scholarly journals Ford Campus vision and lidar data set

2011 ◽  
Vol 30 (13) ◽  
pp. 1543-1552 ◽  
Author(s):  
Gaurav Pandey ◽  
James R McBride ◽  
Ryan M Eustice
Keyword(s):  
Three Dimensional ◽  
Measurement Unit ◽  
Small Scale ◽  
Data Sets ◽  
Camera System ◽  
Data Set ◽  
Mapping Algorithms ◽  
Ground Vehicle ◽  
Localization And Mapping ◽  
Vehicle Path

In this paper we describe a data set collected by an autonomous ground vehicle testbed, based upon a modified Ford F-250 pickup truck. The vehicle is outfitted with a professional (Applanix POS-LV) and consumer (Xsens MTi-G) inertial measurement unit, a Velodyne three-dimensional lidar scanner, two push-broom forward-looking Riegl lidars, and a Point Grey Ladybug3 omnidirectional camera system. Here we present the time-registered data from these sensors mounted on the vehicle, collected while driving the vehicle around the Ford Research Campus and downtown Dearborn, MI, during November–December 2009. The vehicle path trajectory in these data sets contains several large- and small-scale loop closures, which should be useful for testing various state-of-the-art computer vision and simultaneous localization and mapping algorithms.

Bullwinkle: A unique 3-D experiment

Geophysics ◽  
1993 ◽  
Vol 58 (1) ◽  
pp. 167-176 ◽  
Author(s):  
James K. O’Connell ◽  
Madhu Kohli ◽  
Scott Amos
Keyword(s):  
Large Scale ◽  
Three Dimensional ◽  
Development Program ◽  
Bright Spot ◽  
Small Scale ◽  
Data Sets ◽  
Data Set ◽  
Strike Direction ◽  
Salt Complex ◽  
Accuracy And Repeatability

In the spring of 1988, Shell Offshore Inc. acquired two orthogonal three‐dimensional (3-D) surveys at Prospect Bullwinkle, located in the Green Canyon area of the Gulf of Mexico, to aid the development program which began later that year. Two surveys were acquired because of the complexity of the salt structures in the vicinity of the prospect. The independent acquisition and processing of two surveys shot perpendicular to each other provided a unique data set for checking the quality and accuracy of standard 3-D techniques. The high development cost of this deep water (410 m) turbidite field supported the acquisition of two 3-D data sets to provide a valuable redundancy for stratigraphic interpretation. This large scale 3-D experiment has been analyzed in terms of interpretive impact. Detailed comparisons of the seismic images away from the salt complex show good agreement between the two surveys and verify the relative accuracy and repeatability of the acquisition, processing, and interpretation techniques. Structural comparisons between the surveys show that acquisition oriented in a strike direction to the primary salt face yields a superior sediment image, particularly near overhung salt. An examination of the effects of shooting direction on small scale stratigraphic resolution illustrates the importance of fine sampling in the dip direction to the features of interest. Amplitude maps extracted for the main bright spot level show differences in areal continuity that are large enough to affect the geologic model of the prospect.

Comparison of UGV Position Estimation Equipped With GNSS-RTK and GPS Using EKF

2020 ◽  
Author(s):  
Hesham Ismail ◽  
Thani Althani ◽  
Mohammed Minhas Anzil ◽  
Prashanth Subramaniam
Keyword(s):  
Extreme Temperature ◽  
Processing Technique ◽  
Position Estimation ◽  
Image Processing Technique ◽  
Measurement Unit ◽  
Unmanned Ground Vehicle ◽  
Camera System ◽  
Ground Vehicle ◽  
Positioning Device ◽  
Global Navigation Satellite

