• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Journal of Korea Water Resources Association
• /
• v.40 no.9
• /
• pp.743-754
• /
• 2007

This study theoretically compared three possible methods for the ground-truth, that is three ground-truth designs of radar rainfall using the rain gauge rainfall. Theoretical results derived are first applied to the rainfall field generated by the Waymire-Gupta-Rodriguez Iturbe(WGR) model, and then to the Mt. Gwanak radar data using the rain gauge data from MOCT within the radar range of observation. Overall application results were found to be similar to those from theoretical studies, also those from the application to the WGR rainfall field. In conclusion, the ground-truth design using only positive(+) rainfalls from both radar and rain gauges causes serious design bias to be inappropriate as a ground-truth design.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.715-720
• /
• 2002

There are many global/continental or large area land cover mapping projects because land cover is one of key parameters in environmental studies. Though ground truth collection is a important and difficult task in land cover mapping, it is usually performed independently in each project without any cooperation between them. This is the background of the development of Global Land Cover Ground Truth (GLCGT) database by the cooperation of many projects and researchers. The developed GLCGT database will be used freely by any researcher. This cooperative and common development of GLCGT database will realize reliable and continuously improved land cover ground truth data. It also eliminates duplicated efforts of ground truth collection among projects.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.281-284
• /
• 1999

Ground truth measurement system using RC helicopter is very useful to measure BRDF. The helicopter is operated human operator but it can keep its position by GPS aided hovering system. We developed the measurement system and have done ground truth in Mongolia in the summer of 1999 and have made sure the system can measure BRDF expectedly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1416-1417
• /
• 2013

깊이 정보를 획득하기 위해서 가장 많이 시도되는 방법이 스테레오 정합이다. 스테레오 정합 알고리즘은 다양한 알고리즘의 조합으로 구성되며, 파라메터 또한 다양하다. 일반적으로는 middlebury에서 제공하는 영상과 ground truth를 이용해서 스테레오 정합 알고리즘을 연구하고, 파라메터 최적화 과정을 거친다. 실제 시스템에 알고리즘 및 파라메터를 적용할 때 middlebury 영상으로 선택된 알고리즘과 파라메터가 상이할 수 있다. 본 논문에서는 실제 시스템의 스테레오 카메라를 이용해서 ground truth를 만들 수 있는 방법을 제안하다. 프로젝트를 이용해서 패턴을 투사하고, 스테레오 카메라로 영상을 획득한다. 한 장면에 대해서 다양한 영상으로 스테레오 정합을 수행하여 만들어진 disparity map은 높은 정확성을 가지고 있음으로, 스테레오 정합 알고리즘 검증용 ground truth로 사용이 가능하다.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.13-18
• /
• 1999

Land cover map of 30 arc-second grid by NOAA AVHRR data for the whole Asia was produced by the authors as the project of the Asian Association on Remote Sensing(AARS). Land cover change monitoring of continental scale by satellite data needs preprocessing to remove undesirable factors due to noises, atmosphere, or the effect by solar zenith angle. The paper describes the method to remove these factors. The most important thing for better mapping/monitoring in the future is the accumulation of ground truth data by many land cover related researchers. The project of the development of Global Land Cover Ground Truth Database(GLCGT-DB) is proposed.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2014

In the current generation of smart mobile devices, object tracking is one of the most important research topics for computer vision. Because human face tracking can be widely used for many applications, collecting a dataset of face videos is necessary for evaluating the performance of a tracker and for comparing different approaches. Unfortunately, the well-known benchmark datasets of face videos are not sufficiently diverse. As a result, it is difficult to compare the accuracy between different tracking algorithms in various conditions, namely illumination, background complexity, and subject movement. In this paper, we propose a new dataset that includes 91 face video clips that were recorded in different conditions. We also provide a semi-automatic ground-truth generation tool that can easily be used to evaluate the performance of face tracking systems. This tool helps to maintain the consistency of the definitions for the ground-truth in each frame. The resulting video data set is used to evaluate well-known approaches and test their efficiency.

• Proceedings of the KSRS Conference
• /
• 2006.03a
• /
• pp.165-168
• /
• 2006

이 논문에서는 한국항공우주연구원 위성영상 검 보정 test site 중 하나인 충남 당진 연구지역에 대하여 AMS 시스템을 이용한 항공촬영과 분광반사도 측정, GCP target 실험, GPS 측량, 토지피복조사 등 ground truth를 통하여 구축된 자료를 소개하고, 구축된 자료를 이용하여 AMS 영상의 분광특성을 분석하였다. AMS 영상 DN값과 야외 분광반사도 측정값과의 선형회귀분석결과, AMS 영상의 모든 spectral band에서 DN값과 분광반사도 측정값이 매우 밀접한 관계가 있음을 알 수 있었다. 선형회귀식을 이용하여 AMS 영상을 reflectance 영상으로 변환하였으며, reflectance 영상과 야외 분광반사도 그래프가 거의 일치하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.1948-1952
• /
• 2007

본 연구에서는 레이더 강우의 지상보정(ground-truth)을 위해 사용가능한 기상청(KMA), AWS 및 건설교통부(MOCT) 강우자료를 다양한 지상보정 설계에 적용하여 비교 평가하였다. 본 연구에서는 동일 기간의 KMA, MOCT, AWS의 우량계 자료와 관악산 레이더 강우자료를 이용하였으며, 각각 두 관측방법사이의 차이(오차)를 편의(bias)의 유무 및 크기의 관점에서 평가하였다. 추가로 호우 사상의 특성에 따른 차이도 함께 검토하였다. 그 적용 결과 지상우량계 자료별 편의의 차이는 확연하게 부각되지는 않았으나, 통계 특성치에서는 어느 정도의 차이가 존재함을 확인하였다. 전체적으로 보면 MOCT 우량계 자료를 이용하는 경우가 다른 강우자료를 이용하는 경우에 비해 편의의 규모가 제일 작은 것으로 확인되었다. 호우 사상별로는 강우의 공간적 간헐성이 가장 큰 장마 기간의 경우가 태풍이나 대류성 강우에 비해 설계편의가 작게 나타나는 것으로 확인되었다.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.655-659
• /
• 2006

Surface Solar Insolation is important for vegetation productivity, hydrology, crop growth, etc. In this study, Surface Solar Insolation is estimated using Multi-functional Transport Satellite (MTSAT-1R) in clear and cloudy conditions. For the Cloudy sky cases, the surface solar insolation is estimated by taking into account the cloud transmittance and multiple scattering between cloud and surface. This model integrated Kawamura's model and SMAC code computes surface solar insolation with a 5km ${\times}$ 5km spatial resolution in hourly basis. The daily value is derived from the available hourly Surface Solar Insolation, independently for every pixel. To validation, this study uses ground truth data recorded from the pyranometer installed by the Korea Meteorological Agency (KMA). The validation of estimated value is performed through a match-up with ground truth. Various match-up with ground truth. Various match-up window sizes are tested with 3${\times}$3, 5${\times}$5, 7${\times}$7, 9${\times}$9, 10${\times}$10, 11${\times}$11, 13${\times}$13 pixels to define the spatial representativity of pyranometer measurement, and to consider drifting clouds from adjacent pixels across the ground station during the averaging interval of 1 hour are taken into account.