• The Journal of Korea Robotics Society
• /
• v.10 no.1
• /
• pp.16-23
• /
• 2015

This paper presents a method of improving the pose recognition accuracy of objects by using Kinect sensor. First, by using the SURF algorithm, which is one of the most widely used local features point algorithms, we modify inner parameters of the algorithm for efficient object recognition. The proposed method is adjusting the distance between the box filter, modifying Hessian matrix, and eliminating improper key points. In the second, the object orientation is estimated based on the homography. Finally the novel approach of Auto-scaling method is proposed to improve accuracy of object pose estimation. The proposed algorithm is experimentally tested with objects in the plane and its effectiveness is validated.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1550-1552
• /
• 2005

In this paper, we have designed a Fingerprint Recognition System based on the Embedded LINUX. The fingerprint is captured using the AS-S2 semiconductor sensor. To extract a feature vector we transform the image of the fingerprint into a column vector. The image is row-wise filtered with the low-pass filter of the Haar wavelet. The feature vectors of the different fingerprints are compared by computing with the probabilistic neural network the distance between the target feature vector and the stored feature vectors in advance. The system implemented consists of a server PC based on the LINUX and a client based on the Embedded LINUX. The client is a Tynux box-x board using a PXA-255 CPU. The algorithm is simple and fast in computing and comparing the fingerprints.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.204-206
• /
• 2005

In this paper, we have designed a Fingerprint Recognition System based on the Embedded LINUX. The fingerprint is captured using the AS-S2 semiconductor sensor. To extract a feature vector we transform the image of t10he fingerprint into a column vector. The image is row-wise filtered with the low-pass filter of the Haar wavelet. The feature vectors of the different fingerprints are compared by computing with the probabilistic neural network the distance between the target feature vector and the stored feature vectors in advance. The system implemented consists of a server PC based on the LINUX and a client based on the Embedded LINUX. The client is a Tynux box-x board using a PXA-255 CPU. The algorithm is simple and fast in computing and comparing the fingerprints.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.2
• /
• pp.133-139
• /
• 2007

An unmanned ground vehicle can perform its mission automatically without human control in unknown environment. To move up to a destination in various surrounding situation, navigational information is indispensible. In order to be adopted for an unmanned vehicle, the navigation box is small, light weight and low power consumption. This paper suggests navigation system using a low grade MEMS IMU for supplying position, velocity, and attitude of an unmanned ground vehicle. This system consists of low cost and light weight MEMS sensors and a GPS receiver to meet unmanned vehicle requirements. The sensors are basically integrated by loosely coupled method using Kalman filter and internal algorithms are divided into initial alignment, sensor error compensation, and complex navigation algorithm. The performance of the designed navigation system has been analyzed by real time field test and compared to commercial tactical grade GPS/INS system.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.502-510
• /
• 2016

Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.55 no.4
• /
• pp.161-165
• /
• 2006

In this paper, we developed HPF (high pass filter) consists of lumped LC components to decrease the noises that are detected in PD (partial discharge) measuring test, and adapted it to field test. We tested it under laboratory circumstances like the fields, and measured the phase change properties of detected signal in UHF sensor with Lemke Probe and oscilloscope (TDS-3054, Tektronix). As a result, we obtained available data showing the decrease of noises in the experiments with the developed HPF from the joint box of 22.9kV distribution line. The result can be adapted to prevent the degeneration of the XLPE power cable, and to observe and diagnosis the underground power transmission cable at the ultra-high voltage.

• Journal of Korean Society of Transportation
• /
• v.13 no.1
• /
• pp.95-110
• /
• 1995

n this research neural -based model was developed to forecast link travel times , And it is also compared wiht other time series forecasting models such as Box-Jenkins model, Kalman filter model. These models are validated to evaluate the accuracy of models with real time series data gathered by the license plate method. Neural network's convergency and generalization were investigated by modifying learning rate, momentum term and the number of hidden layer units. Through this experiment, the optimum configuration of the nerual network architecture was determined. Optimumlearining rate, momentum term and the number of hidden layer units hsow 0.3, 0.5, 13 respectively. It may be applied to DRGS(dynamic route guidance system) with a minor modification. The methods are suggested at the condlusion of this paper, And there is no doubt that this neural -based model can be applied to many other itme series forecating problem such as populationforecasting vehicel volume forecasting et .

