• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.31-39
• /
• 2006

This paper presents a novel approach to real-time recognition of 3D environment and objects for various applications such as intelligent robots, intelligent vehicles, intelligent buildings,..etc. First, we establish the three fundamental principles that humans use for recognizing and interacting with the environment. These principles have led to the development of an integrated approach to real-time 3D recognition and modeling, as follows: 1) It starts with a rapid but approximate characterization of the geometric configuration of workspace by identifying global plane features. 2) It quickly recognizes known objects in environment and replaces them by their models in database based on 3D registration. 3) It models the geometric details the geometric details on the fly adaptively to the need of the given task based on a multi-resolution octree representation. SIFT features with their 3D position data, referred to here as stereo-sis SIFT, are used extensively, together with point clouds, for fast extraction of global plane features, for fast recognition of objects, for fast registration of scenes, as well as for overcoming incomplete and noisy nature of point clouds.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.651-658
• /
• 2015

Recently, lots of research works have been actively focused on the self-driving car. In order to implement the self-driving car, lots of fusion techniques should be merged and, specially, it is noted that a vehicle-attached camera can provide several useful functionalities such as traffic lights recognition, pedestrian detection, stop-line recognition including simple driving records. Accordingly, as one of the efficient tools for the self-driving car implementation, this paper proposes a mathematical model for estimating effectively the road distance with a vehicle-attached black box camera. The proposed model can be effectively used for estimating the road distance by using the height of black box camera or the widths of the referenced road line and the observed road line. Through several simulations, it is shown that the proposed model is effective in estimating the road distance.

• Archives of design research
• /
• v.13 no.4
• /
• pp.57-66
• /
• 2000

The Korea's automotive industry have been achieved a remarkable growth with various original models since the first original model ‘Pony’for the 25years. Most of the design works were depended upon the designers of the other countries on the early times, but now the design work gets to have the independency with our own technology and the automobile is now one of the major exporting goods of Korea to other countries. The basic design concept of the body shape can be considered into four types, and they have their own characteristics. The period of time for the original model developement of the Korean auto makers can be thought as four periods ; introducing period, settling period, developing period and matured period are them. The models that developed on each period reflects the characteristics of the times with designers, technology and market conditions. The basic design concepts of the Korean car body show the variety but the concepts have been intergrated into the two types as the time gose by. This tendency would comes form mainly technology, but the consumers characteristics of the market would also influence as much as the technological reason. It would become more important on developing the original model with the autonomy in design concept of the body through grasping the change of formal characteristics clearly on an automobile in the future.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.791-794
• /
• 2021

범죄차량 판독 시스템, 지능화된 CCTV 등 차량과 관련된 시각지능에 관한 연구가 큰 관심을 받고 있다. 이 중 차량 분류 기술은, 특정 차량을 인식하는 핵심기술이다. 이와 관련한 기존 연구들은 큰 차종으로만 분류하거나, 분류 가능한 차종의 수, 정확도 등이 낮아 실용성 및 신뢰성이 떨어진다는 단점이 있다. 따라서, 본 논문에서는 차종을 정확하게 분류할 수 있는 2단계 차종 분류 알고리즘을 제안한다. 제안 시스템은 CNN으로 학습된 모델을 기반으로 1차로 차량의 유형을 분류하고, 2차로 정확한 차종을 분류한다. 실험 결과, 52개의 차종을 분류함에 있어 단일 분류 모델에 비해 5.3%p 더 높은 90.2%의 분류 정확도를 보였다. 이를 통해, 더욱 정확한 차종 분류가 가능하다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1026-1031
• /
• 2021

With the development of global automotive technology and the expansion of market size, demand for vehicles is increasing, which is leading to a decrease in the number of passengers on the road and an increase in the number of vehicles on the road. This causes traffic jams, and in order to solve these problems, the number of illegal vehicles continues to increase. Various technologies are being studied to crack down on these illegal activities. Previously developed systems use trigger equipment to recognize vehicles and photograph vehicles using infrared cameras to detect the number of passengers on board. In this paper, we propose a vehicle occupant detection system with deep learning model techniques without exploiting existing system-applied trigger equipment. The proposed technique proposes a system to detect vehicles by establishing triggers within images and to apply deep learning object recognition models to detect real-time boarding personnel.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.5
• /
• pp.919-929
• /
• 2013

