Debajyoti Karmaker

Work place: American International University, Bangladesh



Research Interests: Computer Vision, Machine Learning, Deep Learning


Dr. Debajyoti Karmaker is working as an Associate professor in the department of computer science at American International University-Bangladesh. He worked as Postdoctoral Research Fellow at University of New South Wales (UNSW), Royal Melbourne Institute of Technology (RMIT), Australian National University (ANU), and Stanford University. Before joining ANU, he completed his Ph.D. from The University of Queensland (UQ). His research interests are in Deep Learning, Computer Vision, & Machine Learning. I am particularly interested in the areas of image classification, object detection, segmentation, bio-inspired collision avoidance strategies, and Robust Decision-making and Learning. Before starting His Ph.D., he was working as a Lecturer at the American International University-Bangladesh (AIUB) - in the Department of Computer Science also worked as a software engineer at Infra Blue Technology (IBT Games).

Author Articles
From Nature to UAV - A Study on Collision Avoidance in Bee Congregation

By Nahin Hossain Uday Md. Zahid Hasan Rejwan Ahmed Md. Mahmudur Rahman Abhijit Bhowmik Debajyoti Karmaker

DOI:, Pub. Date: 8 Jun. 2024

Insects engage in a variety of survival-related activities, including feeding, mating, and communication, which are frequently motivated by innate impulses and environmental signals. Social insects, such as ants and bees, exhibit complex collective behaviors. They carry out well-organized duties, including defense, nursing, and foraging, inside their colonies. For analyzing the behavior of any living entity, we selected honeybees (Apis Mellifera) and worked on a small portion of it. We have captured the video of honeybees flying close to a hive (human-made artificial hive) while the entrance was temporarily sealed which resulted in the” bee cloud”. An exploration of the flight trajectories executed and a 3D view of the” bee cloud” constructed. We analyzed the behaviors of honeybees, especially on their speed and distance. The results showed that the loitering honeybees performed turns that are fully coordinated, and free of sideslips so thus they made no collision between themselves which inspired us to propose a method for avoiding collision in unmanned aerial vehicle. This paper gives the collective behavioral information and analysis report of the small portion of data set (honeybees), that bee maintains a safe distance (35mm) to avoid collision.

[...] Read more.
Other Articles