• IEMEK Journal of Embedded Systems and Applications
• /
• v.3 no.3
• /
• pp.151-157
• /
• 2008

In this paper, we propose a three dimensional distance measurement method for a stereo system by using web cams. Using a parallel stereo system, a robot gets two images from each webcam and equalize brightness of both images. And we suggest an image processing method such as labeling, isolating an object from background and finding center of an object. We also propose a method of calculating the focal distance by using least square algorithm based on triangulation and we can reduce calculation error by this method. From experimental results, we show that the proposed method can be effective for 3D distance measurement.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.67-73
• /
• 2010

In this paper, a new face detection method that is more accurate than the conventional methods is proposed. This method utilizes a hybrid of Hausdorff distance based on the geometric similarity between the two sets of points and the LBP distance based on the distribution of local micro texture of an image. The parameters for normalization and the optimal blending factor of the two different metrics were calculated from training sample images. Popularly used face database was used to show that the proposed method is more effective and robust to the variation of the pose, illumination, and back ground than the methods based on the Hausdorff distance or LBP distance. In the particular case, the average error distance between the detected and the true face location was reduced to 47.9% of the result of LBP method, and 22.8% of the result of Hausdorff method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.94.5-94
• /
• 2001

Unrestricted measurement method of three-dimensional walking distance utilizing body acceleration and terrestrial magnetism is discussed. The three-dimensional walking distance is derived by the integration of the three dimensional acceleration of foot during swing phase. Since the sensor system attached on the foot rotates during swing phase, the acceleration data measured on the foot include acceleration of gravity which causes inaccurate calculation of the velocity and the distance. Three gyros are used to compensate the rotation of the sensor system. Moreover, one geomagnetic sensor is employed to derive the heading direction of the subject Healthy volunteers performed ...

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.418-420
• /
• 2005

This paper proposed ultrasonic distance measurement module development for correct distance detection with collision escaping or obstacle of mobile robot is traveling self-regulation. Representative ultrasonic module applied in existing was Polaroid company's 6500 series and Devantech company's SRF04/SRF08 series. This ultrasonic sensors are corrupted by systematic errors due mainly to the dependency of sound speed upon surrounding conditions and random errors of uncertain origin. Therefore Ultrasonic distance detecting means of error compensation method and high definition, narrow beam angle, board area distance detecting means to apply to ultrasonic mobile robot control urgently need. In this paper use internal type temperature compensation method to improve problem of ultrasonic distance measurement method instead of that volume that have shortcoming of used correct temperature compensation methods applied big addition device. Compensate error by environment change of temperature. Humidity density etc. and is applicable to mobile robot offering various interface and real-time processing developed possible distance measurement module.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.2
• /
• pp.401-407
• /
• 2012

This paper analyzes performance of major obstacle avoidance methods. For the analysis, numerical performance indexes are proposed: motion distance to goal point, motion time, distance to obstacles, and smoothness of the motion. Especially, the index of smoothness measures efficiency of the motion using the angular acceleration and jerk of the robot heading. Four major obstacle avoidance methods are compared in terms of the performance indexes. The four methods are artificial potential field(APF) method, elastic force(EF) method, APF with virtual distance, and EF with virtual distance. Through simulation, the four methods are compared and features of the methods are explored.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.4
• /
• pp.122-129
• /
• 2010

High-performance concrete (HPC) is a new terminology used in concrete construction industry. Several studies have shown that concrete strength development is determined not only by the water-to-cement ratio but also influenced by the content of other concrete ingredients. HPC is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed at demonstrating the possibilities of adapting artificial neural network (ANN) to predict the comprresive strength of HPC. Mahalanobis Distance (MD) outlier detection method used for the purpose increase prediction ability of ANN. The detailed procedure of calculating Mahalanobis Distance (MD) is described. The effects of outlier compared with before and after artificial neural network training. MD outlier detection method successfully removed existence of outlier and improved the neural network training and prediction performance.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.52-59
• /
• 2011

In this paper, we propose an indexing method to support efficient similarity search for sequence databases. We present a new distance measurement called minimum DTW distance to enhance the filtering effects. The minimum DTW distance is to measure the minimum distance between a sequence data and the group of similar sequences. It enables similarity search through hierarchical index structure by filtering sequence databases. Finally, we show the superiority of our method through some experiments.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.29 no.2
• /
• pp.58-66
• /
• 2006

This paper addresses the analysis of the travel distance and the number of storage location for storage location allocation methods in a warehouse system. The dedicated, randomized, combined and limited storage methods are considered. The combined and the limited storage methods are suggested here, which the combined storage method is to divide the storage locations into the dedicated storage area and the randomized storage area, and the limited storage method is to restrict the storage area of each product. Through a numerical example, the average travel distance between input/output point and the storage locations, and the number of storage location needed in the warehouse are compared between storage location allocation methods. The nearest randomized storage method is shown as the reasonable one in the travel distance and the number of storage location.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.344-346
• /
• 2019

In this paper, we propose a distance estimation method using the convolutional neural network in Ultra-Wideband (UWB) systems. The training data set used to learn the deep learning model using the convolutional neural network is generated by the MATLAB program and utilizes the IEEE 802.15.4a standard. The performance of the proposed distance estimation method is verified by comparing the threshold based distance estimation technique and the performance comparison used in the conventional distance estimation.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.10a
• /
• pp.700-707
• /
• 2008

As plan connecting island to island or island to land is needed, a lot of long-span bridge is being designed lately in Southern part of Korea. With development of pile equipment, overhanging large-scaled concrete pile are adopted to foundation type of main tower or pylon. About the number of 15~30 group piles per tower foundation is designed to resist long-spaning super-structure load, but by restricted condition of site investigation cost, a few boring-hole tests are performed to identify sub-ground layers. Up to now, direct-curved method connecting two or three known boring logs and representative interval method are usually used to evaluate unknown depth and rock properties at locations where piles are constructed. Because this approach is not logical and so rough, much difference occurs between designed length of piles and real length of it. In this paper, using a lot of various prediction method(reciprocal distance method, inverse square distance method and kriging method etc.), we suggest optimum length of group piles.