Recently, a variety of IT technologies are applied to the vehicle. However, some vehicle-IT technologies without security considerations may cause security problems. Specially, some researches about a smart key system applied to automobiles for authentication show that the system is insecure from replay attacks and modification attacks using a wireless signal of the smart key. Thus, in this paper, we propose an authentication method for the driver by using driving patterns. Nowadays, we can obtain driving patterns using the In-vehicle network data. In our authentication model, we make driving ppatterns of car owner using standard normal distribution and apply these patterns to driver authentication. To validate our model, we perform an k-fold cross validation test using In-vehicle network data and obtain the result(true positive rate 0.7/false positive rate is 0.35). Considering to our result, it turns out that our model is more secure than existing 'what you have' authentication models such as the smart key if the authentication result is sent to the car owner through mobile networks.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.7 no.1
• /
• pp.128-131
• /
• 1996

소아들의 음성장애의 대부분은 음성과 기능에 의한 성대의 오용 및 남용으로부터 기인한다. 그러나 음성장애에 대한 인식의 부족으로 인하여 소아의 음성장애 발견율은 극히 낮은 수준에 머므르고 있다. 치료에 있어서도 행동의 통제가 그다지 쉽지 않기 때문에 많은 어려움이 따른다. 본 연구는 소아의 음성장애의 발생경위와 문제의 설명과 차팅에 의한 남용의 감소에 초점을 둔 치료사례이다. 5세 아동의 심한 음성장애로 의뢰되어졌다. 음성증후는 목쉰소리, 기식화된 소리, 일시적인 발성일탈(phonation break) 등이 두드러졌다. 이비인후과 전문의의 스트로보스코프(stroboscope) 검진결과 초기 양측성 성대결절이 성대 앞쪽으로부터 1/3 지점에서 발견되었으며 비지피치(Visi-Pitch)로 측정된 퍼터베이션(perturbation 수치가 16.8이었다. 사례사 조사 과정에서 아동이 활동적이며 자주 고함을 지르고 자동차놀이를 주로하며 많은 시간을 보낸다는 것이 밝혀졌다. 중재 프로그램은 우선 문제를 설명하고 인식시키는 것과 고함을 지르거나 자동차놀이를 하면서 자동차 소음을 흉내내는 등의 음성남용 회수를 감소시키는 것에 초점을 두었다 17회의 치료로 성대결절이 감소되었고 퍼터베이션은 3.8로 저하되었으며 아동 스스로 음성남용을 통제할 수 있다는 임상적 판단하에 치료를 종결하였다. 1개월 후 추후 검사에서 남용적인 습관이 여전히 나타나지 않았으며 음성상태도 양호하였다. 소아 음성장애의 치료는 소아가 이해할 수 있는 용어로 문제의 인식을 확실히 시키고 행동을 체계적으로 통제할 수 있는 치료프로그램을 실행시키는 임상가의 자질이 대단히 중요하다. 그러나 그에 못지 않게, 많은 시간을 아동과 함께 보내는 부모나 교사의 협력이 치료의 성패를 좌우할 수 있다.조구와 처리구간에 차이가 없었다. 그러나 유지방 함량의 경우 대조구가 3.22%, 처리구가 3.37%로 처리구가 0.15% point 증가했으나 유의차는 없었다. Fan ＋ sprinkler가 설치된 시설에서 사육된 젖소에서 생산된 우유내 체세포수는 대조구에 비해 26.63%가 감소되었으나 유의차는 발견할 수 없었다. 이상의 시험 결과에서 볼 때 fan ＋ sprinkler를 이용한 방서 방법은 고온 stress를 완화시켜 유생산성의 증가에 기여할 수 있는 하나의 방법이라고 본다.을 알 수가 있었다.없다. 본 논문의 대상은 바로 이러한 합성 동사성명사의 논항구조와 동사성명사에 의해 하위범주화된 논항들의 문법적 실현양상이다..그 결과 심리적 특성과 사용자 수용 특성은 아바타 수용도에 부분적으로 영향을 미친다는 것 결과가 나타났다.웨어 프로세스 평가와 개선 모델의 개발을 위한 기초적인 자료를 제공할 것으로 예상된다 또한, 본 연구 결과는, 우리나라 소프트웨어 조직들이 실제로 무엇을 필요로 하는지를 밝힘으로써, 우리나라의 소프트웨어 산업을 육성하기 위한 실효성 있는 정책 입안을 위한 기초 자료를 제공할 것으로 예상된다.다.를 검증하려고 한다. 협력체계 확립, ${\circled}3$ 전문인력 확보 및 인력구성 조정, 그리고 ${\circled}4$ 방문보건사업의 강화 등이다., 대사(代謝)와 관계(關係)있음을 시사(示唆)해 주고 있다.ble nutrient (TDN) was highest in booting stage (59.7%); however no significant difference was found among other stages. The concentrations of Ca and P were not