Abstract Site assessments for bifacial Photovoltaic (PV) installation are quite challenging to conduct manually due to the area size and the extreme temperature conditions at desert sites. We designed and built an autonomous Unmanned Ground Vehicle (UGV) fitted with a Global Navigation Satellite Network-System Real-Time Kinematic (GNSS-RTK) positioning device, an Inertial Measurement Unit (IMU), encoder to improve and aid site assessments in desert condition. Sandy terrains deserts are challenging for UGV’s because they increase the likelihood of wheel slippage due to reduced traction. Sensor details such as IMU, GNSS-RTK, and encoder should be taken into consideration to account for the errors that the desert terrains pose. This study compared the Extended Kalman Filter (EKF) for standard GPS & GNSS-RTK to verify which performs better for the UGV’s position estimation. The estimated UGV’s position from the kinematics model and EKF are validated using a drone camera system that uses an image processing technique to verify the UGV’s position with the help of the visible reference cones. Throughout the experiments, the GNSS-RTK performed better than GPS. Also, the EKF performed as well as the GNSS-RTK by trusting it more than the encoder/gyroscope reading.

Visual-inertial SLAM method based on optical flow in a GPS-denied environment

2018 ◽  
Vol 45 (3) ◽  
pp. 401-406 ◽  
Author(s):  
Chang Chen ◽  
Hua Zhu
Keyword(s):  
Optical Flow ◽  
Measurement Unit ◽  
Data Sets ◽  
Theoretical Derivation ◽  
Content Type ◽  
Feature Extraction Method ◽  
Localization And Mapping ◽  
Global Positioning ◽  
Tightly Coupled ◽  
The Stability

Purpose This study aims to present a visual-inertial simultaneous localization and mapping (SLAM) method for accurate positioning and navigation of mobile robots in the event of global positioning system (GPS) signal failure in buildings, trees and other obstacles. Design/methodology/approach In this framework, a feature extraction method distributes features on the image under texture-less scenes. The assumption of constant luminosity is improved, and the features are tracked by the optical flow to enhance the stability of the system. The camera data and inertial measurement unit data are tightly coupled to estimate the pose by nonlinear optimization. Findings The method is successfully performed on the mobile robot and steadily extracts the features on low texture environments and tracks features. The end-to-end error is 1.375 m with respect to the total length of 762 m. The authors achieve better relative pose error, scale and CPU load than ORB-SLAM2 on EuRoC data sets. Originality/value The main contribution of this study is the theoretical derivation and experimental application of a new visual-inertial SLAM method that has excellent accuracy and stability on weak texture scenes.

scholarly journals Seasonal and intra-diurnal variability of small-scale gravity waves in OH airglow at two Alpine stations

2019 ◽  
Vol 12 (1) ◽  
pp. 457-469 ◽  
Author(s):  
Patrick Hannawald ◽  
Carsten Schmidt ◽  
René Sedlak ◽  
Sabine Wüst ◽  
Michael Bittner
Keyword(s):  
Gravity Waves ◽  
High Frequency ◽  
Phase Speed ◽  
Propagation Direction ◽  
Field Of View ◽  
Small Scale ◽  
Data Sets ◽  
Data Set ◽  
Diurnal Variability ◽  
Fully Automatic

Abstract. Between December 2013 and August 2017 the instrument FAIM (Fast Airglow IMager) observed the OH airglow emission at two Alpine stations. A year of measurements was performed at Oberpfaffenhofen, Germany (48.09∘ N, 11.28∘ E) and 2 years at Sonnblick, Austria (47.05∘ N, 12.96∘ E). Both stations are part of the network for the detection of mesospheric change (NDMC). The temporal resolution is two frames per second and the field-of-view is 55 km × 60 km and 75 km × 90 km at the OH layer altitude of 87 km with a spatial resolution of 200 and 280 m per pixel, respectively. This resulted in two dense data sets allowing precise derivation of horizontal gravity wave parameters. The analysis is based on a two-dimensional fast Fourier transform with fully automatic peak extraction. By combining the information of consecutive images, time-dependent parameters such as the horizontal phase speed are extracted. The instrument is mainly sensitive to high-frequency small- and medium-scale gravity waves. A clear seasonal dependency concerning the meridional propagation direction is found for these waves in summer in the direction to the summer pole. The zonal direction of propagation is eastwards in summer and westwards in winter. Investigations of the data set revealed an intra-diurnal variability, which may be related to tides. The observed horizontal phase speed and the number of wave events per observation hour are higher in summer than in winter.

scholarly journals Accuracy of Low-Cost Alternative Facial Scanners: A Prospective Cohort Study.

