A Precise Indoor Visual Positioning Approach Using a Built Image Feature Database and Single User Image from Smartphone Cameras

Abstract

Indoor visual positioning is a key technology in a variety of indoor location services and applications. The particular spatial structures and environments of indoor spaces is a challenging scene for visual positioning. To address the existing problems of low positioning accuracy and low robustness, this paper proposes a precision single-image-based indoor visual positioning method for a smartphone. The proposed method includes three procedures: First, color sequence images of the indoor environment are collected in an experimental room, from which an indoor precise-positioning-feature database is produced, using a classic speed-up robust features (SURF) point matching strategy and the multi-image spatial forward intersection. Then, the relationships between the smartphone positioning image SURF feature points and object 3D points are obtained by an efficient similarity feature description retrieval method, in which a more reliable and correct matching point pair set is obtained, using a novel matching error elimination technology based on Hough transform voting. Finally, efficient perspective-n-point (EPnP) and bundle adjustment (BA) methods are used to calculate the intrinsic and extrinsic parameters of the positioning image, and the location of the smartphone is obtained as a result. Compared with the ground truth, results of the experiments indicate that the proposed approach can be used for indoor positioning, with an accuracy of approximately 10 cm. In addition, experiments show that the proposed method is more robust and efficient than the baseline method in a real scene. In the case where sufficient indoor textures are present, it has the potential to become a low-cost, precise, and highly available indoor positioning technology.

Error model and simulation for multisource fusion indoor positioning

“…12 Li et al proposed a new mismatch elimination method based on the Hough transform voting to improve the matching accuracy, and thus improve the positioning effect, resulting in a positioning accuracy of about 10 cm. 13 Due to the high cost of single-source high-precision positioning methods, some sub-meterlevel positioning methods, such as RF positioning and the PDR, are still widely used. The main RF positioning ways include ranging positioning based on the time-of-flight of signal techniques 14 and the RSS fingerprint positioning.…”

“…σ xa 2 and σ ya 2 are calculated by Equations ( 14) and ( 15), using the distribution of iBeacons. Finally, the RMSE at point a can be calculated by Equation (13).…”

A Real-Time Infrared Stereo Matching Algorithm for RGB-D Cameras’ Indoor 3D Perception

“…Thorough comparisons of photometric correlation methods showed the Census descriptor to be among the most robust in handling noisy environments [17]. The main mathematical models of the algorithm are shown in Formulas (1) and (2). First, with a pixel p (i, j) in the match image R as the center, select the Census transformation window with a size 7 × 7.…”

“…Indoor 3D environment perception technology is one of the key technologies for robot positioning and navigation, virtual reality, augmented reality and indoor mapping and localization [1][2][3][4][5][6][7]. With the rapid development of sensor technology, there are many devices that can be used for the point cloud acquisition and surface modeling of indoor scenes, such as LiDAR [8], RGB cameras [9], RGB-D cameras [5] and other commercial sensors, which are widely used in indoor 3D perception.…”

VNLSTM-PoseNet: A novel deep ConvNet for real-time 6-DOF camera relocalization in urban streets

“…Its main idea is to extract local features from the image and establish 2D-3D matching with corresponding 3D points, and then determine the camera pose according to the matching relationship. Geometry-based visual positioning methods rely on correct local feature matching, however, not enough accurate matching points can be found in all scenarios (Li et al 2020a;Jin et al 2021;Miao et al 2021). Various complex situations that may exist in the real environments, such as object occlusion, viewpoint changes, motion blur, illumination changes, and lack of texture, may affect feature matching and make it difficult to obtain accurate camera poses or successful positioning.…”