Earticle

본 연구는 도로 위의 객체를 분류하고 그 위치를 추정하기 위해 카메라와 레이저스캐너를 이용한 이종센서 검지 시스 템의 연구를 다루고 있다. 이러한 도로인프라에서의 검지시스템은 ADAS(Advanced Driver Assist System) 및 (반)자동제어 서비스 등의 새로운 C-ITS 서비스에서 요구되는 객체의 위치 정보를 검지할 수 있다. 본 연구에서는 국외 관련 사례를 살펴보고, 카메라와 레이저스캐너를 이용한 검지시스템의 가능성을 살펴보았다. 그 후 이종센서 처리 알고리즘을 제안하 고, 실 도로환경에서 몇 가지 도로상황 시나리오를 설정하여 시험검증을 실시하였다. 그 결과 이종센서 검지시스템으로 차량, 보행자 및 기타 장애물에 대한 검지 및 위치 추정에 대하여 비교적 용이하게 이용될 수 있음을 확인할 수 있었다. 본 연구의 경우 매우 이상적인 조건에서 실험이 실시되었으며, 조도, 날씨 등의 외부환경 조건의 변화에 따른 알고리즘 의 평가가 필요하다. 이러한 연구는 향후 미래의 C-ITS 환경 하에서 객체 검지 기술로 활용될 수 있을 것으로 기대한다.

This paper proposes the new object detection system with two laser-scanners and a camera for classifying the objects and predicting the location of objects on road street. This detection system could be applied the new C-ITS service such as ADAS (Advanced Driver Assist System) or (semi-)automatic vehicle guidance services using object's types and precise position. This study describes the some examples in other countries and feasibility of object detection system based on a camera and two laser-scanners. This study has developed the heterogenous sensor's fusion method and shows the results of implementation at road environments. As a results, object detection system at roadside infrastructure is a useful method that aims at reliable classification and positioning of road objects, such as a vehicle, a pedestrian, and obstacles in a street. The algorithm of this paper is performed at ideal condition, so it need to implement at various condition such as light brightness and weather condition. This paper should help better object detection and development of new methods at improved C-ITS environment.

본 논문에서는 이산웨이블릿 변환과 퍼지추론을 이용하여 물체를 분류하는 방법을 제안 한 바, 컨베이어 혹은 무인 운송장치와 같은 저속도에 적용 할 수 있는 퍼지추론 알고리즘과 알고리즘의 퍼지 규칙수를 최소화하는 방법에 중점을 두었다. 특징추출을 위한 전처리 과정에서 는 이산웨이블릿 변환 계수로부터 물체의 특징 파라미터들을 구하였다. 물체의 특징 파라미터는 계수 블록으로부터 계산된 물체의 면적, 둘레, 면적과 둘레의 비율을 이용하였다. 외부 환경에 기인하는 파라미터들의 변화에 적응할 수 있도록 퍼지 If-then 규칙을 설계하였다. 제안한 추론 알고리즘의 성능 평가를 위하여 Mamdani 및 Larsen의 함의 연산자를 이용하여 실험하였고, 외부 환경 변화에 대하여도 적용 가능성을 보였다.

This paper presents a method of object classification based on discrete wavelet transform (DWT) and fuzzy inference(FI). It concentrated not only on the design of fuzzy inference algorithm which is suitable for low speed uninhabited transportation such as, conveyor but also on the minimize the number of fuzzy rule. In the preprocess of feature extracting, feature parameters are extracted by using characteristics of the coefficients matrix of DWT. Such feature parameters as area, perimeter and a/p ratio are used obtained from DWT coefficients blocks. Secondly, fuzzy if - then rules that can be able to adapt the variety of surroundings are developed. In order to verify the performance of proposed scheme, In the middle of fuzzy inference, the Mamdani's and the Larsen 's implication operators are utilized. Experimental results showed that proposed scheme can be applied to the variety of surroundings.

Training deep learning models involves the use of various optimization algorithms, each with its own advantages and disadvantages. Stochastic gradient descent (SGD) provides consistent performance and stable optimization but has the drawback of a slow convergence rate. On the other hand, Adam offers the advantage of fast convergence but can lead to overfitting. This study proposes a hybrid method that combines the stable convergence of SGD with the fast convergence of Adam, enabling the model to be optimized quickly and stably. This approach was applied to the EfficientNetV2 and Vision Transformer (ViT) architectures in image classification tasks. EfficientNetV2 used Adam up to the 6th block and then switched to SGD, achieving the best performance on the proposed dataset with an accuracy of 97.84%, a loss of 0.0990, and an F1-score of 98.04%. Similarly, ViT used Adam for the first 10 encoders and then switched to SGD for the remaining 10 encoders, showing optimal results on the same dataset with an accuracy of 98.54%, a loss of 0.1345, and an F1-score of 98.53%. This fusion optimizer approach effectively enhances training by using Adam for initial feature extraction and SGD for later stages.

