• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2179-2184
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper described appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.43 no.4
• /
• pp.473-479
• /
• 2016

In connection with medical care, designs have been developed by forming relationships, typically supporting Visual Communication Design, Product Design and Environment Design healthcare environment aesthetically pleasing and convenient. However, in recent designs, expertise has increased, new areas specialized are merged with various areas and academic disciplines and subdivided. In addition, due to the development of technology, the design has been continuously changing, creating a new form of model by fusing with various industries, academics and services. Recognizing the changes and developments of these designs, we are promoting research on utilization of design in medical services, we can create a new value by getting out of design that we have limitedly used in areas of traditional design I will try to know about developing into a design.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.302-306
• /
• 2001

Because face Images have many variations(expression, illumination, orientation of face, etc), there has been no popular method which has high recognition rate. To solve this difficulty, data fusion that fuses various information has been studied. But previous research for data fusion fused additional biological informationUingerplint, voice, del with face image. In this paper, cooperative results from several face image recognition modules are fused without using additional biological information. To fuse results from individual face image recognition modules, we use re-defined mass function based on Dempster-Shafer s fusion theory.Experimental results from fusing several face recognition modules are presented, to show that proposed fusion model has better performance than single face recognition module without using additional biological information.

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.239-244
• /
• 2016

Mugshot face images, routinely collected by police, usually contain both frontal and profile views. Existing automated face recognition methods exploited mugshot databases by enlarging the gallery with synthetic multi-view face images generated from the mugshot face images. This paper, instead, proposes to match the query arbitrary view face image directly to the enrolled frontal and profile face images. During matching, the 3D face shape model reconstructed from the mugshot face images is used to establish corresponding semantic parts between query and gallery face images, based on which comparison is done. The final recognition result is obtained by fusing the matching results with frontal and profile face images. Compared with previous methods, the proposed method better utilizes mugshot databases without using synthetic face images that may have artifacts. Its effectiveness has been demonstrated on the Color FERET and CMU PIE databases.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.2
• /
• pp.7-12
• /
• 2001

In this paper, an estimation method of hybrid feature was proposed to detect linear feature such as the road network from SAR(synthetics aperture radar) images that include speckle noise. First we considered the mean intensity ratio or the statistical properties of locality neighboring regions to detect linear feature of road. The responses of both methods are combined to detect the entire road network. The purpose of this paper is to extract the segments of road and to mutually connect them according to the identical intensity road from the locally detected fusing images. The algorithm proposed in this paper is to define MRF(markov random field) model of the priori knowledge on the roads and applied it to energy function of interacting density points, and to detect the road networks by optimizing the energy function.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.2
• /
• pp.723-743
• /
• 2016

Indoor positioning is considered an enabler for a variety of applications, the demand for an indoor positioning service has also been accelerated. That is because that people spend most of their time indoor environment. Meanwhile, the smartphone integrated powerful camera is an efficient platform for navigation and positioning. However, for high accuracy indoor positioning by using a smartphone, there are two constraints that includes: (1) limited computational and memory resources of smartphone; (2) users' moving in large buildings. To address those issues, this paper uses the TC-OFDM for calculating the coarse positioning information includes horizontal and altitude information for assisting smartphone camera-based positioning. Moreover, a unified representation model of image features under variety of scenarios whose name is FAST-SURF is established for computing the fine location. Finally, an optimization marginalized particle filter is proposed for fusing the positioning information from TC-OFDM and images. The experimental result shows that the wide location detection accuracy is 0.823 m (1σ) at horizontal and 0.5 m at vertical. Comparing to the WiFi-based and ibeacon-based positioning methods, our method is powerful while being easy to be deployed and optimized.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.329-334
• /
• 1998

This work is concerned with the problem of tracking a maneuvering target. In this paper, an error monitoring and recovery method of perception net is utilized to improve tracking performance for a highly maneuvering tar-get. Many researches have been performed in tracking a maneuvering target. The conventional Interacting Multiple Model (IMM) filter is well known as a suboptimal hybrid filter that has been shown to be one of the most cost-effective hybrid state estimation scheme. The subfilters of IMM can be considered as fusing its initial value with new measurements. This approach is also shown in this paper. Perception net based error monitoring and recovery technique, which is a kind of geometric data fusion, makes it possible to monitor errors and to calibrate possible biases involved in sensed data and extracted features. Both detecting a maneuvering target and compensating the estimated state can be achieved by employing the properly implemented error monitoring and recovery technique. The IMM filter which employing the error monitoring and recovery technique shows good tracking performance for a highly maneuvering target as well as it reduces maximum values of estimation errors when maneuvering starts and finishes. The effectiveness of the pro-posed method is validated through simulation by comparing it with the conventional IMM algorithm.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.993-1001
• /
• 2011

Unmanned ground vehicle for facility protection mostly uses model of territory for autonomous navigation. However, modeling of territory using several sensors is highly time consuming and sometimes inefficient for road application. Therefore, an estimation of drivable path based on features of road is required for high speed autonomous navigation on road. In this paper, an estimation method of drivable path using camera and 2D laser rangefinder is proposed. First, a vanishing point is estimated based on image data from CCD camera. Second, a road width is estimated based on range data from 2D laser rangefinder. Finally, the drivable path is estimated by fusing the vanishing point and the road width. The proposed method is tested on both well-structured road and unpaved road like cross-country situation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3390-3405
• /
• 2022

Long Short-Term Memory (LSTM) combined with attention mechanism is extensively used to generate semantic sentences of images in image captioning models. However, features of salient regions and spatial information are not utilized sufficiently in most related works. Meanwhile, the LSTM also suffers from the problem of underutilized information in a single time step. In the paper, two innovative approaches are proposed to solve these problems. First, the Synergy-Gated Attention (SGA) method is proposed, which can process the spatial features and the salient region features of given images simultaneously. SGA establishes a gated mechanism through the global features to guide the interaction of information between these two features. Then, the Recurrent Fusion LSTM (RF-LSTM) mechanism is proposed, which can predict the next hidden vectors in one time step and improve linguistic coherence by fusing future information. Experimental results on the benchmark dataset of MSCOCO show that compared with the state-of-the-art methods, the proposed method can improve the performance of image captioning model, and achieve competitive performance on multiple evaluation indicators.

• Journal of Conservation Science
• /
• v.38 no.1
• /
• pp.55-63
• /
• 2022

The Bigyeokjincheolloe (bomb shell), a scientific cultural heritage, has outstanding historical value for sustaining a gunpowder weapon of Joseon. In this study, the bomb shell was modeled through three-dimensional (3D) scanning centered on the external shape and 𝛾-ray radiography-based on the internal shape. In particular, to improve the contrast in the radiographic image, optimization and image processing were performed. After these processes, the thickness of the inner wall (2.5 cm on average) and the positions of the three mold chaplets were clearly revealed. For exhibition purposes, the 3D model of the bomb shell was output to a 3D printer and the output was rendered realistic by coloring. In addition, the internal functional elements, such as Mokgok, fuse, mud, gunpowder, and caltrops, were reproduced through handwork. The results will contribute to the study of digital heritages in two ways. First, the internal and external shapes of the bomb shell were modeled by fusing two different technologies, namely, 3D scanning and 𝛾-ray radiography. Second, the internal shape of the bomb shell was constructed from the original form data and the reproduction was utilized for museum exhibitions. The developed modeling approach will greatly expand the scope of museum exhibitions, from those centered on historical content to those centered on scientific content.