ece vis

 

 

  
  profile    

Jian(James) Zhao

 

Graduate Student

Advisor: Dr.Sen-Ching (Samson) Cheung


Department of Electrical and Computer Engineering
and
Center for Visualization and Virtual Environments
UNIVERSITY OF KENTUCKY

  
     
 

Contact Information

 
         
 

Office

  

Center for Visualization and Virtual Environments
 One Quality Street, Suite 800
Lexington , KY 40507-1464
Tel: 859-257-1257 (ext 81319)

 

  
   
 

Email:

    
     
 

Education:

    
       
  2005.8 - present

PhD Student

Department of Electrical Engineering, University of Kentucky, USA

 
   

 
2001 - 2005.6

Bachelor of Engineering          
College of Electrical Engineering, Zhejiang University, China.  

Majored in Automation

 

 
2003 - 2005.6

Honors Bachelor

Chu Kechen Honors College, Zhejiang Univ.

Intensive Training Program of High-tech Innovation and Entrepreneurship

  
 

 

  
 

Researches

Publications

  
 
 

Researches:

    
       
 

Under progress :

   
   

Privacy Protected Video Surveillance

  
   

Due to the pervasive use of video surveillance systems, the concern of video privacy became a heating topic. Especially in the working environment, employees working in a confined area may feel their privacy being violated if they are continuously being monitored. In order to deal with this problem, we are building a smart video surveillance system which could hide the privacy of legal people but still provide enough information for security issues.

The system we are building consists of identity recognition, identity concealment and identity preservation. The system first classify the identity of each person, then uses all kinds of object obfuscation techniques to hiding identities and finally, embeds the original information using a novel water-marking technique. You can also refer to our group webpage at http://vis.uky.edu/mialab

 

  
       
   

1.Camera placement for Visual Tagging

 
    Gui epi_privacy  
   

A common goal in many vision applications is to identify and track human objects with distinctive visual features or "tags". Examples range from identifying distinct soccer player by his jersey number to locating the face of an individual that produces a match in a face recognition system. In this paper, we made two contributions to this "visual tagging" problem. First, we propose a general framework for camera placement. This framework can measure the performance of any particular camera placement using simulation method. The optimal placement strategy can be obtained by iterative grid-based linear programming. Second, we focus on tracking specific colored tags used in a privacy-protecting visual surveillance network. By building a color classifier for tag detection and using epipolar geometry between multiple cameras for occlusion handling, our proposed system can identify, track and visually obfuscate individuals whose privacy in the surveillance video needs to be protected.

A poster from the conference can be found here. More experimental result can be found here.

 
   
       

2.Video Inpainting

     
   

Video inpainting is to complete the "holes" (the missing image) in a sequence of video. The same technique can be used in removing certain objects in the video.

We are seeking for the technique which can deal with large space-time holes, occluding objects, and complex indoor situation. We are also trying to use template based inpaiting technique, aiming to make the inpainting visually consistant and computationally efficient. Some primitive results are presented in the following link.

This research is part of the privacy protecting video surveillance project funded by Homeland Security.

Click here to see details

 
   

3.Real-time Face Tracking
   
face_tracker
   

In this project we want to build a system which could detect the faces in a video sequence, keep track of individual and blur the face of specific person. The main contribution of the system is 1) Using a probabilistic frame work, we can integrate the Adaboost face detector and Kalman tracker to improve both the detection and tracking. 2) Constrained by some simple but general condition, like limited motion and almost frontal faces, the system can do all this work in nearly real time.

click here to see the demo(the red rectangles are face detector's outputs and the green ones are the faces tracked, we can see the algorithm can deal with noisy outputs from the detector and situation with no observation).

A privacy protected video surveillance demo using face tracker can be seen here

 

 
 
 

2004.6 - 2005.6

   
         
   

Embedded system of Robots car based on ARM
         
   

The purpose of the program is to design a robot car with a real-time embedded system. Its operating system is ¦ĚC-OS II, which contains files system, network protocols, and USB. We used ARM instead of regular MCU in order to realize a system with more functions, intelligence and stability.

