Object detection from aerial and satellite remote sensing images has been an active research topic over the past decade. Thanks to the increase in computational resources and data availability, deep learning-based object detection methods have achieved numerous successes in computer vision, and more recently in remote sensing. However, the ability of current detectors to deal with (very) small objects still remains limited. In particular, the fast detection of small objects from a large observed scene is still an open question. In this work, we address this challenge and introduce an enhanced one-stage deep learning-based detection model, called You Only Look Once (YOLO)-fine, which is based on the structure of YOLOv3. Our detector is designed to be capable of detecting small objects with high accuracy and high speed, allowing further real-time applications within operational contexts. We also investigate its robustness to the appearance of new backgrounds in the validation set, thus tackling the issue of domain adaptation that is critical in remote sensing. Experimental studies that were conducted on both aerial and satellite benchmark datasets show some significant improvement of YOLO-fine as compared to other state-of-the art object detectors.

This article tackles the problem of detecting small objects in satellite or aerial remote sensing images by relying on super-resolution to increase image spatial resolution, thus the size and details of objects to be detected. We show how to improve the super-resolution framework starting from the learning of a generative adversarial network (GAN) based on residual blocks and then its integration into a cycle model. Furthermore, by adding to the framework an auxiliary network tailored for object detection, we considerably improve the learning and the quality of our final super-resolution architecture, and more importantly increase the object detection performance. Besides the improvement dedicated to the network architecture, we also focus on the training of super-resolution on target objects, leading to an object-focused approach. Furthermore, the proposed strategies do not depend on the choice of a baseline super-resolution framework, hence could be adopted for current and future state-of-the-art models. Our experimental study on small vehicle detection in remote sensing data conducted on both aerial and satellite images (i.e., ISPRS Potsdam and xView datasets) confirms the effectiveness of the improved super-resolution methods to assist with the small object detection tasks.

Roads are important elements in geographic information systems and remote sensing applications. Their automatic extraction is challenging when only aerial or satellite images are used. Recently, some promising attempts have been made with (incomplete) path opening/closing, morphological filters able to deal with curvilinear structures. We propose here to apply morphological path filters not on pixels directly but rather on regions representing road segments, in order to improve both efficiency and robustness. The overall process is organized in two steps: first we map road segments by rectangular areas made of similar content, before we connect such segments into paths of segments or polylines using region-based path filtering. Robustness to occlusion is ensured through the adaptation of the incomplete path filtering strategy to the region scale, while better discrimination between road segments and other objects is achieved through an hit-or-miss transform that exploits background knowledge. Experiments conducted on several satellite images illustrate the interest of the proposed approach, and shows it outperforms pixelwise detection.