• 인터넷정보학회논문지
• /
• 제24권4호
• /
• pp.85-92
• /
• 2023

X-ray, Computed Tomography (CT), Magnetic Resonance Imaging (MRI)과 같은 의료데이터에서 딥러닝을 활용해 질병 유무 판별 태스크와 같은 문제를 해결하려는 시도가 활발하다. 대부분의 데이터 기반 딥러닝 문제들은 높은 정확도 달성과 정답과 비교하는 성능평가의 활용을 위해 지도학습기법을 사용해야 한다. 지도학습에는 다량의 이미지와 레이블 세트가 필요하지만, 학습에 충분한 양의 의료 이미지 데이터를 얻기는 어렵다. 다양한 데이터 증강 기법을 통해 적은 양의 의료이미지와 레이블 세트로 지도학습 기반 모델의 과소적합 문제를 극복할 수 있다. 본 연구는 딥러닝 기반 갈비뼈 골절 세그멘테이션 모델의 성능 향상과 효과적인 좌우 반전, 회전, 스케일링 등의 데이터 증강 기법을 탐색한다. 좌우 반전과 30° 회전, 60° 회전으로 증강한 데이터셋은 모델 성능 향상에 기여하지만, 90° 회전 및 ⨯0.5 스케일링은 모델 성능을 저하한다. 이는 데이터셋 및 태스크에 따라 적절한 데이터 증강 기법의 사용이 필요함을 나타낸다.

• International journal of advanced smart convergence
• /
• 제6권4호
• /
• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• 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.

• 대한원격탐사학회지
• /
• 제24권1호
• /
• pp.1-16
• /
• 2008

Steam and advection fogs are frequently observed in the Yellow Sea from March to July except for May. This study uses remote sensing (RS) data for the monitoring of sea fog. Meteorological data obtained from the Ieodo Ocean Research Station provided a valuable information for the occurrence of steam and advection fogs as a ground truth. The RS data used in this study were GOES-9, MTSAT-1R images and QuikSCAT wind data. A dual channel difference (DCD) approach using IR and shortwave IR channel of GOES-9 and MTSAT-1R satellites was applied to detect sea fog. The results showed that DCD, texture-related measurement and the weak wind condition are required to separate the sea fog from the low cloud. The QuikSCAT wind data was used to provide the wind speed criteria for a fog event. The laplacian computation was designed for a measurement of the homogeneity. A new combined method, which includes DCD, QuikSCAT wind speed and laplacian computation, was applied to the twelve cases with GOES-9 and MTSAT-1R. The threshold values for DCD, QuikSCAT wind speed and laplacian are -2.0 K, $8m\;s^{-1}$ and 0.1, respectively. The validation results showed that the new combined method slightly improves the detection of sea fog compared to DCD method: improvements of the new combined method are $5{\sim}6%$ increases in the Heidke skill score, 10% decreases in the probability of false detection, and $30{\sim}40%$ increases in the odd ratio.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.50-58
• /
• 2013

Estimating a driver's head pose is an important task in driver-assistance systems because it can provide information about where a driver is looking, thereby giving useful cues about the status of the driver (i.e., paying proper attention, fatigued, etc.). This study proposes a system for estimating the head pose using monocular images, which includes a novel use of backprojection. The system can use a single image to estimate a driver's head pose at a particular time stamp, or an image sequence to support the analysis of a driver's status. Using our proposed system, we compared two previous pose estimation approaches. We introduced an approach for providing ground-truth reference data using a mannequin model. Our experimental results demonstrate that the proposed system provides relatively accurate estimations of the yaw, tilt, and roll angle. The results also show that one of the pose estimation approaches (perspective-n-point, PnP) provided a consistently better estimate compared to the other (pose from orthography and scaling with iterations, POSIT) using our proposed system.

• 한국환경과학회지
• /
• 제26권4호
• /
• pp.543-547
• /
• 2017

Normalized Difference Vegetation Index (NDVI) has played an important role in assessing green plant biomass through remote sensing on global scale since the early 1970s. The concept of NDVI is based on the fact that green plants show higher reflection in near-infrared region than in visible region of the electromagnetic spectrum. However, it is well known that the relocation of chloroplasts in plant leaf cells may dramatically change the optical properties of plant leaves. In this study I traced the changes in the reflectance and transmittance properties of Tobacco leaves at the wavelengths of 660 and 800 nm after a sudden increase in light intensity. The results showed that NDVI of leaves gradually decreased from 72.7% to 69.9% when exposed to a sudden increase in light intensity from 30 to $1,200{\mu}mol/m^2{\cdot}s$. This means that the error resulting from the physiological status of the plant should be accounted for a more precise understanding of ground truth corresponding to the data from the remotely acquired images.

