GeoIMO: Geometry-Driven Independent Motion Classification for Event Cameras
For event-based automotive perception, this provides a practical, learning-free motion classification method that avoids reliance on appearance-based annotations.
The paper introduces GeoIMO, a geometry-driven, annotation-free framework that classifies objects as static or independently moving directly from event camera data, using ego-motion structure without learning or manual labels. Experiments on MVSEC and Prophesee datasets show consistent performance, with yaw compensation improving results during turns.
Existing automotive event datasets rely on appearance-based annotations from frame pipelines, making them poorly suited for motion-aware event perception. We present a geometry-driven, annotation-free framework that classifies detected objects as static or independently moving by exploiting ego-motion structure directly from the event stream. A Focus of Expansion model with yaw compensation estimates global background motion, while objects are labeled as moving when local motion deviates from this prediction, as quantified by a scale-invariant residual. Temporal stabilization improves robustness across consecutive event windows. The method requires no learning, no manual motion labels, and works with any input bounding boxes. Experiments on MVSEC and the Prophesee 1 Megapixel Automotive Detection dataset demonstrate consistent performance across diverse driving scenarios, with yaw compensation improving results during turns and a simple translational local model offering a favorable accuracy-efficiency trade-off.