• Title/Summary/Keyword: Ground truth

Search Result 304, Processing Time 0.026 seconds

Image Segmentation for Microstructure based on Semi-supervised Learning (준지도 학습 기반의 미세조직 이미지 분할)

  • YeJi Lee;WooSang Shin;Jong Pil Yun;Moon G. Joo
    • IEMEK Journal of Embedded Systems and Applications
    • /
    • v.19 no.6
    • /
    • pp.307-312
    • /
    • 2024
  • In order to solve problems such as data collection and expensive labeling work, we proposed an image segmentation model using semi-supervised and unsupervised learning methods. Since semi-supervised learning is used, high performance can be achieved even in situations with little ground truth. The proposed model consists of a segmentation module and a cluster module. The Segment Anything Model (SAM) is used for the segmentation module. The cluster module uses the k-means clustering algorithm, a representative method of unsupervised learning, to determine whether components belong to the same class within the microbial image. Finally, by configuring a user interface, the system was created to return all objects and corresponding components belonging to the same cluster when the user selects an element that wants to be divided. Both the segmentation module and the cluster module can use semi-supervised or unsupervised learning to reduce the cost of work such as data collection and labeling, which has been a problem with the existing image segmentation model.

Development of droplets detection system using deep learning (딥러닝 기반 감수지 액적 자동 인식 시스템 개발)

  • Baek-Gyeom Seong;Xiongzhe Han;Seung-Hwa Yu;Chun-Gu Lee;Yeongho Kang;Dae-Hyun Lee
    • Journal of Drive and Control
    • /
    • v.21 no.4
    • /
    • pp.174-181
    • /
    • 2024
  • This study aimed to develop a real-time, drone-based pesticide spraying performance evaluation system applicable in field conditions. To achieve robust detection performance across domain discrepancies and noise, we employed self-supervised learning techniques. The training dataset was collected through a drone spraying test designed to capture droplets on water-sensitive paper and comprised processed ground-truth data and field data captured under various environmental conditions. For practical use in real-world applications, we adopted a lightweight model that can be used in embedded computers. Comparative testing with varied environmental spraying datasets showed that the proposed system demonstrated greater robustness in detecting droplets under diverse, irregular field conditions. With continued research, this system is expected to evolve to deliver even higher detection precision and adaptability across varied environment.

Estimating the Accuracy of Polygraph Test (폴리그라프 검사의 정확도 추정)

  • Jin-Sup Eom ;Hyung-Ki Ji ;Kwangbai Park
    • Korean Journal of Culture and Social Issue
    • /
    • v.14 no.4
    • /
    • pp.1-18
    • /
    • 2008
  • The present study examined the accuracy of polygraph tests through two types of statistical methods with unknown ground truth. One method evaluated the accuracy based on the rates of agreements between polygraph test results of crime suspects and prosecutors' indictment decisions for them. Those crime suspects were tested with polygraph by the Prosecutors' Office of the Republic of Korea between 2000 and 2004. The other method estimated the accuracy by using the latent class analysis based on the frequency distributions of the polygraph results and indictments during 2006. Excluding cases that were 'inconclusive' on the polygraph test, the study showed that the accuracy of the polygraph tests is .914 (SE=.004) for the 2000-2004 data, and .885 (SE=.021) for the 2006 data. With the inclusion of 'inconclusive' cases in the 2006 data, the results from the latent class analysis showed the accuracy in the range between .707 and .734 (SE=.027~.031), with false positives between .078 and .087 (SE=.019~.023), and false negatives between .029 and .078 (SE=.010~.023). The probability that the polygraph test correctly classifies subjects appeared to be in the range between .912 and .925 (SE=.013-.016) for those who lie, and in the range between .867 to .955 (SE=.011-.040) for those who tell the truth.

  • PDF

Development of a Classification Method for Forest Vegetation on the Stand Level, Using KOMPSAT-3A Imagery and Land Coverage Map (KOMPSAT-3A 위성영상과 토지피복도를 활용한 산림식생의 임상 분류법 개발)

  • Song, Ji-Yong;Jeong, Jong-Chul;Lee, Peter Sang-Hoon
    • Korean Journal of Environment and Ecology
    • /
    • v.32 no.6
    • /
    • pp.686-697
    • /
    • 2018
  • Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.

