Search

This study proposes an indoor visible light localization technique incorporating the black-winged kite algorithm to address problems such as limited indoor localization accuracy. The black-winged kite algorithm is an intelligent optimization algorithm inspired by the hunting behavior of black-winged kites in nature, and it is designed to solve the problem of global optimization. The indoor visible light localization problem can be transformed into a problem of solving the optimal coordinates of the receiver globally. Combining the black-winged kite algorithm and the indoor visible light problem can effectively localize the receiver’s position accurately in a complex indoor environment. The simulation results show that in the indoor environment of 5m $\times 5$ m $\times 6$ m, the average error of 1.29cm and the maximum error of 6.29cm are achieved after 100 iterations and 90.02% of the average localization error is less than 2.39cm, the horizontal error is less than 2.20cm. The vertical error is 0.39cm, which realizes high-precision localization. The three-dimensional positioning error distribution map visualizes the distribution of the space error in space, further demonstrating the scheme’s effectiveness. It provides a new method for visible light indoor positioning technology.

The demand for efficient and sustainable agricultural practices has fostered the development of advanced technologies for pest management. This paper presents a research study on the detection of slugs on lettuce and the 3D localization (x , y , z coordinates) of the detected slugs, with the goal of enabling a robotic arm to collect them in a horticultural application. In this regard, deep-learning models (YOLOv5), were developed as a tool in this study. The real-time 3D coordinates of the centers of the detected slugs were calculated by the developed YOLOv5 models. A total of 4344 images were captured under diverse conditions and manually labeled for training (3098 images) and validation (775 images) of the models, while an additional 471 images were used for testing. The evaluation of the YOLOv5l model on the test dataset showed promising results, with 98.6% recall, 98.9% precision, and a mean average precision (mAP) 50–95 of 78.8%. The comparison of box losses during training and validation demonstrated that YOLOv5l had the lowest box losses, emphasizing its better performance. The experimental results show the effectiveness of the developed system in slug detection on lettuce and in providing accurate 3D coordinates of the detected slugs in real-time. This research shows a promising approach to be implemented in a horticultural robotic platform capable of autonomously detecting and collecting slugs, which could contribute to enhanced efficiency and sustainability in agriculture and horticulture. [ABSTRACT FROM AUTHOR]

Accurate detection and localization of fruits in natural environments is a key step for fruit picking robots to achieve precise harvesting. However, existing banana detection and positioning methods have two main limitations in practical applications: a large number of model parameters that make deployment difficult, and a need for performance improvement. To tackle the above issues, a high-precision and lightweight banana bunch recognition and localization method was proposed and deployed on edge devices for application. First, a Slim-Banana model was proposed based on the improvement of YOLOv8l. In order to reduce the model calculation amount and maintain high performance, GSConv was introduced in the Slim-Banana model to replace the standard convolution, and combined with grouped convolution and spatial convolution. At the same time, the cross-stage local network (GSCSP) module was designed to reduce the computational complexity and the complexity of the network structure through a single-stage aggregation method. Then, the RealSense depth sensor is combined with TOF technology to perform image registration and 3D localization of the banana. Finally, the pipeline is deployed on the Nvidia Orin NX edge device and its performance and resource consumption in actual work are deeply analyzed. Experimental results show that the detection precision, recall, mAP and inference time of our method are 0.947, 0.948, 0.98 and 113.6 ms respectively, the network memory size required is 4449MiB, and the average localization errors in the X-axis, Y-axis and Z-axis directions are 13.47 mm, 12.87 mm and 13.87 mm respectively. To our knowledge, this is the first work that implements banana detection and localization on edge devices. Experimental results show that compared with existing methods, our method achieves better performance in complex orchard environments, achieving efficient and lightweight banana recognition and localization.

Wireless Sensor Networks (WSNs) are extensively utilized across diverse applications, ranging from environmental monitoring to industrial automation. These networks deploy autonomous devices equipped with sensors to monitor environmental conditions such as temperature, humidity, and light. They play crucial roles in fields like precision agriculture, healthcare monitoring, and smart cities infrastructure. In the domain of WSNs, ensuring both security and precise localization is vital for sustaining optimal network performance and facilitating timely event detection. Despite numerous localization studies, existing approaches often fall short in 3D localization due to low beacon node accuracy and sparse environment coverage. Furthermore, achieving higher localization accuracy is challenging due to potential attacks that can compromise network integrity and reduce battery life. To address these issues, a novel Secure 3D algorithm is introduced in this paper to combat malicious beacon nodes as well as to enhance localization accuracy. The proposed Secure 3D algorithm demonstrates superior performance compared to the 3D DV-Hop, 3D APIT and Improved 3D localization algorithms in terms of Average Localization Error (ALE), Bad Node Proportion (BNP), and Localized Node Proportion (LNP), while also being energy-efficient. This algorithm achieves an ALE ranging from 3.0 to 6.5, a BNP below 0.2, and an LNP exceeding 0.8, all while consuming 100–130mW of energy. By addressing the challenges of malicious beacon nodes and enhancing localization accuracy, the proposed work not only improves network reliability but also ensures energy-efficient energy localization, making it a promising solution for enhancing the performance and security of WSNs in 3D environments. [ABSTRACT FROM AUTHOR]

