Real-time clustering and multi-target tracking using event-based sensors
This work addresses real-time multi-target tracking for robotics and computer vision applications, presenting an incremental improvement by adapting mean-shift clustering to event-based sensors.
The paper tackled real-time clustering for multi-target tracking using event-based sensors, achieving an F-measure of 0.95 for clustering accuracy, reducing computational cost by 88% compared to frame-based methods, and an average tracking error of 2.5 pixels.
Clustering is crucial for many computer vision applications such as robust tracking, object detection and segmentation. This work presents a real-time clustering technique that takes advantage of the unique properties of event-based vision sensors. Since event-based sensors trigger events only when the intensity changes, the data is sparse, with low redundancy. Thus, our approach redefines the well-known mean-shift clustering method using asynchronous events instead of conventional frames. The potential of our approach is demonstrated in a multi-target tracking application using Kalman filters to smooth the trajectories. We evaluated our method on an existing dataset with patterns of different shapes and speeds, and a new dataset that we collected. The sensor was attached to the Baxter robot in an eye-in-hand setup monitoring real-world objects in an action manipulation task. Clustering accuracy achieved an F-measure of 0.95, reducing the computational cost by 88% compared to the frame-based method. The average error for tracking was 2.5 pixels and the clustering achieved a consistent number of clusters along time.