A Study on the Quality of Photometric Scanning Under Variable Illumination Conditions

  • Jeon, Hyoungjoon;Hafeez, Jahanzeb;Hamacher, Alaric;Lee, Seunghyun;Kwon, Soonchul
    • International journal of advanced smart convergence
    • /
    • v.6 no.4
    • /
    • pp.88-95
    • /
    • 2017
  • The conventional scan methods are based on a laser scanner and a depth camera, which requires high cost and complicated post-processing. Whereas in photometric scanning method, the 3D modeling data is acquired through multi-view images. This is advantageous compared to the other methods. The quality of a photometric 3D model depends on the environmental conditions or the object characteristics, but the quality is lower as compared to other methods. Therefore, various methods for improving the quality of photometric scanning are being studied. In this paper, we aim to investigate the effect of illumination conditions on the quality of photometric scanning data. To do this, 'Moai' statue is 3D printed with a size of $600(H){\times}1,000(V){\times}600(D)$. The printed object is photographed under the hard light and soft light environments. We obtained the modeling data by photometric scanning method and compared it with the ground truth of 'Moai'. The 'Point-to-Point' method used to analyseanalyze the modeling data using open source tool 'CloudCompare'. As a result of comparison, it is confirmed that the standard deviation value of the 3D model generated under the soft light is 0.090686 and the standard deviation value of the 3D model generated under the hard light is 0.039954. This proves that the higher quality 3D modeling data can be obtained in a hard light environment. The results of this paper are expected to be applied for the acquisition of high-quality data.

Human Tracking and Body Silhouette Extraction System for Humanoid Robot (휴머노이드 로봇을 위한 사람 검출, 추적 및 실루엣 추출 시스템)

  • Kwak, Soo-Yeong;Byun, Hye-Ran
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.34 no.6C
    • /
    • pp.593-603
    • /
    • 2009
  • In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

Applicability of Fuzzy Logic Based Data Integration to Geothermal Potential Mapping in Southern Gyeongsang Basin, Korea (경상분지 남부지역의 지열 부존 잠재력 평가를 위한 퍼지기반 자료통합의 적용성 연구)

  • Park, Maeng-Eon;Baek, Seung-Gyun;Sung, Kyu-Youl
    • Economic and Environmental Geology
    • /
    • v.40 no.3 s.184
    • /
    • pp.307-318
    • /
    • 2007
  • The occurrence of geothermal water has high correlates highly with fossil geothermal system. A fuzzy logic based data integration is applied for geothermal potential mapping in the Southern Gyeongsang Basin which is distributed in the regional fossil geothermal system. Several data sets are related with the origin and distribution of fossil geothermal system, such as the geological map, the density of lineaments, the aerial survey map of magnetic intensity, the map of hydrothermal alteration, the distribution density of hydrothermal mines, which were collected as thematic maps for the integration. Fuzzy membership functions for all thematic maps were compared to the locations of the spa hot springs, which were used as ground-truth control points. After integrating all thematic maps, the results of gamma operator (${\gamma}=0.1$) was showed the highest success rate, and new geothermal potential zone is prospected in some area.

Surface Water Mapping of Remote Sensing Data Using Pre-Trained Fully Convolutional Network

  • Song, Ah Ram;Jung, Min Young;Kim, Yong Il
    • Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
    • /
    • v.36 no.5
    • /
    • pp.423-432
    • /
    • 2018
  • Surface water mapping has been widely used in various remote sensing applications. Water indices have been commonly used to distinguish water bodies from land; however, determining the optimal threshold and discriminating water bodies from similar objects such as shadows and snow is difficult. Deep learning algorithms have greatly advanced image segmentation and classification. In particular, FCN (Fully Convolutional Network) is state-of-the-art in per-pixel image segmentation and are used in most benchmarks such as PASCAL VOC2012 and Microsoft COCO (Common Objects in Context). However, these data sets are designed for daily scenarios and a few studies have conducted on applications of FCN using large scale remotely sensed data set. This paper aims to fine-tune the pre-trained FCN network using the CRMS (Coastwide Reference Monitoring System) data set for surface water mapping. The CRMS provides color infrared aerial photos and ground truth maps for the monitoring and restoration of wetlands in Louisiana, USA. To effectively learn the characteristics of surface water, we used pre-trained the DeepWaterMap network, which classifies water, land, snow, ice, clouds, and shadows using Landsat satellite images. Furthermore, the DeepWaterMap network was fine-tuned for the CRMS data set using two classes: water and land. The fine-tuned network finally classifies surface water without any additional learning process. The experimental results show that the proposed method enables high-quality surface mapping from CRMS data set and show the suitability of pre-trained FCN networks using remote sensing data for surface water mapping.

