• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.334-338
• /
• 2022

In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.794-797
• /
• 2024

Despite advancements in deep learning, existing semantic segmentation models exhibit suboptimal performance under adverse weather conditions, such as fog or rain, whereas they perform well in clear weather conditions. To address this issue, much of the research has focused on making image or feature-level representations weather-independent. However, disentangling the style and content of images remains a challenge. In this work, we propose a novel fine-tuning method, 'freeze-n-update.' We identify a subset of model parameters that are weather-independent and demonstrate that by freezing these parameters and fine-tuning others, segmentation performance can be significantly improved. Experiments on a test dataset confirm both the effectiveness and practicality of our approach.

• The Journal of Society for e-Business Studies
• /
• v.18 no.2
• /
• pp.95-110
• /
• 2013

This paper presents a novel feature engineering technique that can improve the conventional machine learning-based text classification systems. The proposed method extends the initial set of features by using hyperlink relationships in order to effectively categorize hypertext web documents. Web documents are connected to each other through hyperlinks, and in many cases hyperlinks exist among highly related documents. Such hyperlink relationships can be used to enhance the quality of features which consist of classification models. The basic idea of the proposed method is to generate a sort of ed concept feature which consists of a few raw feature words; for this, the method computes the semantic similarity between a target document and its neighbor documents by utilizing hierarchical relationships in the WordNet ontology. In developing classification models, the ed concept features are equated with other raw features, and they can play a great role in developing more accurate classification models. Through the extensive experiments with the Web-KB test collection, we prove that the proposed methods outperform the conventional ones.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.4968-4986
• /
• 2017

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.166-172
• /
• 2014

Image classification is an important problem in computer vision. However, it is a very challenging problem due to the variability, ambiguity and scale change that exists in images. In this paper, we propose a method of a hypergraph based modeling can consider the higher-order relationships of semantic attributes of a scene image and apply it to a scene image classification. In order to generate the hypergraph optimized for specific scene category, we propose a novel search method based on a probabilistic subspace method and also propose a method to aggregate the expression values of the member semantic attributes that belongs to the searched subsets based on a linear transformation method via likelihood based estimation. To verify the superiority of the proposed method, we showed that the discrimination power of the feature vector generated by the proposed method is better than existing methods through experiments. And also, in a scene classification experiment, the proposed method shows a competitive classification performance compared with the conventional methods.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.10
• /
• pp.783-789
• /
• 2020

This paper proposes a new method for vision-based navigation using semantically segmented aerial images. Vision-based navigation can reinforce the vulnerability of the GPS/INS integrated navigation system. However, due to the visual and temporal difference between the aerial image and the database image, the existing image matching algorithms have difficulties being applied to aerial navigation problems. For this reason, this paper proposes a suitable matching method for the flight composed of navigational feature extraction through semantic segmentation followed by template matching. The proposed method shows excellent performance in simulation and even flight situations.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.11-18
• /
• 2008

Document clustering is an important method for document analysis and is used in many different information retrieval applications. This paper proposes a new document clustering model using the re-weighted term based NMF(non-negative matrix factorization) to cluster documents relevant to a user's requirement. The proposed model uses the re-weighted term by using user feedback to reduce the gap between the user's requirement for document classification and the document clusters by means of machine. The Proposed method can improve the quality of document clustering because the re-weighted terms. the semantic feature matrix and the semantic variable matrix, which is used in document clustering, can represent an inherent structure of document set more well. The experimental results demonstrate appling the proposed method to document clustering methods achieves better performance than documents clustering methods.

• Annual Conference on Human and Language Technology
• /
• 1999.10e
• /
• pp.105-109
• /
• 1999

영-한 기계번역 중 변환 단계에서 한국어 문장을 생성하기 위해서는 구구조 변환 후 조사 및 대역어 선택으로 이루어진다. 그러나 하나의 영어 단어는 여러 개의 한국어 의미들을 가지고 있기 때문에 문장에서 사용된 영어의 정확한 의미에 해당하는 한국어 대역어를 선택하는 것은 번역의 질을 높이고 시스템의 성능에 매우 중요한 역할을 한다. 특히 용언 및 체언의 대역어 선택은 문장에서 서로 간의 의미적인 관계를 고려하여야 올바른 대역어를 선택할 수 있다. 기존에는 전자 사전에 용언과 체언간의 연어 정보(collocation information)를 구축하여 대역어 선택의 문제를 해결하려고 하였으나 연어 정보가 사전에 존재하지 않을 때 올바른 대역어를 선택할 수 없었다. 또한 용언과 체언의 관계를 나타내는 조사를 선택하기 위하여 격(case)을 세분화하여 사전을 구축하였으나 격의 분류 및 사전을 구축할 경우 격을 선택하는 어려움이 있었다. 이에 따라 본 논문에서는 문형(sentence pattern)에 의한 방법으로 용언의 대역어 및 용언이 갖는 필수격 체언의 조사와 대역어 선택방법을 제안한다. 문형의 구조적인 정보에는 용언과 체언의 의미적 역할(thematic role)을 하는 조사 및 용언이 갖는 필수격 체언의 의미 자질(semantic feature)을 갖고 있다. 이러한 의미 자질을 wordnet과 한/영 및 영/한 사전을 이용하여 의미 지표(semantic marker)를 갖는 문형 사전을 구축한다. 또한 의미 지표를 갖는 문형 사전을 기반으로 조사 및 대역어 선택 알고리즘을 개발한다.

• Journal of Internet Computing and Services
• /
• v.5 no.2
• /
• pp.97-105
• /
• 2004

The reason that an intelligent agent cannot understand the representation of its own perception or activity is caused by the traditional syntactic approach that translates a semantic feature into a simulated string, To implement an autonomously learning intelligent agent, Cohen introduces a experimentally semantic approach that the system learns a contentful representation of physical schema from physically interacting with environment using its own sensors and effectors. We propose that negation is a meta-level schema that enables an agent to recognize its own physical schema, To improve the planner's efficiency, Graphplan introduces the control rule that manipulates the inconsistency between planning operators, but it cannot cognitively understand negation and suffers from redundancy problem. By introducing a negative function not, IPP solves the problem, but its approach is still syntactic and is inefficient in terms of time and space. In this paper, we propose that, to represent a negative fact, a positive atom, which is called opposite concept, is a very efficient technique for implementing an cognitive agent, and demonstrate some empirical results supporting the hypothesis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.6
• /
• pp.545-554
• /
• 2018

As the map paradigm shifts from analog to digital, the LOD (Level Of Detail) of spatial information needs to be redefined. In this study, we propose 4- dimensional indoor LOD model which can be used in digital map environment. For this purpose, the limitation of the previous research is derived through study of related works, and based on this, four different LODs are defined such PLOD (Position accuracy LOD) based on position accuracy, GLOD (Geometric LOD) based on shape representation, CLOD (Complete LOD) based on generalization, and SLOD (Semantic LOD) based on theme accuracy. In addition, we describe the relationships among the four different LODs, and explain how to express the indoor LOD using the four different LODs and show examples. In the future, the case studies of indoor LOD adoption for various indoor services and the study of method for applying CLOD and SLOD to each feature should be performed to verify the feasibility and validity of proposed indoor LOD.