A New Fingertip Detection and Tracking Algorithm and Its Application on Writing-in-the-air System The 2014 7th International Congress on Image and Signal.

Slides:



Advertisements
Similar presentations
Hand Gesture for Taking Self Portrait Shaowei Chu and Jiro Tanaka University of Tsukuba Japan 12th July 15 minutes talk.
Advertisements

Robust Part-Based Hand Gesture Recognition Using Kinect Sensor
Wrist Recognition and the Center of the Palm Estimation Based on Depth Camera Zhengwei Yao ; Zhigeng Pan ; Shuchang Xu Virtual Reality and Visualization.
Real-Time Hand Gesture Recognition with Kinect for Playing Racing Video Games 2014 International Joint Conference on Neural Networks (IJCNN) July 6-11,
VisHap: Guangqi Ye, Jason J. Corso, Gregory D. Hager, Allison M. Okamura Presented By: Adelle C. Knight Augmented Reality Combining Haptics and Vision.
Xin Zhang, Zhichao Ye, Lianwen Jin, Ziyong Feng, and Shaojie Xu
Multi-scenario Gesture Recognition Using Kinect Student : Sin- Jhu YE Student Id : MA Computer Engineering & Computer Science University of Louisville.
M.S. Student, Hee-Jong Hong
Real-Time Accurate Stereo Matching using Modified Two-Pass Aggregation and Winner- Take-All Guided Dynamic Programming Xuefeng Chang, Zhong Zhou, Yingjie.
A Robust Method of Detecting Hand Gestures Using Depth Sensors Yan Wen, Chuanyan Hu, Guanghui Yu, Changbo Wang Haptic Audio Visual Environments and Games.
Multiple People Detection and Tracking with Occlusion Presenter: Feifei Huo Supervisor: Dr. Emile A. Hendriks Dr. A. H. J. Stijn Oomes Information and.
Adviser : Ming-Yuan Shieh Student ID : M Student : Chung-Chieh Lien VIDEO OBJECT SEGMENTATION AND ITS SALIENT MOTION DETECTION USING ADAPTIVE BACKGROUND.
Department of Electrical and Computer Engineering He Zhou Hui Zheng William Mai Xiang Guo Advisor: Professor Patrick Kelly ASLLENGE.
A KLT-Based Approach for Occlusion Handling in Human Tracking Chenyuan Zhang, Jiu Xu, Axel Beaugendre and Satoshi Goto 2012 Picture Coding Symposium.
Proceedings of the British Machine Vision Conference (BMVC), 2010 Qi Wang, Xilin Chen, Wen Gao Skin Color Weighted Disparity Competition for Hand Segmentation.
HCI Final Project Robust Real Time Face Detection Paul Viola, Michael Jones, Robust Real-Time Face Detetion, International Journal of Computer Vision,
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
1 Robust Video Stabilization Based on Particle Filter Tracking of Projected Camera Motion (IEEE 2009) Junlan Yang University of Illinois,Chicago.
Efficient Moving Object Segmentation Algorithm Using Background Registration Technique Shao-Yi Chien, Shyh-Yih Ma, and Liang-Gee Chen, Fellow, IEEE Hsin-Hua.
Boundary Detection Jue Wang and Runhe Zhang. May 17, 2004 UCLA EE206A In-class presentation 2 Outline Boundary detection using static nodes Boundary detection.
Human Posture Recognition with Convex Programming Hao Jiang, Ze-Nian Li and Mark S. Drew School of Computing Science Simon Fraser University Burnaby, BC,
Real-time Hand Pose Recognition Using Low- Resolution Depth Images
1 Integration of Background Modeling and Object Tracking Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung IEEE ICME, 2006.
Linear Solution to Scale and Rotation Invariant Object Matching Professor: 王聖智 教授 Student : 周 節.
UNIVERSITY OF MURCIA (SPAIN) ARTIFICIAL PERCEPTION AND PATTERN RECOGNITION GROUP REFINING FACE TRACKING WITH INTEGRAL PROJECTIONS Ginés García Mateos Dept.
IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 20, NO. 11, NOVEMBER 2011 Qian Zhang, King Ngi Ngan Department of Electronic Engineering, the Chinese university.
Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.
Human tracking and counting using the KINECT range sensor based on Adaboost and Kalman Filter ISVC 2013.
Joint Histogram Based Cost Aggregation For Stereo Matching Dongbo Min, Member, IEEE, Jiangbo Lu, Member, IEEE, Minh N. Do, Senior Member, IEEE IEEE TRANSACTION.
Gesture Recognition Using Laser-Based Tracking System Stéphane Perrin, Alvaro Cassinelli and Masatoshi Ishikawa Ishikawa Namiki Laboratory UNIVERSITY OF.
