ML Anthology

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

Raz Ramon, Hadar Cohen Duwek, Elishai Ezra Tsur
CVPRW 2024 pp. 2191-2199
doi:10.1109/CVPRW63382.2024.00224 /cvprw/2024/ramon2024cvprw-eddcfnet/

Abstract

Neuromorphic cameras feature asynchronous event-based pixel-level processing and are particularly useful for object tracking in dynamic environments. Current 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 indoor 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.

CVPRW Semantic Scholar

Cite

Text

Ramon et al. "ED-DCFNet: An Unsupervised Encoder-Decoder Neural Model for Event-Driven Feature Extraction and Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024. doi:10.1109/CVPRW63382.2024.00224

Markdown

[Ramon et al. "ED-DCFNet: An Unsupervised Encoder-Decoder Neural Model for Event-Driven Feature Extraction and Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2024.](https://mlanthology.org/cvprw/2024/ramon2024cvprw-eddcfnet/) doi:10.1109/CVPRW63382.2024.00224

BibTeX

@inproceedings{ramon2024cvprw-eddcfnet,
  title     = {{ED-DCFNet: An Unsupervised Encoder-Decoder Neural Model for Event-Driven Feature Extraction and Object Tracking}},
  author    = {Ramon, Raz and Duwek, Hadar Cohen and Tsur, Elishai Ezra},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2024},
  pages     = {2191-2199},
  doi       = {10.1109/CVPRW63382.2024.00224},
  url       = {https://mlanthology.org/cvprw/2024/ramon2024cvprw-eddcfnet/}
}