In the realm of computer vision, the integration of advanced techniques into the pre-processing of RGB-D camera inputs poses a significant challenge, given the inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery. Traditional computer vision systems face limitations in simultaneously capturing precise object boundaries and achieving high-precision object detection on depth maps, as they are mainly proposed for RGB cameras. To address this challenge, FusionVision adopts an integrated approach by merging state-of-the-art object detection techniques, with advanced instance segmentation methods. The integration of these components enables a holistic (unified analysis of information obtained from both color RGB and depth D channels) interpretation of RGB-D data, facilitating the extraction of comprehensive and accurate object information in order to improve post-processes such as object 6D pose estimation, Simultanious Localization and Mapping (SLAM) operations, accurate 3D dataset extraction, etc. The proposed FusionVision pipeline employs YOLO for identifying objects within the RGB image domain. Subsequently, FastSAM, an innovative semantic segmentation model, is applied to delineate object boundaries, yielding refined segmentation masks. The synergy between these components and their integration into 3D scene understanding ensures a cohesive fusion of object detection and segmentation, enhancing overall precision in 3D object segmentation. [ABSTRACT FROM AUTHOR]

Purpose: For tumor resection, surgeons need to localize the tumor. For this purpose, a magnetic seed can be inserted into the tumor by a radiologist and, during surgery, a magnetic detection probe informs the distance to the seed for localization. In this case, the surgeon still needs to mentally reconstruct the position of the tumor from the probe's information. The purpose of this study is to develop and assess a method for 3D localization and visualization of the seed, facilitating the localization of the tumor. Methods: We propose a method for 3D localization of the magnetic seed by extending the magnetic detection probe with a tracking-based localization. We attach a position sensor (QR-code or optical marker) to the probe in order to track its 3D pose (respectively, using a head-mounted display with a camera or optical tracker). Following an acquisition protocol, the 3D probe tip and seed position are subsequently obtained by solving a system of equations based on the distances and the 3D probe poses. Results: The method was evaluated with an optical tracking system. An experimental setup using QR-code tracking (resp. using an optical marker) achieves an average of 1.6 mm (resp. 0.8 mm) 3D distance between the localized seed and the ground truth. Using a breast phantom setup, the average 3D distance is 4.7 mm with a QR-code and 2.1 mm with an optical marker. Conclusion: Tracking the magnetic detection probe allows 3D localization of a magnetic seed, which opens doors for augmented reality target visualization during surgery. Such an approach should enhance the perception of the localized region of interest during the intervention, especially for breast tumor resection where magnetic seeds can already be used in the protocol. [ABSTRACT FROM AUTHOR]

Every year millions of lives are lost in emergency situations. Localizing missing people in the shortest possible timeframe is the most effective tool to reduce such a death toll. However, this is challenging when the victims are unable to communicate by themselves or located in large and difficult-toreach areas. Current technological approaches for victim localization are often rendered inoperable under obstacles or low visibility conditions, or due to the lack of cellular networking infrastructure. Toward addressing these issues, we present 3DSAR+, a pioneering single-drone three-dimensional (3D) cellular search-and-rescue (SAR) solution leveraging 5G-new radio (NR) technology. 3DSAR+ system introduces dynamic autonomous 3D UAV trajectories in diverse and challenging environments, offering a robust tool for first responders in SAR missions. The main novelty of the proposed approach lies in advanced distance and angle estimation combined with machine learning (ML) algorithms for position prediction and correction. The approach is able to estimate victims’ locations through their mobile phones without requiring extra equipment and improves localization accuracy by an order of magnitude compared to baseline solutions.

Reconfigurable intelligent surfaces (RISs) have received considerable attention in applications related to localization. However, operation in multi-path scenarios is challenging from both complexity and performance perspectives. This study presents a two-stage low complexity method for joint three-dimensional (3D) localization and synchronization using multiple RISs. Firstly, the received signals are preprocessed, and an efficient deep learning architecture is proposed to initially estimate the angles of departure (AODs) of the virtual line of sight paths from the RISs to the user. Then, a hybrid asynchronous AOD time-of-arrival-based approach is proposed in the first stage to estimate an initial guess of the position of the user equipment (UE). Finally, in the second stage, an optimization problem is formulated to refine the position of the UE by effectively utilizing the estimated delays and the clock offset. Our comparative study reveals that the proposed method outperforms the existing methods in terms of accuracy and complexity. Notably, the proposed method showcases enhanced robustness against multipath effects when compared to the state-of-the-art approaches.

A thorough clinical and radiographical assessment of an impacted maxillary canine’s location forms the basis for proper diagnosis and successful treatment outcomes. Implementing a correct biomechanical approach for directing force application primarily relies on its precise localization. Poor biomechanical planning can resorb the roots of adjacent teeth and result in poor periodontal outcomes of the canine that has been disimpacted. Furthermore, treatment success and time strongly rely on an accurate assessment of the severity of impaction, which depends on its 3D spatial location. The evolution of cone-beam computed tomography (CBCT) radiographs provides more detailed information regarding the location of the impacted canines. In addition, the literature has shown that CBCT imaging has enhanced the quality of diagnosis and treatment planning by obtaining a more precise localization of impacted canines. This review article highlights current evidence regarding comprehensive evaluation of three-dimensional orientations of impacted canines on CBCT images for precise diagnosis and treatment planning.

