MarkerDetector: A method for robust fiducial marker detection in electron micrographs using wavelet-based template.

Fiducial marker detection in electron micrographs becomes an important and challenging task with the development of large-field electron microscopy. The fiducial marker detection plays an important role in several steps during the process of electron micrographs, such as the alignment and parameter calibrations. However, limited by the conditions of low signal-to-noise ratio (SNR) in the electron micrographs, the performance of fiducial marker detection is severely affected. In this work, we propose the MarkerDetector, a novel algorithm for detecting fiducial markers in electron micrographs. The proposed MarkerDetector is built upon the following contributions: Firstly, a wavelet-based template generation algorithm is devised in MarkerDetector. By adopting a shape-based criterion, a high-quality template can be obtained. Secondly, a robust marker determination strategy is devised by utilizing statistic-based filtering, which can guarantee the correctness of the detected fiducial markers. The average running time of our algorithm is 1.67 seconds with promising accuracy, indicating its practical feasibility for applications in electron micrographs.

Safety profile and technical success of narrow window CT-guided percutaneous biopsy with blunt needle approach in the abdomen and pelvis.

OBJECTIVE: To assess success and safety of CT-guided procedures with narrow window access for biopsy. METHODS: Three hundred ninety-six consecutive patients undergoing abdominal or pelvic CT-guided biopsy or fiducial placement between 01/2015 and 12/2018 were included (183 women, mean age 63 ±â€¯14 years). Procedures were classified into "wide window" (width of the needle path between structures > 15 mm) and "narrow window" (≤ 15 mm) based on intraprocedural images. Clinical information, complications, technical and clinical success, and outcomes were collected. The blunt needle approach is preferred by our interventional radiology team for narrow window access. RESULTS: There were 323 (81.5%) wide window procedures and 73 (18.5%) narrow window procedures with blunt needle approach. The median depth for the narrow window group was greater (97 mm, interquartile range (IQR) 82-113 mm) compared to the wide window group (84 mm, IQR 60-106 mm); p = 0.0017. Technical success was reached in 100% (73/73) of the narrow window and 99.7% (322/323) of the wide window procedures. There was no difference in clinical success rate between the two groups (narrow: 86.4%, 57/66; wide: 89.5%, 265/296; p = 0.46). There was no difference in immediate complication rate (narrow: 1.3%, 1/73; wide: 1.2%, 4/323; p = 0.73) or delayed complication rate (narrow: 1.3%, 1/73; wide: 0.6%, 1/323; p = 0.50). CONCLUSION: Narrow window (< 15 mm) access biopsy and fiducial placement with blunt needle approach under CT guidance is safe and successful. CLINICAL RELEVANCE STATEMENT: CT-guided biopsy and fiducial placement can be performed through narrow window access of less than 15 mm utilizing the blunt-tip technique. KEY POINTS: • A narrow window for CT-guided abdominal and pelvic biopsies and fiducial placements was considered when width of the needle path between vital structures was ≤ 15 mm. • Seventy-three biopsies and fiducial placements performed through a narrow window with blunt needle approach had a similar rate of technical and clinical success and complications compared to 323 procedures performed through a wide window approach, with traditional approach (> 15 mm). • This study confirmed the safety of the CT-guided percutaneous procedures through < 15 mm window with blunt-tip technique.

Novel image-guided marker aimed at organ-preserving therapies for prostate cancer.

OBJECTIVE: We developed fiducial imaging-guidance markers for the prostate with less imaging artifacts than currently commercially available markers. The aim of this study was to evaluate the imaging artifacts and potential usefulness and safety of these novel fiducial imaging markers in preclinical experiments. METHODS: We selected specific metal materials and a shape that can minimize artifacts in line with a license we obtained for a metal with a gold-platinum (Au-Pt) alloy composition that maximized artifact-free MRI images. Both phantom and canine prostate tests were conducted in order to evaluate the imaging artifacts for three imaging modalities, MRI, CT and ultrasound, and the risk of migration of the markers from the site of insertion to elsewhere, as well as crushing. RESULTS: The newly developed Au-Pt material had less imaging artifacts in the MRI, CT and ultrasound imaging modalities in comparison with current commercially available fiducial markers made from gold materials only. The Au-Pt markers had sufficient strength and durability and were considered to be potentially clinically useful and safe markers. CONCLUSION: The developed Au-Pt markers could be potential tools for accurate lesion-targeted, organ-preserving therapies such as lesion-targeted focal therapy and active surveillance in addition to conventional radiation therapies.

