VSLink: A Fast and Pervasive Approach to Physical Cyber Space Interaction via Visual SLAM
2022 18th International Conference on Mobility, Sensing and Networking (MSN)(2022)
摘要
With the fast growth of the Internet of Things, people now are surrounded by plenty of devices. To achieve efficient interaction with these devices, human-device interaction technologies are evolving. Because existing methods (mobile App) require users to remember the mapping between the real-world device and the digital one, an important point is to break such a gap. In this paper, we propose VSLink, which offers human-device interaction in an Augmented-Reality-like manner. VSLink achieves fast object identification and pervasive interaction for fusing the physical and cyberspace. To improve processing speed and accuracy, VSLink adopts a two-step object identification method to locate the interaction targets. In VSLink, visual SLAM and object detection neural networks detect stable/-movable objects separately, and detection prior from SLAM is sent to neural networks which enables sparse-convolution-based inference acceleration. VSLink offers a platform where the user could customize the interaction target, function, and interface. We evaluated VSLink in an environment containing multiple objects to interact with. The results showed that it achieves a 33% network inference acceleration on state-of-the-art networks, and enables object identification with 30FPS video input.
更多查看译文
关键词
Human-object interaction,Augmented reality,Visual SLAM,Object detection
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要