My research interest is in visual SLAM (simultaneous localisation and mapping) which is the general problem faced by any robot or other devices with the need to localise, map and navigate a space it has never been in before by utilising various cameras as the main outward looking sensors to achieve this. Although the technology has remarkably matured over the past few years, we still face several challenges: especially the response to rapid motion, handling of extreme lighting variation, minimising overall processing latency and power consumption. My research is therefore focused on developing more robust and efficient SLAM systems by utilising novel sensor and processor hardware technologies such as the event camera.

I have worked in various computer vision related fields including surveillance camera, sensor guided robot, automatic number plate recognition and visual SLAM. And, in my PhD, supervised by Prof. Andrew Davison at Imperial College London, we have developed the first methods which enable incremental reconstruction, tracking and SLAM from event camera data all based on rigorous probabilistic principles, and won the best industry paper award at the British Machine Vision Conference (BMVC) 2014 and the best paper award at the European Conference on Computer Vision (ECCV) 2016. I was also selected as one of the UK winners and the European champion of the Qualcomm Innovation Fellowship 2014 for my research proposal “Visual SLAM
and 3D Reconstruction using an Event-Based Camera”.

Recent News

  • [29/06/2017-14/07/2017] S. Korea and Japan Trips I had a fantastic opportunity to visit many exciting companies and organisations in both S. Korea and Japan, especially to give a talk about our event-based SLAM technology at ...
    Posted 7 Aug 2017, 05:29 by Hanme Kim
  • [02/06/2017] 1st International Workshop on Event-based Vision at ICRA 2017 It was honoured to give a presentation (Event-Based SLAM at Slamcore) on behalf of our startup Slamcore at the first international workshop on event-based vision at ICRA 2017
    Posted 1 Aug 2017, 05:57 by Hanme Kim
  • [26/10/2016] Our work on the iniLabs website Our event camera based SLAM methods [Kim et al., BMVC'14; Kim et al., ECCV'16] are introduced on the iniLabs website.
    Posted 2 Nov 2016, 05:24 by Hanme Kim
  • [13/10/2016] We've got the best paper award at ECCV 2016! We've got the best paper award at ECCV 2016! Big congratulations to Stefan and Andy as well! :)The Qualcomm Innovation Fellowship European champion and the best industry paper award ...
    Posted 14 Oct 2016, 14:07 by Hanme Kim
  • [22/07/2016] Our ECCV'16 paper has been accepted as an oral presentation! I am excited to share our latest work on "Real-Time 3D Reconstruction and 6-DoF Tracking with an Event Camera" in collaboration with Stefan Leutenegger and Andrew Davison which ...
    Posted 6 Oct 2016, 13:52 by Hanme Kim
Showing posts 1 - 5 of 18. View more »

Recent OpenSkill (blog-like)

  • How to debug SceneLib with Eclipse For the last preparation before starting to study about the SceneLib library and Visual SLAM, here is a post describes how to debug SceneLib with Eclipse. Regarding how to install ...
    Posted 24 Jul 2014, 13:36 by Hanme Kim
  • How to install SceneLib 1.0 on Ubuntu 10.04 SceneLib?SceneLib is an open-source C++ library for SLAM designed and implemented by Andrew Davison with additional work by Paul Smith. SceneLib 1.0 is released with full source ...
    Posted 23 Jul 2014, 18:12 by Hanme Kim
Showing posts 1 - 2 of 2. View more »