• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1061-1073
• /
• 2017

In this study, images were classified using convolutional neural network (CNN) - a deep learning technique - to investigate the feasibility of information production through a combination of artificial intelligence and spatial data. CNN determines kernel attributes based on a classification criterion and extracts information from feature maps to classify each pixel. In this study, a CNN network was constructed to classify materials with similar spectral characteristics and attribute information; this is difficult to achieve by conventional image processing techniques. A Compact Airborne Spectrographic Imager(CASI) and an Airborne Imaging Spectrometer for Application (AISA) were used on the following three study sites to test this method: Site 1, Site 2, and Site 3. Site 1 and Site 2 were agricultural lands covered in various crops,such as potato, onion, and rice. Site 3 included different buildings,such as single and joint residential facilities. Results indicated that the classification of crop species at Site 1 and Site 2 using this method yielded accuracies of 96% and 99%, respectively. At Site 3, the designation of buildings according to their purpose yielded an accuracy of 96%. Using a combination of existing land cover maps and spatial data, we propose a thematic environmental map that provides seasonal crop types and facilitates the creation of a land cover map.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• Journal of Korean Society of Rural Planning
• /
• v.30 no.1
• /
• pp.57-66
• /
• 2024

This study aimed to develop a precise vegetation cover classification model for small streams using the combination of drone remote sensing and support vector machine (SVM) techniques. The chosen study area was the Idong stream, nestled within Geosan-gun, Chunbuk, South Korea. The initial stage involved image acquisition through a fixed-wing drone named ebee. This drone carried two sensors: the S.O.D.A visible camera for capturing detailed visuals and the Sequoia+ multispectral sensor for gathering rich spectral data. The survey meticulously captured the stream's features on August 18, 2023. Leveraging the multispectral images, a range of vegetation indices were calculated. These included the widely used normalized difference vegetation index (NDVI), the soil-adjusted vegetation index (SAVI) that factors in soil background, and the normalized difference water index (NDWI) for identifying water bodies. The third stage saw the development of an SVM model based on the calculated vegetation indices. The RBF kernel was chosen as the SVM algorithm, and optimal values for the cost (C) and gamma hyperparameters were determined. The results are as follows: (a) High-Resolution Imaging: The drone-based image acquisition delivered results, providing high-resolution images (1 cm/pixel) of the Idong stream. These detailed visuals effectively captured the stream's morphology, including its width, variations in the streambed, and the intricate vegetation cover patterns adorning the stream banks and bed. (b) Vegetation Insights through Indices: The calculated vegetation indices revealed distinct spatial patterns in vegetation cover and moisture content. NDVI emerged as the strongest indicator of vegetation cover, while SAVI and NDWI provided insights into moisture variations. (c) Accurate Classification with SVM: The SVM model, fueled by the combination of NDVI, SAVI, and NDWI, achieved an outstanding accuracy of 0.903, which was calculated based on the confusion matrix. This performance translated to precise classification of vegetation, soil, and water within the stream area. The study's findings demonstrate the effectiveness of drone remote sensing and SVM techniques in developing accurate vegetation cover classification models for small streams. These models hold immense potential for various applications, including stream monitoring, informed management practices, and effective stream restoration efforts. By incorporating images and additional details about the specific drone and sensors technology, we can gain a deeper understanding of small streams and develop effective strategies for stream protection and management.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.179-197
• /
• 2020

Topographic normalization reduces the terrain effects on reflectance by adjusting the brightness values of the image pixels to be equal if the pixels cover the same land-cover. Topographic effects are induced by the imaging conditions and tend to be large in high mountainousregions. Therefore, image analysis on mountainous terrain such as estimation of wildfire damage assessment requires appropriate topographic normalization techniques to yield accurate image processing results. However, most of the previous studies focused on the evaluation of topographic normalization on satellite images with moderate-low spatial resolution. Thus, the alleviation of topographic effects on multi-temporal high-resolution images was not dealt enough. In this study, the evaluation of terrain normalization was performed for each band to select the optimal technical combinations for rapid and accurate wildfire damage assessment using PlanetScope images. PlanetScope has considerable potential in the disaster management field as it satisfies the rapid image acquisition by providing the 3 m resolution daily image with global coverage. For comparison of topographic normalization techniques, seven widely used methods were employed on both pre-fire and post-fire images. The analysis on bi-temporal images suggests the optimal combination of techniques which can be applied on images with different land-cover composition. Then, the vegetation index was calculated from the images after the topographic normalization with the proposed method. The wildfire damage detection results were obtained by thresholding the index and showed improvementsin detection accuracy for both object-based and pixel-based image analysis. In addition, the burn severity map was constructed to verify the effects oftopographic correction on a continuous distribution of brightness values.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.285-291
• /
• 2020

In manufacturing, humans are being replaced with robots, but expert skills remain difficult to convert to data, making them difficult to apply to industrial robots. One method is by visual motion recognition, but physical features may be judged differently depending on the image data. This study aimed to improve the accuracy of vision methods for estimating the posture of humans. Three OpenPose vision models were applied: MPII, COCO, and COCO+foot. To identify the effects of face-covering accessories and image preprocessing on the Convolutional Neural Network (CNN) structure, the presence/non-presence of accessories, image size, and filtering were set as the parameters affecting the identification of a human's posture. For each parameter, image data were applied to the three models, and the errors between the actual and predicted values, as well as the percentage correct keypoints (PCK), were calculated. The COCO+foot model showed the lowest sensitivity to all three parameters. A <50% (from 3024×4032 to 1512×2016 pixels) reduction in image size was considered acceptable. Emboss filtering, in combination with MPII, provided the best results (reduced error of <60 pixels).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.1C
• /
• pp.55-64
• /
• 2006

