• Journal of the Korea Society of Computer and Information
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2018

In this paper, a kidnapping detection scheme in which human pose estimation is used to classify accurately between kidnapping cases and normal ones is proposed. To estimate human poses from input video, human's 10 joint information is extracted by OpenPose library. In addition to the features which are used in the previous study to represent the size change rates and the regularities of human activities, the human pose estimation features which are computed from the location of detected human's joints are used as the features to distinguish kidnapping situations from the normal accompanying ones. A frame-based kidnapping detection scheme is generated according to the selection of J48 decision tree model from the comparison of several representative classification models. When a video has more frames of kidnapping situation than the threshold ratio after two people meet in the video, the proposed scheme detects and notifies the occurrence of kidnapping event. To check the feasibility of the proposed scheme, the detection accuracy of our newly proposed scheme is compared with that of the previous scheme. According to the experiment results, the proposed scheme could detect kidnapping situations more 4.73% correctly than the previous scheme.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1188-1191
• /
• 2020

In this paper, automotive safety and convenience service is proposed based on bluetooth and smart watch. The proposed service performs accident detection, kidnapping detection, kid-left-alone-in-car detection, parking location recording, and smart key function. Conventional smartphone services often fails to precisely recognize accident and kidnapping situations since smartphone is located on the dashboard or in the bag. On the contrary, smartwatch recognizes accident and kidnapping situations more precisely since it is always worn on the wrist with hearbeat monitoring. The proposed service recognise various situations around drives and passengers using acceleration sensor, GPS sensor, heartbeat sensor and bluetooth link status. It also performs accident notice, sound recording, and other necessary actions. It also performs door opening, door closing, hazard light flickering, and other necessary actions using OBD-II connection to the vehicle.

• Korean journal of communication and information
• /
• v.48
• /
• pp.211-230
• /
• 2009

This study aims to trace the main tendency found in Korean broadcasting news coverage of terror throughout the kidnapping of Sun Il Kim. For this purpose, this study analyzed the contents of 386 news stories found in KBS, MBC, and SBS. Through this process, it investigated the main theme and source found in the coverage of kidnapping. In addition, it analyzed how the press described Al Tawhid Al Jihad, known as the organization who kidnapped Mr. Kim and how well the press transmit the social, historical background of terror. As a result, the dominant theme found in three news company was that which dealt with investigations about suspicions about kidnapping and suspicions related to the kidnapping. However, the voice against dispatching armed forces and the demand of terrorist were seldom found in the coverage. The news sources which three broadcasting news depended on heavily was governmental officials and the media including Al Jazeera was also main source. The description of Al Tawhid Al Jihad by the press was somewhat negative and the expression 'militarized forces' were found mostly. The news which announced the social, historical background of terror were minimal, which indicated that the coverage of terror in Korean broadcasting was still episodic.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.43-45
• /
• 2008

위 인식은 이동 로봇의 자율 주행을 위한 필수 기능이다. 위치 추정을 위해서 Bayes Filter를 기본으로한 칼만 필터 방법들이 주로 제안되어졌고 최근에는 Particle Filter 방법이 제안되어져 사용되고 있다. 본 연구에서는 영역센서를 장착한 이동 로봇의 위치 추정을 위해 레이저 영역 센서를 이용하는 Particle Filter 방법을 구현하였다. Particle Filter방법은 Kalman Filter 방법에 비해서 구현이 간단하면서도 Kidnapping 문제에도 대응할 수 있는 장점이 있다. 본 연구를 통하여 위치 추정의 수렴도, 정확도, 그리고 Kidnapping 발생시의 위치 추정 성능등을 분석하여, 기존 방법의 성능을 개선하는 방법을 제안한다.