Intra- and inter-fractional variations of tumors with fiducial markers measured using respiratory-correlated computed tomography images for respiratory gated lung stereotactic body radiation therapy.

PURPOSE: This study evaluated the intra- and inter-fractional variation of tumors with fiducial markers (FMs), relative to the tumor-FM distance, to establish how close an FM should be inserted for respiratory-gated stereotactic body radiation therapy (RG-SBRT). METHODS: Forty-five lung tumors treated with RG-SBRT were enrolled. End-expiratory computed tomography (CT) (CTplan) and four-dimensional-CT (4D-CT) scans were obtained for planning. End-expiratory CT (CTfr) scanning was performed before each fraction. The FMs were divided into two groups based on the median tumor-FM distance in the CTplan (Dp). For the intra-fractional variation, the correlations between the corresponding tumor and FM intra-fractional motions, defined as the centroid coordinates of those in each 0-90% phase, with the 50% phase of 4D-CT as the origin, were calculated in the left-right, anterior-posterior, and superior-inferior directions. Furthermore, the maximum difference in the tumor-FM distance in each phase of 4D-CT scan, based on those in the 50% phase of 4D-CT scan (Dmax), was obtained. Inter-fractional variation was defined as the maximum distance between the tumors in CTplan and CTfr, when the CT scans were fused based on each FM or vertebra. RESULTS: The median Dp was 26.1 mm. While FM intra-fractional motions were significantly and strongly correlated with the tumor intra-fractional motions in only anterior-posterior and superior-inferior directions for the Dp > 26 mm group, they were significantly and strongly correlated in all directions for the Dp ≤ 26 mm group. In all directions, Dmax values of the Dp ≤ 26 mm group were lower than those of the Dp > 26 mm group. The inter-fractional variations based on the Dp ≤ 26 mm were smaller than those on the Dp > 26 mm and on the vertebra in all directions. CONCLUSIONS: Regarding intra- and inter-fractional variation, FMs for Dp ≤ 26 mm can increase the accuracy for RG-SBRT.

Does a novel 3D printed individualized guiding template based on cutaneous fiducial markers contribute to accurate percutaneous insertion of pelvic screws? A preliminary phantom and cadaver study.

BACKGROUND: Most 3D-printed guiding templates require dissection of soft tissues to match the corresponding surfaces of the guiding templates. This study sought to explore the accuracy and acceptability of the novel 3D printed individualized guiding templates based on cutaneous fiducial markers in minimally invasive screw placement for pelvic fractures. METHODS: The printed template was tested on five high-fidelity biomimetic phantom models of the bony pelvis and its surrounding soft tissues as well as on two fresh frozen cadavers. Four cutaneous fiducial markers were transfixed on each phantom model prior to performing CT scans to reconstruct their 3D models. Personalized templates for guiding screw insertion were designed based on the positions of the fiducial markers and virtually planned target screw channels after scanning, followed by 3D printing of the guide. Phase 1 consisted of five expert surgeons inserting one anterograde supra-pubic screw and one sacroiliac screw percutaneously into each phantom model using the 3D-printed guide. The deviation of screw positions between the pre-operative planned and post-operative actual ones was measured after registering their 3D modelling. A Likert scale questionnaire was completed by the expert surgeons to assess their satisfaction and acceptability with the guiding template. Phase 2 consisted of repeating the same procedures on the fresh frozen cadavers in order to demonstrate face, content and concurrent validity. RESULTS: In Phase 1, all ten screws were successfully implanted with the assistance of the guiding template. Postoperative CT scans confirmed that all screws were safely positioned within the bony pelvic channels without breaching the far cortex. The mean longitudinal deviation at the bony entry point and screw tip between the pre-operative planned and post-operative actual screw paths were 2.83 ± 0.60 mm and 3.12 ± 0.81 mm respectively, with a mean angular deviation of 1.25 ± 0.41°. Results from the Likert questionnaire indicated a high level of satisfaction for using the guiding template among surgeons. In Phase 2, results were similar to those in Phase 1. CONCLUSIONS: The 3D-printed guiding template based on cutaneous fiducial markers shows potential for assisting in the accurate insertion of percutaneous screws in the pelvis.

