Complex Indoor Scenarios Research Articles

Hybrid pedestrian positioning system using wearable inertial sensors and ultrasonic ranging

Pedestrian positioning system (PPS) using wearable inertial sensors has wide applications towards various emerging fields such as smart healthcare, emergency rescue, soldier positioning, etc. The performance of traditional PPS is limited by the cumulative error of inertial sensors, complex motion modes of pedestrians, and the low robustness of the multi-sensor collaboration structure. This paper presents a hybrid pedestrian positioning system using the combination of wearable inertial sensors and ultrasonic ranging (H-PPS). A robust two nodes integration structure is developed to adaptively combine the motion data acquired from the single waist-mounted and foot-mounted node, and enhanced by a novel ellipsoid constraint model. In addition, a deep-learning-based walking speed estimator is proposed by considering all the motion features provided by different nodes, which effectively reduces the cumulative error originating from inertial sensors. Finally, a comprehensive data and model dual-driven model is presented to effectively combine the motion data provided by different sensor nodes and walking speed estimator, and multi-level constraints are extracted to further improve the performance of the overall system. Experimental results indicate that the proposed H-PPS significantly improves the performance of the single PPS and outperforms existing algorithms in accuracy index under complex indoor scenarios.

Sliding Window, Hierarchical Classification, Regression, and Genetic Algorithm for RFID Indoor Positioning Systems

Several surveys in the Indoor Positioning System (IPS) use the Radio Signal Strength Indicator (RSSI) to locate target objects. However, RSSI suffers significantly from the multipath phenomenon and other environmental factors such as the absence of the field of view, reflective materials, excessive obstacles, and a high density of objects. To overcome such problems, we propose three new IPS approaches using Radio Frequency Identification (RFID) technology and the collaborative use of Sliding Window, Hierarchical Classification, Random Forest Regressor, and Genetic Algorithm. We tested the new approaches on three datasets obtained in different environments and compared them with two state-of-the-art IPS approaches (Landmarc and SVR-Landmarc). One of the main results got was a precision of 4.82 cm in an environment with 7,000 target tags, reducing by up to 92.91% the average error w.r.t. other IPS approaches presented in the literature, including more complex indoor scenarios.

BPNN Based Indoor Fingerprinting Localization Algorithm Against Environmental Fluctuations

For mobile users, the ability to accurately acquire their own location is critical. By locating, mobile users can get information about their environment and access location-related services. RSS fingerprint-based indoor localization method collects a training database of measurement fingerprints and uses a machine learning classifier to determine a person’s location from a new fingerprint. However, as the environment changes over time due to furniture or other objects being moved, the new fingerprints diverge from those in the original database. Therefore, an RSS-difference based localization system is designed to deal with the above problem. This method combines back-propagation neural network (BPNN) and weighted K-Nearest Neighbor (WKNN) method to improve the fingerprint similarity based indoor location method (FSIL). We train BPNN in the off-line stage to obtain the optimal BPNN parameter settings. In the online stage, K nearest neighbor points are firstly selected based on the improved FSIL algorithm, and then the difference of signal strength values between the K nearest neighbor points and the target user is input into the BPNN network, to obtain the Euclidean distance between the K nearest neighbor points and the target user, and finally the WKNN algorithm is used to obtain the user’s ultimate location. Simulation experiments based on the LDPL model and the Wireless Insite software, as well as the test results based on the indoor localization dataset IPIN2016, show that the localization accuracy in complex indoor scenarios can be improved by at least 11% when using the method proposed in this paper.