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

The Clustering is representative method of components classification. The previous clustering methods that use cohesion and coupling cannot be effective because design pattern has focused on relation between classes. In this paper, we classified design patterns with features of object-oriented relationship. The result is that classification by clustering showed higher precision than classification by facet. It is effective that design patterns are classified by automatic clustering algorithm. When patterns are retrieved in classification of design patterns, we can use to compare them because similar pattern is saved to same category. Also we can manage repository efficiently because of storing patterns with link information.

The object classification using the images' contents is a big challenge in computer vision. The superpixels' information can be used to detect and classify objects in an image based on locations. In this paper, we proposed a methodology to detect and classify the image's pixels' locations using enhanced bag of words (BOW). It calculates the initial positions of each segment of an image using superpixels and then ranks it according to the region score. Further, this information is used to extract local and global features using a hybrid approach of Scale Invariant Feature Transform (SIFT) and GIST, respectively. To enhance the classification accuracy, the feature fusion technique is applied to combine local and global features vectors through weight parameter. The support vector machine classifier is a supervised algorithm is used for classification in order to analyze the proposed methodology. The Pascal Visual Object Classes Challenge 2007 (VOC2007) dataset is used in the experiment to test the results. The proposed approach gave the results in high-quality class for independent objects' locations with a mean average best overlap (MABO) of 0.833 at 1,500 locations resulting in a better detection rate. The results are compared with previous approaches and it is proved that it gave the better classification results for the non-rigid classes.

This study was performed to construct tree species classification map according to three information types (spectral information, texture information, and spectral and texture information) by altitude (30 m, 60 m, 90 m) using the unmanned aerial vehicle images and the object-based classification method, and to evaluate the concordance rate through field survey data. The object-based, optimal weighted values by altitude were 176 for 30 m images, 111 for 60 m images, and 108 for 90 m images in the case of Scale while 0.4/0.6, 0.5/0.5, in the case of the shape/color and compactness/smoothness respectively regardless of the altitude. The overall accuracy according to the type of information by altitude, the information on spectral and texture information was about 88% in the case of 30 m and the spectral information was about 98% and about 86% in the case of 60 m and 90 m respectively showing the highest rates. The concordance rate with the field survey data per tree species was the highest with about 92% in the case of Pinus densiflora at 30 m, about 100% in the case of Prunus sargentii Rehder tree at 60 m, and about 89% in the case of Robinia pseudoacacia L. at 90 m.

This study detected land use change using Landsat satellite image and calculated landscape index to confirm fragmentation of forest land. The land cover classification items were classified into forest land, cropland, grassland, wetlands, and settlements by referring to IPCC guidelines, and the land cover classification was used by object-based classification technique. The landscape structure analysis of land cover change was performed using five landscape index (NumP, MPS, TD, ED, AWMSI). The optimal weights for object-based classification were scale 7, Shape 0.4, Color 0.6, Compactness 0.5, Smoothness 0.5. The change of land cover was increased in the settlement area in 2009 compared to 1989 and decreased in cropland and forest land. The change of landscape index decreased NumP of cropland and forest land in 2009 compared to 1989, but TD and ED increased. This is because the settlement increased, and the cropland and forest land decreased and fragmentation progressed. In conclusion, object analysis is an effective method to confirm change detection and fragmentation, and it is expected to be used for the cause analysis of forest land fragmentation in the future.

In this study, regions infected by pine wilt disease were extracted by using object-based classification method (OB-infected region), and the characteristics of special distribution about OB-infected region were figured out. Scale 24, Shape 0.1, Color 0.9, Compactness 0.5, and Smoothness 0.5 was selected as the objected-based, optimal weighted value of OB-infected region classification. The total accuracy of classification was high with 99% and Kappa coefficient was also high with 0.97. The area of OB-infected region was approximately 90 ha, 16% of the total area. The OB-infected region in Age class V and VI was intensively distributed with 97% of the total. Also, The OB-infected region in Middle and Large DBH class was intensively distributed with 99% of the total. In terms of the topographic characteristics of OB-infected region, the damages occurred approximately 86% below the altitude of 200 m, and occurred 91% with a slope less than 10 degree. The damage occurred a lot in low hilly mountain and undulating slope. In addition, the accessibility to road and residential area from OB-infected region was less than 300 m in large part. Overall, it was figured out that artificial effect is stronger than natural effect with regard to the spread of pine wilt disease.

