• 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.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.39-52
• /
• 2005

In this paper, a registration method is presented to register partial 3D point clouds, acquired from a multi-view camera, for 3D reconstruction of an indoor environment. In general, conventional registration methods require a high computational complexity and much time for registration. Moreover, these methods are not robust for 3D point cloud which has comparatively low precision. To overcome these drawbacks, a projection-based registration method is proposed. First, depth images are refined based on temporal property by excluding 3D points with a large variation, and spatial property by filling up holes referring neighboring 3D points. Second, 3D point clouds acquired from two views are projected onto the same image plane, and two-step integer mapping is applied to enable modified KLT (Kanade-Lucas-Tomasi) to find correspondences. Then, fine registration is carried out through minimizing distance errors based on adaptive search range. Finally, we calculate a final color referring colors of corresponding points and reconstruct an indoor environment by applying the above procedure to consecutive scenes. The proposed method not only reduces computational complexity by searching for correspondences on a 2D image plane, but also enables effective registration even for 3D points which have low precision. Furthermore, only a few color and depth images are needed to reconstruct an indoor environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.3
• /
• pp.317-327
• /
• 2016

The extraction of significant feature points from a video is directly associated with the suggested method's function. In particular, the occlusion regions in trees or people, or feature points extracted from the background and not from objects such as the sky or mountains are insignificant and can become the cause of undermined matching or recognition function. This paper classifies the feature points required for building recognition by using multi-frames in order to improve the recognition function(algorithm). First, through SIFT(scale invariant feature transform), the primary feature points are extracted and the mismatching feature points are removed. To categorize the feature points in occlusion regions, RANSAC(random sample consensus) is applied. Since the classified feature points were acquired through the matching method, for one feature point there are multiple descriptors and therefore a process that compiles all of them is also suggested. Experiments have verified that the suggested method is competent in its algorithm.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1901-1910
• /
• 2022

Arriving in the new space age, securing technology for fusion application of KOMPSAT-3·3A and global satellite images is becoming more important. In general, multi-sensor satellite images have relative geometric errors due to various external factors at the time of acquisition, degrading the quality of the satellite image outputs. Therefore, we propose a fine-image registration methodology to minimize the relative geometric error between KOMPSAT-3·3A and global satellite images. After selecting the overlapping area between the KOMPSAT-3·3A and foreign satellite images, the spatial resolution between the two images is unified. Subsequently, tie-points are extracted using a hybrid matching method in which feature- and area-based matching methods are combined. Then, fine-image registration is performed through iterative registration based on pyramid images. To evaluate the performance and accuracy of the proposed method, we used KOMPSAT-3·3A, Sentinel-2A, and PlanetScope satellite images acquired over Daejeon city, South Korea. As a result, the average RMSE of the accuracy of the proposed method was derived as 1.2 and 3.59 pixels in Sentinel-2A and PlanetScope images, respectively. Consequently, it is considered that fine-image registration between multi-sensor satellite images can be effectively performed using the proposed method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.911-914
• /
• 2004

본 논문에서는 주어진 영상으로부터 보다 빠르고 효율적인 의미정보 추출을 위하여 블록분할 및 영역구성에 의한 기본영역 및 확장영역을 제안하며, 각 영역들을 구성하는 블록들의 구성관계에 의한 블록탐색 기법도 제안하고 있다. 기본영역은 영상의 중심을 기반으로 구성되는 중심영역과 이웃영역으로 구성되며, 확장영역은 기본영역들의 결합에 의해 생성된다. 블록탐색은 영역을 구성하는 블록간의 구성관계를 기반으로 블록들이 가질 수 있는 특징들의 유사도와 영역정보에 따라 탐색할 수 있는 방법이다. 얼굴추출은 분할된 블록들로부터 피부색상 존재여부를 판별하여 피부색이 존재하는 블록들로부터 얼굴 후보영역들을 획득한 후, 추출된 후보영역들로부터 얼굴을 구성하는 지역적 특성을 비교평가하여 얼굴을 추출할 수 있다. 또한 추출된 얼굴 영역정보는 연속적인 영상이 주어졌을 때, 해당영역들의 블록들에 대한 정합을 통하여 이동경로와 얼굴영역을 탐색할 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.510-515
• /
• 2007