Unobtrusive Pedestrian Identification by Leveraging Footstep Sounds with Replay Resistance

The ability to identify pedestrians unobtrusively is essential for smart buildings to provide customized environments, energy saving, health monitoring and security-enhanced services. In this paper, we present an unobtrusive pedestrian identification system by passively listening to people's walking sounds. The proposed acoustic system can be easily integrated with the widely deployed voice assistant devices while providing the context awareness ability. This work focuses on two major tasks. Firstly, we address the challenge of recognizing footstep sounds in complex indoor scenarios by exploiting deep learning and the advanced stereo recording technology that is available on most voice assistant devices. We develop a Convolutional Neural Network-based algorithm and the footstep sound-oriented signal processing schemes to identify users by their footstep sounds accurately. Secondly, we design a "live" footstep detection approach to defend against replay attacks. By deriving the novel inter-footstep and intra-footstep characteristics, we distinguish live footstep sounds from the machine speaker's replay sounds based on their spatial variances. The system is evaluated under normal scenarios, traditional replay attacks and the advanced replays, which are designed to forge footstep sounds both acoustically and spatially. Extensive experiments show that our system identifies people with up to 94.9% accuracy in one footstep and shields 100% traditional replay attacks and up to 99% advanced replay attacks.

Utilizing Passive Intermodulation Response of Frequency-Modulated Continuous-Wave Signal for Target Identification and Mapping

In this paper, a passive-intermodulation-based tracking system working with a frequency-modulated continuous-wave (FMCW) is proposed for target identification and localization. Signals in the microwave range are chosen to realize ranging purposes for the benefits of small device size, lightweight, and wide available bandwidth. Depending on whether the nonlinear properties of electrical components, such as diodes, transistors, and mixers, are exploited, the tracking systems can be categorized as linear and nonlinear systems. By nature, the linear tracking methods are vulnerable to surrounding clutter, such as furniture, walls, and other objects, since the reflection signals from clutter are of the same nature as the target. In comparison, the nonlinear detection methods are attractive owning to the fact that the majority of the clutter does not possess nonlinear properties. Hence, the nonlinear detection system does not “see” the linear clutter and only senses the target exhibiting nonlinear responses. Among all the nonlinear technologies, the intermodulation-based tracking and mapping approach has less path loss than the harmonic-based, smaller circuit size than the subharmonic-based, and simpler tag design and fewer signal licenses required than both of its counterparts. Therefore, in this work, the intermodulation-based technology is adopted, and a new nonlinear tracking system is designed to track the distance of the target in a complex indoor scenario crowded with unwanted objects.

A Robust Heading Estimation Solution for Smartphone Multisensor-Integrated Indoor Positioning

As a part of Internet-of-Things applications, various smartphone-based indoor location services have considerable commercial value. It is largely agreed that the integration of multiple sensors is the preferable solution for improving the performance of smartphone indoor positioning, thanks to the diversity of built-in sensors. However, heading error remains a challenge for smartphone indoor positioning, especially in complex indoor scenes. This article, therefore, proposes a heading estimation solution to enhance the accuracy and reliability of smartphone indoor positioning. The extended Kalman filter (EKF)-based solution fuses smartphone built-in motion sensors, magnetometers, building map knowledge, and fingerprinting coarse positions from Wi-Fi or Bluetooth. First, the context of pedestrian mobility and scene knowledge is inferred by combining these data. Then, a scene augmentation strategy and magnetic interference online detection method are applied to calibrate the gyro accumulation error and improve the heading estimation accuracy. Additionally, quasistatic and low-dynamic judgments and online calibration are used to mitigate gyro drift. The proposed solution is implemented on a smartphone device and validated in several experiments under natural pedestrian mobility and complex indoor scenarios. Experiments show that the accuracy of heading estimation is improved from 13.1° to 2.0°. The improved heading estimation enhances the accuracy of smartphone indoor positioning from 3.57 to 0.90 m. The proposed solution is applicable to real location-based service scenarios.

