Image-based Positioning Research Articles

A DL-Based High-Precision Positioning Method in Challenging Urban Scenarios for B5G CCUAVs

Unmanned aerial vehicles (UAVs) facilitate services in civilian and industrial fields but suffer from a limited direct link operating range and unreliable satellite positioning in urban canyons. Fortunately, cellular-connected UAVs (CCUAVs) overcome these shortcomings, benefitting from the beyond 5th generation (B5G) network’s <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">city-level coverage</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">high-precision positioning capabilities</i> , and are considered a paradigm of 5G-advanced and beyond. However, in a challenging airspace (e.g., urban canyon), the CCUAV localization accuracy deteriorates due to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">low signal-to-interference-plus-noise (SINR) air-ground channels</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">strong multipath effects</i> . To solve these problems, we first construct channel amplitude-phase response (CAPR) images to characterize the cellular channel in a challenging airspace for CCUAV positioning. In particular, the effect of down-tilted antennas and high-dimensional channel features are embedded into CAPR images, to meet the relevant cellular communication criteria. Subsequently, a deep learning (DL) model, the scale-shared quarter network (SSQ-Net), is devised for CAPR image-based positioning, along with a robustness enhancement method. With this method, the multipath effects and interference in challenging environments are exploited to improve positioning accuracy and robustness, instead of being treated as detriments. Finally, the experimental results in a typical urban canyon show that our method outperforms state-of-the-art methods in terms of accuracy and robustness.

Image-based positioning system using LED Beacon based on IoT central management

The benefits of technologies related to the Internet of Things (IoT), virtual and augmented reality (VR/AR), digital twins, and so on, can be fully realized when associated devices are positioned intuitively. However, AR systems hosted within smartphones pose challenges where auxiliary hardware and computational configurations associated with precise positioning are concerned. To this effect, we propose a deep learning-based indoor measurement system that can determine positions using images collected via beacons designed as IoT terminals. The proposed system is broadly divided into a detection unit, an extraction unit, a positioning unit, and a management server. The beacons were detected using deep learning algorithms, from which the postures were extracted using a homography matrix, and position of the imaging device was determined in reference to the beacon’s position. With the unique design of our system, in that it simultaneously performs posture and positioning estimations, high immersive AR can be achieved. Moreover, scalability of the positioning space is also guaranteed as multiple beacons can be monitored at once. For the experiment, we simulated a virtual indoor space comprising pyramid beacons and the results were promising.

The Image-Based Positioning Technique Using Inter-Pixel Relation Network

Accurate location information is very important for human beings and agents. However, GPS has very limited positioning accuracy or even can not work in challenging environments such as indoor and urban canyons, and other solutions suffer from different shortcomings. It is very meaningful to use the scene image captured by the high-definition camera on the smart phone to locate indoor through the neural network, but the existing image-based positioning methods do not take into account the interrelationship of diffenrent instances of the same feature space. In this paper we present a novel network architecture, which embeds Scene Enhancement module and Relational Network (RN) into the end-to-end positioning system. The system was tested in three typical scenarios, and the test results show that its performance outerperforms existing image-based schemes in most cases.

POSITION ACCURACY ANALYSIS OF A ROBUST VISION-BASED NAVIGATION

Abstract. Using images to determine camera position and attitude is a consolidated method, very widespread for application like UAV navigation. In harsh environment, where GNSS could be degraded or denied, image-based positioning could represent a possible candidate for an integrated or alternative system. In this paper, such method is investigated using a system based on single camera and 3D maps. A robust estimation method is proposed in order to limit the effect of blunders or noisy measurements on position solution. The proposed approach is tested using images collected in an urban canyon, where GNSS positioning is very unaccurate. A previous photogrammetry survey has been performed to build the 3D model of tested area. The position accuracy analysis is performed and the effect of the robust method proposed is validated.

