He Zhang (David)

He Zhang (David)

Postdoc in Computer Science

Virginia Commonwealth University (VCU)

Biography

He Zhang is a Postdoctoral Associate at VCU Robotics Lab. His research interests include SLAM, robotics vision, indoor localization, 3D mapping, human pose tracking, and machine learning. He endeavors to build robust intelligent systems to assist blind people for navigation (CRC, W-ROMA) and mobility-impaired patients for rehabilitation (Q-HARP).

Interests

  • Simultaneous Localization and Mapping (SLAM)
  • Visual-Inertial Odometry (VIO)
  • Computer Vision Applications
  • Machine Learning
  • 3D Mapping & Modeling
  • Human Pose Estimation & Gait Analysis

Education

  • Postdoc in Computer Science, 2018-now

    Virginia Commonwealth University

  • Ph.D. in Electrical & Computer Engineering, 2014-2018

    University of Arkansas at Little Rock

  • Study Certificate of Computer Architecture, 2009-2010

    University of Chinese Academy of Sciences

  • B.E. in Computer Science & Technology, 2005-2009

    Chinese University of Mining and Technology at Beijing

Experience

Academic & Industrial

 
 
 
 
 

Postdoctoral Associate

Virginia Commonwealth University

Jun 2018 – Present Virginia

  • Develop 3D camera based computer vision methods for:

    • Pose estimation of a wearable object manipulation aid (W-ROMA)
    • Human pose tracking for a quadrupedal human-assistive robotic platform (Q-HARP)

  • Write grant proposals

  • Mentor and guide graduate students

  • Teach a graduate level course

 
 
 
 
 

Research Assistant

University of Arkansas at Little Rock

Aug 2014 – May 2018 Arkansas
  • Develop 3D ToF camera based SLAM/VIO methods to localize an robotic navigation aid (RNA) for assitive blind navigation
  • Develop and deploy software systems on two RNA propotypes, Smart Cane (SC) and Co-Robotic Cane(CRC), for human subject test
  • Develop RGB-D camera based computer vision methods to detect human walking pattern for a robotic walker
 
 
 
 
 

Research Assistant in Machine Intelligent Team

Lenovo (Beijing) R&D

May 2010 – May 2014 Beijing
  • Develop 2D Lidar/RGB-D camera based localization methods for mobile robots
  • Develop Client-Server framework to realize hierarchical SLAM
  • Survey advanced techniques for topics: 2D-3D SLAM, 3D HCI, and Cloud-enhanced vision applications, etc.

Recent Projects

Co-Robotic Cane (CRC)

A CRC to aid a visually impaired person for wayfinding and obstacle avoidance.

W-ROMA

A Wearable Robotic Object Manipulation Aid (W-ROMA) to assist a visually impaired individual to locate and manipulate a target object.

Q-HARP

A quadrupedal human-assistive robotic platform (Q-HARP) to aid the elderly for safe walking.

Recent Publications

Quickly discover relevant content by filtering publications.

The VCU-RVI Benchmark: Evaluating Visual Inertial Odometry for Indoor Navigation Applications with an RGB-D Camera

This paper presents VCU-RVI, a new visual inertial odometry (VIO) benchmark with a set of diverse data sequences in different indoor …
He Zhang, Lingqiu Jin, Cang Ye
Code Video
The VCU-RVI Benchmark: Evaluating Visual Inertial Odometry for Indoor Navigation Applications with an RGB-D Camera

DUI-VIO: Depth Uncertainty Incorporated Visual Inertial Odometry based on an RGB-D Camera

This paper presents a new RGB-D-camera-based visual-inertial odometry (VIO), termed DUI-VIO, for estimating the motion state of the …
He Zhang, Cang Ye
Video
DUI-VIO: Depth Uncertainty Incorporated Visual Inertial Odometry based on an RGB-D Camera

A Visual Positioning System for Indoor Blind Navigation

This paper presents a new visual positioning system (VPS) for real-time pose estimation of a robotic navigation aid (RNA) that is used …
He Zhang, Cang Ye
Video
A Visual Positioning System for Indoor Blind Navigation

Camera Intrinsic Parameters Estimation by Visual Inertial Odometry for a Mobile Phone with Application to Assisted Navigation

The increasing computing and sensing capabilities of modern mobile phones have spurred research interests in developing new …
Lingqiu Jin, He Zhang, Cang Ye
PDF DOI
Camera Intrinsic Parameters Estimation by Visual Inertial Odometry for a Mobile Phone with Application to Assisted Navigation

Plane-Aided Visual-Inertial Odometry for 6-DOF Pose Estimation of a Robotic Navigation Aid

The classic visual-inertial odometry (VIO) method estimates the 6-DOF pose of a moving camera by fusing the camera’s ego-motion …
He Zhang, Cang Ye
PDF DOI
Plane-Aided Visual-Inertial Odometry for 6-DOF Pose Estimation of a Robotic Navigation Aid
See all publications

Accomplish­ments

2nd Place in IROS 2020 UZH-FPV VIO Competition

IROS 2020 Workshop on Perception, Learning, and Control for Autonomous Agile Vehicles Oct 2020

Postdoc How-to Talks series

VCU Tompkins-McCaw Library Aug 2019

Self-Driving Car Engineer

Udacity Jun 2018
See certificate

System Engineering Award for Excellent Ph.D. Student

Systems Engineering Department of UA Little Rock Apr 2018

2nd Place Award for 3MT Competition at UA Little Rock

UA Little Rock Feb 2018

Deep Learning Nanodegree Foundation

Udacity Nov 2017
See certificate

Congressional BioMedical Technology Exhibition

American Institute for Medical and Biological Engineering May 2017
Demonstrated CoRobotic Cane at AIMBE Congressional BioMedical Technology Exhibition

NIH Coulter College Commercializing Innovation Program

Coulter Investment Forum Apr 2017
Completed C3i course and Final Pitch

Congressional Robotics Caucus

Computing Research Association Jun 2016
Demonstrated Smart Cane at Congressional Robotics Caucus

Autonomous Navigation for Flying Robots

edX Jul 2014
See certificate

Contact