2021 ◽  
Author(s):  
Alexander K. Bartella ◽  
Josefine Laser ◽  
Mohammad Kamal ◽  
Dirk Halama ◽  
Michael Neuhaus ◽  
...  
Keyword(s):  
Low Cost ◽  
Three Dimensional ◽  
Neck Surgery ◽  
Clinical Analysis ◽  
Smart Device ◽  
Data Sets ◽  
Average Deviation ◽  
Technical Improvement ◽  
Data Set ◽  
Significant Difference

Abstract Introduction: Three-dimensional facial scan images have been showing an increasingly important role in peri-therapeutic management of oral and maxillofacial and head and neck surgery cases. Face scan images can be open using optical facial scanners utilizing line-laser, stereophotography, structured light modality, or from volumetric data obtained from cone beam computed tomography (CBCT). The aim of this study is to evaluate, if two low-cost procedures for creating a three-dimensional face scan images are able to produce a sufficient data set for clinical analysis. Materials and methods: 50 healthy volunteers were included in the study. Two test objects with defined dimensions were attached to the forehead and the left cheek. Anthropometric values were first measured manually, and consecutively, face scans were performed with a smart device and manual photogrammetry and compared to the manually measured data sets.Results: Anthropometric distances on average deviated 2.17 mm from the manual measurement (smart device scanning 3.01 mm vs. photogrammetry 1.34 mm), with 7 out of 8 deviations were statistically significant. Of a total of 32 angles, 19 values showed a significant difference to the original 90° angles. The average deviation was 6.5° (smart device scanning 10.1° vs. photogrammetry 2.8°).Conclusion: Manual photogrammetry with a regular photo-camera shows higher accuracy than scanning with smart device. However, the smart device was more intuitive in handling and further technical improvement of the cameras used should be watched carefully.

scholarly journals Evaluation of Deep Learning-Based Neural Network Methods for Cloud Detection and Segmentation

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6156
Author(s):  
Stefan Hensel ◽  
Marin B. Marinov ◽  
Michael Koch ◽  
Dimitar Arnaudov
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Sets ◽  
Cloud Detection ◽  
Camera System ◽  
Data Set ◽  
Network Methods ◽  
Segmentation Approach ◽  
Coverage Prediction ◽  
Short Time

This paper presents a systematic approach for accurate short-time cloud coverage prediction based on a machine learning (ML) approach. Based on a newly built omnidirectional ground-based sky camera system, local training and evaluation data sets were created. These were used to train several state-of-the-art deep neural networks for object detection and segmentation. For this purpose, the camera-generated a full hemispherical image every 30 min over two months in daylight conditions with a fish-eye lens. From this data set, a subset of images was selected for training and evaluation according to various criteria. Deep neural networks, based on the two-stage R-CNN architecture, were trained and compared with a U-net segmentation approach implemented by CloudSegNet. All chosen deep networks were then evaluated and compared according to the local situation.

scholarly journals Geostatistical FDEM inversion: a three-dimensional real case application

2021 ◽  
Author(s):  
Leonardo Azevedo ◽  
João Narciso ◽  
Ellen Van De Vijver
Keyword(s):  
Spatial Distribution ◽  
Physical Properties ◽  
Three Dimensional ◽  
Real Case ◽  
Small Scale ◽  
Inversion Method ◽  
Two Dimensional ◽  
Data Set ◽  
Near Surface ◽  
Direct Observations

