SOLD BY OUR OWN SHADOW’ HUMAN DETECTION IN UAV BASED INTERNATIONAL BOUNDARY MONITORING

Moreblessings Shoko, Pardon Maunga

Abstract


With the increased use of drones in geo-spatial work, there is a great need for researchers to contribute to the development of novel application areas especially in developing countries. This study combines two areas in geo-information management – international boundary conflict and UAV based image processing. The study looks at the use of drone imagery in the detection of illegal migrants at unauthorised areas at international boundary regions. International boundaries are made up of connected sections with crisp (man-made) and at times fuzzy (natural) areas that collectively distinguish neighboring territories from each other. Fuzzy boundary areas are common especially in the African region where these cross national borders have often been guided by historical agreements dating back to colonial times. These can be a cause of boundary conflict in many African countries hugely contributing to the development of activities such as cross national crime, military attack and illegal migration which are a growing challenge in world economies. The research presents a complete conceptual design for an early detection alert system suitable for use at border controls that is based on imagery collected by a remotely piloted aerial device. RGB imagery is tested for the presence of human pedestrians in the designated hotspots and the information obtained is sent directly to the mobiles of ground patrol staff who can utilise their smart phones and gadgets to navigate to the identified location for verification.

Full Text: PDF