Abstract Improving three-dimensional (3D) localization precision is of paramount importance for super-resolution imaging. By properly engineering the point spread function (PSF), such as utilizing Laguerre–Gaussian (LG) modes and their superposition, the ultimate limits of 3D localization precision can be enhanced. However, achieving these limits is challenging, as it often involves complicated detection strategies and practical limitations. In this work, we rigorously derive the ultimate 3D localization limits of LG modes and their superposition, specifically rotation modes, in the multi-parameter estimation framework. Our findings reveal that a significant portion of the information required for achieving 3D super-localization of LG modes can be obtained through feasible intensity detection. Moreover, the 3D ultimate precision can be achieved when the azimuthal index l is zero. To provide a proof-of-principle demonstration, we develop an iterative maximum likelihood estimation (MLE) algorithm that converges to the 3D position of a point source, considering the pixelation and detector noise. The experimental implementation exhibits an improvement of up to two-fold in lateral localization precision and up to twenty-fold in axial localization precision when using LG modes compared to Gaussian mode. We also showcase the superior axial localization capability of the rotation mode within the near-focus region, effectively overcoming the limitations encountered by single LG modes. Notably, in the presence of realistic aberration, the algorithm robustly achieves the Cramér-Rao lower bound. Our findings provide valuable insights for evaluating and optimizing the achievable 3D localization precision, which will facilitate the advancements in super-resolution microscopy.

The development of advanced robotic systems that can be operated effortlessly by humans is crucial for expanding the capabilities of human-robot interaction and collaboration. In this work, we propose a system that enables real-time and non-invasive tracking of the human wrist's position in three-dimensional space to facilitate an intuitive control of a remotely placed robotic arm, as an improvement towards efficient control mechanism. We leverage color segmentation based human wrist tracking in the viewing plane augmented with a stereo depth estimation for synthesising the localized wrist in the Cartesian space. The centroid of the segmented image is determined to generate the precise coordinates. To remove the variance in the estimated centroid, the trajectory of the localized points is modelled by Kalman filtering approach. Finally, the coordinates are transformed using Inverse Imaging Model and transmitted to an edge device (close to the robot), which then replicates the motion at the robot end using inverse kinematics. The results show a high degree of accuracy in tracking the wrist's movements, enabling precise and natural control over the robotic arm's motion. The system's adaptability to various environments and user populations is validated through tests with diverse subjects. With its high accuracy, real-time performance, the proposed approach holds great potential to enhance the efficiency and safety of human-robot collaborative applications across multiple domains. [ABSTRACT FROM AUTHOR]

RFID-based technology innovated a new field of wireless sensing, which has been applied in posture recognition, object localization, and the other sensing fields. Due to the presence of a Fresnel zone around a magnetic field when the RFID-based system is working, the signal undergoes significant changes when an object moves through two or more different Fresnel zones. Therefore, the moving object can be sensed more easily, and most of the sensing applications required the tag to be attached to the moving object for better sensing, significantly limiting their applications. The existing technologies to detect static objects in agricultural settings are mainly based on X-ray or high-power radar, which are costly and bulky, making them difficult to deploy on a large scale. It is a challenging task to sense a static target without a tag attached in NLOS (non-line-of-sight) detection with low cost. We utilized RFID technologies to sense the static foreign objects in agricultural products, and take metal, rock, rubber, and clod as sensing targets that are common in agriculture. By deploying tag matrices to create a sensing region, we observed the signal variations before and after the appearance of the targets in this sensing region, and determined the targets' positions and their types. Here, we buried the targets in the media of seedless cotton and wheat, and detected them using a non-contact method. Research has illustrated that, by deploying appropriate tag matrices and adjusting the angle of a single RFID antenna, the matrices' signals are sensitive to the static targets' positions and their properties, i.e., matrices' signals vary with different targets and their positions. Specifically, we achieved a 100% success rate in locating metallic targets, while the success rate for clods was the lowest at 86%. We achieved a 100% recognition rate for the types of all the four objects. [ABSTRACT FROM AUTHOR]

A thorough clinical and radiographical assessment of an impacted maxillary canine’s location forms the basis for proper diagnosis and successful treatment outcomes. Implementing a correct biomechanical approach for directing force application primarily relies on its precise localization. Poor biomechanical planning can resorb the roots of adjacent teeth and result in poor periodontal outcomes of the canine that has been disimpacted. Furthermore, treatment success and time strongly rely on an accurate assessment of the severity of impaction, which depends on its 3D spatial location. The evolution of cone-beam computed tomography (CBCT) radiographs provides more detailed information regarding the location of the impacted canines. In addition, the literature has shown that CBCT imaging has enhanced the quality of diagnosis and treatment planning by obtaining a more precise localization of impacted canines. This review article highlights current evidence regarding comprehensive evaluation of three-dimensional orientations of impacted canines on CBCT images for precise diagnosis and treatment planning. [ABSTRACT FROM AUTHOR]

