3D Indoor Positioning Research Articles

Three-Dimensional Indoor Positioning Scheme for Drone with Fingerprint-Based Deep-Learning Classifier

Unmanned aerial vehicles (UAVs) hold significant potential for various indoor applications, such as mapping, surveillance, navigation, and search and rescue operations. However, indoor positioning is a significant challenge for UAVs, owing to the lack of GPS signals and the complexity of indoor environments. Therefore, this study was aimed at developing a Wi-Fi-based three-dimensional (3D) indoor positioning scheme tailored to time-varying environments, involving human movement and uncertainties in the states of wireless devices. Specifically, we established an innovative 3D indoor positioning system to meet the localisation demands of UAVs in indoor environments. A 3D indoor positioning database was developed using a deep-learning classifier, enabling 3D indoor positioning through Wi-Fi technology. Additionally, through a pioneering integration of fingerprint recognition into wireless positioning technology, we enhanced the precision and reliability of indoor positioning through a detailed analysis and learning process of Wi-Fi signal features. Two test cases (Cases 1 and 2) were designed with positioning height intervals of 0.5 m and 0.8 m, respectively, corresponding to the height of the test scene for positioning simulation and testing. With an error margin of 4 m, the simulation accuracies for the (X, Y) dimension reached 94.08% (Case 1) and 94.95% (Case 2). When the error margin was 0 m, the highest simulation accuracies for the H dimension were 91.84% (Case 1) and 93.61% (Case 2). Moreover, 40 real-time positioning experiments were conducted in the (X, Y, H) dimension. In Case 1, the average positioning success rates were 50.8% (Margin-0), 72.9% (Margin-1), and 81.4% (Margin-2), and the corresponding values for Case 2 were 52.4%, 74.5%, and 82.8%, respectively. The results demonstrated that the proposed method can facilitate 3D indoor positioning based only on Wi-Fi technologies.

Information Fusion for 5G IoT: An Improved 3D Localisation Approach Using K-DNN and Multi-Layered Hybrid Radiomap

Indoor positioning is a core enabler for various 5G identity and context-aware applications requiring precise and real-time simultaneous localisation and mapping (SLAM). In this work, we propose a K-nearest neighbours and deep neural network (K-DNN) algorithm to improve 3D indoor positioning. Our implementation uses a novel data-augmentation concept for the received signal strength (RSS)-based fingerprint technique to produce a 3D fused hybrid. In the offline phase, a machine learning (ML) approach is used to train a model on a radiomap dataset that is collected during the offline phase. The proposed algorithm is implemented on the constructed hybrid multi-layered radiomap to improve the 3D localisation accuracy. In our implementation, the proposed approach is based on the fusion of the prominent 5G IoT signals of Bluetooth Low Energy (BLE) and the ubiquitous WLAN. As a result, we achieved a 91% classification accuracy in 1D and a submeter accuracy in 2D.

Analysis of Single Transmitter 3D Indoor Positioning based on Virtual Transmitter Concept

Analysis of Single Transmitter 3D Indoor Positioning based on Virtual Transmitter Concept

A unilateral 3D indoor positioning system employing optical camera communications

AbstractThis article investigates the use of a visible light positioning system in an indoor environment to provide a three dimensional (3D) high‐accuracy solution. The proposed system leveraged the use of a single light‐emitting diode and an image sensor at the transmitter and the receiver (Rx) respectively. The proposed system can retrieve the 3D coordinate of the Rx using a combination of the angle of arrival and received signal strength (RSS). To mitigate the error induced by the lens at the Rx, a novel method is proposed and experimentally tested. The authors show that, the proposed method outperforms previously reported RSS under all circumstances and it is immune to varying exposure times within the standard range of 250 µs to 4 ms. The authors experimentally demonstrate that the proposed algorithm can achieve a 3D root mean squared error of 7.56 cm.

