Selection of A Computer Vision Algorithm to Track Bed Bug Swarms
Abstract
Modern aerospace systems require a new approach for swarm consensus that is distributed, operates with localized information, uses simple agents, and is easily deployable and expandable. The overarching goal of our research is to advance our understanding of bed-bug behavior and use this understanding to improve performance of aerospace swarms. The central hypothesis is that if we record bed-bug response to CO2 exposure, then we will be able to improve our understanding of collective decision making because the bed bugs coordinate their response to environmental conditions. Previous research began this work by developing an algorithm capable of tracking a single target bed-bug utilizing computer vision. We seek to continue this research to develop an algorithm capable of tracking the interaction of multiple target bed-bugs at once utilizing computer vision. The research for the improved algorithm will consist of two undergraduate students and will result in the examination of six viable approaches and algorithms for tracking multiple targets utilizing computer vision. This poster is the first step of reviewing potential algorithms for selection for the project. Difficulties with our scenario include the small size of the bed bug, lack of identifying characteristics, and multiple cameras where movement needs to be tracked from one another, all of these challenges pose difficulties with many existing individual approaches.
Selection of A Computer Vision Algorithm to Track Bed Bug Swarms
Modern aerospace systems require a new approach for swarm consensus that is distributed, operates with localized information, uses simple agents, and is easily deployable and expandable. The overarching goal of our research is to advance our understanding of bed-bug behavior and use this understanding to improve performance of aerospace swarms. The central hypothesis is that if we record bed-bug response to CO2 exposure, then we will be able to improve our understanding of collective decision making because the bed bugs coordinate their response to environmental conditions. Previous research began this work by developing an algorithm capable of tracking a single target bed-bug utilizing computer vision. We seek to continue this research to develop an algorithm capable of tracking the interaction of multiple target bed-bugs at once utilizing computer vision. The research for the improved algorithm will consist of two undergraduate students and will result in the examination of six viable approaches and algorithms for tracking multiple targets utilizing computer vision. This poster is the first step of reviewing potential algorithms for selection for the project. Difficulties with our scenario include the small size of the bed bug, lack of identifying characteristics, and multiple cameras where movement needs to be tracked from one another, all of these challenges pose difficulties with many existing individual approaches.