BIM(건설정보모델링)을 건설사업 전반에 적용하려는 정부정책 이후 업계는 이를 적극적으로 도입, 활용하려는 동향을 보이고 있다. BIM 도입은 모델 객체들을 표준에 맞춰 라이브러리로 구축하여 반복 사용함으로써 업무량을 줄이고 데이터의 정합성과 호환성, 일관된 품질을 확보함으로써 촉진될 수 있다. 이에 국내 건축과 토목분야, 해외 조경분야에서는 이미 상당수의 BIM 라이브러리 표준화 연구를 수행하고 이를 토대로 지침을 마련하였다. 현재 국내 조경분야에서도 BIM에 관한 기초연구 및 도입을 시도하고 있으나 산업현장 적용에 어려움이 많아 확산이 지연되고 있다. 이는 표준화된 라이브러리 사용으로 BIM 설계업무의 효율성을 향상시킴으로써 개선될 수 있으므로 본 연구는 이에 대한 논의의 시발점을 마련함과 동시에 조경실무에서 라이브러리를 제작할 때 참고할 수 있는 객체의 기준을 제시하고자 하였다. 조경 BIM 라이브러리 표준화는 객체분류와 속성정보 도출이라는 두 가지 측면에서 모색되었다. 먼저 국내 건설정보분류체계, 물품분류체계, 조경설계기준, 조경공사표준시방서, 그리고 노르웨이 조경가협회의 BIM 객체분류체계를 참고로 객체분류를 시도하였다. 그 결과 조경객체는 조경식재, 조경시설물, 조경구조물, 조경포장재, 관수 및 배수시설의 5개 대분류하에 교목, 관목, 지피초화류, 옥외시설물, 옥외조명시설, 계단 및 경사로, 옥외벽체, 옥외구조물, 포장재, 경계석, 관수시설, 그리고 급배수시설을 포함하는 12개의 중분류로 나뉘었다. 다음으로 조경객체에 탑재될 속성정보를 도출하고 구조화하였다. 이를 위해 KBIMS(한국 BIM 표준)의 공통 속성정보를 항목에 포함하였고 객체의 종류에 따라 달라지는 객체 속성정보를 영국 조경협회의 PDT(제품정보 템플릿)를 참고하여 추가하였다. 이로써 공통 속성정보에 식별, 보급, 분류체계, 공급정보가 포함되었고, 객체 속성정보에 명명, 규격, 설치 또는 시공, 성능, 지속가능성, 유지관리에 관련된 정보들이 포함되었다. 본 연구는 조경객체의 라이브러리 표준화 방안을 제시함으로써 모델링의 업무 효율성 및 분야 간 BIM 모델의 데이터 정합성을 향상시킴으로써 조경 BIM 도입의 토대를 마련했다는 데에 의의가 있다.

Since the Korean government has decided to apply the policy of BIM (Building Information Modeling) to the entire construction industry, it has experienced a positive trend in adoption and utilization. BIM can reduce workloads by building model objects into libraries that conform to standards and enable consistent quality, data integrity, and compatibility. In the domestic architecture, civil engineering, and the overseas landscape architecture sectors, many BIM library standardization studies have been conducted, and guidelines have been established based on them. Currently, basic research and attempts to introduce BIM are being made in Korean landscape architecture field, but the diffusion has been delayed due to difficulties in application. This can be addressed by enhancing the efficiency of BIM work using standardized libraries. Therefore, this study aims to provide a starting point for discussions and present a classification system for objects and attribute information that can be referred to when creating landscape libraries in practice. The standardization of landscape BIM library was explored from two directions: object classification and attribute information items. First, the Korean construction information classification system, product inventory classification system, landscape design and construction standards, and BIM object classification of the NLA (Norwegian Association of Landscape Architects) were referred to classify landscape objects. As a result, the objects were divided into 12 subcategories, including 'trees', 'shrubs', 'ground cover and others', 'outdoor installation', 'outdoor lighting facility', 'stairs and ramp', 'outdoor wall', 'outdoor structure', 'pavement', 'curb', 'irrigation', and 'drainage' under five major categories: 'landscape plant', 'landscape facility', 'landscape structure', 'landscape pavement', and 'irrigation and drainage'. Next, the attribute information for the objects was extracted and structured. To do this, the common attribute information items of the KBIMS (Korean BIM Standard) were included, and the object attribute information items that vary according to the type of objects were included by referring to the PDT (Product Data Template) of the LI (UK Landscape Institute). As a result, the common attributes included information on 'identification', 'distribution', 'classification', and 'manufacture and supply' information, while the object attributes included information on 'naming', 'specifications', 'installation or construction', 'performance', 'sustainability', and 'operations and maintenance'. The significance of this study lies in establishing the foundation for the introduction of landscape BIM through the standardization of library objects, which will enhance the efficiency of modeling tasks and improve the data consistency of BIM models across various disciplines in the construction industry.

