High-Speed Object Tracking Using an Asynchronous Temporal Contrast Sensor

Abstract

Purely image-based approaches to tracking objects in video sequences are more prone to failure the higher an object's speed, as it covers a greater distance over the camera's exposure time and is subject to increased motion blur. These algorithms are also susceptible to changes in the object's appearance and illumination. In this paper, we approach this problem by asynchronously recording local contrast change at high speed, using a type of visual capture device called a Dynamic Vision Sensor (DVS). We use this additional data to determine motion that takes place during the exposure of a single video frame. We present a multi-modal capture system incorporating both a DVS and a traditional video camera, a method to register the different types of sensor information, and finally apply these datasets to challenging object tracking scenarios.