In this paper, a new web-based remote 3D imaging communication system employing an adaptive matching algorithm is suggested. In the proposed method, feature values are extracted from the stereo image pair through estimation of the disparity and similarities between each pixel of the stereo image. And then, the matching window size for disparity estimation is adaptively selected depending on the magnitude of this feature value. Finally, the detected disparity map and the left image is transmitted into the client region through the network channel. And then, in the client region, right image is reconstructed and intermediate views be synthesized by a linear combination of the left and right images using interpolation in real-time. From some experiments on web based-transmission in real-time and synthesis of the intermediate views by using two kinds of stereo images of 'Joo' & 'Hoon' captured by real camera, it is analyzed that PSNRs of the intermediate views reconstructed by using the proposed transmission scheme are highly measured by 30dB for 'Joo', 27dB for 'Hoon' and the delay time required to obtain the intermediate image of 4 view is also kept to be very fast value of 67.2ms on average, respectively.

• The Korean Journal of Nuclear Medicine
• /
• v.28 no.2
• /
• pp.172-176
• /
• 1994

As the Tc-99m-MIBI myocardial SPECT demonstrated wide application in the diagnosis of myocardial function, the quantitative and severity-dependent information is currently re quired. In this study, we proposed a computerized method for scoring the fixed defects in terms of extent-weighted severity and for identifying the reversibility in ischemic regions. At the first stage of this method, the transverse slices were reconstructed with 0.4 Nyquist freq. and order 5 Butterworth filter. From the oblique/sagittal slices, maximal count per pixel circumferential profiles were extracted for each sector, and then stress/redist. polar maps were normalized and plotted. For reversibility, the stress polar map was subtracted from the de-layed image and positive-valued pixels were categorized into three grades. The extent-weight-ed severity scores were calculated using the assigned grades and their number of pixels. This procedure was done automatically and the reversibility and severity scores were produced for each of the coronary territories (LAD, RCA, LCX) or any combination of these. Clinical ap-plication has shown that the changes In reversibility scores after PTCA were correlated linearly with the pre PTCA scores(r>0.8) in postinfarct cases as well as in angina, and severity scores of persistent defects in stress/rest SPECT study matched to the regional ejection fraction and visual analysis of regional wall motion of gated blood pool scan(r>0.6). We conclude that the computerized severity scoring method for the analysis of myocardial SPECT could be useful in the assessment of the myocardial ischemia and fixed defect.

• Journal of Broadcast Engineering
• /
• v.15 no.4
• /
• pp.474-486
• /
• 2010

In this paper, we propose a new method for detection moving object contour using spatial and temporal edge. In general, contour pixels of the moving object are likely present around pixels with high gradient value along the time axis and the spatial axis. Therefore, we can detect the contour of the moving objects by finding pixels which have high gradient value in the time axis and spatial axis. In this paper, we introduce a new computation method, termed as temporal edge, to compute an gradient value along the time axis for any pixel on an image. The temporal edge can be computed using two input gray images at time t and t-2 using the Sobel operator. Temporal edge is utilized to detect a candidate region of the moving object contour and then the detected candidate region is used to extract spatial edge information. The final contour of the moving object is detected using the combination of these two edge information, which are temporal edge and spatial edge, and then the post processing such as a morphological operation and a background edge removing procedure are applied to remove noise regions. The complexity of the proposed method is very low because it dose not use any background scene and high complex operation, therefore it can be applied to real-time applications. Experimental results show that the proposed method outperforms the conventional contour extraction methods in term of processing effort and a ghost effect which is occurred in the case of entropy method.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.768-779
• /
• 2018

In this paper, we propose a novel video quality function for video processing based on MSSSIM to select an appropriate video processing filter and to accommodate multiple processing filters to each pixel block in a picture frame by a mathematical selection law so as to maintain video quality and to reduce the bitrate of compressed video. In viewpoint of video compression, since the properties of video quality and bitrate is different for each picture of video frames and for each areas in the same frame, it is difficult for the video filter with single property to satisfy the object of increasing video quality and decreasing bitrate. Consequently, to maintain the subjective video quality in spite of decreasing bitrate, we propose the methodology about the MSSSIM as the measure of subjective video quality, the KL-Divergence as the measure of bitrate, and the combination method of those two measurements. Moreover, using the proposed combinatorial measurement, when we use the multiple image filters with mutually different properties as a pre-processing filter for video, we can verify that it is possible to compress video with maintaining the video quality under decreasing the bitrate, as possible.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.129-143
• /
• 2023

In the era of big data, the field of artificial intelligence is showing remarkable growth, and in particular, the image classification learning methods by deep learning are becoming an important area. Various studies have been actively conducted to further improve the performance of CNNs, which have been widely used in image classification, among which a representative method is the Convolutional Recurrent Neural Network (CRNN) algorithm. The CRNN algorithm consists of a combination of CNN for image classification and RNNs for recognizing time series elements. However, since the inputs used in the RNN area of CRNN are the flatten values extracted by applying the convolution and pooling technique to the image, pixel values in the same phase in the image appear in different order. And this makes it difficult to properly learn the sequence of arrangements in the image intended by the RNN. Therefore, this study aims to improve image classification performance by proposing a novel hybrid method of CNN and RNN applying the concepts of encoder and decoder. In this study, the effectiveness of the new hybrid method was verified through various experiments. This study has academic implications in that it broadens the applicability of encoder and decoder concepts, and the proposed method has advantages in terms of model learning time and infrastructure construction costs as it does not significantly increase complexity compared to conventional hybrid methods. In addition, this study has practical implications in that it presents the possibility of improving the quality of services provided in various fields that require accurate image classification.