오늘날 저작권 관련 산업이 사회, 경제적으로 큰 영향을 미치는 대규모 산업으로 성장하였음에도 불구하고 저작물에 대한 소유권 및 저작권에 대한 문제가 끊임없이 발생하고 있으며 특히 이미지 저작권과 관련된 연구는 거의 진행되지 않는 상태이다. 본 연구에서는 기존의 문서 영상처리 기술과 딥 러닝 기술을 융합하여 교육용 도서 영상에서의 객체 자동 추출 및 분류 기술 시스템을 제안한다. 제안된 기술은 먼저 잡음을 제거한 후, 시각적 주의(visual attention) 기반 영역 추출 과정을 수행한다. 추출된 영역을 기반으로 블록화 작업을 수행하고, 각 블록을 그림인지 아니면 문자 영역인지를 분류한다. 마지막으로 추출된 그림 영역 주위를 검색하여 캡션 영역을 추출한다. 본 연구에서 진행한 성능 평가 결과, 그림 영역은 최대 97% 정확도를 보이며, 그림 및 캡션 영역 추출에 있어서는 평균 83%의 정확도를 보여 준다.

Despite the fact that the copyright has grown into a large-scale business, there are many constant problems especially in image copyright. In this study, we propose an automatic object extraction and classification system for the scanned educational book image by combining document image processing and intelligent information technology like deep learning. First, the proposed technology removes noise component and then performs a visual attention assessment-based region separation. Then we carry out grouping operation based on extracted block areas and categorize each block as a picture or a character area. Finally, the caption area is extracted by searching around the classified picture area. As a result of the performance evaluation, it can be seen an average accuracy of 83% in the extraction of the image and caption area. For only image region detection, up-to 97% of accuracy is verified.

본 논문에서는 텍스쳐와 컬러 정보를 기반으로 비디오 감시를 위한 빠른 물체 분류 방법을 제안한다. 영상들로부터 SURF와 색 히스토그램의 국부적 패치들을 추출하여 그들의 장점을 이용한다. SURF는 명암 내용 정보를 제공하고 색 정보는 패치에 대한 특이성을 증강시킨다. SURF의 빠른 계산뿐만 아니라 객체의 색 정보를 활용한다. 국부적 특징을 이용하여 관심 영역 혹은 영상의 전역적 서술자를 생성하기 위해 Bag of Word 모델을 이용하고, 전역적 서술자를 분류하기 위해 Na$\ddot{i}$ve Bayes 모델을 이용한다. 또한 본 논문에서는 판별적인 기술자인 SIFT도 성능 분석한다. 네 종류의 객체에 대한 실험결과 95.75%의 인식률을 보였다.

In this paper, we propose a fast object classification method based on texture and color information for video surveillance. We take the advantage of local patches by extracting SURF and color histogram from images. SURF gives intensity content information and color information strengthens distinctiveness by providing links to patch content. We achieve the advantages of fast computation of SURF as well as color cues of objects. We use Bag of Word models to generate global descriptors of a region of interest (ROI) or an image using the local features, and Na$\ddot{i}$ve Bayes model for classifying the global descriptor. In this paper, we also investigate discriminative descriptor named Scale Invariant Feature Transform (SIFT). Our experiment result for 4 classes of the objects shows 95.75% of classification rate.