• 한국통신학회논문지
• /
• 제38B권8호
• /
• pp.615-622
• /
• 2013

페이로드 시그니쳐 기반 분석 방법에서 정확한 시그니쳐는 분석 성능을 높이는데 있어 필수적이다. 하지만 정확한 시그니쳐를 생성하기 위한 수동생성 방법에는 한계가 있다. 따라서 이를 극복 하기 위해 페이로드 시그니쳐를 자동생성하기 위한 페이로드 시그니쳐 자동 생성 시스템을 제안한다. 또한 프로토콜 필터를 이용한 응용의 프로토콜 인식을 통해 시그니쳐 자동 생성의 효율성을 향상 시키고, 프로토콜 별 응용의 페이로드 시그니쳐를 자동 생성하여 세분화된 분석에 적용 할 수 있는 페이로드 시그니쳐 자동 생성 방법을 제안하였다. 본 논문에서 제안한 시스템의 타당성을 검증하기 위해 수동 생성 시그니쳐와 자동 생성 시그니쳐의 비교 및 프로토콜 별 자동 생성 시그니쳐를 통해 시스템의 타당성을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2075-2092
• /
• 2017

Person re-identification is to match pedestrians observed from non-overlapping camera views. It has important applications in video surveillance such as person retrieval, person tracking, and activity analysis. However, it is a very challenging problem due to illumination, pose and viewpoint variations between non-overlapping camera views. In this work, we propose a viewpoint invariant method for matching pedestrian images using orientation of pedestrian. First, the proposed method divides a pedestrian image into patches and assigns angle to a patch using the orientation of the pedestrian under the assumption that a person body has the cylindrical shape. The difference between angles are then used to compute the similarity between patches. We applied the proposed method to real-time global multi-object tracking across multiple disjoint cameras with non-overlapping field of views. Re-identification algorithm makes global trajectories by connecting local trajectories obtained by different local trackers. The effectiveness of the viewpoint invariant method for person re-identification was validated on the VIPeR dataset. In addition, we demonstrated the effectiveness of the proposed approach for the inter-camera multiple object tracking on the MCT dataset with ground truth data for local tracking.

• ETRI Journal
• /
• 제21권4호
• /
• pp.41-51
• /
• 1999

This research is an attempt to obtain more accurate land cover information from LANDSAT images. Canonical correlation analysis, which has not been widely used in the image classification community, was applied to the classification of a LANDSAT images. It was found that it is easy to select training areas on the classification using canonical correlation analysis in comparison with the maximum likelihood classifier of $ERDAS^{(R)}$ software. In other words, the selected positions of training areas hardly affect the classification results using canonical correlation analysis. when the same training areas are used, the mapping accuracy of the canonical correlation classification results compared with the ground truth data is not lower than that of the maximum likelihood classifier. The kappa analysis for the canonical correlation classifier and the maximum likelihood classifier showed that the two methods are alike in classification accuracy. However, the canonical correlation classifier has better points than the maximum likelihood classifier in classification characteristics. Therefore, the classification using canonical correlation analysis applied in this research is effective for the extraction of land cover information from LANDSAT images and will be able to be put to practical use.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.135-145
• /
• 2020

Recently, deep-learning based methods for low-light image enhancement accomplish great success through supervised learning. However, they still suffer from the lack of sufficient training data due to difficulty of obtaining a large amount of low-/normal-light image pairs in real environments. In this paper, we propose an unsupervised learning approach for single low-light image enhancement using the bright channel prior (BCP), which gives the constraint that the brightest pixel in a small patch is likely to be close to 1. With this prior, pseudo ground-truth is first generated to establish an unsupervised loss function. The proposed enhancement network is then trained using the proposed unsupervised loss function. To the best of our knowledge, this is the first attempt that performs a low-light image enhancement through unsupervised learning. In addition, we introduce a self-attention map for preserving image details and naturalness in the enhanced result. We validate the proposed method on various public datasets, demonstrating that our method achieves competitive performance over state-of-the-arts.