scholarly journals 4D spatio-temporal convolutional networks for object position estimation in OCT volumes

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Marcel Bengs ◽  
Nils Gessert ◽  
Alexander Schlaefer
Keyword(s):  
Spatial Information ◽  
Tracking System ◽  
Computer Assisted Surgery ◽  
Absolute Error ◽  
Position Estimation ◽  
Optical Tracking ◽  
Computer Assisted ◽  
Optical Tracking System ◽  
Spatio Temporal ◽  
The Impact

AbstractTracking and localizing objects is a central problem in computer-assisted surgery. Optical coherence tomography (OCT) can be employed as an optical tracking system, due to its high spatial and temporal resolution. Recently, 3D convolutional neural networks (CNNs) have shown promising performance for pose estimation of a marker object using single volumetric OCT images. While this approach relied on spatial information only, OCT allows for a temporal stream of OCT image volumes capturing the motion of an object at high volumes rates. In this work, we systematically extend 3D CNNs to 4D spatio-temporal CNNs to evaluate the impact of additional temporal information for marker object tracking. Across various architectures, our results demonstrate that using a stream of OCT volumes and employing 4D spatio-temporal convolutions leads to a 30% lower mean absolute error compared to single volume processing with 3D CNNs.

A novel 4 camera multi-stereo tracking system for application in surgical navigation systems

2020 ◽  
Vol 87 (7-8) ◽  
pp. 451-458
Author(s):  
Oliver Gieseler ◽  
Hubert Roth ◽  
Jürgen Wahrburg
Keyword(s):  
Operating Room ◽  
Surgical Navigation ◽  
Tracking System ◽  
Computer Assisted Surgery ◽  
Optical Tracking ◽  
Computer Assisted ◽  
Navigation Systems ◽  
Camera Model ◽  
Camera System ◽  
Industrial Cameras

AbstractIn this paper, we present a novel 4 camera stereo system for application as optical tracking component in navigation systems in computer-assisted surgery. This shall replace a common stereo camera system in several applications. The objective is to provide a tracking component consisting of four single industrial cameras. The system can be built up flexibly in the operating room e. g. at the operating room lamp. The concept is characterized by independent, arbitrary camera mounting poses and demands easy on-site calibration procedures of the camera setup. Following a short introduction describing the environment, motivation and advantages of the new camera system, a simulation of the camera setup and arrangement is depicted in Section 2. From this, we gather important information and parameters for the hardware setup, which is described in Section 3. Section 4 includes the calibration of the cameras. Here, we illustrate the background of camera model and applied calibration procedures, a comparison of calibration results obtained with different calibration programs and a new concept for fast and easy extrinsic calibration.

scholarly journals Photovoltaic Power Forecasting: Assessment of the Impact of Multiple Sources of Spatio-Temporal Data on Forecast Accuracy

Energies ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1432
Author(s):  
Xwégnon Ghislain Agoua ◽  
Robin Girard ◽  
Georges Kariniotakis
Keyword(s):  
Satellite Images ◽  
Forecast Accuracy ◽  
Absolute Error ◽  
Data Sources ◽  
Test Case ◽  
Temporal Data ◽  
Multiple Sources ◽  
Forecasting Error ◽  
Spatio Temporal ◽  
The Impact

The efficient integration of photovoltaic (PV) production in energy systems is conditioned by the capacity to anticipate its variability, that is, the capacity to provide accurate forecasts. From the classical forecasting methods in the state of the art dealing with a single power plant, the focus has moved in recent years to spatio-temporal approaches, where geographically dispersed data are used as input to improve forecasts of a site for the horizons up to 6 h ahead. These spatio-temporal approaches provide different performances according to the data sources available but the question of the impact of each source on the actual forecasting performance is still not evaluated. In this paper, we propose a flexible spatio-temporal model to generate PV production forecasts for horizons up to 6 h ahead and we use this model to evaluate the effect of different spatial and temporal data sources on the accuracy of the forecasts. The sources considered are measurements from neighboring PV plants, local meteorological stations, Numerical Weather Predictions, and satellite images. The evaluation of the performance is carried out using a real-world test case featuring a high number of 136 PV plants. The forecasting error has been evaluated for each data source using the Mean Absolute Error and Root Mean Square Error. The results show that neighboring PV plants help to achieve around 10% reduction in forecasting error for the first three hours, followed by satellite images which help to gain an additional 3% all over the horizons up to 6 h ahead. The NWP data show no improvement for horizons up to 6 h but is essential for greater horizons.

scholarly journals In Vitro and In Vivo Assessment of a New Workflow for the Acquisition of Mandibular Kinematics Based on Portable Tracking System with Passive Optical Reflective Markers

2021 ◽  
Vol 11 (9) ◽  
pp. 3947
Author(s):  
Marco Farronato ◽  
Gianluca M. Tartaglia ◽  
Cinzia Maspero ◽  
Luigi M. Gallo ◽  
Vera Colombo
Keyword(s):  
Measurement Error ◽  
Tracking System ◽  
Intraclass Correlation ◽  
Optical Tracking ◽  
Optical Tracking System ◽  
Rater Reliability ◽  
Tracking Device ◽  
Mandibular Kinematics