A Fast and Robust Fingertips Tracking Algorithm for Vision-Based Multi-touch Interaction Qunqun Xie, Guoyuan Liang, Cheng Tang, and Xinyu Wu th.
Stereo Matching Information Permeability For Stereo Matching – Cevahir Cigla and A.Aydın Alatan – Signal Processing: Image Communication, 2013 Radiometric.
Fingertip Tracking Based Active Contour for General HCI Application Proceedings of the First International Conference on Advanced Data and Information.
3D Fingertip and Palm Tracking in Depth Image Sequences
Robust Hand Tracking with Refined CAMShift Based on Combination of Depth and Image Features Wenhuan Cui, Wenmin Wang, and Hong Liu International Conference.
A Method for Hand Gesture Recognition Jaya Shukla Department of Computer Science Shiv Nadar University Gautam Budh Nagar, India Ashutosh Dwivedi.
Takuya Matsuo, Norishige Fukushima and Yutaka Ishibashi
1 Iterative Multimodel Subimage Binarization for Handwritten Character Segmentation Author: Amer Dawoud and Mohamed S. Kamel Source: IEEE TRANSACTIONS.
Tracking with CACTuS on Jetson Running a Bayesian multi object tracker on a low power, embedded system School of Information Technology & Mathematical.
出處: Signal Processing and Communications Applications, 2006 IEEE 作者: Asanterabi Malima, Erol Ozgur, and Miijdat Cetin 2015/10/251 指導教授:張財榮 學生:陳建宏 學號: M97G0209.
Tracking with CACTuS on Jetson Running a Bayesian multi object tracker on an embedded system School of Information Technology & Mathematical Sciences September.
指導老師 : 蔡亮宙 報告者 : 黃柏愷 A new method of vehicle license plate location under complex scenes.
Online Kinect Handwritten Digit Recognition Based on Dynamic Time Warping and Support Vector Machine Journal of Information & Computational Science, 2015.
Human pose recognition from depth image MS Research Cambridge.
Action and Gait Recognition From Recovered 3-D Human Joints IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS— PART B: CYBERNETICS, VOL. 40, NO. 4, AUGUST.
Interactive Sand Art Drawing Using RGB-D Sensor
Fingertip Detection with Morphology and Geometric Calculation Dung Duc Nguyen ; Thien Cong Pham ; Jae Wook Jeon Intelligent Robots and Systems, IEEE/RSJ.
Fast and Robust Algorithm of Tracking Multiple Moving Objects for Intelligent Video Surveillance Systems Jong Sun Kim, Dong Hae Yeom, and Young Hoon Joo,2011.
Jiu XU, Axel BEAUGENDRE and Satoshi GOTO Computer Sciences and Convergence Information Technology (ICCIT), th International Conference on 1 Real-time.
Automated Fingertip Detection
Su-ting, Chuang 1. Outline Introduction Related work Hardware configuration Detection system Optimal parameter estimation framework Conclusion 2.
Robust Nighttime Vehicle Detection by Tracking and Grouping Headlights Qi Zou, Haibin Ling, Siwei Luo, Yaping Huang, and Mei Tian.
Journal of Visual Communication and Image Representation
A Recognition Method of Restricted Hand Shapes in Still Image and Moving Image Hand Shapes in Still Image and Moving Image as a Man-Machine Interface Speaker.
Preliminary Transformations Presented By: -Mona Saudagar Under Guidance of: - Prof. S. V. Jain Multi Oriented Text Recognition In Digital Images.
Marco Maisto, Massimo Panella, Luca Liparulo, and Andrea Proietti
Trajectory-Based Ball Detection and Tracking with Aid of Homography in Broadcast Tennis Video Xinguo Yu, Nianjuan Jiang, Ee Luang Ang Present by komod.
Zhaoxia Fu, Yan Han Measurement Volume 45, Issue 4, May 2012, Pages 650–655 Reporter: Jing-Siang, Chen.
Video object segmentation and its salient motion detection using adaptive background generation Kim, T.K.; Im, J.H.; Paik, J.K.;  Electronics Letters 
Vision-based Android Application for GPS Assistance in Tunnels
ROBUST FACE NAME GRAPH MATCHING FOR MOVIE CHARACTER IDENTIFICATION
Real-Time Human Pose Recognition in Parts from Single Depth Image
NBKeyboard: An Arm-based Word-gesture keyboard
Text Detection in Images and Video
Dingding Liu* Yingen Xiong† Linda Shapiro* Kari Pulli†
Higher School of Economics , Moscow, 2016
Estimation of Skin Color Range Using Achromatic Features
Gradient Domain Salience-preserving Color-to-gray Conversion
Higher School of Economics , Moscow, 2016
Higher School of Economics , Moscow, 2016
Presentation transcript:

