UAV BASED SURVEILLANCE FOR GEOGRAPHIC AND MANMADE OBJECT DETECTION

摘要

Aerial surveillance has been proven to be important and applicable to a wide range of applications, such as search and rescue missions, resource exploration, wildfire detection etc. In case of search and rescue operations in a disaster area, it is often crucial that the victims are identified and rescued as soon as possible.In the case of flooding, the spatial extent of the disaster area is large, that is, it is difficult to conduct search and rescue operations from the ground by boat. The usual approach for this purpose is to use manned aircraft equipped for covering wide area with special sensors and to assign the actual recognition task (surveillance) to the crew. However, in the usage of manned aircraft, it is difficult to operate from low altitude. A binocular telescope is usually employed in the manned aircraft for the magnification to detect small targets from high altitude. In that case, the range of vision for searching becomes narrow and the possibility of oversight must increase.The objective of this research is to develop an Unmanned Aerial Vehicle (UAV) based surveillance system, which can be used in disaster area in order to enhance search and rescue operation. The main idea is to identify people and estimate their position on the earth surface from the information collected by the system onboard UAV from low altitude.In our experiment, we used a combination of digital cameras, infrared cameras and GPS for mapping a riverside area as a first step of search and rescue operation. In this research, we proposed an image processing technique based on combining digital and infrared images for efficient object detection. The experimental result provides us a basis for extending our research work to develop a system for achieving the final goal.