ملخص
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.
اللغة الأصلية | الإنجليزيّة |
---|---|
عنوان منشور المضيف | Proceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 |
ناشر | IEEE Computer Society |
الصفحات | 2191-2199 |
عدد الصفحات | 9 |
رقم المعيار الدولي للكتب (الإلكتروني) | 9798350365474 |
المعرِّفات الرقمية للأشياء | |
حالة النشر | نُشِر - 2024 |
الحدث | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 - Seattle, الولايات المتّحدة المدة: ١٦ يونيو ٢٠٢٤ → ٢٢ يونيو ٢٠٢٤ |
سلسلة المنشورات
الاسم | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
---|---|
رقم المعيار الدولي للدوريات (المطبوع) | 2160-7508 |
رقم المعيار الدولي للدوريات (الإلكتروني) | 2160-7516 |
!!Conference
!!Conference | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 |
---|---|
الدولة/الإقليم | الولايات المتّحدة |
المدينة | Seattle |
المدة | ١٦/٠٦/٢٤ → ٢٢/٠٦/٢٤ |
ملاحظة ببليوغرافية
Publisher Copyright:© 2024 IEEE.