Clinical use of portable optical tracking system in dentistry could improve the analysis of mandibular movements for diagnostic and therapeutic purposes. A new workflow for the acquisition of mandibular kinematics was developed. Reproducibility of measurements was tested in vitro and intra- and inter-rater repeatability were assessed in vivo in healthy volunteers. Prescribed repeated movements (n = 10) in three perpendicular directions of the tracking-device coordinate system were performed. Measurement error and coefficient of variation (CV) among repetitions were determined. Mandibular kinematics of maximum opening, left and right laterality, protrusion and retrusion of five healthy subjects were recorded in separate sessions by three different operators. Obtained records were blindly examined by three observers. Intraclass correlation coefficient (ICC) was calculated to estimate inter-rater and intra-rater reliability. Maximum in vitro measurement error was 0.54 mm and CV = 0.02. Overall, excellent intra-rater reliability (ICC > 0.90) for each variable, general excellent intra-rater reliability (ICC = 1.00) for all variables, and good reliability (ICC > 0.75) for inter-rater tests were obtained. A lower score was obtained for retrusion with “moderate reliability” (ICC = 0.557) in the inter-rater tests. Excellent repeatability and reliability in optical tracking of primary movements were observed using the tested portable tracking device and the developed workflow.

scholarly journals High Precision Optical Tracking System Based on near Infrared Trinocular Stereo Vision

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2528
Author(s):  
Songlin Bi ◽  
Yonggang Gu ◽  
Jiaqi Zou ◽  
Lianpo Wang ◽  
Chao Zhai ◽  
...  
Keyword(s):  
High Precision ◽  
Stereo Vision ◽  
Near Infrared ◽  
Nearest Neighbor ◽  
Tracking System ◽  
Optical Tracking ◽  
Tracking Accuracy ◽  
Optical Tracking System ◽  
Dynamic Tracking ◽  
Trinocular Stereo

A high precision optical tracking system (OTS) based on near infrared (NIR) trinocular stereo vision (TSV) is presented in this paper. Compared with the traditional OTS on the basis of binocular stereo vision (BSV), hardware and software are improved. In the hardware aspect, a NIR TSV platform is built, and a new active tool is designed. Imaging markers of the tool are uniform and complete with large measurement angle (>60°). In the software aspect, the deployment of extra camera brings high computational complexity. To reduce the computational burden, a fast nearest neighbor feature point extraction algorithm (FNNF) is proposed. The proposed method increases the speed of feature points extraction by hundreds of times over the traditional pixel-by-pixel searching method. The modified NIR multi-camera calibration method and 3D reconstruction algorithm further improve the tracking accuracy. Experimental results show that the calibration accuracy of the NIR camera can reach 0.02%, positioning accuracy of markers can reach 0.0240 mm, and dynamic tracking accuracy can reach 0.0938 mm. OTS can be adopted in high-precision dynamic tracking.

scholarly journals Skill Transference of a Probe-Tube Placement Training Simulator

2020 ◽  
Vol 31 (01) ◽  
pp. 040-049 ◽  
Author(s):  
Robert W. Koch ◽  
Hasan Saleh ◽  
Paula Folkeard ◽  
Sheila Moodie ◽  
Conner Janeteas ◽  
...  
Keyword(s):  
Mixed Model ◽  
Tracking System ◽  
Optical Tracking ◽  
Tube Placement ◽  
Control Group ◽  
Educational Settings ◽  
Training Simulator ◽  
Nonlinear Mixed Model ◽  
Optical Tracking System ◽  
Clinical Scenarios

AbstractProbe-tube placement is a necessary step in hearing aid verification which needs ample hands-on experience and confidence before performing in clinic. To improve the methods of training in probe-tube placement, a manikin-based training simulator was developed consisting of a 3D-printed head, a flexible silicone ear, and a mounted optical tracking system. The system is designed to provide feedback to the user on the depth and orientation of the probe tube, and the time required to finish the task. Although a previous validation study was performed to determine its realism and teachability with experts, further validation is required before implementation into educational settings.This study aimed to examine the skill transference of a newly updated probe-tube placement training simulator to determine if skills learned on this simulator successfully translate to clinical scenarios.All participants underwent a pretest in which they were evaluated while performing a probe-tube placement and real-ear-to-coupler difference (RECD) measurement on a volunteer. Participants were randomized into one of two groups: the simulator group or the control group. During a two-week training period, all participants practiced their probe-tube placement according to their randomly assigned group. After two weeks, each participant completed a probe-tube placement on the same volunteer as a posttest scenario.Twenty-five novice graduate-level student clinicians.Participants completed a self-efficacy questionnaire and an expert observer completed a questionnaire evaluating each participant’s performance during the pre- and posttest sessions. RECD measurements were taken after placing the probe tube and foam tip in the volunteer’s ear. Questionnaire results were analyzed through nonparametric t-tests and analysis of variance, whereas RECD results were analyzed using a nonlinear mixed model method.Results suggested students in the simulator group were less likely to contact the tympanic membrane when placing a probe tube, appeared more confident, and had better use of the occluding foam tip, resulting in more improved RECD measurements.The improved outcomes for trainees in the simulator group suggest that supplementing traditional training with the simulator provides useful benefits for the trainees, thereby encouraging its usage and implementation in educational settings.

Sign in / Sign up

Export Citation Format

Share Document