Real-Time Vehicle Detection in Satellite Videos: Transitioning From Large Scenes to Clusters

Detecting vehicles from satellite videos presents several significant challenges: 1) satellite video frames typically possess extremely high resolutions, often containing millions or even hundreds of millions of pixels, whereas onboard computational resources remain constrained; 2) the nonuniform spatial distribution of vehicles results in inefficient allocation of computational resources; and 3) vehicles are typically small with limited distinguishing features, further complicating the detection task. In this article, we propose large scenes to clusters (LSCNet), an efficient and lightweight satellite video vehicle detection network specifically designed to address these challenges. To alleviate the difficulties associated with large-scale imagery and uneven vehicle distributions, we introduce a plug-and-play object cluster module (OCM). The OCM leverages interframe information from satellite video to adaptively identify and prioritize clustered regions, thereby enhancing detection precision. Furthermore, to improve the extraction of discriminative features from small-sized vehicles, we propose a lightweight multiframe feature aggregation module (MFAG), which effectively captures the spatiotemporal characteristics of vehicles while maintaining computationally efficiency. In addition, we refine the regression loss function by integrating the Kullback-Leibler divergence (KLD), enabling the generation of high-quality bounding boxes and significantly boosting the detection performance for small objects. Experimental evaluations on the Jilin-1 satellite video dataset demonstrate that the proposed method achieves improved detection accuracy while maintaining real-time performance, thereby validating its robustness and practical effectiveness.