Workshops
International Conference on Image Processing and Robotics

Human life sign detection from drone video

Asanka Perera
Postdoctoral Researcher and Robotics & Autonomous Systems Lab Manager
UNSW Canberra

In search and rescue operations, it is crucial to rapidly distinguish between those who are alive and those who are not. With this information, emergency teams can prioritize their operations to save more lives. However, in some natural disasters, people may be lying on the ground, covered with dust, debris, or ashes, making them difficult to detect through video analysis tuned to human shapes. We have introduced a technology that estimates the locations of people from aerial videos using image and signal processing designed to detect breathing movements. Our study demonstrates the effectiveness of this method in detecting both clearly visible people and those who are fully occluded by debris.

Use of Drone based Spectral imaging in agricultural decision making- an introduction

Chamika Janith Perera
PhD Researcher
Graduate School of Engineering, Mie University, Japan

Modernizing the agricultural decision-making process is a long-overdue step to meet the increasing demand with limited available resources. Sensing plays a crucial role in prediction, estimation, and detection tasks within agriculture. Among the various sensing methods, spectral sensing (Hyperspectral and Multispectral) has emerged as a key component in the decision-making process. This workshop session will focus on introducing hyperspectral and multispectral imaging in the context of agricultural decision-making. We will discuss the importance of sensing, what is spectral imaging, key highlights of spectral imaging, the current state of the art, entry barriers, and will place specific emphasis on drone-based sensing methodologies.