unconstrained images , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Henry Medeiros,et al.  Cluster-Based Distributed Face Tracking in Camera Networks , 2010, IEEE Transactions on Image Processing.

[8]  Lu Fang,et al.  Making 3D Eyeglasses Try-on practical , 2014, 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[9]  E. Painkras,et al.  FaceProcessor: A Framework for Hardware Design and Implementation of a Dynamic Face Tracking System , 2005, 2005 5th International Conference on Information Communications & Signal Processing.

[10]  Timothy F. Cootes,et al.  Using grey-level models to improve active shape model search , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[11]  Timothy F. Cootes,et al.  Multi-resolution search with active shape models , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[12]  Anke Neumann,et al.  Graphical Gaussian Shape Models and Their Application to Image Segmentation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Suhuai Luo,et al.  Accurate object segmentation using novel active shape and appearance models based on support vector machine learning , 2014, 2014 International Conference on Audio, Language and Image Processing.

[14]  Hamid Krim,et al.  Flexible Skew-Symmetric Shape Model for Shape Representation, Classification, and Sampling , 2007, IEEE Transactions on Image Processing.

[15]  Jian Sun,et al.  Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Timothy F. Cootes,et al.  Building 3-D Statistical Shape Models by Direct Optimization , 2010, IEEE Transactions on Medical Imaging.

[17]  S. Grover,et al.  A real time face tracking system using rank deficient face detection and motion estimation , 2008, 2008 7th IEEE International Conference on Cybernetic Intelligent Systems.

[18]  Franck Luthon,et al.  Robust face tracking using colour Dempster-Shafer fusion and particle filter , 2006, 2006 9th International Conference on Information Fusion.

[19]  Haitao Yu,et al.  Interactive Virtual Try-On Based on Real-Time Motion Capture , 2012, PCM.

[20]  Laura Igual,et al.  Continuous procrustes analysis to learn 2D shape models from 3D objects , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[21]  Yuki Sugawara,et al.  3-D shape model retrieval using multi range image phase correlation method , 2012, 2012 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[22]  Jake K. Aggarwal,et al.  Occlusion robust multi-camera face tracking , 2011, CVPR 2011 WORKSHOPS.

[23]  Fillia Makedon,et al.  High dimensional statistical shape model for medical image analysis , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[24]  Qiang Ji,et al.  Robust Face Tracking via Collaboration of Generic and Specific Models , 2008, IEEE Transactions on Image Processing.