• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1697-1702
• /
• 2017

This paper proposes a forward vehicle movement estimation algorithm for the image-based forward collision warning. The road region in the acquired image is designated as a region of interest (ROI) and a distance look up table (LUT) is made in advance. The distance LUT shows horizontal and vertical real distances from a reference pixel as a test vehicle position to any pixel as a position of a vehicle on the ROI. The proposed algorithm detects vehicles in the ROI, assigns labels to them, and saves their distance information using the distance LUT. And then the proposed algorithm estimates the vehicle movements such as approach distance, side-approaching and front-approaching velocities using distance changes between frames. In forward vehicle movement estimation test using road driving videos, the proposed algorithm makes the valid estimation of average 98.7%, 95.9%, 94.3% in the vehicle movements, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.7B
• /
• pp.595-605
• /
• 2012

DV-Hop is one of the well known range-free localization algorithms. The algorithm works well in case of isotropic network since the sensor and anchor nodes are placed in the entire area. However, it results in large errors in case of anisotropic networks where the hop count between nodes is not linearly proportional to the Euclidean distance between them. Hence, we proposed a novel range-free algorithm for anisotropic networks to improve the localization accuracy. In the paper, the Euclidean distance between anchor node and unknown node is estimated by the average hop distance calculated at each hop count with hop count and distance information between anchor nodes. By estimating the unknown location of nodes with the estimated distance estimated by the average hop distance calculated at each hop, the localization accuracy is improved. Simulation results show that the proposed algorithm has more accuracy than DV-Hop.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.6C
• /
• pp.453-461
• /
• 2012

This paper proposes an improved phase estimation method for AM(Amplitude Modulation) range measurement system. The previous phase estimation method induces errors by Doppler shift of a moving target. The proposed method compensates phase estimation error through the ADC(Adaptive Doppler Correction) to take the Doppler shift, thus can improve distance measurement accuracy. When compared with the previous method through simulation results, the Doppler shift compensation and accuracy are improved by 94.7% and 50%, respectively. Target distance error in an acoustic tank is estimated to be 7.7cm, which confirms that the proposed method can be used to estimate the distance in the marine environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.560-561
• /
• 2023

지진, 대형화재와 같은 많은 재해의 발생으로 인해 재난 안전 분야에 관심이 증가하고 있으며, 재난재해 시 신속하고 안전한 구조는 생존율에 영향을 준다. 기존 연구에서는 다양한 센서와 멀티카메라를 이용한 위치 추정 연구는 있으나, 가장 많이 설치된 단일카메라 기반의 위치 추정연구는 부족한 상태이다. 본 논문에서 단일카메라를 활용한 딥러닝 객체탐지와 거리측정 알고리즘을 이용하여 인명구조를 위한 구조대상자 위치추정시스템을 제안한다. 딥러닝을 활용한 객체탐지 기술을 이용하여 단일카메라 영상 내 객체와 해상도에 따른 바운딩 박스의 너비를 활용한 거리 계산식으로 거리를 추정하고, 객체의 위치좌표를 제공하여 신속한 재난 구조에 도움이 되는 시스템을 제안한다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.109-119
• /
• 2011

The virtual reality (VR) technology has been used as the application of architectural presentation or simulation tool in the field of industry. The high immersion and intuitive visual information are the great merits of design evaluation or environmental simulation when we are using the virtual environments. But the distortion of distance perception in VR is still a big problem when the accuracy of distance presentation is strictly required. For example, distance estimation is especially important when the virtual environments are applied to the presentational tool for evaluation the space design or planning in the field of architecture. If there are some perception error between the built space in real and represented space in virtual, the accurate design evaluation or modification of design is hard to be carried out during the design development stage. In this paper, we have carried out some experiments about distance estimation in the immersive virtual environments to verify the factors and their influence. We made a hypothesis that the lack of the information for the user in VR causes the different distance estimation from the real world because users are usually comfortable with moving fast and long distance in VR environments compared with moving slow and short distance in real space. So, we carried out basic experiment to prove our hypothesis that the lack of information makes subjects estimate the distance of walking in VR shorter compared with the same distance in real. Also, among the factors that probably affect the distance estimation in VR, we have verified the influence of the image resolution. The influence of resolution degradation of image on the distance estimation was verified with the condition of static and dynamic images. The results showed that the resolution has deep relation with the distance estimation. For example, the subject underestimated the distance at the lower resolution condition. We also found the methods of the making the lower resolution image could affect on the visual perception of subjects.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.305-311
• /
• 2006

In this paper the performance of a array invariant method is evaluated for source-range estimation in horizontally stratified shallow water ocean waveguide. The method has advantage of little computationally effort over existing source-localization methods. such as matched field processing or the waveguide invariant and array gain is fully exploited. And. no knowledge of the environment is required except that the received field should not be dominated by purely interference This simple and instantaneous method is applied to simulated acoustic propagation filed for testing range estimation performance. The result of range estimation according to the SNR for the underwater impulsive source with broadband spectrum is demonstrated. The spatial smoothing method is applied to suppress the effect of mutipath propagation by high frequency signal. The result of performance test for range estimation shows that the error rate is within 20% at the SNR above 10dB.

