• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.110-123
• /
• 2019

Traffic data is the most basic element necessary for transportation planning and traffic system operation. Recently, a method of estimating traffic flow characteristics using distance to a leading vehicle measured by an ADAS camera has been attempted. This study investigated the feasibility of the ADAS vehicle reflecting the distance error of image-based vehicle identification technology as a means to estimate the traffic flow through the normalized root mean square error (NRMSE) based on the number of lanes, traffic demand, penetration rate of probe vehicle, and time-space estimation area by employing the microscopic simulation model, VISSIM. As a result, the estimate of low density traffic flow (i.e., LOS A, LOS B) is unreliable due to the limitation of the maximum identification distance of ADAS camera. Although the reliability of the estimates can be improved if multiple lanes, high traffic demands, and high penetration rates are implemented, artificially raising the penetration rates is unrealistic. Their reliability can be improved by extending the time dimension of the estimation area as well, but the most influential one is the driving behavior of the ADAS vehicle. In conclusion, although it is not possible to accurately estimate the traffic flow with the ADAS camera, its applicability will be expanded by improving its performance and functions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.16 no.3
• /
• pp.103-114
• /
• 2013

In this study, we established the ortho mosaic imagery on the Korean Peninsula using KOMPSAT-2 images and conducted an accuracy assessment. Rational Polynomial Coefficient(RPC) modeling results were mostly less than 2 pixels except for mountainous regions which was difficult to select a Ground Control Point(GCP). Digital Elevation Model(DEM) which was made using the digital topographic map on the scale of 1:5,000 was used for generating an ortho image. In the case of inaccessible area, the Shuttle Radar Topography Mission(SRTM) DEM was used. Meanwhile, the ortho mosaic image of the Korean Peninsula was produced by each ortho image aggregation and color adjustment. An accuracy analysis for the mosaic image was conducted about a 1m color fusion image. In order to verify a geolocation accuracy, 813 check points which were acquired by field survey in South Korea were used. We found that the maximum error was not to exceed 5m(Root Mean Square Error : RMSE). On the other hand, in the case of inaccessible area, the extracted check points from a reference image were used for accuracy analysis. Approximately 69% of the image has a positional accuracy of less than 3m(RMSE). We found that the seam-line accuracy among neighboring image was very high through visual inspection. However, there were a discrepancy with 1 to 2 pixels at some mountainous regions.

• Korean Journal of Optics and Photonics
• /
• v.27 no.3
• /
• pp.106-113
• /
• 2016

In this paper, we deal with the wavefront compensation capability of a silicon carbide (SiC) deformable mirror (DM) with 37 actuators for adaptive optics. The wavefront compensation capability of the SiC DM is predicted by computer simulation and examined by actual experiments with a closed-loop adaptive optics system consistsing of a light source, a phase plate, a SiC DM, a high speed Shack-Hartmann sensor, and a control computer. Distortion of wavefront is caused by the phase plate in the closed-loop adaptive optics system. The distorted wavefront has a peak-to-valley (PV) wavefront error of $0.3{\mu}m{\sim}0.9{\mu}m$ and root-mean-square (RMS) error of $0.06{\mu}m{\sim}0.25{\mu}m$. The high-speed Shack-Hartmann sensor measures the wavefront error of the distortion caused by the phase plate, and the SiC DM compensates for the distorted wavefront. The compensated wavefront has residual errors lower than $0.1{\mu}m$ PV and $0.03{\mu}m$ RMS. Consequently, we conclude that we can compensate for the distorted wavefront using the SiC DM in the closed-loop adaptive optics system with an operating frequency speed of 500 Hz.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.847-859
• /
• 2021

Recently, as the number of high-resolution satellite SAR images increases, the demand for precise matching of SAR imagesin change detection and image fusion is consistently increasing. RMSE (Root Mean Square Error) values using GCPs (Ground Control Points) selected by analysts have been widely used for quantitative evaluation of image registration results, while it is difficult to find an approach for automatically measuring the registration accuracy. In this study, a feasibility analysis was conducted on using the FSIM (Feature Similarity) index as a measure to evaluate the registration accuracy. TerraSAR-X (TSX) staring spotlight data collected from various incidence angles and orbit directions were used for the analysis. FSIM was almost independent on the spatial resolution of the SAR image. Using a single SAR image, the FSIM with respect to registration errors was analyzed, then use it to compare with the value estimated from TSX data with different imaging geometry. FSIM index slightly decreased due to the differencesin imaging geometry such as different look angles, different orbit tracks. As the result of analyzing the FSIM value by land cover type, the change in the FSIM index according to the co-registration error was most evident in the urban area. Therefore, the FSIM index calculated in the urban was mostsuitable for determining the accuracy of image registration. It islikely that the FSIM index has sufficient potential to be used as an index for the co-registration accuracy of SAR image.

• Korean Journal of Remote Sensing
• /
• v.37 no.3
• /
• pp.475-491
• /
• 2021

With the recent increase in available high-resolution (< ~1 m) satellite SAR images, the demand for precise registration of SAR images is increasing in various fields including change detection. The registration between high-resolution SAR images acquired in different look angle is difficult due to speckle noise and geometric distortion caused by the characteristics of SAR images. In this study, registration is performed in two stages, coarse and fine, using the x-band SAR data imaged at staring spotlight mode of TerraSAR-X. For the coarse registration, a method combining the adaptive sampling method and SAR-SIFT (Scale Invariant Feature Transform) is applied, and three rigid methods (NCC: Normalized Cross Correlation, Phase Congruency-NCC, MI: Mutual Information) and one non-rigid (Gefolki: Geoscience extended Flow Optical Flow Lucas-Kanade Iterative), for the fine registration stage, was performed for performance comparison. The results were compared by using RMSE (Root Mean Square Error) and FSIM (Feature Similarity) index, and all rigid models showed poor results in all image combinations. It is confirmed that the rigid models have a large registration error in the rugged terrain area. As a result of applying the Gefolki algorithm, it was confirmed that the RMSE of Gefolki showed the best result as a 1~3 pixels, and the FSIM index also obtained a higher value than 0.02~0.03 compared to other rigid methods. It was confirmed that the mis-registration due to terrain effect could be sufficiently reduced by the Gefolki algorithm.