2차원 영상으로부터 3차원 정보를 획득하기 위해서는 disparity map의 정확한 계산이 요구된다. Disparity map을 구하기 위한 기존의 알고리즘은 크게 상관도 기반 방법과 특징 기반 방법으로 분류되는데, 본 논문에서는 이들 각 방법에 대한 분석을 통해서 좀 더 정확한 disparity map을 구하는 방법을 모색한다. 이를 위해 스테레오 카메라로부터 획득된 2차원 영상에서 건물에 대한 깊이 정보 추출을 위해 SIFT 기법을 이용한 disparity map 생성 알고리즘을 제안한다. 제안된 기법은 수정된 MAD인 MMAD(Modified Mean of Absolute Differences) 알고리즘을 새로 제안하여 영역 기반의 유사도 측정을 기반으로 하면서 특징 기반 방법의 하나인 SIFT를 적용하여 거짓 정합(false matching)에 의한 에러를 줄이고 폐색(occlusion) 영역에 대한 오류를 보정한 disparity map을 생성하는데 초점을 둔다.

• Journal of Broadcast Engineering
• /
• v.20 no.1
• /
• pp.153-163
• /
• 2015

This paper proposes a rain detection and removal algorithm that is robust against camera motion in video sequences. In detection part, the proposed algorithm initially detects possible rain streaks by using intensity properties and spatial properties. Then, the rain streak candidates are selected based on Gaussian distribution model. In removal part, a non-rain block matching algorithm is performed between adjacent frames to find similar blocks to the block that has rain pixels. If the similar blocks to the block are obtained, the rain region of the block is reconstructed by non-local means (NLM) filter using the similar neighbors. Experimental results show that the proposed algorithm outperforms the previous works in terms of subjective visual quality of de-rained video sequences.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.1-9
• /
• 2008

In this paper, to extract object regions in stereo image, we propose an enhanced algorithm that extracts objects combining both of brightness information and disparity information. The approach that extracts objects using both has been studied by Ping and Chaohui. In their algorithm, the segmentation for an input image is carried out using the brightness, and integration of segmented regions in consideration of disparity information within the previously segmented regions. In the regions where the brightness values between object regions and background regions are similar, however, the segmented regions probably include both of object regions and background regions. It may cause incorrect object extraction in the merging process executed in the unit of the segmented region. To solve this problem, in proposed method, we adopt the merging process which is performed in pixel unit. In addition, we perform the bi-directional stereo matching process to enhance reliability of the disparity information and supplement the disparity information resulted from a single directional matching process. Further searching for disparity is decided by edge information of the input image. The proposed method gives good performance in the object extraction since we find the disparity information that is not extracted in the traditional methods. Finally, we evaluate our method by experiments for the pictures acquired from a real stereoscopic camera.

• The KIPS Transactions:PartA
• /
• v.11A no.5
• /
• pp.391-400
• /
• 2004

Within multimodal medical image registration techniques, which correlate different images and Provide integrated information, surface registration methods generally minimize the surface distance between two modalities. However, the features of two modalities acquired from one subject are similar. So, it can improve the accuracy of registration result to match two images based on optimization of both surface distance and shape feature. This research proposes a registration method which optimizes surface distance and surface curvature of two brain modalities. The registration process has two steps. First, surface information is extracted from the reference images and the test images. Next, the optimization process is performed. In the former step, the surface boundaries of regions of interest are extracted from the two modalities. And for the boundary of reference volume image, distance map and curvature map are generated. In the optimization step, a transformation minimizing both surface distance and surface curvature difference is determined by a cost function referring to the distance map and curvature map. The applying of the result transformation makes test volume be registered to reference volume. The suggested cost function makes possible a more robust and accurate registration result than that of the cost function using the surface distance only. Also, this research provides an efficient means for image analysis through volume visualization of the registration result.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.453-457
• /
• 2005

3차원 지형공간정보체계에 대한 관심의 증가와 함께 도심지의 3차원 모델링에 관한 다양한 연구가 활발히 진행되고 있다. 단색영상을 용하여 영역기반정합이나 형상기반정합을 실시하던 기존의 3차원 모델링 기법은 오정합이 많이 발생할 수 있으며, 모델링에 소요되는 시간이 많이 걸리는 단점이 있다. 따라서 본 논문에서는 새로운 3D 모델링에 대한 접근법의 하나의 단계로서 컬러영상으로부터 경계정보와 색상정보를 활용하여 동일건물을 인식하는 방법에 대하여 연구를 수행하였다. 경계정보에 대해서는 보완된 Hausdorff 거리 개념을 사용하였으며, 색상정보에 대해서는 수정된 컬러 인덱싱 기법을 사용하였다 IKONOS영상을 사용하여 실험을 실시한 결과 두 가지 정보를 각각 단독으로 사용하는 경우 보다는 두 가지 정보를 조합하여 사용하는 경우 인식이 보다 효과적으로 이루어지는 것을 확인할 수 있었다.