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.76-77
• /
• 2018

전자기파 환경을 고려한 장비 개발을 위해서 고려되는 설계 사항 중 하나는 외부의 노이즈가 장비 내부로 유입되지 않도록 하고 반대로 장비 내 발생하는 노이즈가 외부로 나가는 것을 막도록 설계하는 것이다. 이를 위해서 전자기파 환경 규격을 만족하기 위한 장비들은 일반적으로 차폐형 구조로 설계된다. 본 논문은 차폐형 구조 설계 시 가장 노이즈에 취약할 수 있는 커넥터를 필터 일체형으로 설계한 사항과 이를 적용한 신호인입함의 성능 개선 사항에 대해 소개한다.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.495-505
• /
• 2019

Typical algorithms of deep learning include CNN(Convolutional Neural Networks), which are mainly used for image recognition, and RNN(Recurrent Neural Networks), which are used mainly for speech recognition and natural language processing. Among them, CNN is able to learn from filters that generate feature maps with algorithms that automatically learn features from data, making it mainstream with excellent performance in image recognition. Since then, various algorithms such as R-CNN and others have appeared in object detection to improve performance of CNN, and algorithms such as YOLO(You Only Look Once) and SSD(Single Shot Multi-box Detector) have been proposed recently. However, since these deep learning-based detection algorithms determine the success of the detection in the still images, stable object tracking and detection in the video requires separate tracking capabilities. Therefore, this paper proposes a method of combining Kalman filters into deep learning-based detection networks for improved object tracking and detection performance in the video. The detection network used YOLO v2, which is capable of real-time processing, and the proposed method resulted in 7.7% IoU performance improvement over the existing YOLO v2 network and 20 fps processing speed in FHD images.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.148-148
• /
• 2017

방역 차량의 약액탱크, 차량의 연료, 워셔액 등의 탱크 내부에는 잔존량을 측정하기 위해 기둥과 floating box로 이루어진 부력식 수위레벨센서가 사용되고 있으나 액체레벨에 따라 float이 상하로 움직이는 측정원리상 차량 주행 중 정확성이 매우 떨어진다(Park et al. 2016). 방역차량이 주행 중 분사할 때, 슬로싱 현상과 방역소독기의 노즐과 펌프에서 발생하는 진동으로 인해 기존의 부력식 센서를 이용한 약제 살포량 측정방법은 정확성이 매우 떨어지는 경향이 있다. 본 연구의 목적은 방역차량이 주행하면서 분사할 때, 수위레벨 센서를 이용한 약제살포량 측정의 정확성을 개선하는 것으로 디지털 칼만필터, Low pass filter와 댐퍼를 제작하여 이용했다. 본 연구에서는 압력식 레벨센서를 이용해 약액탱크의 높이당 단면적과 수위를 측정하여 약제살포량을 계산했다. Python 2.7을 이용해 디지털 칼만필터와 Low pass filter(LPF)를 구현하였으며 3D프린터를 이용해 댐퍼를 제작했다. 실내에서 슬로싱 현상을 인공적으로 만들어 필터와 댐퍼의 수위 측정 정확성 개선효과를 확인 후 실제 방역차량에 부착하여 비포장도로에서 주행하면서 분사할 때 필터와 댐퍼의 효과를 확인하였다. 댐퍼의 공극률(p)을 바꿔가며 수위 측정 정확성 개선효과를 확인하였다. 실내, 현장 실험 결과, 칼만필터가 LPF보다 개선효과가 더 크지만 데이터 50개 처리에 1.71초의 시간지연이 발생했다. 댐퍼는 수위센서를 고정시키고 유체의 운동을 방해하여 이상치와 큰 오차제거에 효과적이었다. 칼만필터와 댐퍼를 동시에 이용할 경우, 수위 측정정확성 $R^2$는 0.9985, 0.9981로 ${\pm}4.3cm$의 범위내에서 수위를 측정할 수 있었다. 필터의 시간지연과 수위 측정정확성을 고려하여 데이터 기록간격을 3초로 설정하면 ${\pm}3cm$이내에서 약탱크 내 수위를 측정할 수 있었다. 공극률(p)가 0.294, 0.291, 0.17에서 측정정확성 $R^2$는 각각 0.9897, 0.9858, 0.9872 로 p가 0.294에서 개선효과가 가장 좋았으나 개선효과의 차이는 크지 않았다.