Edge Assisted Mobile Visual SLAM
Description
In an age where real-time processing and interaction with the physical world through digital lenses are paramount, visual SLAM technology has become the backbone of mobile AR/VR applications, robotics, and autonomous systems. However, the demanding computational load of visual SLAM often strains the limited resources of mobile devices, hindering performance and accuracy. This is exactly where edge computing comes to the forefront, offering a potent solution by performing data processing at the edge of the network, closer to the source of data.
This monograph is a pioneering exploration into how edge computing can elevate visual SLAM systems, overcoming the traditional challenges of computational intensity and resource constraints. Edge computing not only offloads heavy-duty processing from mobile devices to edge servers but also mitigates latency, enhances efficiency, and ensures robust, real-time performance. This monograph unveils the transformative potential of edge-assisted visual SLAM, presenting groundbreaking research and the latest advancements in task decoupling, collaborative mapping, and environmental interaction.
This monograph could serve as a scholarly resource for those within the fields of computer vision and mobile computing. It presents a detailed exploration of current research in edge-assisted visual SLAM and anticipates future developments, offering readers a comprehensive understanding of the field's trajectory and its implications for the next generation of mobile applications and autonomous systems.
More details
Other editions
Additional editions
Persons
Jingao Xu received his PhD and BE degree both from the School of Software, Tsinghua University, in 2017 and 2022, under the supervision of professor Zheng Yang and Yunhao Liu. He is currently a postdoctoral researcher in School of Software, Tsinghua University. His research interests include Internet of Things, mobile and edge computing, and visual SLAM. He is a member of the IEEE and the ACM.
Zheng Yang is an associate professor in School of Software and TNList, Tsinghua University. He received his BE degree in the Department of Computer Science from Tsinghua University and his Ph.D. degree in the Department of Computer Science and Engineering of Hong Kong University of Science and Technology. His research interests include Internet of Things and industrial internet. He received 4 best paper (candidates) awards and has over 14,000 citations with H-index 59. He is a fellow of IEEE.
Yunhao Liu received his BE degree from the Department of Automation, Tsinghua University in 1995. He received his MS and PhD degrees in computer science and engineering from Michigan State University in 2003 and 2004, respectively. He is a professor in the Department of Automation and the dean of the Global Innovation Exchange, Tsinghua University. He is a fellow of CCF, ACM, and IEEE. He is the editor-in-chief of ACM Transactions on Sensor Networks and Communications of the CCF. His research interests include Internet of Things, wireless sensor networks, indoor localization, the industrial internet, and cloud computing. He is an author and co-author of 5 books and over 200 research papers in premier journals and conferences. He has over 39,700 citations with H-index 90.
Hao Cao received his BE degree from the College of Intelligence and Computing, Tianjin University, in 2019. He is currently working toward the PhD degree with the School of Software, Tsinghua University. His research interests include Internet of Things and mobile computing.
Content
Part I. The Background. - Chapter 1. Understanding Visual SLAM.- Chapter 2. Edge Computing in Mobile Visual Systems.- Part II. Edge-Assisted Visual SLAM: System Design Principle .- Chapter 3. EdgeSLAM 1.0: Architectural Innovations in Mobile Visual SLAM.- Chapter 4. EdgeSLAM 2.0: Enhancing Scalability in Multi-Agent Systems.- Part III. Edge-Assisted Visual SLAM: Innovations and Applications .- Chapter 5. Indoor Autonomous Navigation with EdgeSLAM.- Chapter 6. Large-Scale Crowdsourced Mapping with EdgeSLAM.- Chapter 7. Environment Understanding with EdgeSLAM.- Chapter 8. Multi-User AR with EdgeSLAM.- Part IV. Conclusion .- Chapter 9. Research Summary and Open Issues.