This paper proposes a local point cloud map-based Web augmented reality (AR) indoor navigation system solution. By delivering the local point cloud map to the web front end for positioning, the real-time positioning can be implemented only with the help of the computing power of the web front end. In addition, with the characteristics of short time consumption and accurate positioning, an optimization solution to the local point cloud map is proposed, which includes specific measures such as descriptor de-duplicating and outlier removal, thus improving the quality of the point cloud. In this document, interpolation and smoothing effects are introduced for local map positioning, enhancing the anchoring effect and improving the smoothness and appearance of user experience. In small-scale indoor scenarios, the positioning frequency on an iPhone 13 can reach 30 fps, and the positioning precision is within 50 cm. Compared with an existing mainstream visual-based positioning manner for AR navigation, this specification does not rely on any additional sensor or cloud computing device, thereby greatly saving computing resources. It takes a very short time to meet the real-time requirements and provide users with a smooth positioning effect.

With the rapid popularization of mobile devices and the wide application of various sensors, scene perception methods applied to mobile devices occupy an important position in location-based services such as navigation and augmented reality (AR). The development of deep learning technologies has greatly improved the visual perception ability of machines to scenes. The basic framework of scene visual perception, related technologies and the specific process applied to AR navigation are introduced, and future technology development is proposed. An application (APP) is designed to improve the application effect of AR navigation. The APP includes three modules: navigation map generation, cloud navigation algorithm, and client design. The navigation map generation tool works offline. The cloud saves the navigation map and provides navigation algorithms for the terminal. The terminal realizes local real-time positioning and AR path rendering.