Deep Vehicle Detection in Satellite Video

Abstract

This work presents a deep learning approach for vehicle detection in satellite video. Vehicle detection is perhaps impossible in single EO satellite images due to the tininess of vehicles (4-10 pixel) and their similarity to the background. Instead, we consider satellite video which overcomes the lack of spatial information by temporal consistency of vehicle movement. A new spatiotemporal model of a compact 3 × 3 convolutional, neural network is proposed which neglects pooling layers and uses leaky ReLUs. Then we use a reformulation of the output heatmap including Non-Maximum-Suppression (NMS) for the final segmentation. Empirical results on two new annotated satellite videos reconfirm the applicability of this approach for vehicle detection. They more importantly indicate that pretraining on WAMI data and then fine-tuning on few annotated video frames for a new video is sufficient. In our experiment only five annotated images yield a 𝐹 1 score of 0.81 on a new video showing more complex traffic patterns than the Las Vegas video. Our best result on Las Vegas is a 𝐹 1 score of 0.87 which makes the proposed approach a leading method for this benchmark.