An Improved 3D Indoor Positioning Study with Ray Tracing Modeling for 6G Systems

An Improved 3D Indoor Positioning Study with Ray Tracing Modeling for 6G Systems

CWIWD-IPS: A Crowdsensing/Walk-Surveying Inertial/Wi-Fi Data-Driven Indoor Positioning System

Indoor positioning system plays a key role in location-based services since the widely used Global Navigation Satellite System (GNSS) is denied in indoor scenarios. Crowdsensing or walking-surveying based indoor positioning is proposed aiming at providing low-cost and high-efficient 3D location. This paper proposes a crowdsensing/walking-surveying 3D indoor positioning system by fusing the crowd-sensed inertial data and Wi-Fi fingerprinting samples using deep learning frameworks. A sine-wave-based step detector is used for pedestrian dead-reckoning (PDR) to generate original dense-trajectories. An enhanced optimization-based algorithm (Opt) and a smoothing-based algorithm (Smo) are proposed and evaluated to correct the original dense-trajectories into near-true dense-trajectories which are used to construct the inertial database and Wi-Fi radio map. A ResNet-based inertial neural-network and a BiLSTM-based Wi-Fi fingerprinting neural-network are trained on the constructed navigation database and combined by a Kalman filter to provide accurate and robust 3D localization performance. The realistic experimental results among complex indoor environments demonstrate that the proposed algorithms are proved to achieve a precise 3D indoor localization performance which is superior to several existing relative methods.

Indoor high-precision visible light positioning system using Jaya algorithm.

Several indoor positioning systems that utilize visible light communication (VLC) have recently been developed. Due to the simple implementation and high precision, most of these systems are dependent on received signal strength (RSS). The position of the receiver can be estimated according to the positioning principle of the RSS. To improve positioning precision, an indoor three-dimensional (3D) visible light positioning (VLP) system with the Jaya algorithm is proposed. In contrast to other positioning algorithms, the Jaya algorithm has a simple structure with only one phase and achieves high accuracy without controlling the parameter settings. The simulation results show that an average error of 1.06 cm is achieved using the Jaya algorithm in 3D indoor positioning. The average errors of 3D positioning using the Harris Hawks optimization algorithm (HHO), ant colony algorithm with an area-based optimization model (ACO-ABOM), and modified artificial fish swam algorithm (MAFSA) are 2.21 cm, 1.86 cm and 1.56 cm, respectively. Furthermore, simulation experiments are performed in motion scenes, where a high-precision positioning error of 0.84 cm is achieved. The proposed algorithm is an efficient method for indoor localization and outperforms other indoor positioning algorithms.

3D Indoor Positioning of Autonomous Robots Based on Ultra-wide Band Technology

3D Indoor Positioning of Autonomous Robots Based on Ultra-wide Band Technology

Smart Home Control System Using VLC and Bluetooth Enabled AC Light Bulb for 3D Indoor Localization with Centimeter-Level Precision.

Smart home systems (SHSs) are a modern lifestyle trend, changing daily lives in the most intuitive way. To connect and operate various smart devices under one system, an accurate, convenient, and secure control method is of utmost significance. Nowadays, most smart home control systems are based on radio-frequency (RF) technologies such as Bluetooth, Wi-Fi, and Zigbee. They tend to suffer from poor location accuracy in high-density environments due to the interference and noise in RF signals as well as their penetration through walls, leading to security vulnerabilities and low-precision control. To address these issues, this paper presents a smart home control system based on visible light communication (VLC), with enhanced security and accurate localization for precise and convenient control. The system includes an AC lightbulb, a smartphone running the position and control applications, and a cloud server with location-based access and a database of smart home devices. The design of the AC lightbulb integrates VLC and Bluetooth connectivity in a standard form factor for easy installation and plug-n-play capability. A smartphone camera-based 3D indoor positioning and orientation algorithm that allows precise control by pointing the smartphone the device is also presented. We demonstrate the feasibility of this system through prototype implementation and experimental verification.

A 3D indoor positioning system based on common visible LEDs

We propose a realistic 3D positioning system for indoor navigation that exploits visible Light Emitting Diodes (LEDs), placed on the ceiling. A unique frequency tone is assigned to each lamp and modulates its intensity in periodic time slots. The Time Difference of Arrival (TDOA) is measured without the need of a synchronization system between the sources and the receiver, then it is used to accurately estimate the receiver position. We first describe the theoretical approach, then propose the model and characterize the possible sources of noise. Finally, we demonstrate the proof-of-concept of the proposed system by simulation of lightwave propagation. Namely, we assess its performance by using Montecarlo simulations in a common room and estimate the impact of the different implementation parameters on the accuracy of the proposed solution. We find that, in realistic conditions, the technique allows for centimeter precision. Pushing the device requirements, the precision can be further increased to a sub-centimeter accuracy.

