3D Reconstruction Algorithm of Indoor Scene Based on Kinect Camera
Real-time 3D reconstruction based on consumer-grade depth cameras often causes problems such as noise, redundancy, and inter-frame mismatches. Aiming at the BundleFusion real-time indoor scene reconstruction method, a way to improve the accuracy and quality of reconstruction 3D models is proposed, and the adaptive processing of frame blocks is proposed. Local dynamic chunking is adopted to reduce the number of mismatched frames and improve model quality and clarity. Experiments show that the scene data after frame block adaptive processing retains more available frames, which improves the accuracy of reconstruction effect.
Authors
- Yiwen Liu (ORCID: https://orcid.org/0009-0002-2851-4604)
- Yan Qi (ORCID: https://orcid.org/0000-0002-0782-8674)
Institutions
- Shenyang Ligong University (CN)
Publication Details
- Published
- 2024-09-20
- DOI
- https://doi.org/10.1109/spic62469.2024.10691486
- Primary Topic
- Simulation and Modeling Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00