Tape-Shaped, Multiscale, and Continuous-Readable Fiducial Marker for Indoor Navigation and Localization Systems.

The present study proposes a fiducial marker for location systems that uses computer vision. The marker employs a set of tape-shaped markers that facilitate their positioning in the environment, allowing continuous reading to cover the entire perimeter of the environment and making it possible to minimize interruptions in the location service. Because the marker is present throughout the perimeter of the environment, it presents hierarchical coding patterns that allow it to be robust against multiple detection scales. We implemented an application to help the user generate the markers with a floor plan image. We conducted two types of tests, one in a 3D simulation environment and one in a real-life environment with a smartphone. The tests made it possible to measure the performance of the tape-shaped marker with readings at multiple distances compared to ArUco, QRCode, and STag with detections at distances of 10 to 0.5 m. The localization tests in the 3D environment analyzed the time of marker detection during the journey from one room to another in positioning conditions (A) with the markers positioned at the baseboard of the wall, (B) with the markers positioned at camera height, and (C) with the marker positioned on the floor. The localization tests in real conditions allowed us to measure the time of detections in favorable conditions of detections, demonstrating that the tape-shaped-marker-detection algorithm is not yet robust against blurring but is robust against lighting variations, difficult angle displays, and partial occlusions. In both test environments, the marker allowed for detection at multiple scales, confirming its functionality.

Large-Scale Indoor Camera Positioning Using Fiducial Markers.

Estimating the pose of a large set of fixed indoor cameras is a requirement for certain applications in augmented reality, autonomous navigation, video surveillance, and logistics. However, accurately mapping the positions of these cameras remains an unsolved problem. While providing partial solutions, existing alternatives are limited by their dependence on distinct environmental features, the requirement for large overlapping camera views, and specific conditions. This paper introduces a novel approach to estimating the pose of a large set of cameras using a small subset of fiducial markers printed on regular pieces of paper. By placing the markers in areas visible to multiple cameras, we can obtain an initial estimation of the pair-wise spatial relationship between them. The markers can be moved throughout the environment to obtain the relationship between all cameras, thus creating a graph connecting all cameras. In the final step, our method performs a full optimization, minimizing the reprojection errors of the observed markers and enforcing physical constraints, such as camera and marker coplanarity and control points. We validated our approach using novel artificial and real datasets with varying levels of complexity. Our experiments demonstrated superior performance over existing state-of-the-art techniques and increased effectiveness in real-world applications. Accompanying this paper, we provide the research community with access to our code, tutorials, and an application framework to support the deployment of our methodology.

The GoldX Fiducial Eraser.

Gold nanoparticles with sizes in the range of 5-15 nm are a standard method of providing fiducial markers to assist with alignment during reconstruction in cryogenic electron tomography. However, due to their high electron density and resulting contrast when compared to standard cellular or biological samples, they introduce artifacts such as streaking in the reconstructed tomograms. Here, we demonstrate a tool that automatically detects these nanoparticles and suppresses them by replacing them with a local background as a post-processing step, providing a cleaner tomogram without removing any sample relevant information or introducing new artifacts or edge effects from uniform density replacements.

Verification of the accuracy of dynamic navigation for conventional and mouthpiece methods: in vivo study.