A 3D Indoor Positioning Method of Wireless Network with Single Base Station in Multipath Environment

The proliferation of indoor location-based services has increased the demand of indoor positioning technology. Severe multipath and coherence effects are the difference between signal propagation indoors and outdoors. Most existing indoor localization methods build their models in 2-dimensional space and try to avoid the influence of multipath. We propose a method to realize 3-dimensional indoor positioning with single base station by using multipath channel. The angles of multipath coherent signals are estimated by MIMO antenna and the delays are estimated by OFDM signal. To avoid the complicated calculation in joint estimation of angles and delays in 3-dimensional space, the angles and delays are estimated separately and matched by the proposed algorithm. The line-of-sight channel is differentiated by time delay, and the reflection paths for non-line-of-sight channels are established with angle information and indoor maps. Finally, combine the angle information of the reflection paths and the line-of-sight path to obtain the target position in 3-dimensional indoor space. We verified the method through simulation in an indoor space of 6 m × 8 m × 4.5 m . The positioning errors are submeter level in 95 % cases and less than 0.4m in 60 % cases. The proposed method requires only one base station and can be applied in most wireless networks. Compared with existing indoor localization methods, it has lower computational complexity and higher application potential.

Precise 3D Indoor Localization and Trajectory Optimization Based on Sparse Wi-Fi FTM Anchors and Built-In Sensors

Indoor location-based services have become more and more important due to their potential applications in a wide range of personalized services in recent years. The accuracy of smartphone based 3D indoor localization is subjected to the poor performance of low-cost sensors and limited coverage of location sources. In order to solve these problems, this paper proposes a precise 3D indoor localization and trajectory optimization framework that uses the combination of sparse Wi-Fi Fine Time Measurement (FTM) anchors and built-in sensors (3D-LOWS). The inertial navigation system (INS) mechanization, multi-level constraints and observed values are integrated by the adaptive unscented Kalman filter to eliminate effects of cumulative error, indoor magnetic interference, and diversity of handheld modes. The Wi-Fi based ranging and landmark detection information is used to provide an accurate absolute reference to the built-in sensors based method. In addition, this paper proposes and evaluates two different trajectory optimization algorithms and compares the improved localization performance. The comprehensive experiments indicate that the proposed 3D-LOWS is proved to achieve accurate and stable 3D indoor positioning and trajectory optimization performance under complex indoor environments using sparse wireless stations.

Smartphone-Based Pedestrian Dead Reckoning for 3D Indoor Positioning.

Indoor localization based on pedestrian dead reckoning (PDR) is drawing more and more attention of researchers in location-based services (LBS). The demand for indoor localization has grown rapidly using a smartphone. This paper proposes a 3D indoor positioning method based on the micro-electro-mechanical systems (MEMS) sensors of the smartphone. A quaternion-based robust adaptive cubature Kalman filter (RACKF) algorithm is proposed to estimate the heading of pedestrians based on magnetic, angular rate, and gravity (MARG) sensors. Then, the pedestrian behavior patterns are distinguished by detecting the changes of pitch angle, total accelerometer and barometer values of the smartphone in the duration of effective step frequency. According to the geometric information of the building stairs, the step length of pedestrians and the height difference of each step can be obtained when pedestrians go up and downstairs. Combined with the differential barometric altimetry method, the optimal height can be computed by the robust adaptive Kalman filter (RAKF) algorithm. Moreover, the heading and step length of each step are optimized by the Kalman filter to reduce positioning error. In addition, based on the indoor map vector information, this paper proposes a heading calculation strategy of the 16-wind rose map to improve the pedestrian positioning accuracy and reduce the accumulation error. Pedestrian plane coordinates can be solved based on the Pedestrian Dead-Reckoning (PDR). Finally, combining pedestrian plane coordinates and height, the three-dimensional positioning coordinates of indoor pedestrians are obtained. The proposed algorithm is verified by actual measurement examples. The experimental verification was carried out in a multi-story indoor environment. The results show that the Root Mean Squared Error (RMSE) of location errors is 1.04–1.65 m by using the proposed algorithm for three participants. Furthermore, the RMSE of height estimation errors is 0.17–0.27 m for three participants, which meets the demand of personal intelligent user terminal for location service. Moreover, the height parameter enables users to perceive the floor information.

