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.
The documents contained in these directories are included by the contributing authors as a means to ensure timely dissemination of scholarly and technical work on a non-commercial basis. Copyright and all rights therein are maintained by the authors or by other copyright holders, notwithstanding that they have offered their works here electronically. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.