LAUSR

In this paper, we propose an event-guided support vector machine (ESVM) for tracking high-speed moving objects. Tracking fast-moving objects with low frame rate cameras is always difficult due to motion blur and large displacements. The accuracy problem can be solved by using high frame rate cameras at the expense of tremendous computational cost. For this issue, our ESVM incorporates event-based guiding methods into the traditional structured support vector machine to improve the tracking accuracy at a relatively low-complexity level. The event-based guiding methods include two models, event position guided search localization and event intensity guided sample supplement, which are based on the event features of the CeleX motion sensor. The motion sensor continuously responds to intensity change, which is generally related to object motion. Once it has detected intensity change, the motion sensor outputs event packages, and each of them contains the pixel location, time stamp, and pixel illumination. The generated events are continuous in the temporal domain and thus record the motion trajectory of fast-moving objects, which cannot be fully captured by frame-based cameras. In this paper, we convert high-speed test sequences into sequences of spiking events recorded by the CeleX motion sensor. Our approach presents fairly high computational efficiency, and experiments over sequences from multiple tracking benchmarks demonstrate the superior accuracy and real-time performance of our method, compared to the state-of-the-art trackers.