基于事件的滑动窗口优化连续时间特征跟踪
Event-Based Feature Tracking in Continuous Time with Sliding Window Optimization
摘要：
我们提出了一种新的方法在事件相机的连续时间特征跟踪。为此，我们通过沿着时空中的估计轨迹对齐事件来跟踪特征，使得在图像平面上的投影导致最尖锐的事件补丁图像。轨迹由$n^{th}$阶B样条参数化，该样条在$(n-2)^{th}$导数上是连续的。与以前的工作相比，我们优化的曲线参数在一个滑动窗口的方式。在一个公共数据集上，我们通过实验证实，所提出的滑动窗口B样条优化导致比以前的工作更长，更准确的特征跟踪。
英文摘要：
We propose a novel method for continuous-time feature tracking in event cameras. To this end, we track features by aligning events along an estimated trajectory in space-time such that the projection on the image plane results in maximally sharp event patch images. The trajectory is parameterized by $n^{th}$ order B-splines, which are continuous up to $(n-2)^{th}$ derivative. In contrast to previous work, we optimize the curve parameters in a sliding window fashion. On a public dataset we experimentally confirm that the proposed sliding-window B-spline optimization leads to longer and more accurate feature tracks than in previous work.
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。