Incorporating SLAM and mobile sensing for indoor CO2 monitoring and source position estimation

Indoor Air Quality (IAQ) monitoring is becoming an increasingly important topic since it critically affects occupants’ health, comfort, and safety, etc. Conventionally, monitoring sensors are distributed at stationary positions for measurement acquisitions, which cannot easily become wireless causing a high cost of infrastructure installation and maintenance. Furthermore, stationary sensing often incurs the problems of non-detection zones and low-granularity monitoring, especially in complex indoor scenarios where environmental factors are dynamic and non-convex functions. To address these critical issues, this paper proposes a mobile IAQ sensing using an automated robot equipped with one LIDAR and one CO2 sensor, to enable the prompt detection and positioning of contaminant sources (a CO2 contaminant source). Both stationary sensing (with 9 CO2 sensors) and mobile sensing (a robot with one CO2 sensor) are evaluated in real-world experiments carried out in a typical laboratory room. The spatiotemporal analysis demonstrates that the automated mobile sensing is capable of efficient and agile IAQ survey. The heat maps of the CO2 concentration illustrate that mobile sensing observes better accuracy and granularity of the pollutant detections, as mobile sensing estimates the position of the CO2 source about 1.83 m away from the ground truth position, in contrast with stationary sensing of 3.1 m. The proposed autonomous and mobile IAQ monitoring consumes much less infrastructure (one sensor instead of nine stationary sensors), implementation complexity, and amount of data for communication and processing.

Automated Sustainable Multi-Object Segmentation and Recognition via Modified Sampling Consensus and Kernel Sliding Perceptron

Object recognition in depth images is challenging and persistent task in machine vision, robotics, and automation of sustainability. Object recognition tasks are a challenging part of various multimedia technologies for video surveillance, human–computer interaction, robotic navigation, drone targeting, tourist guidance, and medical diagnostics. However, the symmetry that exists in real-world objects plays a significant role in perception and recognition of objects in both humans and machines. With advances in depth sensor technology, numerous researchers have recently proposed RGB-D object recognition techniques. In this paper, we introduce a sustainable object recognition framework that is consistent despite any change in the environment, and can recognize and analyze RGB-D objects in complex indoor scenarios. Firstly, after acquiring a depth image, the point cloud and the depth maps are extracted to obtain the planes. Then, the plane fitting model and the proposed modified maximum likelihood estimation sampling consensus (MMLESAC) are applied as a segmentation process. Then, depth kernel descriptors (DKDES) over segmented objects are computed for single and multiple object scenarios separately. These DKDES are subsequently carried forward to isometric mapping (IsoMap) for feature space reduction. Finally, the reduced feature vector is forwarded to a kernel sliding perceptron (KSP) for the recognition of objects. Three datasets are used to evaluate four different experiments by employing a cross-validation scheme to validate the proposed model. The experimental results over RGB-D object, RGB-D scene, and NYUDv1 datasets demonstrate overall accuracies of 92.2%, 88.5%, and 90.5% respectively. These results outperform existing state-of-the-art methods and verify the suitability of the method.

Classification of Point Clouds for Indoor Components Using Few Labeled Samples

The existing deep learning methods for point cloud classification are trained using abundant labeled samples and used to test only a few samples. However, classification tasks are diverse, and not all tasks have enough labeled samples for training. In this paper, a novel point cloud classification method for indoor components using few labeled samples is proposed to solve the problem of the requirement for abundant labeled samples for training with deep learning classification methods. This method is composed of four parts: mixing samples, feature extraction, dimensionality reduction, and semantic classification. First, the few labeled point clouds are mixed with unlabeled point clouds. Next, the mixed high-dimensional features are extracted using a deep learning framework. Subsequently, a nonlinear manifold learning method is used to embed the mixed features into a low-dimensional space. Finally, the few labeled point clouds in each cluster are identified, and semantic labels are provided for unlabeled point clouds in the same cluster by a neighborhood search strategy. The validity and versatility of the proposed method were validated by different experiments and compared with three state-of-the-art deep learning methods. Our method uses fewer than 30 labeled point clouds to achieve an accuracy that is 1.89–19.67% greater than existing methods. More importantly, the experimental results suggest that this method is not only suitable for single-attribute indoor scenarios but also for comprehensive complex indoor scenarios.

Enhancing Indoor Inertial Odometry with WiFi

Accurately measuring the distance traversed by a subject, commonly referred to as odometry, in indoor environments is of fundamental importance in many applications such as augmented and virtual reality tracking, indoor navigation, and robot route guidance. While theoretically, odometry can be performed using a simple accelerometer, practically, it is well-known that the distances measured using accelerometers suffer from large drift errors. In this paper, we propose WIO, a WiFi-assisted Inertial Odometry technique that uses WiFi signals as an auxiliary source of information to correct these drift errors. The key intuition behind WIO is that among multiple reflections of a transmitted WiFi signal arriving at the WiFi receiver, WIO first isolates one reflection and then measures the change in the length of the path of that reflection as the subject moves. By identifying the extent through which the length of the path of that reflection changes, along with the direction of motion of the subject relative to that path, WIO can estimate the distance traversed by the subject using WiFi signals. WIO then uses this distance estimate to correct the drift errors. While researchers have previously proposed to use WiFi signals to correct drift errors, prior schemes suffer from one or more of the following six limitations: they 1) do not work indoors, 2) require manual exhaustive fingerprinting, 3) are not resilient against changes in environment including human movements, 4) do not work on commodity WiFi devices, 5) require multiple access points, and/or 6) can measure distance traversed by humans but not by non-human subjects. WIO addresses all of these limitations. We implemented WIO using commodity devices, and extensively evaluated it in a wide variety of complex indoor scenarios on both human and robotic subjects. Our results demonstrate that WIO achieved an average error of just 6.28% in estimating the distances traversed by the subjects.

A FREQUENCY-DRIFT COMPENSATED CLOSED-FORM SOLUTION FOR STEREO RGB-D MAPPING

Abstract. In this work, we present a frequency-drift compensated (Fd-C) closed-form solution for stereo RGB-D SLAM. The intrinsic parameters for each sensor are first obtained with a standard camera calibration process and the extrinsic orientation parameters achieved through a coarse-to-fine scheme that solves the initial exterior orientation parameters (EoPs) from control markers and further refines the initial value by an iterative closest point (ICP) variant minimizing the distance between the RGB-D point clouds and the referenced laser point clouds. With the assumption of fix transformation between the frames with the same timestamp, we define one sensor as reference sensor and the other sensor as slave sensor and the slave frames can be mapped to the timeline of the references sensor. Rather than endow the camera pose of the nearest frame to the slave frames, we derive the accurate camera pose for slave frames in a spatially variant way. Therefore, the pose relations between the slave frame and the adjacent reference frame can be derived, which provided opportunity to use the more accuracy observations from multiple frames for better tracking and global optimization. We present the mathematical analysis of the iterative optimizations for pose tracking in multi-RGB-D camera cases. Finally, the experiments in complex indoor scenarios demonstrate the efficiency of the proposed multiple RGB-D slam algorithm.

Robust Cooperative Indoor Localization Based on Reliability Evaluation

Due to the complex mixed non-line-of-sight (NLOS) and line-of-sight (LOS) propagation conditions, it is a challenging problem to achieve robust and high-performance localization in complex indoor scenarios. To solve this problem, this paper proposes a robust cooperative localization method (CLM) based on the reliability evaluation. The proposed CLM scheme leverages the advantages of the compressive sensing (CS) algorithm in the LOS condition and the particle filter (PF) algorithm in the NLOS condition. We propose a reliability evaluation method to evaluate the estimation results of the CS and PF algorithms, and develop a cooperative localization framework by considering the reliability when merging the estimation results. We also develop a localization system based on ultra-wideband hardware to evaluate the performance of the proposed CLM. Extensive experimental results carried out in different scenarios demonstrate the robust performance of the proposed schemes and the stability of the developed system.

Challenges in Wireless System Integration as Enablers for Indoor Context Aware Environments.

The advent of fully interactive environments within Smart Cities and Smart Regions requires the use of multiple wireless systems. In the case of user-device interaction, which finds multiple applications such as Ambient Assisted Living, Intelligent Transportation Systems or Smart Grids, among others, large amount of transceivers are employed in order to achieve anytime, anyplace and any device connectivity. The resulting combination of heterogeneous wireless network exhibits fundamental limitations derived from Coverage/Capacity relations, as a function of required Quality of Service parameters, required bit rate, energy restrictions and adaptive modulation and coding schemes. In this context, inherent transceiver density poses challenges in overall system operation, given by multiple node operation which increases overall interference levels. In this work, a deterministic based analysis applied to variable density wireless sensor network operation within complex indoor scenarios is presented, as a function of topological node distribution. The extensive analysis derives interference characterizations, both for conventional transceivers as well as wearables, which provide relevant information in terms of individual node configuration as well as complete network layout.

Influence of meshing adaption in convergence performance of deterministic ray launching estimation in indoor scenarios

In this paper, an adaptive meshing solution implemented in an in-house developed three-dimensional ray launching algorithm to model the radio wave propagation channel in large environments is presented. Results show that when large scenarios are analyzed, adaptive meshing is necessary to avoid algorithm divergence, leading to accurate results when comparing with real measurements. In addition, simulation results of an indoor large and complex scenario in terms of received power and power delay profile are presented, showing significant influence of multipath propagation in indoor radio channel behavior. The use of the adaptive meshing for the analysis of large and complex scenarios can aid in the adequate deployment of wireless communication systems for large, complex indoor scenarios.

Design and performance analysis of wireless body area networks in complex indoor e-Health hospital environments for patient remote monitoring

In this article, the design and performance analysis of wireless body area network–based systems for the transmission of medical information readable in an android-based application deployed within complex indoor e-Health scenarios is presented. The scenario under analysis is an emergency room area, where a patient is being monitored remotely with the aid of wearable wireless sensors placed at different body locations. Due to the advent of Internet of Things, in the near future a cloud of a vast number of wireless devices will be operating at the same time, potentially interfering one another. Ensuring good performance of the deployed wireless networks in this kind of environment is mandatory and obtaining accurate radio propagation estimations by means of a computationally efficient algorithm is a key issue. For that purpose, an in-house three-dimensional ray launching algorithm is employed, which provides radio frequency power distribution values, power delay profiles, and delay spread values for the complete volume of complex indoor scenarios. Using this information together with signal-to-noise estimations and link budget calculations, the most suitable wireless body area network technology for this context is chosen. Additionally, an in-house developed human body model has been developed in order to model the impact of the presence of monitored patients. A campaign of measurements has been carried out in order to validate the obtained simulation results. Both the measurements and simulation results illustrate the strong influence of the presented scenario on the overall performance of the wireless body area networks: losses due to material absorption and the strong influence of multipath components due to the great number of obstacles and the presence of persons make the use of the presented method very useful. Finally, an android-based application for the monitoring of patients is presented and tested within the emergency room scenario, providing a flexible solution to increase interactivity in health service provision.

Hybrid equivalent source – 3D ray-launching simulation technique for deterministic estimation of radiated emissions of electrical appliances

In this work, a method for modeling the leaked radiofrequency radiation from electrical appliances is presented, with the aim of obtaining a model for a 3D ray-launching algorithm. The domestic microwave oven is the appliance under analysis, as it radiates a substantial amount of power and it is spread worldwide. The method uses numerical electromagnetic field simulations to obtain the exterior oven radiation. Due to the complexity of the metallic mesh of the oven door, a retrieval process has been implemented in order to accelerate the electromagnetic field simulation. This result is incorporated to a proprietary 3D ray-launching algorithm by obtaining equivalent radiation sources. Finally, the microwave oven leakage is obtained for the complete volume of an indoor scenario. The numerical results are then compared with experimental measurements, with good agreement. The proposed model is useful to predict accurately the leakage of the domestic microwave oven within a complete complex indoor scenario, aiding in further radioplanning considerations.

Utilizing the Virtual Triangulation for Wireless Indoor Localization of Mobile Devices with Channel State Information

To locate an RF device or to enable target oriented communication services in wireless indoor environment, RF properties as RSSI and CSI have been widely adopted in the research and commercial societies. However, the complex indoor scenario makes the task to locate an RF device with fine-grained accuracy more difficult. This paper deals with a virtual triangulation utilization to estimate the length of Line of Sight (LoS) signal out of non LoS on receiving multipath signals from any dimension. Thus, it forms a virtual right angled triangle of the received signals. From the angles ratio, the propose method estimates the side corresponding to the reference LoS length. Eventually, it estimates the distance error between the measured reference LoS of the virtual triangle and the approximated LoS from the CSI. The error is utilized to provide a basement for more precise localization of an RF device.

Estimation of radiofrequency power leakage from microwave ovens for dosimetric assessment at nonionizing radiation exposure levels.

The electromagnetic field leakage levels of nonionizing radiation from a microwave oven have been estimated within a complex indoor scenario. By employing a hybrid simulation technique, based on coupling full wave simulation with an in-house developed deterministic 3D ray launching code, estimations of the observed electric field values can be obtained for the complete indoor scenario. The microwave oven can be modeled as a time- and frequency-dependent radiating source, in which leakage, basically from the microwave oven door, is propagated along the complete indoor scenario interacting with all of the elements present in it. This method can be of aid in order to assess the impact of such devices on expected exposure levels, allowing adequate minimization strategies such as optimal location to be applied.

Radio characterization for ISM 2.4 GHz Wireless Sensor Networks for judo monitoring applications.

In this work, the characterization of the radio channel for ISM 2.4GHz Wireless Sensor Networks (WSNs) for judo applications is presented. The environments where judo activity is held are usually complex indoor scenarios in terms of radiopropagation due to their morphology, the presence of humans and the electromagnetic interference generated by personal portable devices, wireless microphones and other wireless systems used by the media. For the assessment of the impact that the topology and the morphology of these environments have on electromagnetic propagation, an in-house developed 3D ray-launching software has been used in this study. Time domain results as well as estimations of received power level have been obtained for the complete volume of a training venue of a local judo club's facilities with a contest area with the dimensions specified by the International Judo Federation (IJF) for international competitions. The obtained simulation results have been compared with measurements, which have been carried out deploying ZigBee-compliant XBee Pro modules at presented scenario, using approved Judogis (jacket, trousers and belt). The analysis is completed with the inclusion of an in-house human body computational model. Such analysis has allowed the design and development of an in house application devoted to monitor the practice of judo, in order to aid referee activities, training routines and to enhance spectator experience.

Analysis of challenges in the application of deterministic wireless channel modelling in the implementation of WLAN-based indoor location system in large complex scenarios

This paper describes user location and tracking on indoor scenarios based on the pattern recognition of IEEE 802.11 signal strength measurements by means of a fuzzy inference system. Signal fluctuation makes difficult and imprecise the trilateration of the user location, so we propose the use of fuzzy techniques to deal with such imprecision. To implement the location system, deterministic wireless channel characterisation is obtained by means of in–house implemented 3D ray launching code. Several scenarios are analysed, since their size strongly impacts on algorithm convergence. The limitations and solution, based on subdivision of the scenario in sub–zones, are analysed and applied to the case of a new emergency hospital complex in Navarra. Simulation and measurement results are presented showing good agreement. The results can aid in the determination of an optimised WiFi–based location system providing efficient positioning and communication services in complex indoor scenarios.