A Sparse Gaussian Approach to Region-Based 6DoF Object Tracking
| Autor: | Stoiber, Manuel, Pfanne, Martin, Strobl, Klaus, Triebel, Rudolph, Albu-Schäffer, Alin Olimpiu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Source code
Computer science media_common.quotation_subject Gaussian Probabilistic 02 engineering and technology Tracking (particle physics) symbols.namesake 0202 electrical engineering electronic engineering information engineering Sparse 6DoF Object Tracking Pose estimation Newton optimization media_common business.industry 020207 software engineering Statistical model Monocular Video tracking symbols RGB color model Object model 020201 artificial intelligence & image processing Artificial intelligence Likelihood function business Region-based Real-time Algorithm |
| Zdroj: | Computer Vision – ACCV 2020 ISBN: 9783030695316 ACCV (2) |
| DOI: | 10.1007/978-3-030-69532-3_40 |
| Popis: | We propose a novel, highly efficient sparse approach to region-based 6DoF object tracking that requires only a monocular RGB camera and the 3D object model. The key contribution of our work is a probabilistic model that considers image information sparsely along correspondence lines. For the implementation, we provide a highly efficient discrete scale-space formulation. In addition, we derive a novel mathematical proof that shows that our proposed likelihood function follows a Gaussian distribution. Based on this information, we develop robust approximations for the derivatives of the log-likelihood that are used in a regularized Newton optimization. In multiple experiments, we show that our approach outperforms state-of-the-art region-based methods in terms of tracking success while being about one order of magnitude faster. The source code of our tracker is publicly available (https://github.com/DLR-RM/RBGT). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|