• Journal of Korean Society of Transportation
• /
• v.20 no.2
• /
• pp.125-134
• /
• 2002

도시화물수요예측모형에는 화물기반모형과 트럭통행기반모형이 있는데 화물기반모형은 화물체계가 기본적으로 화물운송과 관계가 있다는 개념에 기초를 두고 있으며, 차량이 아닌 화물의 움직임을 주요 분석대상으로 삼고 있다. 반면에, 트럭통행기반모형은 집합화된 독립변수를 이용하여 각 죤(Zone)에 유·출입하는 트럭의 통행을 분석하는 것이다. 본 연구의 목적은 트럭통행기반모형의 O-D 추정시 화물통행과 트럭통행 사이의 관계식을 산출하고 이를 설명할 수 있는 통행거리분포함수(Trip Length Distribution : TLD)를 추정함에 있다. 본 연구의 자료는 교통개발연구원에서 수행한 '서울시 물류조사 및 물류종합계획수립구상(1998)'의 화물 물동량 조사 자료를 이용하였으며, 이를 통해 통행거리분포에 따르는 화물 및 차량의 비율을 함수로서 나타내었다. 본 연구를 통하여 트럭통행기반모형에서 트럭통행거리분포를 이용하여 화물기반모형에서 도출할 수 있는 화물의 통행거리분포를 추정할 수 있었으며, 또한 각각의 통행거리분포는 감마분포를 이용하여 함수식으로 도출하고 상기한 두 가지 분포모형을 하나의 관계식을 통해 재산정할 수 있는 이론적인 틀을 제공하였다는 데 의의가 있다고 하겠다. 트럭통행거리분포, 화물통행거리분포 모두 통계적인 검증을 통해 적합한 것으로 분석되었으며, 전체화물의 통행거리분포와 매개함수를 통해 재산정된 모형의 결과 값 또한 통계적으로 유의하였다. 품목별 적용에서는 잡공업품과 화학공업품은 본 연구의 매개함수식을 통해 화물거리분포 모형이 적합하였으나 금속공업 품과 경공업품은 다소 차이가 있는 것으로 분석되었다.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1802_1803
• /
• 2009

위치추정은 현재 이동로봇 분야에서 매우 중요하게 다루어지는 문제이다. RFID 위치추정 시스템은 저렴하고, 오차누적의 위험이 없고, map과 같은 사전정보의 제약이 없기에 범용적으로 사용될 수 있다. 하지만 RFID 위치추정에 있어, tag들의 서로 다른 인식거리 차이는 위치추정의 오차를 증폭시키는 역할을 한다. 따라서 이 논문에서는 이를 극복하기 위해 tag들의 인식거리 정보를 활용하여 위치추정을 수행한다. 또한 보다 정확한 위치추정을 위해, 송신신호 전력조절을 통하여, 인식거리를 조절하는 방법을 사용한다. 이들의 성능은 simulation을 통해서 확인하였다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.353-356
• /
• 2001

본 논문은 수중 음향을 이용하여 다중경로(Multipath) 환경에서의 해저면 설치 수신기의 3차원 위치 추정 알고리즘을 제안한다. 해저면 설치 수신기의 위치 추정을 위해 기준 음원의 위치와 음원과 수신기 사이의 수평거리를 사용하며, 수평거리 산출 시 다중경로의 영향을 고려하기 위해 음선 이론 모델을 사용하여 음원과 수신기 사이의 수평거리를 추정한다. 또한 특이치 분해법(Singular Value Decomposition estimator; SVD)을 사용하여 설정된 3차원 위치 추정 문제의 최적해를 추정하며, 이를 사용하여 동해 해상 실험 자료를 분석한다. 논문의 연구 결과 제안된 해저면 설치 3원 위치 추정 알고리즘은 다중경로 환경에서도 좋은 성능을 나타냄을 알 수 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.279-286
• /
• 2021

Recently, We are carrying out a policy of physical distancing of at least 1m from each other to prevent the spreading of COVID-19 disease in public places. In this paper, we propose a method for measuring distances between people in real time and an automation system that recognizes objects that are within 1 meter of each other from stereo images acquired by drones or CCTVs according to the estimated distance. A problem with existing methods used to estimate distances between multiple objects is that they do not obtain three-dimensional information of objects using only one CCTV. his is because three-dimensional information is necessary to measure distances between people when they are right next to each other or overlap in two dimensional image. Furthermore, they use only the Bounding Box information to obtain the exact coordinates of human existence. Therefore, in this paper, to obtain the exact two-dimensional coordinate value in which a person exists, we extract a person's key point to detect the location, convert it to a three-dimensional coordinate value using Stereo Vision and Camera Calibration, and estimate the Euclidean distance between people. As a result of performing an experiment for estimating the accuracy of 3D coordinates and the distance between objects (persons), the average error within 0.098m was shown in the estimation of the distance between multiple people within 1m.