BACKGROUND: Dynamic navigation for implant placement is becoming popular under the concept of top-down treatment. The purpose of this study is to verify the accuracy of a dynamic navigation system for implant placement. METHODS: Implant placement was performed on 38 patients using 50 implant fixtures. Patients in group C were treated using a conventional method, in which thermoplastic clips were fixed to the teeth, and patients in group M were treated using thermoplastic clips fixed to a mouthpiece attached to the teeth. The groups were compared to verify whether an accuracy difference existed. A treatment planning support program for dental implants was used to superimpose the postoperative computed tomography data on the preoperative implant design data to measure the entry point, apex point, and angular deviation. RESULTS: The accuracy of group C was 1.36 ± 0.51 mm for entry point, 1.30 ± 0.59 mm for apex point, and 3.20 ± 0.74° for angular deviation. The accuracy of group M was 1.06 ± 0.31 mm for the entry point, 1.02 ± 0.30 mm for the apex point, and 2.91 ± 0.97° for angular deviation. Significant differences were observed in the entry and apex points between the two groups. CONCLUSIONS: The results indicate that group M exhibited better accuracy than group C, indicating that the stability of the thermoplastic clip is important for ensuring the accuracy of the dynamic navigation system. No previous studies have verified the accuracy of this system using the mouthpiece method, and additional data is required to confirm its accuracy for dental implant placement. The mouthpiece method improves the accuracy of implant placement and provides a safer implant treatment than the conventional method. TRIAL REGISTRATION: University hospital Medical Information Network Clinical Trials Registry (UMIN-CTR), Registration Number: UMIN000051949, URL: https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view_his.cgi on August 21, 2023.

The in-vitro accuracy of fiducial marker-based versus markerless registration of an intraoral scan with a cone-beam computed tomography scan in the presence of restoration artifact.

OBJECTIVES: To determine the effect of restoration artifact ('metal artifact') on registration accuracy of an intraoral scan and cone-beam computed tomography (CBCT) scan, comparing fiducial marker-based registration with markerless registration. MATERIALS AND METHODS: A maxillary model was fitted with multiple configurations of zirconia crowns to simulate various states of oral rehabilitation. Intraoral scans and CBCT scans (half and full rotation) were acquired. Registration was performed using markerless (point-based registration with surface-based refinement) and fiducial marker-based registration. Each experimental condition was repeated 10 times (n = 320). The absolute deviation was measured at the canines and first molars, and the average and maximum values were analysed using multiple linear regression. RESULTS: R2 was 0.874 for average error and 0.858 for maximum error. For markerless registration, there were 0.041 mm (p < .001) and 0.045 mm (p < .001) increases in average and maximum error per crown, respectively. For fiducial marker-based registration, the effect of additional crowns was not statistically significant for average (p = .067) or maximum (p = .438) error. For a full arch of crowns, the regression model predicted average and maximum errors of 0.581 and 0.697 mm for the markerless technique, and 0.185 and 0.210 mm for the fiducial marker-based technique. Overall, the fiducial marker-based technique was more accurate for four or more crowns. The half rotation scan increased average error by 0.021 mm (p = .001) and maximum error by 0.029 mm (p < .001). CONCLUSIONS: Under the present study's experimental conditions, the fiducial marker-based technique should be considered if four or more full-coverage highly radiopaque restorations are present.

Intra-prostatic gold fiducial marker insertion for image-guided radiotherapy (IGRT): five-year experience on 795 patients.

