• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.610-614
• /
• 2006

In this paper the advanced method of geodesic active contours was developed for the task of building detection from aerial and satellite images. Automatic extraction of man-made structures including buildings, building blocks or roads from remote sensing data is useful for land use mapping, scene understanding, robotic navigation, image retrieval, surveillance, emergency management procedures, cadastral etc. A level set method based on a region-driven segmentation model was implemented with which building boundaries were detected, through this curve propagation technique. The essence of this approach is to optimize the position and the geometric form of the curve by measuring information along that curve, and within the regions that compose the image partition. To this end, one can consider uniform intensities inside objects and the background. Thus, given an initial position of the curve, one can determine global, region-driven functions and provide a statistical description of the inside and outside object area. The calculus of variations and a gradient descent method was used to optimize the variational functional by an iterative steady state process. Experimental results demonstrate the potential of the proposed processing scheme.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.6
• /
• pp.444-454
• /
• 2005

Recently, the requirements of multi-resolution models of a solid model, which represent an object at multiple levels of feature detail, are increasing for engineering tasks such as analysis, network-based collaborative design, and virtual prototyping and manufacturing. The research on this area has focused on several topics: topological frameworks for representing multi-resolution solid models, criteria for the level of detail (LOD), and generation of valid models after rearrangement of features. As a solution to the feature rearrangement problem, the new concept of the effective zone of a feature is introduced in the former part of the paper. In this paper, we propose a feature-based non-manifold modeling system to provide multi-resolution models of a feature-based solid or non-manifold model on the basis of the effective feature zones. To facilitate the implementation, we introduce the class of the multi-resolution feature whose attributes contain all necessary information to build a multi-resolution solid model and extract LOD models from it. In addition, two methods are introduced to accelerate the extraction of LOD models from the multi-resolution modeling database: the one is using an NMT model, known as a merged set, to represent multi-resolution models, and the other is storing differences between adjacent LOD models to accelerate the transition to the other LOD. We also suggest the volume of the feature, regardless of feature type, as a criterion for the LOD. This criterion can be used in a wide range of applications, since there is no distinction between additive and subtractive features unlike the previous method.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.37-43
• /
• 2006

The target of this study is development of web based mold discrimination system by matching vision information with CAD database. The use of 2D vision image makes possible speedy mold discrimination from many databases. The image processing such as preprocessing, cleaning is done for obtaining vivid image with object information. The web-based system is a program which runs to exchange messages between a server and a client by making of ActiveX control and the result of mold discrimination is shown on web-browser. For effective feature classification and extraction, signature method is used to make sensible information from 2D data. As a result, the possibility of proposed system is shown as matching feature information from vision image with CAD database samples.

• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.17-24
• /
• 2017

This paper describes the general process of making augmented reality game for real objects without markers. In this paper, point cloud data created by using slam technology is edited using a separate editing tool to optimize performance in mobile environment. Also, in the game execution stage, a lot of load is generated due to the extraction of feature points and the matching of descriptors. In order to reduce this, optical flow is used to track the matched feature points in the previous input image.

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.787-795
• /
• 2008

Human recognition on camera is an interesting topic in computer vision. While fingerprint and face recognition have been become common, gait is considered as a new biometric feature for distance recognition. In this paper, we propose a gait recognition algorithm based on the knee angle, 2 feet distance, walking velocity and head direction of a person who appear in camera view on one gait cycle. The background subtraction method firstly use for binary moving object extraction and then base on it we continue detect the leg region, head region and get gait features (leg angle, leg swing amplitude). Another feature, walking speed, also can be detected after a gait cycle finished. And then, we compute the errors between calculated features and stored features for recognition. This method gives good results when we performed testing using indoor and outdoor landscape in both lateral, oblique view.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.808-810
• /
• 2004

본 논문에서는 Contrast map과 Salient point를 이용하여 영상에서 중요한 객체를 자동으로 추출하는 방법을 제안한다. 우선 인간의 시각 체계와 유사한 밝기(luminance), 색상(color) 그리고 방향성(orientation) 3가지의 특징정보를 이용하여 각각의 특징정보로부터 feature map을 생성하고 이 3가지의 feature map을 선형 결합하여 contrast map을 생성한다. 이렇게 생성된 하나의 contrast map을 이용하여 대략적인 Attention Window (AW)의 위치를 결정한다. 다음으로, 영상으로부터 웨이블릿 변환을 적용하여 salient point를 찾고, salient point의 분포와 contrast map의 중요도에 따라 AW의 크기를 실제 중요 객체의 크기와 가장 유사하도록 축소시킨다. 이렇게 선택되고 축소된 AW안에서 실제 중요 객체를 추출하기 위해 AW 내부에 존재하는 영상에 대해서만 영상 분할을 하고 불필요한 영역을 제거하여 자동으로 중요객체를 추출하도록 한다.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.1220-1223
• /
• 2023

폐기물을 처리하는데 있어 배출과 수거에 대한 프로세스 자동화를 위해 폐기물 객체 유사도 판별이 요구된다. 이를 위해 본 연구에서는 폐기물 데이터셋에서 SIFT(Scale-Invariant Feature Transform)와 HSV(Hue, Saturation, Value)기반으로 두 이미지의 공통된 특징을 추출해 융합하고, 기계학습을 통해 이미지 객체 간의 유사도를 측정하는 모델을 제안한다. 실험을 위해 수집된 폐기물 데이터셋 81,072 장을 활용하여 이미지를 학습시키고, 전통적인 임계치 기반 유사도 측정과 본 논문에서 제시하는 유사도 측정을 비교하여 성능을 확인하였다. 임계치 기반 측정에서 SIFT 와 HSV 는 각각 0.82, 0.89(Acc)가 측정되었고, 본 논문에서 제시한 특징 추출 방법을 사용한 기계학습의 성능은 DT(Decision Tree)와 SVM(Support Vector Machine) 모두 0.93 (Acc)로 4%의 정확도가 향상되었다.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Journal of Information Processing Systems
• /
• v.3 no.1
• /
• pp.33-37
• /
• 2007

Semantic clustering is important to various fields in the modem information society. In this work we applied the Independent Component Analysis method to the extraction of the features of latent concepts. We used verb and object noun information and formulated a concept as a linear combination of verbs. The proposed method is shown to be suitable for our framework and it performs better than a hierarchical clustering in latent semantic space for finding out invisible information from the data.