Equivariant Filter for High Performance Image Tracking using an Event Camera

2026-07-10

AI Summary

This work addresses the degradation in accuracy and stability of event camera-based tracking caused by highly temporally correlated observations. It introduces, for the first time, an equivariant filtering framework tailored to this task, proposing a method that integrates Asynchronous Event Blob (AEB) feature extraction with SE(2) group symmetry. By designing an equivariant measurement update mechanism, the approach effectively decouples the highly correlated positional observations from AEB outputs, substantially enhancing tracking robustness under high-speed motion. Experimental results demonstrate that, in scenarios involving rapid rotation at speeds up to 7000 pixels per second, the proposed method consistently outperforms baseline approaches—including direct optimization and covariance intersection—in both smoothness and accuracy.

Abstract

Image tracking is the problem of estimating the transformation that relates a moving image of a scene to an original reference image. The problem is important in control of autonomous vehicles or robots, where the image encodes information about the motion of the camera or environment, as well as in pure computer vision applications. In this paper, we present an equivariant filter design for high performance tracking of planar image transformations using an event camera. The design exploits the Asynchronous Event Blob (AEB) tracker (Wang et al., 2024) to extract feature-position measurements from the raw event stream, and an equivariant filter to compute an affine image translation and rotation using the special Euclidean group symmetry. The equivariant filter incorporates an equivalent-measurement update step that de-correlates the (highly temporally correlated) feature-position measurements provided by the AEB tracker. We evaluate the design experimentally using two datasets involving general and fast rotational motion. We benchmark results against direct optimisation (estimating the relative transformation from the raw blob tracks), and a covariance intersection approach for overcoming data correlation. Our design provides smooth image tracking for features moving up to 7000 pixels per second on the image plane.

Problem

• image tracking
• event camera
• planar transformation
• temporal correlation
• high-speed motion

Innovation

• equivariant filter
• event camera
• image tracking
• Asynchronous Event Blob
• special Euclidean group