INTRODUCTION: Prostate cancer is the second most commonly diagnosed cancer in males. The use of intra-prostatic fiducial markers (FM) for image-guided radiotherapy (IGRT) has become widespread due to their accuracy, relatively safe use, low cost, and reproducibility. FM provides a tool to monitor prostate position and volume changes. Many studies reported low to moderate rates of complications following FM implantation. In the current study, we present our five years' experience regarding the insertion technique, technical success, and rates of complication and migration of intraprostatic insertion of FM gold marker. METHODS: From January 2018 to January 2023, 795 patients with prostate cancer candidate for IGRT (with or without a history of radical prostatectomy) enrolled in this study. We used three fiducial markers (3*0.6 mm) inserted through an 18-gauge Chiba needle under transrectal ultrasonography (TRUS) guidance. The patients were observed for complications up to seven days after the procedure. Besides, the rate of marker migration was recorded. RESULTS: All procedures were completed successfully, and all patients tolerated the procedure well with minimal discomfort. The rate of sepsis after the procedure was 1%, and transient urinary obstruction was 1.6%. Only two patients experienced marker migration shortly after insertion, and no fiducial migration was reported throughout radiotherapy. No other major complication was recorded. DISCUSSION: TRUS-guided intraprostatic FM implantation is technically feasible, safe, and well-tolerated in most patients. The FM migration can seldom occur, with negligible effects. This study can provide convincing evidence that TRUS-guided intra-prostatic FM insertion is an appropriate choice for IGRT.

Automatic landmark identification in cone-beam computed tomography.

OBJECTIVE: To present and validate an open-source fully automated landmark placement (ALICBCT) tool for cone-beam computed tomography scans. MATERIALS AND METHODS: One hundred and forty-three large and medium field of view cone-beam computed tomography (CBCT) were used to train and test a novel approach, called ALICBCT that reformulates landmark detection as a classification problem through a virtual agent placed inside volumetric images. The landmark agents were trained to navigate in a multi-scale volumetric space to reach the estimated landmark position. The agent movements decision relies on a combination of DenseNet feature network and fully connected layers. For each CBCT, 32 ground truth landmark positions were identified by 2 clinician experts. After validation of the 32 landmarks, new models were trained to identify a total of 119 landmarks that are commonly used in clinical studies for the quantification of changes in bone morphology and tooth position. RESULTS: Our method achieved a high accuracy with an average of 1.54 ± 0.87 mm error for the 32 landmark positions with rare failures, taking an average of 4.2 second computation time to identify each landmark in one large 3D-CBCT scan using a conventional GPU. CONCLUSION: The ALICBCT algorithm is a robust automatic identification tool that has been deployed for clinical and research use as an extension in the 3D Slicer platform allowing continuous updates for increased precision.

MRI-based navigated cryosurgery of extra-abdominal desmoid tumors using skin fiducial markers: a case series of 15 cases.

BACKGROUND: Precision surgery is becoming increasingly important in the field of Orthopaedic Oncology. Image-guided percutaneous cryosurgery (CRA) has emerged as a valid treatment modality for extra-abdominal desmoid tumors (EDTs). To date, most CRA procedures use CT-based guidance which fails to properly characterize tumor segments. Computer-guided MRI navigation can address this issue however, the lack of a fixed landmark for registration remains a challenge. Successful CRA correlates directly with precision approaches facilitated by intraoperative imaging guidance. This is the first study that attempts to assess the feasibility and efficacy of a novel approach of using skin fiducial markers to overcome the challenge of a MRI-based navigation CRA for symptomatic or progressive EDTs. METHODS: In this retrospective study conducted between 2018 and 2020, 11 patients at a single center with symptomatic or progressive EDTs were treated with CRA using intraoperative MRI navigation. Fifteen cryosurgery procedures were performed, each adhering to a personalized pre-operative plan. Total tumor size, viable and non-viable portions pre- and post-operation, and SF-36 questionnaire evaluating subjective health were recorded. RESULTS: All CRAs demonstrated 100% adherence to the predetermined plan. Overall, tumor size decreased Median= -56.9% [-25.6, -72.4]) with a reduction in viable tissue, (Median= -80.4% [-53.3, -95.2]). Four patients required additional CRAs. Only one patient's tumor did not reduce in size. One patient suffered from local muscle necrosis. Pre-operation, the average physical and mental scores 41.6 [29.4, 43] and 26.3 [17.6, 40.9] respectively. Post-operation, the average physical and mental scores were 53.4[38, 59.7] and 38 [31.2, 52.7] respectively. CONCLUSION: These findings provide an early indication of the feasibility and efficacy of performing percutaneous cryosurgery using skin fiducial marker registration for MRI-computed navigation to treat EDTs safely. Larger cohorts and multicenter evaluations are needed to determine the efficacy of this technique.