<p>The near surface is a complex and often highly heterogeneous system as its current status results from interacting processes of both natural and anthropogenic origin. Effective sustainable management and land use planning, especially in urban environments, demands high-resolution subsurface property models enabling to capture small-scale processes of interest. The modelling methods based only on discrete direct observations from conventional invasive sampling techniques have limitations with respect to capturing the spatial variability of these systems. Near-surface geophysical surveys are emerging as powerful techniques to provide indirect measurements of subsurface properties. Their integration with direct observations has the potential for better predicting the spatial distribution of the subsurface physical properties of interest and capture the heterogeneities of the near-surface systems.</p><p>Within the most common geophysical techniques, frequency-domain electromagnetic (FDEM) induction methods have demonstrated their potential and efficiency to characterize heterogeneous deposits due to their simultaneous sensitivity to electrical conductivity (EC) and magnetic susceptibility (MS). The inverse modelling of FDEM data based on geostatistical techniques allows to go beyond conventional analyses of FDEM data. This geostatistical FDEM inversion method uses stochastic sequential simulation and co-simulation to perturbate the model parameter space and the corresponding FDEM forward model solutions, including both the synthetic FDEM responses and their sensitivity to changes on the physical properties of interest. A stochastic optimization driven by the misfit between true and synthetic FDEM data is applied to iterative towards a final subsurface model. This method not only improve the confidence of the obtained EC and MS inverted models but also allows to quantify the uncertainty related to them. Furthermore, taking into account spatial correlations enables more accurate prediction of the spatial distribution of subsurface properties and a more realistic reconstruction of small-scale spatial variations, even when considering highly heterogeneous near surface systems. Moreover, a main advantage of this iterative geostatistical FDEM inversion method is its ability to flexibly integrate data with different resolution in the same framework.</p><p>In this work, we apply this iterative geostatistical FDEM inversion technique, which has already been successfully demonstrated for one- and two-dimensional applications, to invert a real case FDEM data set in three dimensions. The FDEM survey data set was collected on a site located near Knowlton (Dorset, UK), which is geologically characterized by Cretaceous chalk overlain by Quaternary siliciclastic sand deposits. The subsurface at the site is known to contain several archaeological features, which produces strong local in-phase anomalies in the FDEM survey data. We discuss the particular challenges involved in the three-dimensional application of the inversion method to a real case data set and compare our results against previously obtained ones for one- and two-dimensional approximations.</p>

scholarly journals Early results from the Whisper instrument on Cluster: an overview

2001 ◽  
Vol 19 (10/12) ◽  
pp. 1241-1258 ◽  
Author(s):  
P. M. E. Décréau ◽  
P. Fergeau ◽  
V. Krasnoselskikh ◽  
E. Le Guirriec ◽  
M. Lévêque ◽  
...  
Keyword(s):  
Electron Density ◽  
Small Scale ◽  
Data Sets ◽  
Total Density ◽  
Total Electron Density ◽  
Data Set ◽  
Total Electron ◽  
Density Data ◽  
Early Results ◽  
Natural Emissions

Abstract. The Whisper instrument yields two data sets: (i) the electron density determined via the relaxation sounder, and (ii) the spectrum of natural plasma emissions in the frequency band 2–80 kHz. Both data sets allow for the three-dimensional exploration of the magnetosphere by the Cluster mission. The total electron density can be derived unambiguously by the sounder in most magnetospheric regions, provided it is in the range of 0.25 to 80 cm-3 . The natural emissions already observed by earlier spacecraft are fairly well measured by the Whisper instrument, thanks to the digital technology which largely overcomes the limited telemetry allocation. The natural emissions are usually related to the plasma frequency, as identified by the sounder, and the combination of an active sounding operation and a passive survey operation provides a time resolution for the total density determination of 2.2 s in normal telemetry mode and 0.3 s in burst mode telemetry, respectively. Recorded on board the four spacecraft, the Whisper density data set forms a reference for other techniques measuring the electron population. We give examples of Whisper density data used to derive the vector gradient, and estimate the drift velocity of density structures. Wave observations are also of crucial interest for studying small-scale structures, as demonstrated in an example in the fore-shock region. Early results from the Whisper instrument are very encouraging, and demonstrate that the four-point Cluster measurements indeed bring a unique and completely novel view of the regions explored.Key words. Space plasma physics (instruments and techniques; discontinuities, general or miscellaneous)

