Airplane Detection Based on Unsupervised Deep Domain Adaptation in Remote Sensing Images
Youssef Ben Youssef, Soufiane Lyaqini, Khalid Fakhar, Elhassane Abdelmounim · Research Square · 2022
Abstract In this work, we use the detection and localization capabilities of the pre-trained Faster Region Convolutional Neuronal Network (Faster R-CNN) model including Resnet50 as the backbone of the architecture. Our model has been trained with a huge benchmark dataset Common Objects in Context (MSCOCO) as a source domain. The model pre-trained is used in Unsupervised Deep Domain adaptation (UDDA) for airplane detection and localization in Remote Sensing Image (RSI) as a domain target. We evaluate our proposed approach using images containing multi-objects (airplanes) on a different scale and types collected from the public dataset for Object Detection in Aerial Images (DOTA) and different airport images extracted from Google Earth. Extensive experiments in a Cloud environment reveal the usefulness of the proposed approach regarding score. UDDA algorthm proposed is a non deterministic machine learning approach for detecting the airplane in RSI.