Qi Zhang 张麒

Qi Zhang 张麒

Phd candidate in Computer Vision

University Of Glasgow

University Of Amsterdam

Biography

Zhang Qi is a first-year PhD student in the computer vision group at UvA, researching the optimization of the tracking module for Monocular Gaussian SLAM under the joint supervision of Dr. Martin R. Oswald, Dr. Sezer Karaoglu, and Prof. Theo Gevers. Occasionally, I do interesting things with Prof. Arnoud about real-world robots.

During the master’s studies at the University of Glasgow, he is working on optimizing monocular vSLAM in dynamic environments for his final year project under the supervision of Prof. Paul Siebert, alongside collaborating on the Camera-Assisted Algorithm for Autonomous Exploration Aiding the Visually Impaired in dynamic environments with Dr. Zhihao Lin and Dr. Zhen Tian under the supervision of Dr. Jianglin Lan in Glasgow. Outside his research work, he is an outstanding beatbox performer and an amateur long-distance runner (10km/40min).

!!!

More collaborations are needed (vision-based navigation, joint position estimation in dynamic environments, etc.) Please contact me directly at

q.zhang2@uva.nl

!!!

Reviewer for IROS 2024, Measurement

Interests
  • Visual SLAM
  • Indoor Localization
  • Multi-Object Tracking
Education
  • MSc in Data Science, 2022

    University Of Glasgow

Skills

Python

90%

C++/C

90%

Shell

100%

Statistics

100%

Mathematics

80%

Beatbox

100%

Accomplish­ments

Joint Doctoral Scholarship of the University of Amsterdam and the China Scholarship Council (CSC)
See certificate

Projects

*
CDS-SLAM-Semantic-mapping-in-dynamic-environment

• Method overview:

  1. The semantic module only combines the ORB-SLAM3 and YOLOX-s

  2. The mapping module refers to a system for semantic Labelling 3D Point Cloud in vSLAM

    1. X. Qi, S. Yang, and Y. Yan, Deep Learning Based Semantic Labelling of 3D Point Cloud in Visual SLAM, 10 2018, vol. 428, p. 012023.

• Open source work: The work is open source on Github and presented on Bili (8000+v).

CDS-SLAM-Semantic-mapping-in-dynamic-environment
An Earth Rover dataset recorded at the ICRA@40 party
The ICRA conference is celebrating its anniversary in Rotterdam in September 2024, with as highlight the Happy Birthday ICRA Party at the iconic Holland America Line Cruise Terminal. One month later the IROS conference will take place, which will include the Earth Rover Challenge.
An Earth Rover dataset recorded at the ICRA@40 party

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). DPL-SLAM: Enhancing Dynamic Point-Line SLAM through dense semantic methods. IEEE Sensors Journal.

Contact

I welcome exchanges and collaborations with fellow scholars. Undergraduate students are also welcome to work together on projects. Please feel free to contact me.