In the end of our project, we completed the motion control, operating system transplantion and Human Computer Interaction(HCI) design.

        arm
 

2003.11 - 2004.5

  
         
   

Automatic System for the delivery of barreled water
         
    The project aimed to design a device that would monitor the water lever and automatically transmit these signals to the company. The project provided an oppertunity for apply the knowledge we learned from textbook such as sensors, Radio Frequency, signal processing, power electronics, and Microcontroller into real life.
         
 

Publications

  
 

(Journals and book chapters)
    Jian Zhao, Sen-Ching S. Cheung and Thinh Nguyen, Optimal Camera Network Configurations for Visual Tagging IEEE Journal of Selected Topics in Signal Processing. 2008, Volume: 2, Issue: 4: pp. 464-479.
     
    Venkatesh, M. V, Jian Zhao, ProfittJr, Larry J and Sen-Ching Cheung, Audio-visual Privacy Protection for Video Conference, Accepted in "Emerging Multimedia Circuits and System Technologies" Workshop within the IEEE International Conference on Multimedia and Expo (ICME 09)., 2009
     
    Jian Zhao, Sen-ching S. Cheung and Thinh Nguyen, Camera Network Configuration and its application in privacy-protected video surveillance, to be appear in book "Multi-Camera Networksˇ±( ELSEVIER) edited by Hamid Aghajan and Andrea Cavallaro. May, 2009
     
    M., V. Venkatesh, S.-C. Cheung and J. Zhao. Efficient Object-Based Video Inpainting. To
appear in Pattern Recognition Letter, Available online 30 March 2008
     
    S.-C. Cheung, Venkatesh, M. V., ?J. Paruchuri, J. Zhao and T. Nguyen. 2008. Protecting and Managing Privacy Information In Video Surveillance Systems. To appear in book Protecting Privacy in Video Surveillance, edited by Andrew Senior, Springer, 2008.
         
        Yushen Han, ?Jian Zhao, Lin Guoying, Zhong Linfeng,? Design and Engineering Realization of Delivery of Barreled Water Based on Wireless and DTMF through Line, ?Journal of Engineering Design(Chinese)(Vol. 12, No. 1), 2005 : 48 - 51
         
        Yu Shenwei, Jian Zhao, Bibo Wang, Wenjun Yan, A Low-cost Mobile Robot Platform with ARM Embedded System, Modern Machinery (Chinese)(Vol 5, 2006)
         
     

    (Conferences)
        Jian Zhao and Sen-Ching Cheung, Human Segmentation by Fusing Visible-light and Thermal Imaginary, accepted to IEEE International Workshop on Visual Surveillance 2009( ICCV workshop).
         
        Zhao, J. and S.-C. Cheung. 2009. Optimal Visual Sensor Planning. IEEE
    International Symposium on Circuits and Systems (ISCAS 09), May 2009.
         
        Venkatesh, M. V, Jian Zhao, ProfittJr, Larry J and Sen-Ching Cheung, Audio-visual Privacy Protection for Video Conference,? Accepted in "Emerging Multimedia Circuits and System Technologies" Workshop within the IEEE International Conference on Multimedia and Expo (ICME 09)., 2009
         
        J. Zhao and S.-C. Cheung, Multi-camera Surveillance with Visual Tagging and Generic Camera Placement.ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC07, September 25-28,2007. Vienna, Austria
         
       

    Cheung, S.-C., J. Zhao and M. V. Venkatesh. Efficient Object-based Video Inpainting. IEEE International Conference on Image Processing, ICIP 2006, October 8-11, Atlanta, GA.
           
        Yu Shenwei, Jian Zhao, Bibo Wang and Wenjun Yan, A Low-cost Mobile Robot Platform with ARM Embedded System, Modern Machinery (Chinese)(Vol 5, 2006)  
           
       

    Han Yushen, Zhao Jian, Lin Guoying, Zhong Linfeng, Design and Engineering Realization of Delivery of Barreled Water Based on Wireless and DTMF through Line, Journal of Engineering Design (Chinese)(Vol. 12, No. 1):48-51