• Journal of the Korea Institute of Building Construction
• /
• v.23 no.2
• /
• pp.209-220
• /
• 2023

Ensuring accuracy within tolerance is crucial for a marking robot; however, rebar displacement frequently occurs during the structural work process, necessitating corrections to layout lines or rebar locations. To guarantee precision and automation, the marking robot must be capable of measuring rebar error and determining appropriate adjustments for marking lines and rebar placement. Consequently, this study proposes a method for measuring rebar location error using a LiDAR sensor and implementing a layout assessment process based on the measurement results. The rebar recognition experiment using the LiDAR sensor yielded an average error of 5mm, demonstrating a reliable level of accuracy for wall rebars. Additionally, this research proposed a process that enables the robot to evaluate rebar and marking corrections based on the error range. The findings of this study can contribute to the automated operation of marking robots while accounting for construction errors, potentially leading to improvements in structural quality.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.81-84
• /
• 2004

본 논문에서는 1대의 CCD카메라로 주행 중 차선과 선행차량을 인식하고 선행차량까지의 거리를 실시간으로 계측하는 알고리즘을 제시하였다. 도로와 카메라간의 기하구조를 분석하여 사영행렬을 추출하였고, 주행 중 차간 거리를 실시간으로 계측하는데 이용하였다. 또한 차선 인식을 위해서 Hough Transform을 적용하여 처리시간을 단축하였다. 도로상의 장애물은 인식된 주행차선 내로 한정하였고 도로 영상에서 수평에지성분을 구한 후 히스토그램 투영을 적용하여 장애물을 검출하였다. 거리가 점차 멀어질수록 계측오차가 증가함을 볼 수 있었으나 기존의 방법에 비하여 주행 중에 운전자가 장애물을 판단하여 제동을 취할 수 있는 정도의 유효한 오차특성을 보였다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.1
• /
• pp.156-161
• /
• 2009

This paper proposes a new method about performance improvement of soccer robots system by the revision of lens distortion most commonly occurred in camera and the revision of position and angle error in robot patch for the realization of robot position. Among the lens distortions, we revise geometrical distortion and apply it to soccer robots system for realtime environment. Patch used in the recognition and the distinction for coordination and direction of robot occurs a position and angle error according to the figure of it. In this paper, we suggest the method of reduction for position and angle error of robot by improved patch and verify its propriety through the experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2177-2184
• /
• 2012

A different and effective method for indoor positioning system is needed and increased it's importance compare to the outdoor GPS based method. The FingerPrint positioning method is known as a superior method in indoor positioning system that maintains signal strength patterns for RPs(Reference Points) in database and compare the DB with the measured real-time signals on the mobile device. FingerPrint positioning method is necessary to establish an accurate database, but errors can occur by several factors. In this paper, we analyze the signal patterns of each terminal in accordance with connection state of access point and trace that the error in accordance with connection state of access point can be an important error in FingerPrint DB configuration through an experimental case study.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.141-146
• /
• 2018

Recently, location recognition technology has attracted much attention, especially for locating people or objects in an indoor environment without being influenced by the surrounding environment GPS technology is widely used as a method of recognizing the position of an object or a person. GPS is a very efficient, but it does not allow the positions of objects or people indoors to be determined. RFID is a technology that identifies the location information of a tagged object or person using radio frequency information. In this study, an RFID system is constructed and the position is measured using tags. At this time, an error occurs between the actual and measured positions. To overcome this problem, a neural network is trained using the measured and actual position data to reduce the error. In this case, since the number of read tags is not constant, they are not suitable as input values for training the neural network, so the neural network is trained by converting them into center-of-gravity inputs and median value inputs. This allows the position error to be reduce by the neural network. In addition, different numbers of trained data are used, viz. 50, 100, 200 and 300, and the correlation between the number of data input values and the error is checked. When the training is performed using the neural network, the errors of the center-of-gravity input and median value input are compared. It was found that the greater the number of trained data, the lower the error, and that the error is lower when the median value input is used than when the center-of-gravity input is used.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.63-65
• /
• 2012

