• 한국농공학회지
• /
• 제45권5호
• /
• pp.77-84
• /
• 2003

Recent advances in remote sensing techniques provide the potential for monitoring soil color as well as soil moisture conditions at the spatial and temporal scales required for detailed local modeling efforts. Soil moisture as well as soil color is a key feature used in the identification and classification of soils. Soil spectral reflectance has a direct relationship with soil color, as well as to other parameters such as soil moisture, soil texture. and organic matter. We evaluate the influence of seven soil properties, soil color and soil moisture, on soil spectral reflectance. This paper presents the results obtained from the ground-truth spectral reflectance measurements in the 300-1100 nm wavelength range for various land surfaces. The results suggest that the reflectance properties of soils are related to soil color, soil texture, and soil moisture. Increasing soil moisture content generally decreases soil reflectance which leads to parallel curves of soil reflectance spectra across the entire shortwave spectrum. We discuss the relationships between the soil reflectance and the Munsell Soil Color Charts which contain standard color chips with colors specified by designations for hue, value, and chroma.

• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.481-489
• /
• 2020

Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.

• 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.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 2005년도 학술발표회 논문집
• /
• pp.68-73
• /
• 2005

In succession of the previous works, seismo-acoustic analysis was conducted to collect ground truth events and to discriminate surface explosions from natural earthquakes in the Korean Peninsula for 2004. In this period, total 510 seismo-acoustic events corresponding to 10.8 percent of total seismic events occurred in and near the Korean Peninsula were analyzed and discriminated as artificial surface explosions. Events distribution of the seismo-acoustic events in 2004 is similar to the previous results of 1999-2003. And newly determined seismo-acoustic events were added to the surface explosions database. To extend infrasound detection capability, Korea Institute of Geoscience and Mineral Resources (KIGAM) and Southern Methodist University (SMU) installed new seismo-acoustic array (BRDAR) in Baekryoung Island last November, 2004. The array configuration and design is nearly same to previous seismo-acoustic arrays CHNAR, KSGAR, a triangular 1 km aperture. BRDAR consists of 5 short period vertical seismometers (GS-13) in seismic vaults and 13 microbarometers (Chaparral Model 2). Preliminary analysis using data collected from BRDAR shows an extension of infrasound detection capability to western part of the Korean Peninsula. Also, multiple observations of infrasound at BRDAR and other arrays gave an opportunity to localize sound source regions.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1509-1518
• /
• 2015

Because a logo is a medium that connects between consumers and corporations or brands, designing memorable logo images is vital. Although predicting logo's memorability for brand marketing is essential, there have been only few researches that deal with memorability of logo images. In this paper, we analyze the memorability characteristics in logo images by performing experiments based upon our proposed prediction method for logo image's memorability. Our proposed research consists of three phases: crowdsourcing for memorability computing, computational phase for logo image's memorability, and development of a prediction model. Using computed memorability of logo images by "Visual Memory Game," we analyze the different characteristics of logo's memorability. We first developed a novel computational method that reflects logo image's color and shape. Each computational method on color and shape are selected by comparing the correlations between result values and ground truth memorability. Selected computational value is then converged with generic image feature descriptors such as SIFT and HoG to make a prediction model of logo's memorability. Using our method, we obtain reasonable performances in predicting logo image's memorability.

• 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.

• 방송공학회논문지
• /
• 제16권2호
• /
• pp.247-257
• /
• 2011

본 논문에서는 장면의 밝기에 적합한 셔터 속도를 가진 두 장의 LDR (low dynamic range) 영상을 취득하여 HDR (high dynamic range) 영상을 고속으로 생성하는 효율적인 기법을 제안한다. 즉, 장면의 밝기에 최적인 HDR 영상을 취득하기 위해 본 논문에서는 오직 두 장의 초기 입력 LDR 영상을 이용하여 장면의 밝기에 대한 노출 곡선을 초기 추정한 후, 장면의 밝기 변화에 따른 최적의 셔터 속도를 시간 변화에 따라 지속적으로 추정하는 기법을 제안한다. 성능 평가를 위해 기존의 고화질 HDR 기법으로 생성한 영상과 제안된 방법으로 취득된 영상간의 유사도를 PSNR (peak signal to noise ratio)로 비교하였으며, 모든 두 장의 조합을 탐색하지 않고도 최적에 근사하는 두 개의 셔터 속도를 얻을 수 있음을 보인다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2012년도 하계학술대회
• /
• pp.83-86
• /
• 2012

본 논문에서는 다양한 변이 추정 방식 중 영역기반(Area-based) 알고리듬과 특정기반(Feature-based) 알고리듬을 결합한 하이브리드(Hybrid) 변이추정 알고리듬을 제안한다. 제안하는 알고리듬은 Features from Accelerated Segment Test(FAST) 코너 점 추출기[2]를 이용하여 좌, 우 영상 각각의 특징 점을 추출한 후, 특징 점들의 정보를 이용한 스테레오 정함을 통해 신뢰도 높은 초기 변이지도(Disparity map)를 생생하게 된다. 그러나 생성된 초기 변이지도는 조밀하지 못하므로, 조밀한 변이 지도를 획득하기 위해 특징점이 추출된 영역에 대해서는 추정된 초기 변이 값을 이웃 픽셀과의 색 유사도를 고려하여 전파시키고 특징 점이 추출되지 않은 영역에 대해서는 이진 윈도우(Binary window)를 활용한 영역기반 변이추정 알고리듬[1]을 이용하여 변이 값을 추정한다. 이를 통해, 제안 알고리듬은 특징 기반 알고리듬에서 발생할 수 있는 보간법 문제를 해결함과 동시에 신뢰도가 높은 초기 변이지도를 사용함으로써, 영역 기반 알고리듬의 정합 오차를 줄여 신뢰도 높은 변이지도를 생생할 수 있다. 실험 결과 추정된 초기 변이지도는 ground truth와 비교 시 약 99%이상의 정확도를 보이며, 특징 점이 추출된 영역에서 기존의 영역기반 알고리듬보다 더 정확한 변이 값이 추정되었음을 확인하였다.

• 환경영향평가
• /
• 제11권4호
• /
• pp.231-238
• /
• 2002

In this study we classified sediment types of tidal flat using Landsat-5 images. This is for groping the method which can analyze correctly various kinds of sediment faces through satellite images. This work was performed by referencing ground truth of sediment faces which was investigated in the field. With this data we classified Landsat-5 image of 1997's to grope a most suitable classification method. As a result, in case of south Kanghwa island area, it was the optimum way to compound band 4, 5, 7 of Landsat-5 TM imagery. And, this work classified 3 kinds of sediment faces - M(mud), sM(sandy mud) and (g)M(slightly gravelly mud) - in land and mixed water area. It is anticipated that if this method is applied to a image of extremely lower sea level time, it can classify the sediment types of a broad tidal flat area. This is expected to be a beginning of estimating the effect of sediment faces to the change of the tidal flat ecosystem.