본 논문에서는 레이저스캐너만으로 이루어진 감지 시스템을 이용하여 도로 위에 있는 객체의 위치를 추정하고 분류 하는 알고리즘을 제안한다. 각각의 레이저 스캐너에서 획득한 데이터는 그리드 맵을 사용하여 데이터를 융합하였으며, 팽창 연산과 레이블링 방법을 사용하여 측정 오차를 보정하였다. 추출한 객체의 정보(길이, 폭)를 입력으로 사용한 퍼지 방법을 통해 객체를 보행자, 자전거, 차량으로 분류하였으며, 이러한 방법은 레이저스캐너로만 이루어진 감지 시스템의 정확도를 증가시켰다. 또한 본 논문에서는 실제 도로 환경에서 몇 가지 시나리오를 설정하여 실험을 하였다. 실험을 통 해 감지 시스템이 객체를 정확히 분류하는지, GPS-RTK 장비를 사용하여 획득한 위치 정보와 비교하여 객체의 위치 정 보를 정확히 추정하는지 검증하였다.

This paper proposes the on-road object detection and classification algorithm by using a detection system consisting of only laser scanners. Each sensor data acquired by the laser scanner is fused with a grid map and the measurement error and spot spaces are corrected using a labeling method and dilation operation. Fuzzy method which uses the object information (length, width) as input parameters can classify the objects such as a pedestrian, bicycle and vehicle. In this way, the accuracy of the detection system is increased. Through experiments for some scenarios in the real road environment, the performance of the proposed detection and classification system for the actual objects is demonstrated through the comparison with the actual information acquired by GPS-RTK.

재난은 자연적 또는 인위적 요인으로 인해 예측이 어렵게 발생하며, 복합적 양상으로 확대되어 심각한 피해를 초래한다. 이러한 재난 상황에서 신속하고 정확한 탐지는 피해 최소화를 위한 초기 대응의 핵심 요소이다. 본 연구에서는 6종 재난 유형을 탐지·분류할 수 있는 YOLOv8 기반 객체 탐지 모델을 개발하였다. 수집된 이미지를 전처리하고 애노테이션을 수행한 후, 다양한 이미지 증강(image augmentation) 기법을 적용하여 모델의 일반화 성능을 강화하였다. 성능 평가 결과 Precision = 0.956, Recall = 0.937, mAP@0.5 = 0.964, mAP@0.5-0.95 = 0.792로 높은 탐지 정확도를 보였다. 특히 화재 및 홍수 관련 재난에서 우수한 성능을 나타냈으나, 산불화재 및 도로균열처럼 배경과 색상·질감이 유사한 객체에서는 상대적으로 낮은 탐지율을 보였다. 제안된 모델은 다양한 환경에서도 신속하고 정확한 재난 탐지 및 분류가 가능한 고성능 프레임워크를 제시하였으며, 향후 시민제보, 드론 영상, CCTV 영상 등 실시간 영상 데이터와 연계한 재난 대응 및 관리 체계의 고도화에 기여할 수 있을 것으로 기대된다.

Disasters occur in diverse and unpredictable forms, underscoring the necessity of rapid initial response. Citizen-reported images captured via smartphones provide a valuable means of acquiring disaster scene information without temporal or spatial constraints; however, the risk of misinformation necessitates careful verification. This study developed a YOLOv8-based object detection model to detect and classify six disaster types forest fire, vehicle fire, building fire, pothole, road crack, and flood using citizen-reported images. The dataset was collected, preprocessed, and augmented, and transfer learning was applied to optimize model performance. Evaluation was conducted through cross-validation and an independent test dataset, yielding strong results with Precision = 0.956, Recall = 0.937, mAP@0.5 = 0.964, and mAP@0.5-0.95 = 0.792. The model achieved excellent performance in fire- and flood-related categories, while relatively lower performance was observed for forest fire and road crack due to similarities in color and texture with the background. The proposed model improves the reliability and timeliness of image-based disaster detection and classification, contributing to the advancement of early disaster response and management systems. Furthermore, it supports the verification of citizen-reported images, reducing false detections caused by misinformation, and provides a foundation for building standardized disaster image databases and developing intelligent disaster management systems.

Along with the current rapid development of technology, object classification is being researched, developed, and applied to security systems, autonomous driving, and other applications. A common technique is to use vision cameras to collect data of objects in the surrounding environment. Along with many other methods, LiDAR sensors are being used to collect data in space to detect and classify objects. By using the LiDAR sensors, some disadvantages of image sensors with the negative influence on the image quality by weather and light condition will be covered. In this study, a volumetric image descriptor in 3D shape is developed to handle 3D object data in the urban environment obtained from LiDAR sensors, and convert it into image data before using deep learning algorithms in the process of object classification. The study showed the potential possibility of the proposal and its further application.