본 논문에서는 입력된 음성이 남성화자인지 여성화자인지를 구분하는 FFT 스펙트럼 및 LPC 켑스트럼 입력에 의한 성별인식 알고리즘을 제안한다. 본 논문에서는 특히 남성화자와 여성화자의 특징벡터를 비교 분석하여, 이러한 남녀의 음향학적인 특징벡터의 차이점을 이용하여 신경회로망에 의한 성별 인식에 대한 실험을 수행한다. 특히 12차의 LPC 켑스트럼 및 8차의 저역 FFT 스펙트럼의 특징벡터를 사용한 경우에, 남성화자 및 여성화자에 대해서 양호한 남녀 성별인식률이 구해졌다.

• Proceedings of the KAIS Fall Conference
• /
• 2008.11a
• /
• pp.240-242
• /
• 2008

본 논문은 치아의 전치 교합과 후치 교합 상태에서 획득된 영상들에 대해 BMME와 LDA에 기반한 개인 인증 방법을 제안한다. 이 방법은 두 치아 교합 상태의 영상들로부터 치아 영역 추출, BMME, 패턴인식 과정으로 구성된다. 두 상태의 치아 교합을 사용하면 영상에서 일정한 치아 모양이 유지되며, BMME는 패턴인식에서 정합 오차를 줄일 수 있도록 해 준다. 강체인 치아는 영상 획득시 왜곡되지 않으므로 치아 영상을 이용하는 방법은 생체 인식에 장점으로 작용한다. 실험에서, 제안한 방법은 20명에 대해 개인 인증을 위한 인식에 성공하여 다중 인증 시스템에 사용될 수 있음을 보였다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.210-216
• /
• 2017

In the paper we propose and implement a new indoor localization system where the techniques of magnetic field based fingerprinting and pedestrian dead reckoning are combined. First, we determine a target's location by comparing acquired magnetic field values with a magnetic field map containing pre-collected field values at different locations and choosing the location having the closest value. As the target moves, we use pedestrian dead reckoning to estimate the expected moving path, reducing the maximum positioning error of the initial location. The system eliminates the problem of localization error accumulation in pedestrian dead reckoning with the help of the fingerprinting and does not require Wi-Fi AP infrastructure, enabling cost-effective localization solution.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.817-822
• /
• 2011

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame using a neural network training by back-propagation algorithm, then proposes the spectral subtraction method which removes the noises at each frame according to detection of the speech and noise sections. In this experiment, the performance of the proposed recognition system was evaluated based on the recognition rate using various speeches that are degraded by white noise and car noise. Moreover, experimental results of the noise reduction by the spectral subtraction method demonstrate using the speech and noise sections detecting by the speech recognition algorithm at each frame. Based on measuring signal-to-noise ratio, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise using signal-to-noise ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.3 no.2
• /
• pp.46-58
• /
• 1984

본 논문은 한국어 음성 인식을 위한 유성음, 무성음, 묵음 식별에 관한 연구이다. 주어진 음성 구간을 3가지 음성 신호 부류로 식별하기 위하여 패턴 인식 방법을 사용하였다. 여기에 사용한 분석 파 라메타는 음성 신호의 영교차율, 대수 에너지, 정규화 된 첫 번째 자동 상관 계수, 선형 예측 분석에서 얻은 첫 번째 예측 계수, 그리고 예측 오차의 에너지이다. 한편 측정된 파라메타들이 다차원 가우스 확 률 밀도 함수에 따라 분산되었다는 가정하에서 어어진 최소 거리 법칙에 기본을 두고 음성 구간을 결정 하였다. 측정된 파라메타들을 여러 가지 방법으로 조합하여 식별한 결과 영교차율, 첫 번째 예측계수, 예측 오차의 에너지를 측정 파라메타로 사용했을 때 1%보다 적은 식별 오차율을 얻었다.