CNN classification subject to practical aspects of Search and Rescue UAV missions

The use of Unmanned Aerial Vehicles (UAVs)equipped with classification systems in Search and Rescue missions has increasingly shown great application potential. There are however pratical concerns regarding limited embedded computing power and adapting the classifier performance to the characteristics of a specific mission. The UAVs may acquire a large number of images during a mission and it is difficult for humans to search throughout this material. For this matter, we study the performance of a leaner Convolutional Neural Network model to select images with salient objects and present a tool that can help in decision making regarding the definition of the classification threshold through the analysis of possible operational impacts and consequences of eventual detection errors. We also show that, in this application, Data Augmentation is important to improve the classifier performance.