Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Automatic Image Analysis

Sortuj według:

Ogranicz wyniki do:

Automatic System for Acquisition and Analysis of Microscopic Digital Images Containing Activated Sludge

Staniszewski Michał, Dziadosz Marcin, Zaburko Jacek, Babko Roman, Łagód Grzegorz

Advances in Science and Technology. Research Journal

2024

Vol. 18, no. 7

51--61

The article contains the procedure of image acquisition, including sampling of analyzed material as well as technical solutions of hardware and preprocessing used in research. A dataset of digital images containing identified objects were obtained with help of automated mechanical system for controlling the microscope table and used to train the YOLO models. The performance of YOLOv4 as well as YOLOv8 deep learning networks was compared on the basis of automatic image analysis. YOLO constitutes a one-stage object detection model, aiming to examine the analyzed image only once. By utilizing a single neural network, the image is divided into a grid of cells, and predictions are made for bounding boxes, as well as object class probabilities for each box. This approach allows real-time detection with minimal accuracy loss. The study involved ciliated protozoa Vorticella as a test object. These organisms are found both in natural water bodies and in treatment plants that employ the activated sludge method. As a result of its distinct appearance, high abundance and sedentary lifestyle, Vorticella are good subjects for detection tasks. To ensure that the training dataset is accurate, the images were manually labeled. The performance of the models was evaluated using such metrics as accuracy, precision, and recall. The final results show the differences in metrics characterizing the obtained outputs and progress in the software over subsequent versions of the YOLO algorithm.

Concrete surface evaluation based on the reflected TLS laser beam’s intensity image classification

Zaczek-Peplinska J., Osińska-Skotak K.

Studia Geotechnica et Mechanica

2018

Vol. 40, nr 1

56--64

Dynamically developing terrestrial laser scanning technology (TLS) provides modern surveying tools, that is, scanning total stations and laser scanners. Owing to these instruments, periodic control surveys of concrete dams were performed as a part of geodetic monitoring yield point models characterised by quasicontinuity. Using the results of such measurements as a base, one can carry out a number of geometric analyses as well as acquire information for detailed analytical and calculative considerations. The scanner, similar to total station, by determining distances and angles, identifies spatial coordinates (X, Y, Z) of the surveyed points. Registration of the reflected laser beam’s intensity value (Intensity) emitted by the scanner provides additional information on the surveyed object. Owing to high working speed and the large amount of the collected data, the scanners became an indispensable tool for geodesists. The article assesses the possibility of application of terrestrial laser scanning in surveying changes in the surface of a concrete dam based on the experimental measurements. The condition of the dam’s downstream concrete wall was evaluated. The evaluation included changes in the surface’s roughness, cracks, seepage points, erosion caused by plant overgrowth and the degressive durability parameter of the used material (concrete). The article presents an example of the application of the results of a laser scan in the assessment of the condition of a water dam’s external concrete surfaces. The results of experimental measurements were analysed – the results of a scan of the downstream concrete wall of a dam in Ecker (Germany) using two laser scanners characterised by different technical parameters, that is, laser wavelength (laser’s colour), range, definable point density, method of distance measurement – Leica C10, Z+F Imager 5006h. The measurement was carried out in the same weather conditions from the same sites of the test base. The results of the measurements were analysed using, inter alia, statistical methods by defining template fields and supervised and unsupervised classification methods in reference to the selected fragments of the Surface characterised by known concrete surface properties. Various classification algorithms were used. The obtained results make it possible to assess the suitability of the proposed methodology of evaluating the concreto surface’s condition and establish tool selection principles to match the practical application requirements.