Radar Image-Based Positioning for USV Under GPS Denial Environment

Unmanned surface vehicle (USV) is an important application of unmanned systems, and these USVs provide safe and secure operation in hostile environments. But these USVs are highly reliant on their positioning system, such as global position system (GPS), and loss of positioning information from GPS can cause catastrophe. To overcome this positioning challenge for a USV under a GPS denial environment, we propose a real-time positioning algorithm based on radar and satellite images to determine the USV position. The algorithm takes coastline as a registration feature to implement an image registration between a horizontal viewing angle image from a radar and a vertical viewing angle image from a satellite. The contributions of this paper consist of two parts. First, a coastline feature extraction method based on edge gray features for both radar and satellite images is provided. Second, a high-efficiency image registration method, which takes the dimensionality reduction distance as an indicator, was proposed for the USV embedded system. The results from six typical application scenarios show that the maximum positioning error of the proposed algorithm is 28.02 m under the worst case. A continuous positioning experiment shows that the average error of the algorithm is 9.77 m, which indicates that the algorithm can meet the positioning requirements of a USV under GPS denial environment.

Towards efficient mobile image-guided navigation through removal of outliers

A novel approach for positioning using smartphones and image processing techniques is developed. Using structure from motion, 3D reconstructions of given tracks are created and stored as sparse point clouds. Query images are matched later to these 3D models. High computational costs of image matching and limited storage require compressing point clouds without loss of positioning performance. In this work, localization is improved and memory and storage requirements are minimized. We assumed that the computational speed and, at the same time, storage requirements benefit from reducing the number of points with appropriate outlier detection. In particular, our hypothesis was that positioning accuracy is maintained while reducing outliers in a reconstructed model. To evaluate the hypothesis, three methods were compared: (i) density-based (Sotoodeh, International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences XXXVI-5, 2006), (ii) connectivity-based (Wang et al. Comput Graph Forum 32(5):207–10, 2013), and (iii) our distance-based approach. In tenfold cross-validation, applied to a pre-reconstructed reference 3D model, localization accuracy was measured. In each new model, the positions of test images were identified and compared to the according positions in the reference model. We observed that outlier removal has a positive impact on matching run-time and storage requirements, while there are no significant differences in the localization error within the methods. That confirmed our initial hypothesis and allows mobile application of image-based positioning.

Analysis of Factors Affecting Performance of Integrated INS/SPR Positioning during GPS Signal Blockage

Since the accuracy of Global Positioning System (GPS)-based vehicle positioning system is significantly degraded or does not work appropriately in the urban canyon, the integration techniques of GPS with Inertial Navigation System (INS) have intensively been developed to improve the continuity and reliability of positioning. However, its accuracy is degraded as INS errors are not properly corrected due to the GPS signal blockage. Recently, the image-based positioning techniques have been started to apply for the vehicle positioning for the advanced in processing techniques as well as the increased the number of cars installing the camera. In this study, Single Photo Resection (SPR), which calculates the camera exterior orientation parameters using the Ground Control Points (GCPs,) has been integrated with the INS/GPS for continuous and stable positioning. The INS/GPS/SPR integration was implemented in both of a loosely and a tightly coupled modes, based on the Extended Kalman Filter (EKF). In order to analyze the performance of INS/SPR integration during the GPS outage, the simulation tests were conducted with a consideration of factors affecting SPR performance. The results demonstrate that the accuracy of INS/SPR integration is depended on magnitudes of the GCP errors and SPR processing intervals. Additionally, the simulation results suggest some required conditions to achieve accurate and continuous positioning, used the INS/SPR integration.

Automated long-term monitoring of parallel microfluidic operations applying a machine vision-assisted positioning method.

As microfluidics has been applied extensively in many cell and biochemical applications, monitoring the related processes is an important requirement. In this work, we design and fabricate a high-throughput microfluidic device which contains 32 microchambers to perform automated parallel microfluidic operations and monitoring on an automated stage of a microscope. Images are captured at multiple spots on the device during the operations for monitoring samples in microchambers in parallel; yet the device positions may vary at different time points throughout operations as the device moves back and forth on a motorized microscopic stage. Here, we report an image-based positioning strategy to realign the chamber position before every recording of microscopic image. We fabricate alignment marks at defined locations next to the chambers in the microfluidic device as reference positions. We also develop image processing algorithms to recognize the chamber positions in real-time, followed by realigning the chambers to their preset positions in the captured images. We perform experiments to validate and characterize the device functionality and the automated realignment operation. Together, this microfluidic realignment strategy can be a platform technology to achieve precise positioning of multiple chambers for general microfluidic applications requiring long-term parallel monitoring of cell and biochemical activities.

