Wyniki wyszukiwania - BazTech

1

Implementation of Object Detection Algorithms in the Inventory of Technical Infrastructure, Case Study of Utility Poles Detection

Czyrzniak Mateusz, Rapiński Jacek

Civil and Environmental Engineering Reports

|

2025

|

Vol. 35, no. 1

177--189

EN

Roads, bridges, railways, poles, and power lines are one of main elements of technical infrastructure. Their proper condition is essential for ensuring people, goods, and electricity transportation. Inventory is a crucial process for maintaining the health of technical infrastructure. Conducting inventory with traditional surveying techniques, such as Global Navigation Satellite Systems (GNSS) or trigonometry, is both time and money consuming. In recent years, modern remote sensing techniques like LiDAR (Light Detection and Ranging) and aerial and ground based imaging have been employed for inventory purposes. These methods enable data collection over large areas, reducing both the time and cost of measurement processes. Data from these devices is often processed in conjunction with artificial intelligence algorithms that assist in processing large data sets. This paper aims to introduce deep learning (DL) algorithms for inventory purposes using object detection with utility poles as a case study. The research was conducted using empirical data. A key element in training a DL model is the optimal selection of hyperparameters. During the study, ten models were trained, and their performance was compared based on selected metrics. For this study, a dataset of 1,736 original utility pole images was used. To augment the data, new images were created through rotation and mirroring. The best model achieved the following results: Precision = 98.82%, Recall = 97.29%, F1-score = 98.05%, mAP50 = 97.92%, mAP75 = 89.93%. The performance of the model gives a solid base for further implementation of DL object detection techniques for inventory of technical infrastructure.

2

Advanced, on-line gnss multi-constellation mission planning and multipath mitigation tool

Tomaszewski Dariusz, Rapiński Jacek, Janowski Artur

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2024

|

Vol. 27

409--428

EN

Despite the growing number of satellites in multi-constellation GNSS positioning systems, the issue of signal availability and quality persists in urban and forest areas. Additionally, obstacles such as high buildings or dense vegetation can lead to severe multipath problems. Various methods have been developed to mitigate the impact of multipath on measurement results, including optimizing antenna placement, antenna type, receiver type, and employing measurement post processing techniques. However, despite these efforts, multipath interference cannot be completely eliminated and can significantly impact positioning accuracy. To tackle this challenge, a tool GNSS MPD for predicting satellite signal obstruction was developed. This tool considers Line of Sight (LOS) vectors between specific locations and satellite positions, as well as obstacle models derived from airborne LiDAR data. The LiDAR data is automatically acquired from geoportal.gov.pl, and an approximate terrain cover model is generated. Satellite obstructions are then validated using a ray casting method. The authors of the study outlined the platform’s design and implementation. Subsequently, two experiments were conducted. The first experiment consisted in comparing the obtained satellite visibility scenarios with the results obtained from hemispherical photography. The second study involved performing five daily satellite observations in an area characterized by severe terrain obstacles. Based on the receiver’s approximate position, satellite visibility scenarios were generated using the developed platform. Static positioning was performed as part of the experiment, producing two sets of results: one using raw receiver observations without modifications, and the other incorporating visibility scenarios from the platform to adjust observation files. The tests were performed in 5 research scenarios. In each of the cases results demonstrated improvements in both accuracy and the success rate of position determination. For success rate, an increase of more than 20% was achieved. In many cases, positioning accuracy improved by more than 50%.

3

On the numerical minimisation of the objective function applied to spherical harmonics fitting

Czyrzniak Mateusz, Rapiński Jacek

Diagnostyka

|

2023

|

Vol. 24, No. 3

art. no. 2023313

EN

The paper presents some considerations on the performance of various objective function minimization methods in the process of GNSS antenna PCV determination. It is particulary important in the case of structural health monitoring and diagnostics. PCV are used as an additional feature to improve the GNSS positioning accuracy. The process of PCV derivation is complex and involves fitting spherical harmonics into a set of observables. The paper compares computing performance and accuracy of few methods used in the fitting process.

4

Preliminary assessment of ADIS16470AMLZ sensor for monitoring of seismic activity in mining area

Śmieja Michał, Banach Jakub, Majkusiak Tomasz, Rapiński Jacek

Diagnostyka

|

2022

|

Vol. 23, No. 4

art. no. 2022404

EN

Seismic activity monitoring in the mining exploitation area is an important factor, that has an effect on safety and infrastructure management. The introduction sections presents the outline of mining interference into rock mass structure and selected parameters and methods of observation related to its effects. Further in the article an alternative to currently seismic measurement devices was proposed, and an preliminary research of its metrological quality was carried out based on experimental data. Assessment was based on short time Fourier transform (STFT) and Pearson cross-correlation coefficient.