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.12
• /
• pp.8940-8947
• /
• 2015

Mixed-model assembly line has been widely used in automotive assembly industry to quickly respond the diverse product demands. But, this model can lead to part confusion, which is a source for assembly errors when parts are physically interchangeable in a mixed-model assembly line. With the recent application of new technologies such as radio frequency identification (RFID) and ZigBee wireless sensor network (WSN) to the assembly process, real-time information has become available in this manufacturing systems through IT infrastructures. At first, this paper presents an RFID application for assembly processes, specifically, for a mixed-model assembly line. Thus, to ensure that parts be picked accurately, each cockpit module on the assembly line is attached with a RFID tag and the tag is scanned using a RFID reader and recognizes the vehicle, and each part of the cockpit module is attached with a barcode and the barcode is scanned by a barcode reader and each part is identified correctly for the vehicle. Second, this paper presents a ZigBee wireless sensor network (WSN) protocol-based application for a reconfigurable mixed-model assembly line of cockpit module to reduce the assembly errors and the cost of the change/reconfiguration on the assembly lines due to the various orders and new models from the motor company, avoiding the wiring efforts and inconvenience by wiring between the several RFID devices and the IT server system. Finally, we presents the operation results for several years using this RFID/ZigBee wireless sensor network (WSN) protocol-based cockpit module assembly line.

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.203-212
• /
• 2015

This paper proposes a traffic sign recognition method in real road environments. The video stream in driving environments has two different characteristics compared to a general object video stream. First, the number of traffic sign types is limited and their shapes are mostly simple. Second, the camera cannot take clear pictures in the road scenes since there are many illumination changes and weather conditions are continuously changing. In this paper, we improve a modified census transform(MCT) to extract features effectively from the road scenes that have many illumination changes. The extracted features are collected by histograms and are transformed by the dense descriptors into very high dimensional vectors. Then, the high dimensional descriptors are encoded into a low dimensional feature vector by Fisher-vector coding and Gaussian Mixture Model. The proposed method shows illumination invariant detection and recognition, and the performance is sufficient to detect and recognize traffic signs in real-time with high accuracy.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.12 no.1
• /
• pp.121-135
• /
• 2013

This paper propose an efficient algorithm for selecting electric bus charging facility location. In nature, the optimal charging facility location problem is similar to Set Covering Problem. Set Covering Problem is the problem of covering all the rows of an $m{\times}n$ matrix of ones and zeros by a subset of columns with a minimal cost. It has many practical applications of modeling of real world problems. The Set Covering Problem has been proven to be NP-Complete. In order to overcome the computational complexity involved in seeking optimal solutions, this paper present an enhanced greedy algorithm and simulated annealing algorithm. In this paper, we apply the developed algorithm to Seoul's public bus system.