Evaluation of computed tomography metal artifact and CyberKnife fiducial recognition for novel size fiducial markers.

PURPOSE: This study aimed to compare fiducial markers used in CyberKnife treatment in terms of metal artifact intensity observed in CT images and fiducial recognition in the CyberKnife system affected by patient body thickness and type of marker. METHODS: Five markers, ACCULOC 0.9 mm × 3 mm, Ball type Gold Anchor (GA) 0.28 mm × 10 mm, 0.28 mm × 20 mm, and novel size GA 0.4 mm × 10 mm, 0.4 mm × 20 mm were evaluated. To evaluate metal artifacts of CT images, two types of CT images of water-equivalent gels with each marker were acquired using Aquilion LB CT scanner, one applied SEMAR (SEMAR-on) and the other did not apply this technique (SEMAR-off). The evaluation metric of artifact intensity (MSD ) which represents a variation of CT values were compared for each marker. Next, 5, 15, and 20 cm thickness of Tough Water (TW) was placed on the gel under the condition of overlapping the vertebral phantom in the Target Locating System, and the live image of each marker was acquired to compare fiducial recognition. RESULTS: The mean MSD of SEMAR-off was 78.80, 74.50, 97.25, 83.29, and 149.64 HU for ACCULOC, GA0.28 mm × 10 mm, 20 mm, and 0.40 mm × 10 mm, 20 mm, respectively. In the same manner, that of SEMAR-on was 23.52, 20.26, 26.76, 24.89, and 33.96 HU, respectively. Fiducial recognition decreased in the order of 5, 15, and 20 cm thickness, and GA 0.4 × 20 mm showed the best recognition at thickness of 20 cm TW. CONCLUSIONS: We demonstrated the potential to reduce metal artifacts in the CT image to the same level for all the markers we evaluated by applying SEMAR. Additionally, the fiducial recognition of each marker may vary depending on the thickness of the patient's body. Particularly, we showed that GA 0.40 × 20 mm may have more optimal recognition for CyberKnife treatment in cases of high bodily thickness in comparison to the other markers.

Fiducial Objects: Custom Design and Evaluation.

Camera pose estimation is vital in fields like robotics, medical imaging, and augmented reality. Fiducial markers, specifically ArUco and Apriltag, are preferred for their efficiency. However, their accuracy and viewing angle are limited when used as single markers. Custom fiducial objects have been developed to address these limitations by attaching markers to 3D objects, enhancing visibility from multiple viewpoints and improving precision. Existing methods mainly use square markers on non-square object faces, leading to inefficient space use. This paper introduces a novel approach for creating fiducial objects with custom-shaped markers that optimize face coverage, enhancing space utilization and marker detectability at greater distances. Furthermore, we present a technique for the precise configuration estimation of these objects using multiviewpoint images. We provide the research community with our code, tutorials, and an application to facilitate the building and calibration of these objects. Our empirical analysis assesses the effectiveness of various fiducial objects for pose estimation across different conditions, such as noise levels, blur, and scale variations. The results suggest that our customized markers significantly outperform traditional square markers, marking a positive advancement in fiducial marker-based pose estimation methods.

A fiducial approach for testing the non-inferiority of proportion difference in matched-pairs design.

The non-inferiority of one treatment/drug to another is a common and important issue in medical and pharmaceutical fields. This study explored a fiducial approach for testing the non-inferiority of proportion difference in matched-pairs design. Approximate tests constructed using fiducial quantities with a combination of different parameters were proposed. Four simulation studies were employed to compare the performance of fiducial tests by comparing their type I errors and powers. The results showed that fiducial quantities with parameter 0.6 ≤ w 1 ≤ 0.8 performed satisfactorily from small to large samples. Therefore, the fiducial tests could be recommended for practical applications. The recommended fiducial tests might be a competitive alternative to other available tests. Three real data sets were analyzed to illustrate the proposed methods were competitive or even better than other tests.

