Keerthy Kusumam

Contact

• workRoom B86
  Jubilee Campus
  Wollaton Road
  Nottingham
  NG8 1BB
  UK
• Keerthy.Kusumam2@nottingham.ac.uk
• https://highlights.cdt.horizon.ac.uk/students/psxkk4

Biography

I am a PhD student affiliated to the CVL University of Nottingham, funded by Horizon. I am supervised by Dr. Georgios Tzimiropoulos. My research focuses on the problem of mood assessment and analysis for detecting mood disorders such as depression from video and audio data in natural environments. The outcomes of the proposed research can be successfully applied in delivering mental health care in automated patient monitoring or therapy administering platforms.

Previously, I have worked as a research assistant focussing on the problem of automated harvesting of broccoli heads at the Lincoln Centre of Autonomous Systems.

Expertise Summary

computer vision, machine learning

Recent Publications

• KUSUMAM, KEERTHY, KRAJNÍK, TOMÁVS, PEARSON, SIMON, DUCKETT, TOM and CIELNIAK, GRZEGORZ, 2017. 3D-vision based detection, localization, and sizing of broccoli heads in the field Journal of Field Robotics. 34(8), 1505-1518
• KUSUMAM, KEERTHY, KRAJNIK, TOMAS, PEARSON, SIMON, CIELNIAK, GRZEGORZ, DUCKETT, TOM and OTHERS, 2016. Can you pick a broccoli? 3D-vision based detection and localisation of broccoli heads in the field
• KRAJNIK, T, 2015. P. deCristoforis, M. Nitsche, K. Kusumam, T. Duckett, et al. Image features and seasons revisited In: European Conference on Mobile Robots.

• View all publications

Past Research

Research Assistant Sep 2016 - Sep 2017, University of Nottingham • Software and game development for the project lazy-iBit to treat amblyopia in children using eye-gaze tracking.

Research Assistant (Feb 2015 - Aug 2016, Lincoln Centre for Autonomous Systems, University of Lincoln

Robotic harvesting of broccoli using 3D vision Jun 2015 to Aug 2016 • Developed a 3D vision system using low-cost RGB-D sensors to recognize and localize mature broccoli heads in the field. • Evaluates different 3D features, machine learning and temporal filtering methods for detection and tracking of broccoli heads in 3D point clouds. • Evaluates Kinect V2, Asus Xtion Pro and Ensenso cameras for imaging along with IMU and GPS sensors. • Funded by BBSRC and Innovate UK.

• KUSUMAM, KEERTHY, KRAJNÍK, TOMÁVS, PEARSON, SIMON, DUCKETT, TOM and CIELNIAK, GRZEGORZ, 2017. 3D-vision based detection, localization, and sizing of broccoli heads in the field Journal of Field Robotics. 34(8), 1505-1518
• KUSUMAM, KEERTHY, KRAJNIK, TOMAS, PEARSON, SIMON, CIELNIAK, GRZEGORZ, DUCKETT, TOM and OTHERS, 2016. Can you pick a broccoli? 3D-vision based detection and localisation of broccoli heads in the field
• KRAJNIK, T, 2015. P. deCristoforis, M. Nitsche, K. Kusumam, T. Duckett, et al. Image features and seasons revisited In: European Conference on Mobile Robots.