• 대한원격탐사학회지
• /
• 제31권4호
• /
• pp.303-319
• /
• 2015

The objectives of this paper are to measure surface imperviousness using three different classification methods: per-pixel, sub-pixel, and object-oriented classification. They are tested on high-spatial resolution QuickBird data at 2.4 meters (four spectral bands and three principal component bands) as well as a medium-spatial resolution Landsat TM image at 30 meters. To measure impervious surfaces, we selected 30 sample sites with different land uses and residential densities across image representing the city of Phoenix, Arizona, USA. For per-pixel an unsupervised classification is first conducted to provide prior knowledge on the possible candidate spectral classes, and then a supervised classification is performed using the maximum-likelihood rule. For sub-pixel classification, a Linear Spectral Mixture Analysis (LSMA) is used to disentangle land cover information from mixed pixels. For object-oriented classification several different sets of scale parameters and expert decision rules are implemented, including a nearest neighbor classifier. The results from these three methods show that the object-oriented approach (accuracy of 91%) provides more accurate results than those achieved by per-pixel algorithm (accuracy of 67% and 83% using Landsat TM and QuickBird, respectively). It is also clear that sub-pixel algorithm gives more accurate results (accuracy of 87%) in case of intensive and dense urban areas using medium-resolution imagery.

• International Journal of Knowledge Content Development & Technology
• /
• 제7권1호
• /
• pp.57-78
• /
• 2017

There are several statistical classification algorithms available for land use/land cover classification. However, each has a certain bias or compromise. Some methods like the parallel piped approach in supervised classification, cannot classify continuous regions within a feature. On the other hand, while unsupervised classification method takes maximum advantage of spectral variability in an image, the maximally separable clusters in spectral space may not do much for our perception of important classes in a given study area. In this research, the output of an ANN algorithm was compared with the Possibilistic c-Means an improvement of the fuzzy c-Means on both moderate resolutions Landsat8 and a high resolution Formosat 2 images. The Formosat 2 image comes with an 8m spectral resolution on the multispectral data. This multispectral image data was resampled to 10m in order to maintain a uniform ratio of 1:3 against Landsat 8 image. Six classes were chosen for analysis including: Dense forest, eucalyptus, water, grassland, wheat and riverine sand. Using a standard false color composite (FCC), the six features reflected differently in the infrared region with wheat producing the brightest pixel values. Signature collection per class was therefore easily obtained for all classifications. The output of both ANN and FCM, were analyzed separately for accuracy and an error matrix generated to assess the quality and accuracy of the classification algorithms. When you compare the results of the two methods on a per-class-basis, ANN had a crisper output compared to PCM which yielded clusters with pixels especially on the moderate resolution Landsat 8 imagery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.426-429
• /
• 2006

Flood caused by Typhoon and severe rain during summer is the most destructive natural disasters in Korea. Almost every year flood has resulted in a big lost of national infrastructure and loss of civilian lives. It usually takes time and great efforts to estimate the flood-related damages. Government also has pursued proper standard and tool for using state-of-art technologies. High resolution satellite imagery is one of the most promising sources of ground truth information since it provides detailed and current ground information such as building, road, and bare ground. Once high resolution imagery is utilized, it can greatly reduce the amount of field work and cost for flood related damage assessment. The classification of high resolution image is pre-required step to be utilized for the damage assessment. The classified image combined with additional data such as DEM and DSM can help to estimate the flooded areas per each classified land use. This paper applied object-oriented classification scheme to interpret an image not based in a single pixel but in meaningful image objects and their mutual relations. When comparing it with other classification algorithms, object-oriented classification was very effective and accurate. In this paper, IKONOS image is used, but similar level of high resolution Korean KOMPSAT series can be investigated once they are available.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권6호
• /
• pp.654-662
• /
• 2010