Improving three-dimensional (3D) localization precision is of paramount importance for super-resolution imaging. By properly engineering the point spread function (PSF), such as utilizing Laguerre–Gaussian (LG) modes and their superposition, the ultimate limits of 3D localization precision can be enhanced. However, achieving these limits is challenging, as it often involves complicated detection strategies and practical limitations. In this work, we rigorously derive the ultimate 3D localization limits of LG modes and their superposition, specifically rotation modes, in the multi-parameter estimation framework. Our findings reveal that a significant portion of the information required for achieving 3D super-localization of LG modes can be obtained through feasible intensity detection. Moreover, the 3D ultimate precision can be achieved when the azimuthal index l is zero. To provide a proof-of-principle demonstration, we develop an iterative maximum likelihood estimation (MLE) algorithm that converges to the 3D position of a point source, considering the pixelation and detector noise. The experimental implementation exhibits an improvement of up to two-fold in lateral localization precision and up to twenty-fold in axial localization precision when using LG modes compared to Gaussian mode. We also showcase the superior axial localization capability of the rotation mode within the near-focus region, effectively overcoming the limitations encountered by single LG modes. Notably, in the presence of realistic aberration, the algorithm robustly achieves the Cramér-Rao lower bound. Our findings provide valuable insights for evaluating and optimizing the achievable 3D localization precision, which will facilitate the advancements in super-resolution microscopy. [ABSTRACT FROM AUTHOR]

The detection and localization of acoustic sources remain technological challenges in bioacoustics, in particular, the tracking of moving underwater sound sources with a portable waterproof tool. For instance, this type of tool is important to describe the behavior of cetaceans within social groups. To contribute to this issue, an original innovative autonomous device, called a CETOSCOPE©, was designed by ABYSS NGO, including a 360° video camera and a passive acoustic array with 4 synchronized hydrophones. Firstly, different 3D structures were built and tested to select the best architecture to minimize the errors of the localizations. Secondly, a specific software was developed to analyze the recorded data and to link them to the acoustic underwater sources. The 3D localization of the sound sources is based on time difference of arrival processing. Following successful simulations on a computer, this device was tested in a pool to assess its efficiency. The final objective is to use this device routinely in underwater visual and acoustic observations of cetaceans. [ABSTRACT FROM AUTHOR]

Indoor localization is one of the emergent technologies in location based services, which find useful for commercial as well as civilian industries. Global position systems are a familiar solution for outdoor localization systems. But the presence of complicated obstacles in buildings poses a major challenge in indoor localization. Though few indoor localization techniques based on ranging and fingerprint based techniques are devised, they are time consuming and laborious. Therefore, this paper devises an efficient deer hunting optimization algorithm with weighted least square estimation (DHOA-WLSE) technique for accurate 3D indoor node localization technique. The proposed DHOA-WLSE technique has the ability to accomplish minimal localization error with least localization time. In DHOA-WLSE technique, the DHOA is used to estimate the primary target location to eliminate the non-line of sight errors. Based on the primary locations attained, the WLSE technique is applied to determine the accurate target's final location. In order to validate the 3D indoor localization performance of the DHOA-WLSE technique, an extensive simulation analysis is performed and the results are investigated in terms of different measures. The simulation outcomes demonstrated the superior performance of the DHOA-WLSE technique over the recent state of art techniques. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) localization plays an important role in visual sensor networks. However, the frame rate and flexibility of the existing vision-based localization systems are limited by using synchronized multiple cameras. For such a purpose, this paper focuses on developing an indoor 3D localization system based on unsynchronized multiple cameras. First of all, we propose a calibration method for unsynchronized perspective/fish-eye cameras based on timestamp matching and pixel fitting by using a wand under general motions. With the multi-camera calibration result, we then designed a localization method for the unsynchronized multi-camera system based on the extended Kalman filter (EKF). Finally, extensive experiments were conducted to demonstrate the effectiveness of the established 3D localization system. The obtained results provided valuable insights into the camera calibration and 3D localization of unsynchronized multiple cameras in visual sensor networks.

Positions of unmanned aerial vehicles (UAVs) are typically obtained using the global positioning system (GPS). However, in GPS-denied or GPS-degraded environments, ad hoc networks with flying sensor nodes are used for UAV localization. In this study, we propose a novel three-dimensional (3D) localization algorithm for UAVs in flying ad hoc sensor networks. Interacting multiple model probability data association and finite impulse response filters are integrated in our hybrid localization algorithm. The non-line-of-sight condition can be overcome using the proposed algorithm, which is demonstrated through 3D localization simulations based on flying ad hoc networks. [ABSTRACT FROM AUTHOR]

Background: The Automated Arrhythmia Origin Localization (AAOL) algorithm was developed for real-time prediction of early ventricular activation origins on a patient-specific electroanatomic (EAM) surface using a 3-lead electrocardiogram (AAOL-Surface). It has not been evaluated in 3-dimensional (3D) space (AAOL-3D), however, which may be important for predicting the arrhythmia origin from intramural or intracavity sites., Objectives: This study sought to assess the accuracy of AAOL for localizing earliest ventricular activation in 3D space., Methods: This was a retrospective study of 3 datasets (BWH [Brigham and Women's Hospital], JHH [Johns Hopkins Hospital], and QEII [Queen Elizabeth II Health Sciences Centre]) involving 47 patients and 48 procedures, with an average of 19 ± 10 pacing sites each. In each patient, individual pacing sites were identified as target sites; the remaining pacing sites served as a training set (including QRS integrals from leads III, V 2 , and V 6 with associated 3D coordinates). The AAOL-3D was then used to predict 3D coordinates of the pacing site. Localization error was assessed as the distance between known and predicted site coordinates, considering different EAM resolutions., Results: The AAOL-3D achieved a localization accuracy of 7.2 ± 3.1 mm, outperforming the AAOL-Surface (7.2 vs 7.8 mm; P < 0.05), with greater localization error for epicardial than endocardial pacing sites (8.7 vs 7.1 mm; P < 0.05). Cohort-specific analysis consistently favored AAOL-3D over AAOL-Surface in terms of accuracy. Exploration of AAOL-Surface accuracy across varying EAM resolutions showed optimal performance at the original and 75% resolution, with performance declining as resolution decreased., Conclusions: The AAOL approach accurately identifies early ventricular activation origins in 3D and on EAM surfaces, potentially useful for identifying intramural arrhythmia origins., Competing Interests: Funding Support and Author Disclosures This study was funded by American Heart Association (AIREA grant # 949812) and NIH grant R15HL167222. Drs Zhou, Chrispin, Jonathan, and Trayanova are coholders of a patent for automated VT localization (AAOL). Dr AbdelWahab is a coholder of a patent for automated VT localization (AAOL); and has received speaker honoraria from Abbott and Medtronic. Dr Sapp is a coholder of a patent for automated VT localization (AAOL); has received research funding from Biosense Webster and Abbott (for clinical trial of catheter ablation of VT); and has received modest speaker/consulting honoraria from Medtronic, Biosense Webster, Abbott, and Varian. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose., (Copyright © 2025 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)

Surface acoustic wave (SAW) radio-frequency identification (RFID) has high potential for industrial applications, where automated identification and localization of assets represent the backbone of process controlling and logistics. However, in situations where multiple tags are simultaneously interrogated, the response patterns corresponding to the hard-coded reflectors are prone to overlap, preventing their association with the corresponding tags and, hence, the correct tag decoding. Identification and localization of multiple SAW RFID tags are addressed in this work under this challenging effect, known as collision, with a multi-antenna mobile robot-based synthetic aperture approach. Using the estimation of the spatial probability density functions of the SAW tag reflectors over a given interrogation aperture, the received impulse responses can be resolved in three dimensions and clustered with respect to their estimated locations. The performance of the proposed approach to associate and localize the signals from multiple tags was evaluated theoretically and experimentally.

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this study, a universal gated recurrent unit (u-GRU)-based location estimation (LE) method is proposed to obtain the location of an ultra-wideband (UWB) transmitter. The proposed u-GRU-LE system consists of a GRU-based classifier and nine localizers for nine channel models (CMs). The classifier first predicts the CM, and then, the proper localizer is selected according to the predicted CM to estimate the location of the transmitter. Rigorous simulations are executed with various CMs. From the results, it is verified that the proposed universal GRU-based 3D localization method generally performs well irrespective of the channel environments.

The performance of Wi-Fi fingerprinting indoor localization systems (ILS) in indoor environments depends on the channel state information (CSI) that is usually restricted because of the fading effect of the multipath. Commonly referred to as the next positioning generation (NPG), the Wi-Fi™, IEEE 802.11az standard offers physical layer characteristics that allow positioning and enhanced ranging using conventional methods. Therefore, it is essential to create an indoor environment dataset of fingerprints of CIR based on 802.11az signals, and label all these fingerprints by their location data estimate STA locations based on a portion of the dataset for fingerprints. This work develops a model for training a convolutional neural network (CNN) for positioning and localization through generating IEEE® 802.11data. The study includes the use of a trained CNN to predict the position or location of several stations according to fingerprint data. This includes evaluating the performance of the CNN for multiple channel impulses responses (CIRs). Deep learning and Fingerprinting algorithms are employed in Wi-Fi positioning models to create a dataset through sampling the fingerprints channel at recognized positions in an environment. The model predicts the locations of a user according to a signal acknowledged of an unidentified position via a reference database. The work also discusses the influence of antenna array size and channel bandwidth on performance. It is shown that the increased training epochs and number of STAs improve the network performance. The results have been proven by a confusion matrix that summarizes and visualizes the undertaking classification technique. We use a limited dataset for simplicity and last in a short simulation time but a higher performance is achieved by training a larger data [ABSTRACT FROM AUTHOR]

The performance of modern digital cameras approaches physical limits and enables high-precision measurements in optical metrology and in computer vision. All camera-assisted geometrical measurements are fundamentally limited by the quality of camera calibration. Unfortunately, this procedure is often effectively considered a nuisance: calibration data are collected in a non-systematic way and lack quality specifications; imaging models are selected in an ad hoc fashion without proper justification; and calibration results are evaluated, interpreted, and reported inconsistently. We outline an (arguably more) systematic and metrologically sound approach to calibrating cameras and characterizing the calibration outcomes that is inspired by typical machine learning workflows and practical requirements of camera-based measurements. Combining standard calibration tools and the technique of active targets with phase-shifted cosine patterns, we demonstrate that the imaging geometry of a typical industrial camera can be characterized with sub-mm uncertainty up to distances of a few meters even with simple parametric models, while the quality of data and resulting parameters can be known and controlled at all stages. [ABSTRACT FROM AUTHOR]

Purpose: Most cardiology procedures are guided using X-ray (XR) fluoroscopy. However, the projective nature of the XR fluoroscopy does not allow for true depth perception as required for safe and efficient intervention guidance in structural heart diseases. For improving guidance, different methods have been proposed often being radiation-intensive, time-consuming, or expensive. We propose a simple 3D localization method based on a single monoplane XR projection using a co-registered centerline model. Methods: The method is based on 3D anatomic surface models and corresponding centerlines generated from preprocedural imaging. After initial co-registration, 2D working points identified in monoplane XR projections are localized in 3D by minimizing the angle between the projection lines of the centerline points and the working points. The accuracy and reliability of the located 3D positions were assessed in 3D using phantom data and in patient data projected to 2D obtained during placement of embolic protection system in interventional procedures. Results: With the proposed methods, 2D working points identified in monoplane XR could be successfully located in the 3D phantom and in the patient-specific 3D anatomy. Accuracy in the phantom (3D) resulted in 1.6 mm (± 0.8 mm) on average, and 2.7 mm (± 1.3 mm) on average in the patient data (2D). Conclusion: The use of co-registered centerline models allows reliable and accurate 3D localization of devices from a single monoplane XR projection during placement of the embolic protection system in TAVR. The extension to different vascular interventions and combination with automatic methods for device detection and registration might be promising. [ABSTRACT FROM AUTHOR]

Wireless techniques have progressed beyond two-dimensional (2D) applications; in particular, three-dimensional (3D) localization in wireless sensor networks has attracted increasing attention. While many research works in 3D localization focused on the accuracy enhancement of schemes based on the sensors’ measurements, limited research works addressed the design of 3D localization schemes considering the narrowband signal restriction of sensors. Against this background, we propose a cube-based multitarget three-dimensional (3D) localization solution by exploiting sensors’ time-difference-of-arrival (TDOA) measurements. In particular, unlike the traditional TDOA based scheme, our scheme works in an asynchronous network. Our contributions are twofold. First, the distributed TDOA–based sensor arrays placed with a predefined method create a cube-based location system in 3D space. Second, we propose a turbo expectation propagation (EP)-based decoding algorithm (TED). EP computation is an efficient tool in Bayesian machine learning. With the assistance of the iterative sensor reliability correction (ISRC), we propose an improved algorithm referred to as ISRC-TED. Specifically, the ISRC-TED algorithm outperforms the TED algorithm by utilizing the decisions of the sensor array at every iteration to improve the decoding accuracy further. A reduced-complexity tree search–based decoding strategy for TED and ISRC-TED is also proposed. In simulations, the proposed TED and ISRC-TED algorithms were highly effective, even when the partial sensor network was in power-saving mode. For example, the proposed ISRC-TED algorithm had almost no localization performance loss when 10% of the sensors were in sleep mode. [ABSTRACT FROM AUTHOR]

Acupoint stimulation has proven to be of significant importance for rehabilitation and preventive therapy. Moxibustion, a kind of acupoint therapy, has mainly been performed by practitioners relying on manual localization and positioning of acupoints, leading to variance in the accuracy owing to human error. Developments in the automatic detection of acupoints using deep learning techniques have proven to somewhat tackle the problem. But the current methods lack depth-based localization and are thus confined to two-dimensional (2D) localization. In this research, a new approach towards 3D acupoint localization is introduced, based on a fusion of RGB and depth convolutional neural networks (CNN) to guide the manipulator. This research aims to tackle the challenge of real-time 3D acupoint localization in order to provide guidance for robot-controlled moxibustion. In the first step, the 3D sensor (Kinect v1) is calibrated and transformation matrix is computed to project the depth data into the RGB domain. Secondly, a fusion of RGB-CNN and depth-CNN is employed, in order to obtain 3D localization. Lastly, 3D coordinates are fed to the manipulator to perform artificially controlled moxibustion therapy. Furthermore, a 3D acupoint dataset consisting of RGB and depth images of hands, is constructed to train, validate and test the network. The network was able to localize 5 sets of acupoints with an average localization error of less than 0.09. Further experiments prove the efficacy of the approach and lay grounds for development of automatic moxibustion robots. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) consist of nodes distributed in the region of interest (ROI) that forward collected data to the sink. The node’s location plays a vital role in data forwarding to enhance network efficiency by reducing the packet drop rate and energy consumption. WSN scenarios, such as tracking, smart cities, and agriculture applications, require location details to accomplish the objective. Assuming a 3D application space, a combination of received signal strength (RSS) and time of arrival (TOA) can be helpful for reliable range estimation of nodes. Notably, the anchor node can minimize localization error for non-line-of-sight (NLOS) signals. We proposed an error minimization protocol for localization of the sensor node, assuming that the anchor node’s location is known prior and can limit the receiving signal in LOS, single, or twice reflection. We start to exploit the sensor node’s geometrical relationship and the anchor node for LOS and NLOS signals and address misclassification. We started initially from the erroneous node position, bound its volume in 3D space, and reduced volume with each iteration following the constraint. Our simulation result outperforms the traditional methods on many occasions, such as boundary volume and computational complexity. [ABSTRACT FROM AUTHOR]

