• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.11-16
• /
• 2023

The technology of 3D reconstruction, primarily relying on point cloud data, is essential for digitizing objects or spaces. This paper aims to utilize reinforcement learning to achieve the acquisition of point clouds in a given environment. To accomplish this, a simulation environment is constructed using Unity, and reinforcement learning is implemented using the Unity package known as ML-Agents. The process of point cloud acquisition involves initially setting a goal and calculating a traversable path around the goal. The traversal path is segmented at regular intervals, with rewards assigned at each step. To prevent the agent from deviating from the path, rewards are increased. Additionally, rewards are granted each time the agent fixates on the goal during traversal, facilitating the learning of optimal points for point cloud acquisition at each traversal step. Experimental results demonstrate that despite the variability in traversal paths, the approach enables the acquisition of relatively accurate point clouds.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.1
• /
• pp.111-114
• /
• 2010

Purpose: There has been recent interest in the radioactivity uptake and image acquisition of radioactivity concentration. The degree of uptake is strongly affected by many factors containing $^{18}F$-FDG injection volume, tumor size and the density of blood glucose. Therefore, we investigated how radioactivity uptake in target influences 2D or 3D image analysis and elucidate radioactivity concentration that mediate this effect. This study will show the relationship between the radioactivity uptake and 2D,3D image acquisition on radioactivity concentration. Materials and Methods: We got image with 2D and 3D using 1994 NEMA PET phantom and GE Discovery(GE, U.S.A) STe 16 PET/CT setting the ratio of background and hot sphere's radioactivity concentration as being a standard of 1:2, 1:4, 1:8, 1:10, 1:20, and 1:30 respectively. And we set 10 minutes for CT attenuation correction and acquisition time. For the reconstruction method, we applied iteration method with twice of the iterative and twenty times subset to both 2D and 3D respectively. For analyzing the images, We set the same ROI at the center of hot sphere and the background radioactivity. We measured the radioactivity count of each part of hot sphere and background, and it was comparative analyzed. Results: The ratio of hot sphere's radioactivity density and the background radioactivity with setting ROI was 1:1.93, 1:3.86, 1:7.79, 1:8.04, 1:18.72, and 1:26.90 in 2D, and 1:1.95, 1:3.71, 1:7.10, 1:7.49, 1:15.10, and 1:23.24 in 3D. The differences of percentage were 3.50%, 3.47%, 8.12%, 8.02%, 10.58%, and 11.06% in 2D, the minimum differentiation was 3.47%, and the maximum one was 11.06%. In 3D, the difference of percentage was 3.66%, 4.80%, 8.38%, 23.92%, 23.86%, and 22.69%. Conclusion: The difference of accumulated concentrations is significantly increased following enhancement of radioactivity concentration. The change of radioactivity density in 2D image is affected by less than 3D. For those reasons, when patient is examined as follow up scan with changing the acquisition mode, scan should be conducted considering those things may affect to the quantitative analysis result and take into account these differences at reading.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.183-186
• /
• 2003

A vision sensor should be calibrated prior to infer a Euclidian shape reconstruction. A point to point calibration. also referred to as a hard calibration, estimates calibration parameters by means of a set of 3D to 2D point pairs. We proposed a new method for determining a set of 3D to 2D pairs for the structured light hard calibration. It is simply determined based on epipolar geometry between camera image plane and projector plane, and a projector calibrating grid pattern. The projector calibration is divided two stages; world 3D data acquisition Stage and corresponding 2D data acquisition stage. After 3D data points are derived using cross ratio, corresponding 2D point in the projector plane can be determined by the fundamental matrix and horizontal grid ID of a projector calibrating pattern. Euclidian reconstruction can be achieved by linear triangulation. and experimental results from simulation are presented.

• Analytical Science and Technology
• /
• v.5 no.3
• /
• pp.295-301
• /
• 1992

A versatile data acquisition and control adaptor for IBM personal computers has been developed. The data acquisition and control adaptor developed contains major components necessary for computerized data acquisition and control instrumentaions. Up to 4 differential analog signals can be acquired through a choice of dual 12-bit analog-to digital converters depending on the experimental requirements. Also, dual 12-bit digital-to-analog converters, three 16-bit programmable most computerized laboratory data acquisition and control instrumentation. The design principle and its applications are described.