Seamless Positioning and Navigation by Using Geo-Referenced Images and Multi-Sensor Data

Ubiquitous positioning is considered to be a highly demanding application for today's Location-Based Services (LBS). While satellite-based navigation has achieved great advances in the past few decades, positioning and navigation in indoor scenarios and deep urban areas has remained a challenging topic of substantial research interest. Various strategies have been adopted to fill this gap, within which vision-based methods have attracted growing attention due to the widespread use of cameras on mobile devices. However, current vision-based methods using image processing have yet to revealed their full potential for navigation applications and are insufficient in many aspects. Therefore in this paper, we present a hybrid image-based positioning system that is intended to provide seamless position solution in six degrees of freedom (6DoF) for location-based services in both outdoor and indoor environments. It mainly uses visual sensor input to match with geo-referenced images for image-based positioning resolution, and also takes advantage of multiple onboard sensors, including the built-in GPS receiver and digital compass to assist visual methods. Experiments demonstrate that such a system can greatly improve the position accuracy for areas where the GPS signal is negatively affected (such as in urban canyons), and it also provides excellent position accuracy for indoor environments.

A validation study of image-based positioning in space mission

A validation study of image-based positioning in space mission

EVALUATING PHOTOGRAMMETRIC APPROACH OF IMAGE-BASED POSITIONING

Abstract. In recent years, researches in the domain of location-based services have increasingly focused on developing and utilizing alternative positioning techniques for in GPS-denied environment. Image based positioning technique holds good promise for such applications. In this paper, a previously proposed image-based positioning system using photogrammetric methods has been put into rigorous evaluation. The precision and accuracy of such photogrammetric approach of image-based positioning is depending on the precision and accuracy of final space resection process, which is a function of PGCP distribution and measurement accuracy, and any factor that has certain impact on either of these two major components will to certain degree influence final positioning accuracy. Therefore in this article, the way that different factors influencing the positioning accuracy are analysed through both mathematical model and experiments, which includes simulations and tests based on real data. Through evaluation of such system, we aims at better understanding image-based positioning system alike so as to find its strength, weaknesses and ways to improve the overall performance for it to realize its full potential.

Research on an Image-Based Visual Positioning System in the PDP Lighting Inspection Machine

Visual positioning system is of great importance in the structure of PDP lighting inspection machine. This paper describes the overall structure of the system, the process of the interaction with the PLC system, the hard structure and continuous positioning principle. A point correspondence method is also studied.

Navigating the Fluoroscope's C-Arm Back into Position: An Accurate and Practicable Solution to Cut Radiation and Optimize Intraoperative Workflow

During complex image-guided orthopedic trauma procedures, repetitive fluoroscopic scout imaging is performed. A number of preparatory positioning images often must be taken to reproduce a comparable projection. These scout images have no intrinsic clinical relevance but nevertheless expose the patient and the surgical team to considerable radiation, which could be avoided. This study presents and validates a method to decrease intraoperative radiation. Precision, time requirements, and number of scout images for repositioning the fluoroscope, with and without navigation aid, were recorded on 20 test-rig and 3 phantom setups. A commercially available image-guided surgical navigation system (Vector Vision, BrainLAB), originally designed for instrument navigation, was employed to register and retrieve the C-arm positions. A newly developed software computed the necessary moves to reposition the C-arm on an intuitive visual display. Retrieving a given C-arm position with the conventional non-navigated technique required an average of 7 scout images (range, 3 to 12 images). In contrast, navigation-assisted repositioning did not necessitate a single scout image. Deviations from the original projection were minimal for both navigated (0.9 degrees, 95% CI 0.8 to 1.1 degrees) and non-navigated repositioning (0.8 degrees, 95% CI 0.7 to 0.9 degrees). Average positioning times were comparable when navigating the C-arm (46 seconds, 95% CI 41 to 51 seconds) and in scout image-based positioning (49 seconds, 95% CI 44 to 53 seconds). Navigated C-arm positioning avoids multiple scout images and yields sufficient precision for clinical deployment. Radiation exposure can be reduced considerably by a combination of instrument navigation and navigated C-arm positioning.

Методика расчета точности определения координат объектов по космическим снимкам

Методика расчета точности определения координат объектов по космическим снимкам

Application of Neural Networks to Image-Based Control of Robot Arms

This paper describes experiments with the use of neural networks for image-based positioning of industrial robots. Firstly, an improved neural “visual-servoing” method based on geometric image characteristics is developed and analyzed. Subsequently, a more flexible and robust scheme is shown, based on global descriptors of the image.