Orb-Slam2

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 63

All topics

NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU
May 12, 2024Yuhao Zhang, Mihai Bujanca, Mikel LujánOrb-Slam2 Simultaneous Localization And Mapping
University of Manchester. 2University of Cambridge. · 3Qualcomm Technologies XR Labs, Austria.
Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting
Date pendingFernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco +1Mediterranean Greenhouses Orb-Slam2
Department of Informatics, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain · Department of Engineering, CIESOL, ceiA3, Universidad de Almería, Ctra. Sacramento s/n, Almería, 04120, Spain
NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction
Date pendingJiaheng Li, Binsheng Zhang, Xinhai Chang +1Orb-Slam2 Simultaneous Localization And Mapping
Wangxuan Institute of Computer Technology, Peking University Beijing Academy of Artificial Intelligence, Beijing, China · School of Computer Science and Technology, Beihang University · Yuanpei College, Peking University

May 12, 2024, cs.ROJ/K move · Enter open · S save

NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU

Yuhao Zhang, Mihai Bujanca, Mikel Luján

University of Manchester. 2University of Cambridge. · 3Qualcomm Technologies XR Labs, Austria.

Orb-Slam2 Simultaneous Localization And Mapping Robotic Perception Real-Time Systems Deep Learning Graphics Processing Unit Resources

Open paper AskPDF arXiv

Many existing visual SLAM methods can achieve high localization accuracy in dynamic environments by leveraging deep learning to mask moving objects. However, these methods incur significant computational overhead as the camera tracking needs to wait for the deep neural network to generate mask at each frame, and they typically require GPUs for real-time operation, which restricts their practicality in real-world robotic applications. Therefore, this paper proposes a real-time dynamic SLAM system that runs exclusively on a CPU. Our approach incorporates a mask propagation mechanism that decouples camera tracking and deep learning-based masking for each frame. We also introduce a hybrid tracking strategy that integrates ORB features with optical flow methods, enhancing both robustness and efficiency by selectively allocating computational resources to input frames. Compared to previous methods, our system maintains high localization accuracy in dynamic environments while achieving a tracking frame rate of 60 FPS on a laptop CPU. These results demonstrate the feasibility of utilizing deep learning for dynamic SLAM without GPU support. Since most existing dynamic SLAM systems are not open-source, we make our code publicly available at: https://github.com/yuhaozhang7/NGD-SLAM

Momentum

Related topics

Latest papers 63

NGD-SLAM: Towards Real-Time Dynamic SLAM without GPU

Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting

NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction