RSSI-based smooth localization for indoor environment.
Ontology highlight
ABSTRACT:
SUBMITTER: Wang Y
PROVIDER: S-EPMC4101211 | biostudies-other | 2014
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Precise localization and pose estimation in indoor environments are commonly employed in a wide range of applications, including robotics, augmented reality, and navigation and positioning services. Such applications can be solved via visual-based localization using a pre-built 3D model. The increase in searching space associated with large scenes can be overcome by retrieving images in advance and subsequently estimating the pose. The majority of current deep learning-based image retrieval methods require labeled data, which increase data annotation costs and complicate the acquisition of data. In this paper, we propose an unsupervised hierarchical indoor localization framework that integrates an unsupervised network variational autoencoder (VAE) with a visual-based Structure-from-Motion (SfM) approach in order to extract global and local features. During the localization process, global features are applied for the image retrieval at the level of the scene map in order to obtain candidate images, and are subsequently used to estimate the pose from 2D-3D matches between query and candidate images. RGB images only are used as the input of the proposed localization system, which is both convenient and challenging. Experimental results reveal that the proposed method can localize images within 0.16 m and 4° in the 7-Scenes data sets and 32.8% within 5 m and 20° in the Baidu data set. Furthermore, our proposed method achieves a higher precision compared to advanced methods.
| S-EPMC8153307 | biostudies-literature
Project description:Evaluations of different technologies and solutions for indoor localization exist but only a few are aimed at the industrial context. In this paper, we compare and analyze two prominent solutions based on Ultra Wide Band Radio (Pozyx) and Ultrasound (GoT), both installed in an industrial manufacturing laboratory. The comparison comprises a static and a dynamic case. The static case evaluates average localization errors over 90 s intervals for 100 ground-truth points at three different heights, corresponding to different relevant objects in an industrial environment: mobile robots, pallets, forklifts and worker helmets. The average error obtained across the laboratory is similar for both systems and is between 0.3 m and 0.6 m, with higher errors for low altitudes. The dynamic case is performed with a mobile robot travelling with an average speed of 0.5 m/s at a height of 0.3 m. In this case, low frequency error components are filtered out to focus the comparison on dynamic errors. Average dynamic errors are within 0.3-0.4 m for Pozyx and within 0.1-0.2 m for GoT. Results show an acceptable accuracy required for tracking people or objects and could serve as a guideline for the least achievable accuracy when applied for mobile robotics in conjunction with other elements of a robotic navigation stack.
| S-EPMC9026763 | biostudies-literature
Project description:In this paper we tackle the problem of indoor robot localization by using a vision-based approach. Specifically, we propose a visual odometer able to give back the relative pose of an omnidirectional automatic guided vehicle (AGV) that moves inside an indoor industrial environment. A monocular downward-looking camera having the optical axis nearly perpendicular to the ground floor, is used for collecting floor images. After a preliminary analysis of images aimed at detecting robust point features (keypoints) takes place, specific descriptors associated to the keypoints enable to match the detected points to their consecutive frames. A robust correspondence feature filter based on statistical and geometrical information is devised for rejecting those incorrect matchings, thus delivering better pose estimations. A camera pose compensation is further introduced for ensuring better positioning accuracy. The effectiveness of proposed methodology has been proven through several experiments, in laboratory as well as in an industrial setting. Both quantitative and qualitative evaluations have been made. Outcomes have shown that the method provides a final positioning percentage error of 0.21% on an average distance of 17.2 m. A longer run in an industrial context has provided comparable results (a percentage error of 0.94% after about 80 m). The average relative positioning error is about 3%, which is still in good agreement with current state of the art.
| S-EPMC7038713 | biostudies-literature
Project description:Accurate, inexpensive, and reliable real-time indoor localization holds the key to the full potential of the context-aware applications and location-based Internet of Things (IoT) services. State-of-the-art indoor localization systems are coping with the complex non-line-of-sight (NLOS) signal propagation which hinders the use of proven multiangulation and multilateration methods, as well as with prohibitive installation costs, computational demands, and energy requirements. In this paper, we present a novel sensor utilizing low-range infrared (IR) signal in the line-of-sight (LOS) context providing high precision angle-of-arrival (AoA) estimation. The proposed sensor is used in the pragmatic solution to the localization problem that avoids NLOS propagation issues by exploiting the powerful concept of the wireless sensor network (WSN). To demonstrate the proposed solution, we applied it in the challenging context of the supermarket cart navigation. In this specific use case, a proof-of-concept navigation system was implemented with the following components: IR-AoA sensor prototype and the corresponding WSN used for cart localization, server-side application programming interface (API), and client application suite consisting of smartphone and smartwatch applications. The localization performance of the proposed solution was assessed in, altogether, four evaluation procedures, including both empirical and simulation settings. The evaluation outcomes are ranging from centimeter-level accuracy achieved in static-1D context up to 1 m mean localization error obtained for a mobile cart moving at 140 cm/s in a 2D setup. These results show that, for the supermarket context, appropriate localization accuracy can be achieved, along with the real-time navigation support, using readily available IR technology with inexpensive hardware components.