Node localization is one of the key technologies in the wireless sensor network research field, which is crucial to the high-accuracy localization of mobile nodes, but the positioning error of traditional algorithms such as received signal strength indicator and angle of arrival is more than 4 m, which has almost no practical value. For example, the localization accuracy of the localization algorithm based on received signal strength indicator will be reduced sharply when affected by signal reflection, multipath propagation, and other interference factors. To solve the problem, a three-dimensional localization algorithm of mobile nodes was proposed in this article based on received signal strength indicator–angle of arrival and least-squares support-vector regression, which fused the ranging information of received signal strength indicator algorithm and the angle of arrival algorithm and optimized the estimated distance of unknown nodes. Next, the mobile node model and least-squares support-vector regression modeling mechanism were built according to the hop count of the shortest distance between nodes. Finally, the unknown mobile nodes were localized based on least-squares support-vector regression modeling. The experimental results showed that compared with the localization algorithms without optimized ranging information or least-squares support-vector regression modeling, the algorithm proposed in this study exhibited significantly improved stability, a reduced mean localization error by more than 50%, and increased localization accuracy. [ABSTRACT FROM AUTHOR]

The localization system has been extensively studied because of its diverse applicability, for example, in the Internet of Things, automatic management, and unmanned aerial vehicle services. There have been numerous studies on localization in two-dimensional (2D) environments, but those in three-dimensional (3D) environments are scarce. In this paper, we propose a novel localization method that utilizes the gated recurrent unit (GRU) and ultra-wideband (UWB) signals. For the purpose of this study, we considered that the UWB transmitter (Tx) and many UWB receivers (Rx) were placed inside a confined space. The input of the proposed model was generated from the UWB signals that are sent from the Tx to the Rxs, and the output was the location of the Tx. The proposed GRU-based model converts the localization problem into a regression problem by combining the ranging and positioning phase. Thus, the proposed model can directly estimate the location of the Tx. Our proposed GRU-based method achieves 15 and four times shorter execution times for the training and testing, respectively, compared to the existing convolutional neural network (CNN)-based localization methods. The input data can also be easily generated with low complexity. The rows of the input matrix are the downsampled version of the UWB received signal. Throughout numerous simulation results, our novel localization method can achieve a lower root-mean-squared error up to 0.8 meters compared to the recently proposed existing CNN-based method. Furthermore, the proposed method operates well inside a confined space with fixed volume but varying width, height, and depth.

A method of hybrid macro and micro vision to detect and locate sub-millimeter defects in meter-sized glass-ceramics is proposed. A 3D localization model of defects with dual camera imaging and triaxial linear motion is established mathematically. The system is calibrated using a coarse-fine chessboard. A macroscopic camera with a large field of view is used to detect the 2D planar coordinates of possible defects in a large glass-ceramic, then a microscope with a small field of view is utilized to obtain the depth coordinates of these defects by image sharpness evaluation using the triaxial linear stage. Experiments show that the calibrated defect detection and localization system with hybrid macro and micro vision can detect and locate sub-millimeter defects in large glass-ceramics. [ABSTRACT FROM AUTHOR]

The detection and localization of acoustic sources remain technological challenges in bioacoustics, in particular, the tracking of moving underwater sound sources with a portable waterproof tool. For instance, this type of tool is important to describe the behavior of cetaceans within social groups. To contribute to this issue, an original innovative autonomous device, called a CETOSCOPE©, was designed by ABYSS NGO, including a 360° video camera and a passive acoustic array with 4 synchronized hydrophones. Firstly, different 3D structures were built and tested to select the best architecture to minimize the errors of the localizations. Secondly, a specific software was developed to analyze the recorded data and to link them to the acoustic underwater sources. The 3D localization of the sound sources is based on time difference of arrival processing. Following successful simulations on a computer, this device was tested in a pool to assess its efficiency. The final objective is to use this device routinely in underwater visual and acoustic observations of cetaceans.

Nowadays, multi-sensor fusion is a popular tool for feature recognition and object detection. Integrating various sensors allows us to obtain reliable information about the environment. This article proposes a 3D robot trajectory estimation based on a multimodal fusion of 2D features extracted from color images and 3D features from 3D point clouds. First, a set of images was collected using a monocular camera, and we trained a Faster Region Convolutional Neural Network. Using the Faster Region Convolutional Neural Network, the robot detects 2D features from camera input and 3D features using the point's normal distribution on the 3D point cloud. Then, by matching 2D image features to a 3D point cloud, the robot estimates its position. To validate our results, we compared the trained neural network with similar convolutional neural networks. Then, we evaluated their response for the mobile robot trajectory estimation. [ABSTRACT FROM AUTHOR]

