• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.142-152
• /
• 2019

There is growing interest in ultra-high-resolution content that gives a more realistic sense of presence than existing broadcast content. However, in order to provide ultra-high-resolution contents in existing broadcast services, there are limitations in view angle and resolution of the image acquisition device. In order to solve this problem, many researches on stitching, which is an image synthesis method using a plurality of input devices, have been conducted. In this paper, we propose method of dynamic object based video stitching using minimal error seam in order to overcome the temporal invariance degradation of moving objects in the stitching process of horizontally oriented videos.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.298-303
• /
• 2014

In this paper, we proposed a robust object extraction and tracking algorithm in the IR image sequence acquired in the sea environment. In order to extract size-invariant object, we detect horizontal and vertical edges by using DWT and combine it to generate saliency map. To extract object region, binarization technique is applied to saliency map. The correspondences between objects in consecutive frames are defined by the calculating minimum weighted Euclidean distance as a matching measure. Finally, object trajectories are determined by considering false correspondences such as entering object, vanishing objects and false object and so on. The proposed algorithm can find trajectories robustly, which has shown by experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.12
• /
• pp.1465-1474
• /
• 1992

This paper describes a new overlapped object recognition method using extended local features. At first, we extract the extended local features consisting of corners, arcs, parallel-lines, and corner-arcs from the images consisting of model objects. Based on the extended local features we construct a knowledge-base. In order to match objects, we also extract the extended local features from the input image, and then check the compatibility between the extracted features and the features in the knowledge-base. From the set of compatible features, we compute geometric transforms. If any geometric transforms are clustered, we generate the hypothesis of the objects as the centers of the clusters, and then verify the hypothesis by a reverse geometric transform. An experiment shows that the proposed method increases the recognition rate and the accuracy as compared with existing methods.

• The Journal of the Acoustical Society of Korea
• /
• v.12 no.2
• /
• pp.51-59
• /
• 1993

본 논문에서는 입력으로 들어 온 레인지데이타에서 특징 추출을 통하여 3차원물체를 식별하는 방법을 제안하고자 한다. Z축 기울기를 이용하여 형상특징을 추출하고, 각 표면조각에서 법선벡터를 구해 기하학적 특징을 추출한다. 그 후 위에서 구한 특징들을 퍼지화데이타로 만들어 일치도 연산에 의해 표준 물체와 입력화상 물체 사이의 정합을 수행한다. 최종적으로 본 논문의 유용성을 실험에 의해 입증하고자 한다.

• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.589-591
• /
• 2000

비디오 데이터가 포함하고 있는 카메라와 이동물체의 동작정보를 추출하기 위한 대표적인 방법으로 동작벡터 추출알고리즘이 있다. 본 논문에서는 영상 내에 밝기 값 분포가 균일한 영역이 존재할 때 부정확한 정합 결과를 보이는 것은 기존 알고리즘의 문제점과 이를 개선할 수 있는 계층적 블록정합 알고리즘의 정합오류 전파가능성, 높은 시간복잡도 문제를 동시에 해결할 수 있는 블록정합 알고리즘을 제안한다. 제안하는 알고리즘은 Coarse-to-Fine 방식의 탐색방법과 Dynamic Control Strategy를 결합한 것으로서 정합한 블록의 상황에 따라 탐색 레이어를 동적으로 변경시키는 방법을 사용한다. 본 알고리즘은 크게 두단계로 나뉘어 지는데 탐색 레이어를 결정하는 Control 변경 결정 단계와 정합도 측정함수를 통해 블록에 대한 정합 정확도를 측정하는 단계로 구성이 된다.

• 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 Journal of Information Technology
• /
• v.7 no.4
• /
• pp.1-8
• /
• 2004

The depth information of 3D image lost by projecting 3D-object to 2D-screen for earning image. If depth information is restored and is used to recognize 3D-object, we can make the more effective recognition system. We often use shape from stereo algorithm in order to restore this information. In this paper, we suggest 3-D object recognition system in which the 3-D Hough transform domain is employed to represent the 3-D objects. In this system, we use the moving vector of object to reduce matching time and In second matching step, the unknown input image is compared with the reference images, which is made with octree codes. Octree codes are used in volume-based representation of a three dimensional object. The result of simulation show that the proposed 3-D object recognition system provides satisfactory performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.2
• /
• pp.69-76
• /
• 2018

Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a new deep neural network model for referring expression comprehension. The proposed model finds out the region of the referred object in the given image by making use of the rich information about the referred object itself, the context object, and the relationship with the context object mentioned in the referring expression. In the proposed model, the object matching score and the relationship matching score are combined to compute the fitness score of each candidate region according to the structure of the referring expression sentence. Therefore, the proposed model consists of four different sub-networks: Language Representation Network(LRN), Object Matching Network (OMN), Relationship Matching Network(RMN), and Weighted Composition Network(WCN). We demonstrate that our model achieves state-of-the-art results for comprehension on three referring expression datasets.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.269-272
• /
• 2009

본 논문에서는 변이지도의 정확도 향상을 위하여, 비용 함수를 이용한 교차 일치성 검사 기법을 제안하고, 다양한 조건의 실험을 통하여 제안한 알고리듬이 효율적임을 보였다. 좌우 변이정보를 이용하는 교차 일치성 검사로 오정합을 검출하는 방법을 시도해왔다. 하지만 이러한 방법은 물체의 경계에서 발생하는 오정합을 찾기가 어렵다. 본 논문에서는 최종 변이의 신뢰도 향상을 위해 교차 일치성 검사의 정확도를 높이는 방법을 제안하였다. 일반적으로 영역 기반 스테레오정합 방법은 물체의 경계에서 정확도 높지 못하다. 이러한 문제점을 해결하기 위해 정합창의 크기를 늘리거나 특징 점을 이용한 적응적 가변 정합창을 적용하는 방법을 시도하였다. 하지만, 여전히 기존 교차 일치성 검사를 통한 오정합 검출은 부정확하다. 이러한 영역의 비용 함수 값들을 비교한 결과 첫 번째와 두 번째 값의 차이가 적거나 크게 나타난다. 제안한 방법은 기존 방법에 비해 오정합 검출 능력을 향상 시킨다. 제안한 방법의 결과를 확인하기 위해 스테레오 비전에서 많이 사용되는 영상을 적용하고 분석하였다. 또한, 기존 교차 일치성 검사 방법과 제안한 방법의 객관적으로 비교하기 위해 전체 영역에 대한 오차율 (error ratio)과 교차 일치성 검사로 유효하다고 판단된 변이 값 중 실제 변이 값과 일치하지 않은 변이값의 오차율을 비교하였다. 실험 결과 기존 방법에 비해 제안한 방법이 1~5%정도 낮은 오차율을 보였다