A New Fingertip Detection and Tracking Algorithm and Its Application on Writing-in-the-air System The th International Congress on Image and Signal Processing (CISP) Kunpeng Li and Xin Zhang School of Electronic and Information Engineering, South China University of Technology Speaker: Yi-Ting Chen

Outline Introduction Flowchart Proposed Method –Hand Mode Estimation –Detection and Tracking by the dual mode Experimental Result Conclusions 2

Introduction Natural Human Computer Interaction (NHCI) is an important and vibrant research topic for decades. NHCI always brings effective communication with the computer and great convenience to our daily life. Application: finger-painting, virtual mouse, gesture recognition, sign-language, writing system, etc. [1][2] present a writing-in-the-air (WIA) system. 3

Reference [1] Z. Ye, X. Zhang, L. Jin, Z. Feng, and S. Xu, “Finger-writing-in-the air system using kinect sensor,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), [2] L. J. X Zhang, Z Ye, “A new writing experience: Finger writing in the air using a kinect sensor.” MultiMedia, IEEE, vol. 20, pp. 85–93,

Related Work The algorithm failed with the fast writing situation and environment with challenging lighting background. 5 [1] Z. Ye, X. Zhang, L. Jin, Z. Feng, and S. Xu, “Finger-writing-in-the air system using kinect sensor,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), 2013.

Main Contributions We propose a new tracking-detection based robust and accurate fingertip position estimation algorithm. 6

Flowchart 7

8

Hand Mode Estimation We propose to use the projected 2D distance between the arm point and palm point as an additional feature. 9

Hand Mode Estimation 10

Hand Mode Estimation 11 Side mode Frontal mode

Flowchart 12

Detection-based Side Mode Fingertip Estimation Combine the skin and depth model’s result, the algorithm called choose-to-trust algorithm (CTTA). (1) Determine the segmentation quality. (2) Choose one segmentation model to trust for the final segmentation. (3) Estimate the fingertip again. 13

Detection-based Side Mode Fingertip Estimation 14

Detection-based Side Mode Fingertip Estimation (3) Estimate the fingertip again. –We use the decided model to add hand region which is omitted in the DSB-MM. 15

Flowchart 16

The Oriented Gradient Feature Using simplified oriented gradient (OG) feature to describe the fingertip. –The fingertip is not always the point with minimum depth. 17

The Oriented Gradient Feature 18

Tracking Feature 19 [14] R. E. Kalman, “A new approach to linear filtering and prediction problems,” Journal of Basic Engineering, vol. 82, pp. 35–45, 1960.

Multi-objective Optimization Strategy 20

Multi-objective Optimization Strategy 21

Finger-Writing Character Recognition Using mean filter to remove the noise caused by wrong fingertip detection. Reducing feature by LDA (Linear Discriminant Analysis) Recognized by MQDF classifier. It can recognize 6,763 frequent Chinese characters, 26 English letters (upper case and lower case) and 10 digits. 22

Experimental Results The testing system: –PC with Intel Core i CPU, 3.10GHz –4GB RAM –Only one Kinect with 20fps Three experiments are designed here including: –Experiment on hand mode detection –fingertip estimation –character recognition 23

Hand Mode detection We manually marked out hand mode of 1636 frames and regarded them as ground truth. 24

Fingertip Detection and Tracking Data Set: –SCUT-WIA-I : 3207 frames –SCUT-WIA-II : 3293 frames Writing fast, ambient environment changing Fingertip positions are manually labeled. We calculate the Euclidean distance between labeled and estimated fingertip position as error distance. 25

Fingertip Detection and Tracking 26 (Pixels)

Fingertip Detection and Tracking 27

Character Recognition Conducted on 375 videos totally 44,522 frames. Successfully recognize 6,763 frequent Chinese, all English character (lower and upper cases) and digits. 28

Conclusion In general, our fingertip estimation maintain real-time properties and improve the recognition accuracy. The hand-mode detection can achieves 97.63% in precision. For the side-mode, our CTTA is more robust. For the frontal-mode, our tracking feature and OG feature solves the detection problem. The final character recognition rate reaches 100% in the first five candidates for all types of characters. 29

Thanks for your listening! 30