使用分布式摄像机网络的异方差地理空间跟踪
Heteroskedastic Geospatial Tracking with Distributed Camera Networks
AI总结：
针对分布式摄像机网络中无法集中原始图像且需估计位置不确定性的地理空间跟踪问题，提出四摄像机数据集与含新型骨干的可微分跟踪建模框架。
摘要：
近年来，视觉目标跟踪取得了显著进展。然而，这类工作绝大多数聚焦于在单个摄像机的图像平面内跟踪目标，而忽略了与预测目标位置相关的不确定性。在本工作中，我们关注利用分布式摄像机网络数据进行地理空间目标跟踪的问题。其目标是在遵守禁止集中原始图像数据的通信约束的同时，预测目标在地理空间坐标中的轨迹以及目标位置的不确定性。我们提出了一个新颖的单目标地理空间跟踪数据集，其中包含来自四台摄像机组成的网络的高精度目标位置真值和视频数据。我们提出了一个用于解决该任务的建模框架，包括一个新颖的骨干模型，并探究了通过可微分跟踪器进行不确定性校准和微调如何影响性能。
英文摘要：
Visual object tracking has seen significant progress in recent years. However, the vast majority of this work focuses on tracking objects within the image plane of a single camera and ignores the uncertainty associated with predicted object locations. In this work, we focus on the geospatial object tracking problem using data from a distributed camera network. The goal is to predict an object's track in geospatial coordinates along with uncertainty over the object's location while respecting communication constraints that prohibit centralizing raw image data. We present a novel single-object geospatial tracking data set that includes high-accuracy ground truth object locations and video data from a network of four cameras. We present a modeling framework for addressing this task including a novel backbone model and explore how uncertainty calibration and fine-tuning through a differentiable tracker affect performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
