ED-DCFNet: An Unsupervised Encoder-decoder Neural Model for Event-driven Feature Extraction and Object Tracking

Raz Ramon, Hadar Cohen-Duwek, Elishai Ezra Tsur; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 2191-2199

Neuromorphic cameras feature asynchronous event-based pixel-level processing and are particularly useful for object tracking in dynamic environments. Cur- rent approaches for feature extraction and optical flow with high-performing hybrid RGB-events vision systems require large computational models and supervised learning which impose challenges for embedded vision and require annotated datasets. In this work we propose ED- DCFNet a small and efficient (< 72k) unsupervised multi-domain learning framework which extracts events-frames shared features without requiring annotations with comparable performance. Furthermore we introduce an open-sourced event and frame-based dataset that captures in-door scenes with various lighting and motion-type conditions in realistic scenarios which can be used for model building and evaluation. The dataset is available at https://github.com/NBELab/UnsupervisedTracking.