• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Korean Journal of Remote Sensing
• /
• v.31 no.3
• /
• pp.255-265
• /
• 2015

Very high resolution (VHR) satellite imagery provide valuable information on urban change monitoring due to multi-temporal observation over large areas. Recently, there has been increased interest in the urban change detection technique using VHR Synthetic Aperture Radar (SAR) imaging system, because it can take images regardless of solar illumination and weather condition. In this paper, we proposed a texture-based urban change detection method using the VHR SAR texture features generated from Gray-Level Co-Occurrence Matrix (GLCM). In order to evaluate the efficiency of the proposed method, the result was compared, visually and quantitatively, with the result of Non-Coherent Change Detection (NCCD) which is widely used for the change detection of VHR SAR image. The experimental results showed the greater detection accuracy and the visually satisfactory result compared with the NCCD method. In conclusion, the proposed method has shown a great potential for the extraction of urban change information from VHR SAR imagery.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1389-1403
• /
• 2021

Disaster management using VHR (very high resolution) satellite images supports rapid damage assessment and also offers detailed information of the damages. However, the acquisition of pre-event VHR satellite images is usually limited due to the long revisit time of VHR satellites. The absence of the pre-event data can reduce the accuracy of damage assessment since it is difficult to distinguish the changed region from the unchanged region with only post-event data. To address this limitation, in this study, we conducted the wildfire-induced change detection on national wildfire cases using post-fire VHR satellite images and GIS (Geographic Information System) data. For GIS data, a national land cover map was selected to simulate the pre-fire NIR (near-infrared) images using the spatial information of the pre-fire land cover. Then, the simulated pre-fire NIR images were used to analyze bi-temporal NDVI (Normalized Difference Vegetation Index) correlation for unsupervised change detection. The whole process of change detection was performed on a superpixel basis considering the advantages of superpixels being able to reduce the complexity of the image processing while preserving the details of the VHR images. The proposed method was validated on the 2019 Gangwon wildfire cases and showed a high overall accuracy over 98% and a high F1-score over 0.97 for both study sites.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.2
• /
• pp.63-69
• /
• 2013

Change detection technique is essential to various applications of Very High-Resolution(VHR) satellite imagery and land monitoring. However, change detection accuracy of VHR satellite imagery can be decreased due to various geometrical dissimilarity. In this paper, the existing fusion evaluation indexes were revised and applied to improve VHR imagery based change detection accuracy between multi-temporal images. In addition, appropriate change detection methodology of VHR images are proposed through comparison of general change detection algorithm with cross-sharpened image based change detection algorithm. For these purpose, ERGAS, UIQI and SAM, which were representative fusion evaluation index, were applied to unsupervised change detection, and then, these were compared with CVA based change detection result. Methodologies for minimizing the geometrical error of change detection algorithm are analyzed through evaluation of change detection accuracy corresponding to image fusion method, also. The experimental results are shown that change detection accuracy based on ERGAS index by using cross-sharpened images is higher than these based on other estimation index by using general fused image.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.3
• /
• pp.125-132
• /
• 2017

Even after applying an image registration, Very High Resolution (VHR) multi-temporal images acquired from different optical satellite sensors such as IKONOS, QuickBird, and Kompsat-2 show a local misalignment due to dissimilarities in sensor properties and acquisition conditions. As the local misalignment, also referred to as Registration Noise (RN), is likely to have a negative impact on multi-temporal information extraction, detecting and reducing the RN can improve the multi-temporal image processing performance. In this paper, an approach to fine registration between VHR multi-temporal images by considering local distribution of RN is proposed. Since the dominant RN mainly exists along boundaries of objects, we use edge information in high frequency regions to identify it. In order to validate the proposed approach, datasets are built from VHR multi-temporal images acquired by optical satellite sensors. Both qualitative and quantitative assessments confirm the effectiveness of the proposed RN-based fine registration approach compared to the manual registration.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.109-118
• /
• 2019

Road information is one of the most significant geospatial data for applications such as transportation, city planning, map generation, LBS (Location-Based Service), and GIS (Geographic Information System) database updates. Robust technologies to acquire and update accurate road information can contribute significantly to geospatial industries. In this study, we analyze the limitations of ACO (Ant Colony Optimization) road extraction, which is a recently introduced object-based road extraction method using high-resolution satellite images. Object-based ACO road extraction can efficiently extract road areas using both spectral and morphological information. This method, however, is highly dependent on object descriptor information and requires manual designations of descriptors. Moreover, reasonable iteration closing point needs to be specified. In this study, we perform improved ACO road extraction on VHR (Very High Resolution) optical satellite image by proposing an optimization stopping criteria and descriptors that complements the limitations of the existing method. The proposed method revealed 52.51% completeness, 6.12% correctness, and a 51.53% quality improvement over the existing algorithm.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.481-489
• /
• 2019

Change detection, one of the main applications of multi-temporal satellite images, is an indicator that directly reflects changes in human activity. Change detection can be divided into pixel-based change detection and object-based change detection. Although pixel-based change detection is traditional method which is mostly used because of its simple algorithms and relatively easy quantitative analysis, applying this method in VHR (Very High Resolution) images cause misdetection or noise. Because of this, pixel-based change detection is less utilized in VHR images. In addition, the sensor of acquisition or geographical characteristics bring registration noise even if co-registration is conducted. Registration noise is a barrier that reduces accuracy when extracting spatial information for utilizing VHR images. In this study object-based change detection of VHR images was performed considering registration noise. In this case, object-based change detection results were derived considering various pixel-based change detection methods, and the major voting technique was applied in the process with segmentation image. The final object-based change detection result applied by the proposed method was compared its performance with other results through reference data.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.387-396
• /
• 2024

Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms,such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically,we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_4
• /
• pp.1341-1350
• /
• 2019

This research deals with algorithm for forest fire severity classification using multi-temporal KOMPSAT-3A image to mapping forest fire areas. The recent satellite of the KOMPSAT series, KOMPSAT-3A, demonstrates high resolution and multi-spectral imagery with infrared and high resolution electro-optical bands. However, there is a lack of research to classify forest fire severity using KOMPSAT-3A. Therefore, the purpose of this study is to analyze forest fire severity using KOMPSAT-3A images. In addition, this research used pre-fire and post-fire Sentinel-2 with differenced Normalized Burn Ratio (dNBR) to taking for burn severity distribution map. To test the effectiveness of the proposed procedure on April 4, 2019, Gangneung wildfires were considered as a case study. This research used the probability density function for the classification of forest fire damage severity based on R software, a free software environment of statistical computing and graphics. The burn severities were estimated by changing NDVI before and after forest fire. Furthermore, standard deviation of probability density function was used to calculate the size of each class interval. A total of five distribution of forest fire severity were effectively classified.