Un-EVIMO: Unsupervised Event-Based Independent Motion Segmentation
This work addresses the lack of unsupervised methods for detecting independently moving objects in event-based vision, which is incremental but useful for applications requiring low latency and high dynamic range.
The paper tackles the problem of unsupervised independent motion segmentation for event cameras by proposing a framework that generates pseudo-labels using geometric constraints, achieving competitive performance with supervised methods on the EVIMO dataset.
Event cameras are a novel type of biologically inspired vision sensor known for their high temporal resolution, high dynamic range, and low power consumption. Because of these properties, they are well-suited for processing fast motions that require rapid reactions. Although event cameras have recently shown competitive performance in unsupervised optical flow estimation, performance in detecting independently moving objects (IMOs) is lacking behind, although event-based methods would be suited for this task based on their low latency and HDR properties. Previous approaches to event-based IMO segmentation have been heavily dependent on labeled data. However, biological vision systems have developed the ability to avoid moving objects through daily tasks without being given explicit labels. In this work, we propose the first event framework that generates IMO pseudo-labels using geometric constraints. Due to its unsupervised nature, our method can handle an arbitrary number of not predetermined objects and is easily scalable to datasets where expensive IMO labels are not readily available. We evaluate our approach on the EVIMO dataset and show that it performs competitively with supervised methods, both quantitatively and qualitatively.