Vehicle detection and counting from VHR satellite images: efforts and open issues
This work addresses the problem of monitoring economic and urban growth for urban planners and analysts, but it is incremental as it applies existing deep learning methods to a specific domain.
The paper tackles vehicle counting from high-resolution satellite images to infer activity levels at infrastructure sites, achieving precision rates over 85% and recall rates of 76.4% and 71.9% using Tiramisu and YOLO models.
Detection of new infrastructures (commercial, logistics, industrial or residential) from satellite images constitutes a proven method to investigate and follow economic and urban growth. The level of activities or exploitation of these sites may be hardly determined by building inspection, but could be inferred from vehicle presence from nearby streets and parking lots. We present in this paper two deep learning-based models for vehicle counting from optical satellite images coming from the Pleiades sensor at 50-cm spatial resolution. Both segmentation (Tiramisu) and detection (YOLO) architectures were investigated. These networks were adapted, trained and validated on a data set including 87k vehicles, annotated using an interactive semi-automatic tool developed by the authors. Experimental results show that both segmentation and detection models could achieve a precision rate higher than 85% with a recall rate also high (76.4% and 71.9% for Tiramisu and YOLO respectively).