Abstract
As drone technology advances, using unmanned aerial vehicles for aerial surveys has become the dominant trend in modern low-altitude remote sensing. The surge in aerial video data necessitates accurate prediction for future scenarios and motion states of the interested target, particularly in applications like traffic management and disaster response. Existing video prediction methods focus solely on predicting future scenes (video frames), suffering from the neglect of explicitly modeling target's motion states, which is crucial for aerial video interpretation. To address this issue, we introduce a novel task called Target-Aware Aerial Video Prediction, aiming to simultaneously predict future scenes and motion states of the target. Further, we design a model specifically for this task, named TAFormer, which provides a unified modeling approach for both video and target motion states. Specifically, we introduce Spatiotemporal Attention (STA), which decouples the learning of video dynamics into spatial static attention and temporal dynamic attention, effectively modeling the scene appearance and motion. Additionally, we design an Information Sharing Mechanism (ISM), which elegantly unifies the modeling of video and target motion by facilitating information interaction through two sets of messenger tokens. Moreover, to alleviate the difficulty of distinguishing targets in blurry predictions, we introduce Target-Sensitive Gaussian Loss (TSGL), enhancing the model's sensitivity to both target's position and content. Extensive experiments on UAV123VP and VisDroneVP (derived from single-object tracking datasets) demonstrate the exceptional performance of TAFormer in target-aware video prediction, showcasing its adaptability to the additional requirements of aerial video interpretation for target awareness.
Abstract (translated)
随着无人机技术的进步，使用无人机进行航空测量已成为现代低空遥感的优势趋势。高空视频数据的激增迫使对未来场景和感兴趣目标的动态状态进行准确预测，特别是在交通管理和灾害应对等领域。现有的视频预测方法仅关注预测未来场景（视频帧），忽略了明确建模目标运动状态，这是高空视频解释的关键。为解决这个问题，我们引入了一个名为 Target-Aware Aerial Video Prediction 的新任务，旨在同时预测未来场景和目标的动态状态。此外，我们为这个任务设计了一个名为 TAFormer 的模型，提供了一种统一建模视频和目标运动状态的方法。具体来说，我们引入了 Spatiotemporal Attention（STA），将视频动态学习的空间静态注意力和时间动态注意力解耦，有效建模场景外观和运动。此外，我们设计了一个信息共享机制（ISM），通过促进信息交互来统一建模视频和目标运动。为了减轻在模糊预测中区分目标的努力，我们引入了 Target-Sensitive Gaussian Loss（TSGL），提高了模型对目标位置和内容的敏感度。对于 UAV123VP 和 VisDroneVP（源于单对象跟踪数据集）的实验表明，TAFormer 在目标意识视频预测方面的表现异常出色，展示了它对空中视频解释额外需求的适应能力。
URL
https://arxiv.org/abs/2403.18238