A New Method of Identifying Characteristic Points in the Impedance Cardiography Signal Based on Empirical Mode Decomposition.

The accurate detection of fiducial points in the impedance cardiography signal (ICG) has a decisive impact on the proper estimation of diagnostic parameters such as stroke volume or cardiac output. It is, therefore, necessary to find an algorithm that is able to assess their positions with great precision. The solution to this problem is, however, quite challenging with regard to the high sensitivity of the ICG technique to the noise and varying morphology of the acquired signals. The aim of this study is to propose a novel method that allows us to overcome these limitations. The developed algorithm is based on Empirical Mode Decomposition (EMD)-an effective technique for processing and analyzing various types of non-stationary signals. We find high correlations between the results obtained from the algorithm and annotated by an expert. This, in turn, implies that the difference in estimation of the diagnostic-relevant parameters is small, which suggests that the method can automatically provide precise clinical information.

Image Segmentation of Fiducial Marks with Complex Backgrounds Based on the mARU-Net.

Circuits on different layers in a printed circuit board (PCB) must be aligned according to high-precision fiducial mark images during exposure processing. However, processing quality depends on the detection accuracy of fiducial marks. Precise segmentation of fiducial marks from images can significantly improve detection accuracy. Due to the complex background of PCB images, there are significant challenges in the segmentation and detection of fiducial mark images. In this paper, the mARU-Net is proposed for the image segmentation of fiducial marks with complex backgrounds to improve detection accuracy. Compared with some typical segmentation methods in customized datasets of fiducial marks, the mARU-Net demonstrates good segmentation accuracy. Experimental research shows that, compared with the original U-Net, the segmentation accuracy of the mARU-Net is improved by 3.015%, while the number of parameters and training times are not increased significantly. Furthermore, the centroid method is used to detect circles in segmentation results, and the deviation is kept within 30 microns, with higher detection efficiency. The detection accuracy of fiducial mark images meets the accuracy requirements of PCB production.

Analytical Models for Pose Estimate Variance of Planar Fiducial Markers for Mobile Robot Localisation.

Planar fiducial markers are commonly used to estimate a pose of a camera relative to the marker. This information can be combined with other sensor data to provide a global or local position estimate of the system in the environment using a state estimator such as the Kalman filter. To achieve accurate estimates, the observation noise covariance matrix must be properly configured to reflect the sensor output's characteristics. However, the observation noise of the pose obtained from planar fiducial markers varies across the measurement range and this fact needs to be taken into account during the sensor fusion to provide a reliable estimate. In this work, we present experimental measurements of the fiducial markers in real and simulation scenarios for 2D pose estimation. Based on these measurements, we propose analytical functions that approximate the variances of pose estimates. We demonstrate the effectiveness of our approach in a 2D robot localisation experiment, where we present a method for estimating covariance model parameters based on user measurements and a technique for fusing pose estimates from multiple markers.

A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition.

Localization is a crucial skill in mobile robotics because the robot needs to make reasonable navigation decisions to complete its mission. Many approaches exist to implement localization, but artificial intelligence can be an interesting alternative to traditional localization techniques based on model calculations. This work proposes a machine learning approach to solve the localization problem in the RobotAtFactory 4.0 competition. The idea is to obtain the relative pose of an onboard camera with respect to fiducial markers (ArUcos) and then estimate the robot pose with machine learning. The approaches were validated in a simulation. Several algorithms were tested, and the best results were obtained by using Random Forest Regressor, with an error on the millimeter scale. The proposed solution presents results as high as the analytical approach for solving the localization problem in the RobotAtFactory 4.0 scenario, with the advantage of not requiring explicit knowledge of the exact positions of the fiducial markers, as in the analytical approach.