Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking
This work addresses the lack of event-based tracking methods for textured objects and cluttered backgrounds, offering a solution for applications in fast motion and low-light conditions.
The paper tackles the problem of generic bounding box-based object tracking using event cameras by proposing an asynchronous Event-based Tracking-by-Detection (ETD) method with an Adaptive Time-Surface conversion algorithm, achieving superior performance compared to seven existing methods in challenging environments.
Event cameras, which are asynchronous bio-inspired vision sensors, have shown great potential in a variety of situations, such as fast motion and low illumination scenes. However, most of the event-based object tracking methods are designed for scenarios with untextured objects and uncluttered backgrounds. There are few event-based object tracking methods that support bounding box-based object tracking. The main idea behind this work is to propose an asynchronous Event-based Tracking-by-Detection (ETD) method for generic bounding box-based object tracking. To achieve this goal, we present an Adaptive Time-Surface with Linear Time Decay (ATSLTD) event-to-frame conversion algorithm, which asynchronously and effectively warps the spatio-temporal information of asynchronous retinal events to a sequence of ATSLTD frames with clear object contours. We feed the sequence of ATSLTD frames to the proposed ETD method to perform accurate and efficient object tracking, which leverages the high temporal resolution property of event cameras. We compare the proposed ETD method with seven popular object tracking methods, that are based on conventional cameras or event cameras, and two variants of ETD. The experimental results show the superiority of the proposed ETD method in handling various challenging environments.