• Korean Security Journal
• /
• no.13
• /
• pp.507-528
• /
• 2007

June 2006, five korean oil workers, three who worked for Daewoo and two for Korea Gas, released after being held hostage by separatist militants in Nigeria. The kidnapping was happened in the Niger Delta where armed separatists are demanding a larger share in oil revenues and compensation for environmental destruction due to oil exploration. Seven months later, nine Korean pipeline workers of Daewoo together with a Nigerian were kidnapped again and safely released thanks to the efforts of the company and the Korean government. These two kidnapping incidents have shown that companies engaged in the overseas business are not safe any more from the terrorist attacks and has given an invaluable lesson that the company having an intention to go abroad for business should take all possible anti and counter-measures against terrorism. The main purpose of this study is to suggest a guideline for the establishment of counter-terrorism and security strategy against terrorist attacks on the private companies at the overseas. In order to foster a better understanding of the problem, a brief history of terrorism is presented in the first part. In addition, this study analyses and describes the variations of terrorist attacks against private companies together with the terrorism related environment of Korea. Based on the outcome of the study, this paper takes a global view and perspectives of terrorist attacks against private companies and suggests consideration for the future.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.92.3-92
• /
• 2002

A lot of localization algorithms have been developed in order to achieve autonomous navigation. However, most of localization algorithms are restricted to certain conditions. In this paper, Monte Carlo localization scheme with a map-matching algorithm is suggested as a robust localization method for the Public Service Robot to accomplish its tasks autonomously. Monte Carlo localization can be applied to local, global and kidnapping localization problems. A range image based measure function and a geometric pattern matching measure function are applied for map matching algorithm. This map matching method can be applied to both polygonal environments and un-polygonal environments and achieves...

• Korean Security Journal
• /
• no.6
• /
• pp.215-233
• /
• 2003

The Serial murder is a serious social phenomenon that gives a shock to community and society, because of it's habituate and scheme. We could identify a happening of serial killing crime at Western society, especially in U. S, but hardly to find many cases in Korea except some of cases. We can easily prospect the happening of serial killing crime at Korea in the future, at least it exists that home and social disorganization cause by divorcing and hasty economic development. There will be a reserve criminal who have distorted personality effected by undesirable surrounding, therefore he may become a serial murder. This study examines criminal psychological analysis of On Bo Hwan's serial murder case in 1994 at Korea, according to criminal records and press report and his statement and confession. This paper also show his domestic background and growing atmosphere and human relation between his parents.

• The Journal of Korea Robotics Society
• /
• v.3 no.3
• /
• pp.245-254
• /
• 2008

Recently, many vision-based navigation methods have been introduced as an intelligent robot application. However, many of these methods mainly focus on finding an image in the database corresponding to a query image. Thus, if the environment changes, for example, objects moving in the environment, a robot is unlikely to find consistent corresponding points with one of the database images. To solve these problems, we propose a novel navigation strategy which uses fast motion estimation and a practical scene recognition scheme preparing the kidnapping problem, which is defined as the problem of re-localizing a mobile robot after it is undergone an unknown motion or visual occlusion. This algorithm is based on motion estimation by a camera to plan the next movement of a robot and an efficient outlier rejection algorithm for scene recognition. Experimental results demonstrate the capability of the vision-based autonomous navigation against dynamic environments.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.554-556
• /
• 2006

A key component for autonomous mobile robot is to localize ifself. In this paper we suggest a vision-based localization and compensation of robot's location using ultrasound. Mobile robot travels along wall and searches each feature in indoor environment and transformed absolute coordinates of actuality environment using these points and builds a map. And we obtain information of the environment because mobile robot travels along wall. Localzation search robot's location candidate point by ultrasound and decide position among candidate point by features matching.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.5
• /
• pp.1165-1171
• /
• 2012

Latest, it is dealt with seriously problems that an intruder kidnapping students in elementary school. Especially young students is more vulnerable in these risks. Elementary School has many limitations in controlling the intrusion of trespassers. A problem occurs that requires a lot of manpower through the deployment and management of security systems such as CCTV and control systems. In this paper, we is designed and implemented the outsider access management system using a sensor network and PZT camera called the USN's core technology to monitoring the access control for controlling the mobility of the trespassers.