5

Switching Edge Detector as a tool for seismic events detection based on GNSS timeseries

Tomaszewski Dariusz, Rapiński Jacek, Stolecki Lech, Śmieja Michał

Archives of Mining Sciences

|

2022

|

Vol. 67, no. 2

317--332

EN

Contemporary mine exploitation requires information about the deposit itself and the impact of mining activities on the surrounding surface areas. In the past, this task was performed using classical seismic and geodetic measurements. Nowadays, the use of new technologies enables the determination of the necessary parameters in global coordinate systems. For this purpose, the relevant services create systems that integrate various methods of determining interesting quantities, e.g., seismometers / GNSS / PSInSAR. These systems allow detecting both terrain deformations and seismic events that occur as a result of exploitation. Additionally, they enable determining the quantity parameters that characterise and influence these events. However, such systems are expensive and cannot be set up for all existing mines. Therefore, other solutions are being sought that will also allow for similar research. In this article, the authors examined the possibilities of using the existing GNSS infrastructure to detect seismic events. For this purpose, an algorithm of automatic discontinuity detection in time series “Switching Edge Detector” was used. The reference data were the results of GNSS measurements from the integrated system (seismic / GNSS / PSInSAR) installed on the LGCB (Legnica-Głogów Copper Belt) area. The GNSS data from 2020 was examined, for which the integrated system registered seven seismic events. The switching Edge Detector algorithm proved to be an efficient tool in seismic event detection.

6

Wyznaczenie dynamicznych przemieszczeń punktów z wykorzystaniem autorskiego automatycznego modułu opracowania wysokoczęstotliwościowych obserwacji GNSS

Paziewski Jacek, Tomaszewski Dariusz, Rapiński Jacek, Stolecki Lech

Cuprum : czasopismo naukowo-techniczne górnictwa rud

|

2021

|

nr 3-4

27--38

PL

W artykule przedstawiono wyniki walidacji modułu opracowania wysokoczęstotliwościowych obserwacji GNSS, powstałego w ramach realizacji projektu ASMOW. Moduł przeznaczony jest do wyznaczania dynamicznych przemieszczeń wywoływanych zdarzeniami para-sejsmicznymi. Badania przeprowadzono w oparciu o dane pomiarowe, zebrane podczas realizacji projektu ASMOW przez testową sieć stacji monitorujących, która została założona w rejonie oddziaływania głębinowej kopalni rud miedzi Rudna. Walidacje wykonano na podstawie opracowania rejestracji sejsmicznych oraz wysokoczęstotliwościowych obserwacji GNSS, pozyskanych podczas zdarzenia sejsmicznego z 30 lipca 2020 r. na testowym obszarze. Analizowane zdarzenie sejsmiczne charakteryzowało się energią = 1,9x108 J oraz magnitudą = 3,6. Na podstawie całkowania rejestracji z akcelerometrów obliczono wartości dynamicznych przemieszczeń dla stacji sejsmicznych, kolokowanych ze stacjami GNSS. Tak wyznaczone przemieszczenia potraktowano jako wartości referencyjne i do nich odniesiono wartości przemieszczeń, które zostały wyznaczone autorskim automatycznym modułem opracowania wysokoczęstotliwościowych obserwacji GNSS, powstałym w ramach projektu ASMOW. Na podstawie wykonanych badań stwierdzono wysoką zgodność pomiędzy rozwiązaniami z dwóch technik obserwacyjnych. Określono dokładność wyznaczania dynamicznych przemieszczeń w oparciu o wysokoczęstotliwościowe sygnały GNSS na poziomie pojedynczych milimetrów. W szczególności średnia kwadratowa różnic przemieszczeń z obu technik zawierała się w zakresie 0,6-2,6 mm dla składowych poziomych oraz 1,8-2,5 mm dla wysokości.

EN

The article presents a validation of the use of high-rate GNSS observations to determine dynamic displacements caused by seismic events. This task was performed on the basis of measurement data generated as part of the ASMOW project. The study concerns the measurement network which was established in the Rudna mine influence area. The validations were made on the basis of data from seismographs and GNSS measurement collected on July 30, 2020 during the seismic event. The seismic event was characterized by an energy of 1.9x108 J and a magnitude of 3.6. As part of the study, data collected from accelerographs were treated as reference values. Then, based on the integration of accelerations, the values of soil displacements at GNSS stations collocating with seismic stations were calculated. The same values were determined by the developed automatic GNSS high-rate processing module. On the basis of performed studies, a high agreement was found between the solutions from the two independent observation techniques. Moreover, we showed that it is feasible to reach a few millimeters accuracy level of dynamic displacements determination with high-rate GNSS. In particular, the root mean square of the displacement differences from both techniques was in the range of 0.6-2.6 mm for the horizontal components and 1.8-2.5 mm for the height.