• Korean Journal of Radiology
• /
• v.22 no.9
• /
• pp.1525-1536
• /
• 2021

Objective: To investigate the feasibility of cine three-dimensional (3D) balanced steady-state free precession (b-SSFP) imaging combined with a non-local means (NLM) algorithm for image denoising in evaluating cardiac function in children with repaired tetralogy of Fallot (rTOF). Materials and Methods: Thirty-five patients with rTOF (mean age, 12 years; range, 7-18 years) were enrolled to undergo cardiac cine image acquisition, including two-dimensional (2D) b-SSFP, 3D b-SSFP, and 3D b-SSFP combined with NLM. End-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), and ejection fraction (EF) of the two ventricles were measured and indexed by body surface index. Acquisition time and image quality were recorded and compared among the three imaging sequences. Results: 3D b-SSFP with denoising vs. 2D b-SSFP had high correlation coefficients for EDV, ESV, SV, and EF of the left (0.959-0.991; p < 0.001) as well as right (0.755-0.965; p < 0.001) ventricular metrics. The image acquisition time ± standard deviation (SD) was 25.1 ± 2.4 seconds for 3D b-SSFP compared with 277.6 ± 0.7 seconds for 2D b-SSFP, indicating a significantly shorter time with the 3D than the 2D sequence (p < 0.001). Image quality score was better with 3D b-SSFP combined with denoising than with 3D b-SSFP (mean ± SD, 3.8 ± 0.6 vs. 3.5 ± 0.6; p = 0.005). Signal-to-noise ratios for blood and myocardium as well as contrast between blood and myocardium were higher for 3D b-SSFP combined with denoising than for 3D b-SSFP (p < 0.05 for all but septal myocardium). Conclusion: The 3D b-SSFP sequence can significantly reduce acquisition time compared to the 2D b-SSFP sequence for cine imaging in the evaluation of ventricular function in children with rTOF, and its quality can be further improved by combining it with an NLM denoising method.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.811-816
• /
• 2016

In light of recently developed 3D printers for rapid prototyping, there is increasing attention on the 3D scanner as a 3D data acquisition system for an existing object. This paper presents a prototypical 3D scanner based on a striped laser light image. In order to solve the problem of shadowy areas, the proposed 3D scanner has two cameras with one laser light source. By using a horizontal rotation table and a rotational arm rotating about the latitudinal axis, the scanner is able to scan in all directions. To remove an additional optical filter for laser light pixel extraction of an image, we have adopted a differential image method with laser light modulation. Experimental results show that the scanner's 3D data acquisition performance exhibited less than 0.2 mm of measurement error. Therefore, this scanner has proven that it is possible to reconstruct an object's 3D surface from point cloud data using a 3D scanner, enabling reproduction of the object using a commercially available 3D printer.

• Proceedings of the Optical Society of Korea Conference
• /
• 2009.10a
• /
• pp.4-5
• /
• 2009

• Journal of Sensor Science and Technology
• /
• v.16 no.3
• /
• pp.187-191
• /
• 2007

This paper presents a development of the multi-channel data acquisition/logging system for a sensor signal processing and a method of the evaluation and a temperature compensation for the A/D converters with the specific analog and digital circuit including the software. Also, we have designed a hardware and a software filters with smart algorithm for better signal processing of the proposed system. Software approach was adopted to obtain the stable data from A/D converter.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.3
• /
• pp.186-191
• /
• 2016

This paper addresses the development of 3D data acquisition system (3D scanner) based laser structured-light image. The 3D scanner consists of a stripe laser generator, a conventional camera, and a rotation table. The stripe laser onto an object has distortion according to 3D shape of an object. By analyzing the distortion of the laser stripe in a camera image, the scanner obtains a group of 3D point data of the object. A simple semiconductor stripe laser diode is adopted instead of an expensive LCD projector for complex structured-light pattern. The camera has an optical filter to remove illumination noise and improve the performance of the distance measurement. Experimental results show the 3D data acquisition performance of the scanner with less than 0.2mm measurement error in 2 minutes. It is possible to reconstruct a 3D shape of an object and to reproduce the object by a commercially available 3D printer.

• Electronics and Telecommunications Trends
• /
• v.33 no.5
• /
• pp.103-110
• /
• 2018

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.