Configuration of 3D Indoor Positioning System Based on Bluetooth Beacons

This paper devoted to research of indoors navigation problems under poor or insufficient quality of satellite navigational data environment. The problem of object positioning in 3D space by Bluetooth devices located indoors forming a multi-position tracking system is considered in this research. Emphasized that in order to succeed for such system it is required to pre-estimate distinctive accuracy. The proposed model interpretation of the positioning problem as the system of linear equations. The classic model interpretation for method of least squares is used for resolution. General problem of linearization around reference resolution is the locality of its features. There are three concepts of problems solvability, such as fundamental solvability (observability), solvability in conditions of instrumental measurement errors and solvability under conditions of finite accuracy of computation on a computer. The first aspect of solvability is interpreted by the completeness of the rank of the corresponding system of linear algebraic equations, the second and third ones represents by the conditionality of the problem and the convergence of the iterative estimation procedure. The conducted experiments show that for the positioning problem the attributes of the linearized model are accurate enough to represent the original nonlinear problem. Such interpretation allows to build theoretical accuracy estimation priors for object coordinates evaluations and to identify the areas with insufficient positioning accuracy. In this paper there are results of expected accuracy evaluation for various system patterns with full-scale experiments proving the theoretical calculations. Experiments for problems with using SKYLAB Beacon VG01 Bluetooth transmitters and smartphone HUAWEI WAS-LX1 are presented and confirmed that math model with linear approximation defined by authors is usable for solving indoors navigation problems using Bluetooth signal. So, for good enough quantity and appropriate location of the tracks the achievable positioning accuracy could be as good as 0.2—0.3 meters for all three coordinates. Such accuracy allows to navigate small hovering objects such as drones. In general, it looks promising to use Bluetooth trackers for solving positioning problems for indoors environments.

Implementing Deep Learning Techniques in 5G IoT Networks for 3D Indoor Positioning: DELTA (DeEp Learning-Based Co-operaTive Architecture).

In the near future, the fifth-generation wireless technology is expected to be rolled out, offering low latency, high bandwidth and multiple antennas deployed in a single access point. This ecosystem will help further enhance various location-based scenarios such as assets tracking in smart factories, precise smart management of hydroponic indoor vertical farms and indoor way-finding in smart hospitals. Such a system will also integrate existing technologies like the Internet of Things (IoT), WiFi and other network infrastructures. In this respect, 5G precise indoor localization using heterogeneous IoT technologies (Zigbee, Raspberry Pi, Arduino, BLE, etc.) is a challenging research area. In this work, an experimental 5G testbed has been designed integrating C-RAN and IoT networks. This testbed is used to improve both vertical and horizontal localization (3D Localization) in a 5G IoT environment. To achieve this, we propose the DEep Learning-based co-operaTive Architecture (DELTA) machine learning model implemented on a 3D multi-layered fingerprint radiomap. The DELTA begins by estimating the 2D location. Then, the output is recursively used to predict the 3D location of a mobile station. This approach is going to benefit use cases such as 3D indoor navigation in multi-floor smart factories or in large complex buildings. Finally, we have observed that the proposed model has outperformed traditional algorithms such as Support Vector Machine (SVM) and K-Nearest Neighbor (KNN).

Infection Spread and High-Resolution Detection of Close Contact Behaviors.

Knowledge of human behaviors is important for improving indoor-environment design, building-energy efficiency, and productivity, and for studies of infection spread. However, such data are lacking. In this study, we designed a device for detecting and recording, second by second, the 3D indoor positioning and head and body motions of each graduate student in an office. From more than 400 person hours of data. Students spent 92.2%, 4.1%, 2.9%, and 0.8% of their time in their own office cubicles, other office cubicles, aisles, and areas near public facilities, respectively. They spent 9.7% of time in close contact, and each student averagely had 4.0 close contacts/h. Students spent long time on close contact in the office which may lead to high infection risk. The average interpersonal distance during close contact was 0.81 m. When sitting, students preferred small relative face orientation angle. Pairs of standing students preferred a face-to-face orientation during close contact which means this pattern had a lower infection risk via close contact. Probability of close contact decreased exponentially with the increasing distance between two students’ cubicles. Data on human behaviour during close contact is helpful for infection risk analysis and infection control and prevention.