An Approach to Measurement of Water Quality Factors and its Application Using NOAA satellite Data

  • Jang, Dong-Ho;Jo, Gi-Ho;Chi, Kwang-Hoon
    • Proceedings of the KSRS Conference
    • /
    • 1999.11a
    • /
    • pp.363-370
    • /
    • 1999
  • Remotely sensed data is regarded as a potentially effective data source for the measurement of water quality and for the environmental change of water bodies. In this study, we measured the spectral reflectance by using multi-spectral image of low resolution camera(LRC) which will be loaded in the OSMI multi-purpose satellite(KOMPSAT) scheduled to be launched on 1999 to use the data in analyzing water pollution. We also investigated the possibility of extraction of water quality factors in water bodies by using remotely sensed low resolution data such as NOAA/AVHRR. In this study, Shiwha-District and Sang-Sam Lake was set up as the subject areas for the study. In this part of the study, we measured the spectral reflectance of the water surface to analyze the radiance of the water bodies in low resolution spectral band and tried to analyze the water quality factors in water bodies by using radiance feature from another remotely sensed data such as NOAA/AVHRR. As the method of this study, first, we measured the spectral reflectance of the water surface by using SFOV( Single Field of View) to measure the reflectance of water quality analysis from every channel in LRC spectral band(0.4~O.9${\mu}{\textrm}{m}$). Second, we investigated the usefulness of ground truth data and the LRC data by measuring every spectral reflectance of water quality factors. Third, we analyzed water quality factors by using the radiance feature from another remotely sensed data such as NOAA/AVHRR. We carried out ratio process of what we selected Chlorophyll-a and suspended sediments as the first factors of the water quality. The results of the analysis are below. First, the amount of pollutants of Shiwha-Lake has been increasing every you since 1987 by factors of eutrophication. Second, as a result of the reflectance, Chlorophyll-a represented high spectral reflectance mainly around 0.52${\mu}{\textrm}{m}$ of green spectral band, and turbidity represented high spectral reflectance at 0.57${\mu}{\textrm}{m}$. But suspended sediments absorbed high at 0.8${\mu}{\textrm}{m}$. Third, Chlorophyll-a and suspended sediments could have a distribution chart as a result of the water quality analysis by using NOAA/AVHRR data.

  • PDF

An Evaluation of ETM+ Data Capability to Provide 'Forest-Shrub land-Range' Map (A Case Study of Neka-Zalemroud Region-Mazandaran-Iran)

  • Latifi Hooman;Olade Djafar;Saroee Saeed;jalilvand Hamid
    • Proceedings of the KSRS Conference
    • /
    • 2005.10a
    • /
    • pp.403-406
    • /
    • 2005
  • In order to evaluate the Capability of ETM+ remotely- sensed data to provide 'Forest-shrub land-Rangeland' cover type map in areas near the timberline of northern forests of Iran, the data were analyzed in a portion of nearly 790 ha located in Neka-Zalemroud region. First, ortho-rectification process was used to correct the geometric errors of the image, yielding 0/68 and 0/69 pixels of RMS. error in X and Y axis, respectively. The original and panchromatic bands were fused using PANSHARP Statistical module. The ground truth map was made using 1 ha field plots in a systematic-random sampling grid, and vegetative form of trees, shrubs and rangelands was recorded as a criteria to name the plots. A set of channels including original bands, NDVI and IR/R indices and first components of PCI from visible and infrared bands, was used for classification procedure. Pair-wise divergence through CHNSEL command was used, In order to evaluate the separability of classes and selection of optimal channels. Classification was performed using ML classifier, on both original and fused data sets. Showing the best results of $67\%$ of overall accuracy, and 0/43 of Kappa coefficient in original data set. Due to the results represented above, it's concluded that ETM+ data has an intermediate capability to fulfill the spectral variations of three form- based classes over the study area.

  • PDF