• Journal of Environmental Impact Assessment
• /
• v.31 no.2
• /
• pp.83-94
• /
• 2022

In this study, DNN-based models were learned using air quality determination data for 2017, 2019, and 2020 provided by the National Measurement Network (Air Korea), and this models evaluated using data from 2016 and 2018. Based on Pearson correlation coefficient 0.2, four items (SO₂, CO, NO₂, PM₁₀) were initially modeled as independent variables. In order to improve the accuracy of prediction, monthly independent modeling was carried out. The error was calculated by RMSE (Root Mean Square Error) method, and the initial model of RMSE was 5.78, which was about 46% betterthan the national moving average modelresult (10.77). In addition, the performance improvement of the independent monthly model was observed in months other than November compared to the initial model. Therefore, this study confirms that DNN modeling was effective in predicting PM_2.5 concentrations based on air pollutants concentrations, and that the learning performance of the model could be improved by selecting additional independent variables.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.487-494
• /
• 2023

In this study, performance comparison was performed on R and TensorFlow, which are free deep learning tools. In the experiment, six types of deep neural networks were built using each tool, and the neural networks were trained using the 10-year Korean temperature dataset. The number of nodes in the input layer of the constructed neural network was set to 10, the number of output layers was set to 5, and the hidden layer was set to 5, 10, and 20 to conduct experiments. The dataset includes 3600 temperature data collected from Gangnam-gu, Seoul from March 1, 2013 to March 29, 2023. For performance comparison, the future temperature was predicted for 5 days using the trained neural network, and the root mean square error (RMSE) value was measured using the predicted value and the actual value. Experiment results shows that when there was one hidden layer, the learning error of R was 0.04731176, and TensorFlow was measured at 0.06677193, and when there were two hidden layers, R was measured at 0.04782134 and TensorFlow was measured at 0.05799060. Overall, R was measured to have better performance. We tried to solve the difficulties in tool selection by providing quantitative performance information on the two tools to users who are new to machine learning.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.434-440
• /
• 2022

The ICAO (International civil aviation organization)recommended the implementation of the GANP (global air navigation plan) for strategic decision-making and air traffic management evaluation. In this study, we proposed a new method for finding the route distance from KPI (key performance indicator) 05 actual route extension presented for air traffic management evaluation. For this purpose, we collected trajectory data for one month and calculated the en-route distances using the methods presented in ICAO and the methods presented by this author. In the ICAO method, the intersection point must be estimated through the equation of a circle for radius 40 NM and the equation of a straight line for an inner and outer point close to a circle in the track data, and four flight distances are calculated to calculate the en-route distance. In the method presented in this study, two flight distances are calculated without estimating the intersection point to calculate the en-route distance. To determine the error between the two methods, we used the performance evaluation index RMSE (root mean square error) and the determination factor R² of the regression model.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.301-307
• /
• 2023

Deep learning requires building a deep neural network, collecting a large amount of training data, and then training the built neural network for a long time. If training does not proceed properly or overfitting occurs, training will fail. When using deep learning tools that have been developed so far, it takes a lot of time to collect training data and learn. However, due to the rapid advent of the mobile environment and the increase in sensor data, the demand for real-time deep learning technology that can dramatically reduce the time required for neural network learning is rapidly increasing. In this study, a real-time deep learning system was implemented using an Arduino system equipped with a fine dust sensor. In the implemented system, fine dust data is measured every 30 seconds, and when up to 120 are accumulated, learning is performed using the previously accumulated data and the newly accumulated data as a dataset. The neural network for learning was composed of one input layer, one hidden layer, and one output. To evaluate the performance of the implemented system, learning time and root mean square error (RMSE) were measured. As a result of the experiment, the average learning error was 0.04053796, and the average learning time of one epoch was about 3,447 seconds.

• Journal of Positioning, Navigation, and Timing
• /
• v.4 no.2
• /
• pp.73-77
• /
• 2015

Global Positioning System (GPS) Precise Point Positioning (PPP) has been extensively used for geodetic applications. Since December 2012, BeiDou navigation satellite system has provided regional positioning, navigation and timing (PNT) services over the Asia-Pacific region. Recently, many studies on BeiDou system have been conducted, particularly in the area of precise orbit determination and precise positioning. In this paper PPP method based on BeiDou observations are presented. GPS and BeiDou data obtained from Mokpo (MKPO) station are processed using the Korea Astronomy and Space Science Institute Global Navigation Satellite System (GNSS) PPP software. The positions are derived from the GPS PPP, BeiDou B₁/B₂ PPP and BeiDou B₁/B₃ PPP, respectively. The position errors on BeiDou PPP show a mean bias < 2 cm in the east and north components and approximately 3 cm in the vertical component. It indicates that BeiDou PPP is ready for the precise positioning applications in the Asia-Pacific region. In addition, BeiDou tropospheric zenith total delay (ZTD) is compared to GPS ZTD at MKPO station. The mean value of their difference is approximately 0.52 cm.