Semi-Automated Roller Parameters Extraction from Terrestrial Lidar

2021 ◽  
Vol 87 (12) ◽  
pp. 879-890
Author(s):  
Sagar S. Deshpande ◽  
Mike Falk ◽  
Nathan Plooster
Keyword(s):  
Rotation Axis ◽  
Moving Average ◽  
Three Dimensional ◽  
Data Sets ◽  
Steel Mill ◽  
Data Set ◽  
Terrestrial Lidar ◽  
Two Dimensional Image ◽  
Average Rotation

Rollers are an integral part of a hot-rolling steel mill. They transport hot metal from one end of the mill to another. The quality of the steel highly depends on the surface quality of the rollers. This paper presents semi-automated methodologies to extract roller parameters from terrestrial lidar points. The procedure was divided into two steps. First, the three-dimensional points were converted to a two-dimensional image to detect the extents of the rollers using fast Fourier transform image matching. Lidar points for every roller were iteratively fitted to a circle. The radius and center of the fitted circle were considered as the average radius and average rotation axis of the roller, respectively. These parameters were also extracted manually and were compared to the measured parameters for accuracy analysis. The proposed methodology was able to extract roller parameters at millimeter level. Erroneously identified rollers were identified by moving average filters. In the second step, roller parameters were determined using the filtered roller points. Two data sets were used to validate the proposed methodologies. In the first data set, 366 out of 372 rollers (97.3%) were identified and modeled. The second, smaller data set consisted of 18 rollers which were identified and modelled accurately.

Apple Disease Recognition Based on Small-scale Data Sets

2021 ◽  
Vol 37 (3) ◽  
pp. 481-490
Author(s):  
Chenyong Song ◽  
Dongwei Wang ◽  
Haoran Bai ◽  
Weihao Sun
Keyword(s):  
Identification Accuracy ◽  
Model Complexity ◽  
Geometric Transformation ◽  
Small Scale ◽  
Model Parameters ◽  
Data Sets ◽  
List Type ◽  
Data Set ◽  
Disease Identification ◽  
Scale Data

HighlightsThe proposed data enhancement method can be used for small-scale data sets with rich sample image features.The accuracy of the new model reaches 98.5%, which is better than the traditional CNN method.Abstract: GoogLeNet offers far better performance in identifying apple disease compared to traditional methods. However, the complexity of GoogLeNet is relatively high. For small volumes of data, GoogLeNet does not achieve the same performance as it does with large-scale data. We propose a new apple disease identification model using GoogLeNet’s inception module. The model adopts a variety of methods to optimize its generalization ability. First, geometric transformation and image modification of data enhancement methods (including rotation, scaling, noise interference, random elimination, color space enhancement) and random probability and appropriate combination of strategies are used to amplify the data set. Second, we employ a deep convolution generative adversarial network (DCGAN) to enhance the richness of generated images by increasing the diversity of the noise distribution of the generator. Finally, we optimize the GoogLeNet model structure to reduce model complexity and model parameters, making it more suitable for identifying apple tree diseases. The experimental results show that our approach quickly detects and classifies apple diseases including rust, spotted leaf disease, and anthrax. It outperforms the original GoogLeNet in recognition accuracy and model size, with identification accuracy reaching 98.5%, making it a feasible method for apple disease classification. Keywords: Apple disease identification, Data enhancement, DCGAN, GoogLeNet.

Sign in / Sign up

Export Citation Format

Share Document