Optical Camera Communication system for three-dimensional indoor localization

Nowadays, indoor localization methods are intensively researched due to their potential use in location-based services, robots’ navigation and applications for Industrial Internet of Things (IIoT). The tendency of including small devices with Light Emitting Diodes (LED) for decoration purposes and the emergence of better low-cost cameras in the market, impulse the use of Optical Camera Communication (OCC) for Indoor Positioning Systems (IPS). In this work a real-time two-step 3D Indoor Positioning System for multiple devices using OCC and LED beacons is proposed. The beacons are positioned at a predefined static distance from the camera, forming a virtual reference plane that represents the frame of the real world elements’ positions captured in a photo. A simplified version of the trigonometric equations for transforming 2D pixel projection into real distances is applied to obtain the vertical and horizontal separation between the objects and the beacons. While the relation of the beacons’ and the objects’ projection size is used to determine the distance of each object to the camera. These distances together allowed to calculate the 3D location of the elements by trilateration. Experimental validation of the method was performed, and the results showed a mean location error of 1.24 cm for the three dimensions with an average process time of 18.2 ms per frame for four simultaneous targets correctly identified, at a distance of 2.00 m.

Assisting 3D Indoor Positioning for Robot Navigation

DOI : 10.26650/electrica.2019.18038 With the increasing employment of mobile robots to achieve different tasks in various applications, the need for localization and body position for these robots is increasing rapidly. Many techniques are proposed to calculate the precise coordinates of a robot based on the distances measured between the robot and a set of reference points. Also, internal sensors, such as accelerometers and gyroscopes, are used to detect the body position and the direction of the robot. However, the effect of obstacles in an indoor environment and sensor drifts still limit the applicability of such systems. Thus, in this study, a novel technique that uses one or more robots to compensate for the missing stationary points is proposed. The robots in the proposed technique collaborate to improve the positioning accuracy, by providing reference points to each other. Per each movement execution of one robot, the remaining robots remain stationary, to provide the required reference points. When the robot finishes the movement execution, its position is updated based on the signals collected from the other robots, in addition to the position calculated by the onboard sensors. Then, another robot is selected to execute its movement.. The results show that the proposed method has been able to improve the positioning accuracy, by increasing the number of collaborating robots, when the median function if used to select the coordinates of the robot, among the candidate positions. Cite this article as: Albayati BIR, Kurt S. Assisting 3D Indoor Positioning for Robot Navigation. Electrica, 2019; 19(1): 85-90.

3D Indoor Positioning of UAVs with Spread Spectrum Ultrasound and Time-of-Flight Cameras.

This work proposes the use of a hybrid acoustic and optical indoor positioning system for the accurate 3D positioning of Unmanned Aerial Vehicles (UAVs). The acoustic module of this system is based on a Time-Code Division Multiple Access (T-CDMA) scheme, where the sequential emission of five spread spectrum ultrasonic codes is performed to compute the horizontal vehicle position following a 2D multilateration procedure. The optical module is based on a Time-Of-Flight (TOF) camera that provides an initial estimation for the vehicle height. A recursive algorithm programmed on an external computer is then proposed to refine the estimated position. Experimental results show that the proposed system can increase the accuracy of a solely acoustic system by 70–80% in terms of positioning mean square error.

3D Tracking via Shoe Sensing

Most location-based services are based on a global positioning system (GPS), which only works well in outdoor environments. Compared to outdoor environments, indoor localization has created more buzz in recent years as people spent most of their time indoors working at offices and shopping at malls, etc. Existing solutions mainly rely on inertial sensors (i.e., accelerometer and gyroscope) embedded in mobile devices, which are usually not accurate enough to be useful due to the mobile devices’ random movements while people are walking. In this paper, we propose the use of shoe sensing (i.e., sensors attached to shoes) to achieve 3D indoor positioning. Specifically, a short-time energy-based approach is used to extract the gait pattern. Moreover, in order to improve the accuracy of vertical distance estimation while the person is climbing upstairs, a state classification is designed to distinguish the walking status including plane motion (i.e., normal walking and jogging horizontally), walking upstairs, and walking downstairs. Furthermore, we also provide a mechanism to reduce the vertical distance accumulation error. Experimental results show that we can achieve nearly 100% accuracy when extracting gait patterns from walking/jogging with a low-cost shoe sensor, and can also achieve 3D indoor real-time positioning with high accuracy.