• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.104-113
• /
• 2022

In this paper, we propose deep learning-based target distance and velocity estimation technique for OFDM radar systems. In the proposed technique, the 2D periodogram is obtained via 2D fast Fourier transform (FFT) from the reflected signal after removing the modulation effect. The periodogram is the input to the conventional and proposed estimators. The peak of the 2D periodogram represents the target, and the constant false alarm rate (CFAR) algorithm is the most popular conventional technique for the target's distance and speed estimation. In contrast, the proposed method is designed using the multiple output convolutional neural network (CNN). Unlike the conventional CFAR, the proposed estimator is easier to use because it does not require any additional information such as noise power. According to the simulation results, the proposed CNN improves the mean square error (MSE) by more than 5 times compared with the conventional CFAR, and the proposed estimator becomes more accurate as the number of transmitted OFDM symbols increases.

• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.209-216
• /
• 2005

In wireless sensor networks, an estimation method is proposed for distances between nodes within two hops. The method uses only proximity information of nodes without physiccal distance measurements. It drastically improves the performance of localization algorithms based on Proximity information. In addition, it is the first method that estimates distances between nodes exactly in two hops. The distances are estimated from the number of common neighbors under an assumption that the number of common neighbors is proportional to the intersection of two unit disks centered at the two nodes. Simulation analysis shows that the estimation error is roughly from 10 to 20 percent of real distances. Meanwhile, the number of messages required by a distributed algorithm realizing this method is only two times the number of nodes.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.210-213
• /
• 1999

수동소나체계에서 음원의 위치와 관련된 매개변수를 산출하기 위해 정합장처리(Matched Field Processing)가 이용된다 본 연구에서는 수직선배열센서를 이용한 정합장처리에서 음원 위치추정에 영향을 미치는 다양한 요인 중, 수직음속분포 오정합(mismatch)에 의한 영향을 MV 프로세서 (Minimum Variance Processor)를 이용하여 모의실험함으로써 그 결과를 분석하였다. 천해 모의환경에서 동일한 기울기로 증감하는 수직음속분포 오정합은 음원 위치추정에서 거리성분의 오차를 가지며, 상이한 기울기를 갖는 수직음속분포 오정합은 거리와 수심 성분의 오차가 유발됨을 확인할 수 있었다. 심해 모의 환경에서 수직음속분포 오정합은 거리와 수심 성분의 오차가 유발되고, 거리추정의 전반적인 경향은 천해의 동일한 기울기를 가지는 경우와 유사함을 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.494-500
• /
• 2020

This paper proposes a new distance estimation technique for indoor localization in ultra wideband (UWB) systems. The proposed technique is based on recurrent neural network (RNN), one of the deep learning methods. The RNN is known to be useful to deal with time series data, and since UWB signals can be seen as a time series data, RNN is employed in this paper. Specifically, the transmitted UWB signal passes through IEEE802.15.4a indoor channel model, and from the received signal, the RNN regressor is trained to estimate the distance from the transmitter to the receiver. To verify the performance of the trained RNN regressor, new received UWB signals are used and the conventional threshold based technique is also compared. For the performance measure, root mean square error (RMSE) is assessed. According to the computer simulation results, the proposed distance estimator is always much better than the conventional technique in all signal-to-noise ratios and distances between the transmitter and the receiver.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1997.06a
• /
• pp.44-46
• /
• 1997

Near field 에서는 진폭 감쇄정보를 이용할 수 있으므로 음원의 거리와 도래각을 추정하는 것이 가능하다. 고정된 3개의 수음점에서 자기,상관 파워스펙트럼 분석을 하여 추정하는 원리와 추정치의 분포영역, 음원의 정위한계에 대하여 나타내었다.

• 한국IT서비스학회:학술대회논문집
• /
• 2006.05a
• /
• pp.241-248
• /
• 2006

네트워크 거리 (Network distance : 일반적으로 ping이나 traceroute 등으로 측정 가능한 round trip time 등 네트워크 상에서 패킷 전송 시간) 추정 기법은 인터넷상의 많은 응용프로그램들에서 유용하게 사용된다. 예를 들면 다수의 서버를 인터넷상에 설치하고자 하는 경우 사용자들 간의 네트워크 거리를 알고 있다면 서버와 사용자간의 왕복 전송 시간 (Round Trip Time)등을 최소화할 수 있도록 서버를 분산하여 설치하는 구성을 도출해 낼 수 있을 것이다. Peer to Peer 응용 프로그램들에서도 이 네트워크 거리 정보는 매우 유용하다. 기존에 존재하는 추정 기법들은 대부분 유클리드 공간 좌표 기반 기법들로서 유클리드 좌표 상의 거리가 실제 네트워크 거리와 유사하도록 유클리드 공간 좌표를 지정한다. 그러나 이런 방법들의 문제점은 인터넷 상의 네트워크 거리가 삼각 부등식을 만족하지 않는 경우가 존재하는 등 유클리드 공간의 기본적인 가정을 만족하지 못한다는데 있다. 이런 문제점 때문에 새로운 모델이 필요하고, 이 논문에서는 가상 토폴로지(Virtual Topology) 모델과 지역 조정 항 (Local Adjustment Term) 모델을 제시하고, 기본적인 성능 분석을 시도하였다.

• 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.