Research

MY Research Topics

Person Re-Identification Using Deep Learning

Person re-identification is a critical task in video surveillance. Person re-identification problem can be defined as recognizing the same person across a bunch of cameras with overlapping fields of view with the given query image.

Read More related to Deep Learning

Remote Heart Rate Estimation

Heart Rate (HR) is an important physiological sign since we can monitor our cardiac activity through it and cardiac diseases are directly connected to the human life. Video-based HR estimation is a safe and low-cost remote HR estimation technique originated from the Photoplethysmography. By analyzing the human face video, we can estimate the small varaition underneath the skin which carries the HR signal.

Read More

EXPERIENCE

MY Educational and Professional Timeline

  • 2017 May - Aug (Internship)
  • 2013 - Present
  • 2012 - 2013
  • 2010 - 2012
  • 2006 - 2010
  • Dolby Laboratories, Sunnyvale, CA

    Video Imaging Research Intern

  • VIPER Lab, Purdue University, West Lafayette, IN


    Research Experience

    Person Re-Identification

    : Learning discriminative spatial and temporal features using two stream CNN

    Video-based Health Measurement System

    : Heart Rate and Respiration Rate Estimation Algorithm from Video


    Teaching Experience

    Fall 2016 : Engineering Projects in Community Service (EPICS)

    Fall 2015 - Spring 2016 : ECE 301 Signals and Systems

    Spring 2014 - Spring 2015 : ECE 208 Electronic Devices and Design Laboratory (Lab Instructor)


  • Research Engineer

    Development of Android Application Framework.

    Development of Web Application for Web OS.

  • IILAB (Image and Information Lab), Yonsei University, Seoul, Korea


    Research Assistant

    03/2010 - 02/2012

    Master of Science in Electrical and Electronic Engineering

    Thesis : A contour map based false contour reduction algorithm for bit depth expansion

  • Ewha Womans University, Seoul, Korea

    03/2006 - 02/2010

    Bachelor of Science degree in Electronic and Information Engineering

What I have achieved

MY Publication

Conference

  1. Dahjung Chung, K. Tahboub, and E. J. Delp, “A Two Stream Siamese Convolutional Neural Network for Person Re-identification,” Proceedings of the International Conference on Computer Vision, October 2017, to appear.

  2. Dahjung Chung, Jeehyun Choe, Maggie E. O’Haire, A.J. Schwichtenberg, and Edward J. Delp,"Improving video-based heart rate estimation," Proceedings of the IS&T International Symposium on Electronic Imaging, February 2016, San Francisco, CA.

  3. Jeehyun Choe, Dahjung Chung, A. J. Schwichtenberg, and Edward J. Delp," Improving video-based resting heart rate estimation: A comparison of two methods ," Proceedings of the IEEE 58th International Midwest Symposium on Circuits and Systems, pp. 1–4, August 2015, Fort Collins, CO.

  4. Soongi Hong, Dahjung Chung; , Yoon Sik Choe," Selective merging-based reference frame memory compression," , Proceedings of the 2011 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PacRim), pp. 896–900, Aug 2011.

  5. Dahjung Chung, Hong Lin Jin, Yoon Sik Choe," Reversible data hiding algorithm for high quality stego images," Proceedings of the TENCON - IEEE Region 10 Conference on,pp.251,254, 21-24 Nov. 2011