DAL: A Deep Depth-Aware Long-term Tracker
| Autor: | Song Yan, Jiri Matas, Alan Lukezic, Yanlin Qian, Matej Kristan, Joni-Kristian Kamarainen |
|---|---|
| Přispěvatelé: | Tampere University, Computing Sciences |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
BitTorrent tracker business.industry Correlation filter 020207 software engineering 02 engineering and technology Tracking (particle physics) 113 Computer and information sciences Term (time) Discriminative model 0202 electrical engineering electronic engineering information engineering RGB color model 020201 artificial intelligence & image processing Computer vision Artificial intelligence business |
| Zdroj: | ICPR |
| Popis: | The best RGBD trackers provide high accuracy but are slow to run. On the other hand, the best RGB trackers are fast but clearly inferior on the RGBD datasets. In this work, we propose a deep depth-aware long-term tracker that achieves state-of-the-art RGBD tracking performance and is fast to run. We reformulate deep discriminative correlation filter (DCF) to embed the depth information into deep features. Moreover, the same depth-aware correlation filter is used for target redetection. Comprehensive evaluations show that the proposed tracker achieves state-of-the-art performance on the Princeton RGBD, STC, and the newly-released CDTB benchmarks and runs 20 fps. acceptedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|