| S-EPMC7663400 | biostudies-literature
Project description:Accurate indoor person localization is essential for several services, such as assisted living. We introduce a tagless indoor person localization system based on capacitive sensing and localization algorithms that can determine the location with less than 0.2 m average error in a 3 m × 3 m room and has recall and precision better than 70%. We also discuss the effects of various noise types on the measurements and ways to reduce them using filters suitable for on-sensor implementation to lower communication energy consumption. We also compare the performance of several standard localization algorithms in terms of localization error, recall, precision, and accuracy of detection of the movement trajectory.
| S-EPMC5038726 | biostudies-literature
Project description:This paper proposes a novel multi-sensor-based indoor global localization system integrating visual localization aided by CNN-based image retrieval with a probabilistic localization approach. The global localization system consists of three parts: coarse place recognition, fine localization and re-localization from kidnapping. Coarse place recognition exploits a monocular camera to realize the initial localization based on image retrieval, in which off-the-shelf features extracted from a pre-trained Convolutional Neural Network (CNN) are adopted to determine the candidate locations of the robot. In the fine localization, a laser range finder is equipped to estimate the accurate pose of a mobile robot by means of an adaptive Monte Carlo localization, in which the candidate locations obtained by image retrieval are considered as seeds for initial random sampling. Additionally, to address the problem of robot kidnapping, we present a closed-loop localization mechanism to monitor the state of the robot in real time and make adaptive adjustments when the robot is kidnapped. The closed-loop mechanism effectively exploits the correlation of image sequences to realize the re-localization based on Long-Short Term Memory (LSTM) network. Extensive experiments were conducted and the results indicate that the proposed method not only exhibits great improvement on accuracy and speed, but also can recover from localization failures compared to two conventional localization methods.
| S-EPMC6359079 | biostudies-literature
Project description: Not available
| S-EPMC7395586 | biostudies-literature
Project description:Physical distancing has been an important policy to mitigate the spread of the novel coronavirus disease 2019 (COVID-19) in public settings. However, the current 1-2 m physical distancing rule is based on the physics of droplet transport and could not directly translate into infection risk. We therefore revisit the 2-m physical distancing rule by developing an infection-risk-based model for human speaking. The key modeling framework components include viral load, droplets dispersion and evaporation, deposition efficiency, viral dose-response rate and infection risk. The results suggest that the one-size-fits-all 2-m physical distancing rule derived from the pure droplet-physics-based model is not applicable under some realistic indoor settings, and may rather increase transmission probability of diseases. Especially, in thermally stratified environments, the infection risk could exhibit multiple peaks for a long distance beyond 2 m. With Sobol's sensitivity analysis, most variance of the risk is found to be significantly attributable to the variability in temperature gradient, exposure time and breathing height difference. Our study suggests there is no such magic 2 m physical distancing rule for all environments, but it needs to be used alongside other strategies, such as using face cover, reducing exposure time, and controlling the thermal stratification of indoor environment.
| S-EPMC8016632 | biostudies-literature
Project description:In this paper, we study the influence of multipath magnitude, bandwidth, and communication link number on the performance of the existing time-reversal (TR) based fingerprinting localization approach and find that the localization accuracy deteriorates with a limited bandwidth. To improve the localization performance, by exploiting two unique location-specified signatures extracted from Channel State Information (CSI), we propose a high accuracy TR fingerprint localization approach, HATRFLA. Furthermore, we employ a density-based spatial clustering algorithm to minimize the storage space of the fingerprint database by adaptively selecting the optimal number of fingerprints for each location. Experimental results confirm that the proposed approach can efficiently mitigate accuracy deterioration caused by a limited bandwidth and consequently, achieve higher accuracy compared with the existing TR localization approach.
| S-EPMC6210306 | biostudies-literature
Project description:This paper presents a constrained Kalman filter for Wi-Fi-based indoor localization. The contribution of this work is to introduce constraints on the object speed and to provide a numerically optimized form for fast computation. The proposed approach is suitable to flexible space organization, as in warehouses, and when objects can be spun around, for example barcode readers in a hand. We experimented with the proposed technique using a robot and three devices, on five different journeys, in a 6000 m2 warehouse equipped with six Wi-Fi access points. The results highlight that the proposed approach provides a 19% improvement in localization accuracy.
| S-EPMC8779188 | biostudies-literature