본 논문에서는 상황 변화 환경에서 적응적인 객체 인식을 위한 계층적 트리 구조를 이용한 조명 온톨로지 분류에 대한 방식을 제안한다. 본 논문에서는 상황이 불변하는 환경에서 동작하는 개발된 많은 시스템을 찾아냈고, 상황에 맞는 감지를 위한 새로운 개념의 트리 구조를 이용한 온톨로지를 도입하였다. 조명의 영향이 상황 인지 인식 시스템을 아주 설계하기 어려운 시스템으로 만들기 때문에 본 논문에서는 트리 구조의 온톨로지를 사용하여 이러한 상황 변화 시스템을 설계하는데 더 중점을 두었다. 온톨로지는 일반적으로 사람들이 특정 분야의 것들에 대해 생각하는 방법의 추상적 모델에서 전형적으로 캡처된 한 분야의 개념화의 명시적 사양으로 정의 할 수 있다. 인간은 기본 원칙과 환경을 이해하고 설명하기 위해 온톨로지를 생성한다. 본 연구에서는 상황 온톨로지, 상황 모델링, 상황 적응 및 조명 기준에 따라 트리 구조 온톨로지를 설계하는 상황 분류를 제안했다. 조명 온톨로지의 적당한 영역을 선택한 후, 그 영역에서 더 나은 성능을 생산하는 동작의 한 집합을 선택하는데 있어서 장점을 얻었다. 본 논문에서는 역동적인 변화 환경에서 객체 인식의 영역에서 이러한 개념을 이용하여 폭 넓은 실험을 수행하였으며 제안하는 기본 개념에 대해 수행할 수 있는 많은 성공을 얻었다.

This paper proposes a ontology of tree structure approach for adaptive object recognition in a situation-variant environment. In this paper, we introduce a new concept, ontology of tree structure ontology, for context sensitivity, as we found that many developed systems work in a context-invariant environment. Due to the effects of illumination on a supreme obstinate designing context-sensitive recognition system, we have focused on designing such a context-variant system using ontology of tree structure. Ontology can be defined as an explicit specification of conceptualization of a domain typically captured in an abstract model of how people think about things in the domain. People produce ontologies to understand and explain underlying principles and environmental factors. In this research, we have proposed context ontology, context modeling, context adaptation, and context categorization to design ontology of tree structure based on illumination criteria. After selecting the proper light-ontology domain, we benefit from selecting a set of actions that produces better performance on that domain. We have carried out extensive experiments on these concepts in the area of object recognition in a dynamic changing environment, and we have achieved enormous success, which will enable us to proceed on our basic concepts.

Quiet often, an organization tries to grapple with inconsistent and partial information to generate relevant information to support decision making and action. As such, an organization scans the environment interprets scanned data, executes actions, and learns from feedback of actions, which boils down to computational interpretations and learning in terms of machine learning, statistics, and database. The ExOM proposed in this paper is geared to facilitate such knowledge discovery found in large databases in a most flexible manner. It supports a broad range of learning and classification styles and integrates them with traditional database functions. The learning and classification components of the ExOM are tightly integrated so that learning and classification of objects is less burdensome to ordinary users. A brief sketch of a strategy as to the expressiveness of terminological language is followed by a description of prototype implementation of the learning and classification components of the ExOM.

본 논문은 서베일런스 네트워크에서 이동하는 객체 추적 시 영상 데이터의 전송량을 감소시키는 신경망 계산 시간의 단축 알고리즘을 제안한다. 객체 검출은 디지털화 연속된 영상으로부터 객체 존재 유무를 판단하고, 객체가 존재할 경우 영상 내 객체의 위치, 방향, 크기 등을 알아내는 기술로 정의된다. 그러나 영상 내의 객체는 위치, 크기, 빛의 방향 및 밝기, 장애물 등의 환경적 변화로 인해 객체 모양이 다양해지므로 정확하고 빠른 검출이 어렵다. 따라서 본 논문에서는 신경망을 사용하여 몇 가지 환경적 조건을 극복한 정확하고 빠른 객체 검출 방법을 제안한다. 검색 영역의 축소는 영상 내 색상 영역의 분할과 차영상을 이용하였고, 주성분 분석을 통해 신경망의 입력 벡터를 축소시킴으로써 신경망 수행 시간과 학습 시간을 단축시켰다. 실시간으로 입력되는 동영상에서 모두 실험하였으며, 색상 영역의 분할을 사용할 경우 입력 영상의 칼라 설정의 유무에 따른 검출 성공률의 차를 보였다. 실험 결과에서 보면 제안하는 방법으로써 객체의 움직임을 탐지하였을 때 기존의 방법보다 30% 정도 더 높은 인식 성능을 보여준다.

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.