본 논문은 2단계 연속(cascade) 방법을 이용한 향상된 보행자/비보행자 인식 알고리즘을 제안한다. 인식을 위한 분류기로는 약한 분류기를 강한 분류기로 만드는 아다부스트 알고리즘을 적용하였다. 먼저 두 가지 특징벡터를 추출 한다: (i) 기존의 기울기 히스토그램(HOG) 특성과 (ii) 한 점이 가지는 곡률특성 네 가지를 이용한 곡률-HOG를 제안하고 이용하였다. 그 다음 훈련 영상을 통하여 두 가지의 특징 벡터에 대해 약한 분류기로부터 강한 분류기를 얻었으며, 인식은 입력 영상으로부터 하나의 특징을 선택하여 이미 만들어진 강한 분류기를 통하여 1차적인 인식과 오인식을 실시하며, 오인식된 영상에 대해 2차적인 특징을 투입하여 이에 해당하는 강한 분류기를 통하여 2단계 아다부스트 알고리즘을 적용하여 최종적인 인식결과를 얻는다. 두 가지의 서로 다른 특성 벡터를 이용하여 연속 방법에 의한 2단계 아다부스트 알고리즘을 적용한 결과 기존의 실험 방법보다 더 정확한 인식 결과를 얻을 수 있었다.

• 지능정보연구
• /
• 제12권1호
• /
• pp.33-41
• /
• 2006

본 논문에서는 공장 자동화 시스템의 한 예로, 컨베이어 벨트로 흘러 들어오는 생산품을 모델별로 자동 인식하기 위한 방법을 제안하고 있다. 일반적으로 NTSC 방식의 카메라를 사용할 경우 움직이는 물체는 카메라 고유의 잔상이 발생하게 된다. 잔상이 존재하는 영상을 이용하여 효율적인 처리가 불가능하므로 적당한 후처리 방법이 요구된다. 이를 위하여 제안하는 인터레이스 제거 기법을 통하여 잔상을 제거하고, 이진화를 통하여 대략적 물체 영역을 판별한 후 물체를 에워싸는 직사각형 영역을 구한다. 그 후 윤곽선 검출을 거쳐 직사각형 영역을 블록별로 세분화한 후 각 블록별 화소수를 계산하여 평균을 중심으로 재분류한 후 모델 코드를 생성하여 모델 분류를 하였다. 실험결과 본 논문에서 제안하는 방법의 경우 기존의 방법보다 높은 분류 성공률을 나타내었다.

• 대한본초학회지
• /
• 제21권2호
• /
• pp.175-180
• /
• 2006

Objectives : The difference of delayed luminescence-biophoton emission was investigated in Cervi Pantotrichum Cornu selected randomly. Cervi Pantotrichum Cornu was used as a tonic in Korean medicine. Methods : Randomly selected samples of Cervi Pantotrichum Cornu were radiated with 150 W metal halide lamp for 1 minute. After radiation, biophoton emissions of each sample were detected by electron multiplication(EM)-charge coupled device camera. The detected biophoton image was calculated with unit of counts per pixel. Results : The average biophoton emissions of delayed luminescence with EM ratio of ${\times}l50\;and\;{\times}250$ were distinguished significantly. The maximum biophoton emissions of delayed luminescence with EM ratio of ${\times}250$ were distinguished significantly. Conclusion : These results suggest that biophoton imaging of Cervi Pantotrichum Cornu could become the meaningful method for the study of differentiation and classification of Cervi Pantotrichum Cornu.

• 한국측량학회지
• /
• 제36권5호
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제9권11호
• /
• pp.1435-1444
• /
• 2006

본 논문은 얼굴 영상에서 추출된 특징 값들을 주성분 분석(Principle Component Analysis; 이하 PCA)을 이용하여 재해석하고, 서포트 벡터 머신(Support Vector Machine; 이하 SVM)을 이용한 이진 분류를 통하여 효과적이면서 실시간으로 얼굴을 검출할 수 있는 방법론을 제안한다. 얼굴과 얼굴이 아닌 영상들로 학습데이터를 구성하여, 이 영상들로부터 Haar-like 특징값들을 추출한다. 추출된 다량의 특징 값들 중에 얼굴과 얼굴이 아닌 영역에 대하여 판별 능력이 우수한 특징값들은 PCA를 이용하여 재해석되고 유용한 특징들을 선별한다. 선별된 특징들을 SVM의 입력 차원으로 사용하여 최종 분류기를 학습 및 구성한다. 제안하는 분류기는 학습데이터 집단의 구성에 크게 영향을 받지 않고, 소량의 학습데이터만으로도 90.1%의 만족할만한 얼굴 검출률을 보여주며, $320{\times}240$ 크기의 영상에 대하여 실시간 얼굴 검출에 사용 가능한 초당 8프레임의 처리속도를 보여주었다.