Long-term object tracking with a moving event camera

This paper presents a long-term object tracking algorithm for event cameras. A first of its kind for these revolutionary cameras, the tracking framework uses a discriminative representation for the object with online learning, and detects and re-tracks the object when it comes back into the field-of-view. One of the key novelties is the use of an event-based local sliding window technique that performs reliably in scenes with cluttered and textured background. In addition, Bayesian bootstrapping is used to assist real-time processing and boost the discriminative power of the object representation. Extensive experiments on a publicly available event camera dataset demonstrates the ability to track and detect arbitrary objects of various shapes and sizes. This is a significant improvement compared to earlier works that simply track objects as long as they are visible under simpler background settings. In other words, when the object re-enters the field-of-view of the camera, a data-driven, global sliding window based detector locates the object under different view-point conditions for subsequent tracking.