Copyright of FME Transactions is the property of University of Belgrade, Faculty of Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Human detection in the wild is a research topic of paramount importance in computer vision, and it is the starting step for designing intelligent systems oriented to human interaction thatwork in complete autonomy. To achieve this goal, computer vision and machine learning should aim at superhuman capabilities. In this work, we address the problem of fine-grained human analysis under occlusions and perspective constraints. More specifically, we discuss some issues and some possible solutions to effectively detect people using pose estimation methods and to detect humans under occlusions both in the two-dimensional (2D) image plane and in the 3D space exploiting single monocular cameras. Dealing with occlusion can be done at the joint level or pixel level: We discuss two different solutions, the former based on a supervised neural network architecture for detecting occluded joints and the latter based on a semi-supervised specialized GAN that exploits both appearance and human shape attributes to determine the missing parts of the visible shape. To deal with perspective constraints, we further discuss a neural approach based on a double architecture that learns to create an optimal neural representation, which is useful to reconstruct the 3D position of human keypoints starting with simple RGB images. All these approaches have a critical point in common: the need for large annotated datasets. To have large, fair, consistent, transparent, and ethical datasets, we propose the adoption of synthetic datasets as, for example, JTA and MOTSynth. In this article, we discuss the pros and cons of using synthetic datasets while tackling several human-centered AI issues with respect to European GDPR rules for privacy.We further explore and discuss an application in the field of risk assessment by space occupancy estimation during the COVID-19 pandemic called Inter-Homines. [ABSTRACT FROM AUTHOR]

A Parallel and Compact version of the Sine Cosine Algorithm (PCSCA) is proposed in this article. Parallel method can effectively improve search ability and increase the diversity of solutions. We develop three communication strategies based on parallelism idea to serve different types of optimization function to achieve the best performance. Furthermore, compact method uses statistical distribution to represent the solutions, which can save memory space and energy of the digital device. To check the optimization effect of the proposed PCSCA algorithm, it is tested on the CEC2013 benchmark function set and compared to SCA, parallel compact Cuckoo Search (PCCS) algorithms. The empirical study demonstrates that PCSCA has improved by 50.1% and 5.6%, compared to SCA and PCCS, respectively. Finally, we apply PCSCA to optimize the position accuracy of sensor node deployed in 3D actual terrain. Experimental results show that PCSCA can achieve lower localization error via Time Difference of Arrival method. [ABSTRACT FROM AUTHOR]

In automated fruit detection, RGB-Depth (RGB-D) images aid the detection model with additional depth information to enhance detection accuracy. However, outdoor depth images are usually of low quality, which limits the quality of depth data. In this study, an approach/technique for real-time apple fruit detection in a high-density orchard environment by using multi-modal data is presented. Non-targeted background removal using the depth fusion (NBR-DF) method was developed to reduce the high noise condition of depth images. The noise occurred due to the uncontrolled lighting condition and holes with incomplete depth information in the depth images. NBR-DF technique follows three primary steps: pre-processing of depth images (point cloud generation), target object extraction, and background removal. The NBR-DF method serves as a pipeline to pre-process multi-modal data to enhance features of depth images by filling holes to eliminate noise generated by depth holes. Further, the NBR-DF implemented with the YOLOv5 enhances the detection accuracy in dense orchard conditions by using multi-modal information as input. An attention-based depth fusion module that adaptively fuses the multi-modal features was developed. The integration of the depth-attention matrix involved pooling operations and sigmoid normalization, both of which are efficient methods for summarizing and normalizing depth information. The fusion module improves the identification of multiscale objects and strengthens the network's resistance to noise. The network then detects the fruit position using multiscale information from the RGB-D images in highly complex orchard environments. The detection results were compared and validated with other methods using different input modals and fusion strategies. The results showed that the detection accuracy using the NBR-DF approach achieved an average precision rate of 0.964 in real time. The performance comparison with other state-of-the-art methods and the model generalization study also establish that the present advanced depth-fusion attention mechanism and effective preprocessing steps in NBR-DF-YOLOv5 significantly surpass those in performance. In conclusion, the developed NBR-DF technique showed the potential to improve real-time apple fruit detection using multi-modal information. • The non-targeted background removal using depth fusion (NBR-DF) is developed to enhance apple fruit detection accuracy. • The NBR-DF used as pipeline with YOLOv5 detection model, as NBR-DF-YOLOv5. • A pipeline works to generate point cloud filtration, segmentation and object extraction from depth images. • AP0.5 of NBR-DF-YOLOv5 is 0.964 as compared to 0.925 achieved with YOLOv5. [ABSTRACT FROM AUTHOR]

Recent research efforts regarding advanced Robotic Capsule Endoscopes (RCEs) have primarily focused on the development of actively locomotive endoscope capsules. However, accurate movement of an RCE inside the digestive organs remains a challenge that hinders the further development of an autonomous RCE that with applicability in clinical practice. To address this challenge, this study proposed and developed a novel three-dimensional (3D) location positioning method that is compatible with an RCE manipulated by an external magnetic actuation system. The developed localization methodology employed one embedded single-axis receiving coil (Rx) in the RCE and three external transmitting coils (Txs) placed under the clinical bed. The magnetic flux density obtained from the electromotive force at the Rx was applied to the solution of 3D nonlinear Biot-Savart equations and enabled the determination of the position of the Rx in relation to the corresponding magnetoquasistatic field source in the Tx. For implementation, this study developed: (1) an accurate mathematical model and volumetric analysis method for the magnetoquasistatic field by applying equipotential contour and surface mapping, (2) a method to determine the optimal Tx arrangement, and (3) a prototyped device and in-vitro validation of the feasibility of the 3D localization. In the helical trajectory tracking experiment, the device demonstrated an error of 2.03 ± 1.14 mm, and the feasibility in the clinical environment was verified through gastrointestinal phantom experiments. The proposed method will be further evaluated clinically for the retargeting and accurate localization of internal pathologies as well as the closed-loop control of an actively locomotive RCE.