• 한국HCI학회논문지
• /
• 제6권1호
• /
• pp.9-16
• /
• 2011

물체를 3차원으로 모델링 하는 데에 있어서 기존의 연구들은 주로 모델링할 물체 외에 다른 방해 요소가 없는 제한된 환경에서 작업을 수행하였다. 이러한 환경 제약이 없는 일상적인 생활환경에서 물체를 모델링하기 위해서는 관심영역 외의 주변 물체들이 복잡하게 섞여있고 빈번하게 변하는 상황을 고려해야 한다. 본 논문에서는 스테레오 비전 카메라를 이용하여 동적인 환경에서 대상 물체가 포함된 전경 영역을 배경으로부터 분리하고 지속적으로 추적하는 방법을 제안한다. 스테레오 영상으로부터 획득된 거리 정보를 이용하여 색상 정보를 이용할 때보다 환경변화에 강인하게 전경 영역을 분리할 수 있다. 또한 시간적으로 연속된 두 영상에 나타나는 전경 영역은 위치나 상태에 따른 변화가 크지 않으므로 관심영역의 상대적인 거리 분포를 비교하여 추적할 수 있다. 다양한 조건의 동적인 환경에서 전경 영역을 분리 및 추적하는 실험을 통해 본 논문에서 제안하는 방법의 성능을 평가한다. 이를 통해 분리 및 추적된 전경 영역으로부터 물체 영역을 추출하여 3차원 물체 모델링이 가능함을 보인다.

• 대한기계학회논문집A
• /
• 제28권2호
• /
• pp.125-132
• /
• 2004

In this paper, we propose a new two-stage segmentation method for the effective object recognition which uses region-growing algorithm and k-means clustering method. At first, an image is segmented into many small regions via region growing algorithm. And then the segmented small regions are merged in several regions so that the regions of an object may be included in the same region using typical k-means clustering method. This paper also establishes similarity measurement which is useful for object recognition in an image. Similarity is measured by fuzzy system whose input variables are compactness, magnitude of biasness and orientation of biasness of the object image, which are geometrical features of the object. To verify the effectiveness of the proposed two-stage segmentation method and similarity measurement, experiments for object recognition were made and the results show that they are applicable to object recognition under normal circumstance as well as under abnormal circumstance of being.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• 한국컴퓨터정보학회논문지
• /
• 제11권4호
• /
• pp.283-289
• /
• 2006

현재 영상분할은 사용자가 원하는 영상을 분할하고, 분할된 객체에 다른 영상을 합성하는 기술에 대해 많은 연구가 진행되어왔다. 본 논문에서는 점진적 영역병합과 유전자 알고리즘을 이용하여 새로운 반자동 영상 분할방법을 제안하였다. 제안된 알고리즘은 사용자가 원하는 객체를 선정한 후, 유전자 알고리즘을 이용해 객체의 경계를 검색한다. 검색된 경계를 기반으로 분수령 알고리즘을 이용하여 사용자가 원하는 객체의 영역을 분할하였다. 분할된 객체에서 불명확한 영역들을 점진적 영역 병합으로 배경과 객체를 분리하였다. 그리고, 알고리즘 개발을 효과적으로 수행하기 위해 GUI기반의 인터페이스를 만들어 사용자가 원하는 값을 적용할 수 있게 하였다. 실험에서는 제한된 방법의 우수성 입증을 위하여 다양한 영상을 분석하였다.

• 한국정보통신학회논문지
• /
• 제18권3호
• /
• pp.687-696
• /
• 2014

본 논문은 사용자의 입력, 색상 및 깊이 정보를 이용한 의미론적 물체 분할 방법을 제안한다. 의미있는 영역을 깊이영상에서 유사한 깊이 정보와 사용자 스트로크 입력의 중심에 위치한다고 가정한다. 제안된 방법은 스트로크 입력을 이용하여 관심 영역을 설정하고, 색상과 깊이 정보를 이용하여 의미있는 영역을 검출한다. 구체적으로 제안방법은 관심영역에 대해 색상과 깊이 정보를 이용한 과분할 과정과 과분할 영역에 대해 깊이 정보를 이용한 의미론적 물체 추출과정으로 구성되어 있다. 과분할 과정에서 적응적 임계값 적용 및 형태학적 기울기에 대한 적응적인 가중치 적용을 통한 마커 추출 방법을 제안하였다. 의미론적 물체 추출과정에서는 관심영역의 가장자리 영역에서 내부 영역으로의 순서대로 전체 깊이의 평균과 차이를 이용하여 추출하고자 하는 물체 영역인지 아닌지를 결정하도록 하였다. 실험 결과에서 제안한 방법이 효과적으로 의미있는 물체 추출 결과를 얻을 수 있음을 보인다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.247-256
• /
• 2022

Visual tracking of selected target objects is fundamental challenging problems in computer vision. Object tracking localize the region of target object with bounding box in the video. We propose a Siam-FPN based custom fully CNN to solve visual tracking problems by regressing the target area in an end-to-end manner. A method of preserving the feature information flow using a feature map connection structure was applied. In this way, information is preserved and emphasized across the network. To regress object region and to classify object, the region proposal network was connected with the Siamese network. The performance of the tracking algorithm was evaluated using the OTB-100 dataset. Success Plot and Precision Plot were used as evaluation matrix. As a result of the experiment, 0.621 in Success Plot and 0.838 in Precision Plot were achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.207-210
• /
• 2002

In this paper, content-based retrieval for region of interest(ROI) has been described, using maximum bin color. From a given query image, the object of interest is selected by a user. Using maximum bin color of the selected object, candidate regions are extracted from database images. The final regions of interest are determined by comparing the normalized histograms of the selected object and each candidate region.