• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.11a
• /
• pp.327-329
• /
• 2000

This paper is concerned with the development of vibration measurement using the image processing. With the advance of the personal computer and the image processing device, it becomes possible to measure vibrations by converting the image into motion data. The image stored in the computer is based on pixels. Hence, the efficient technique which can compute vibrational motions from pixel data should be developed. In this study, we will show the feasibility of the image processing technique for vibration measurement. The experimental results show that vibrations can be measured from image data.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.113-116
• /
• 2002

Windows provides Directshow for efficient multimedia streaming processings such as multimedia capture, storage, display and etc. Presently, many motion picture codecs and audio codecs are made to be used in Directshow framework and Windows also supports many codecs (MPEG4, H,263, WMV, WMA, ASF, etc.) in addition to a lot of useful tools for multimedia streaming processing. Therefore, Directshow can be effectively utilized for developing windows-based multimedia streaming applications such as visual monitoring systems which needs to store real-time video data for later retrieval. In this paper, we present our efforts for developing a Directshow Filter System supporting storage of motion pictures in various motion picture codecs. Our Directshow Filter system also provides an additional functionality of motion detection.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.468-472
• /
• 1992

In recent years, lots of researches on autonomous mobile robot have been accomplished. However they focused on environment recognition and its processing to make a decision on the motion, And cooperative multi-robot, which must be able to avoid crash and to make mutual communication, has not been studied much. This paper deals with cooperative motion of two robots, 'Meari 1" and "Meari 2 " made in our laboratory, based on communication between the two. Because there is an interference on communication occurring in cooperative motion of multi-robot, many restrictive conditions are required. Therefore, we have designed these robot system so that communication between them is available and mutual interference is precluded, and we used fuzzy interference to overcome unstability of sensor data.of sensor data.

• Journal of the Korea Society of Computer and Information
• /
• v.3 no.2
• /
• pp.119-124
• /
• 1998

Block Matching Motion Estimation(BMME) Algorithm is demands a very large amount of computing power and have been proposed many fast algorithms. These algorithms are many problem that larger size of VLSI scale due to non-localized search block data and problem of non-reuse of input data for each processing step. In this paper, we designed systolic arry of high processing capacity, constraints input output pin size and reuse of input data for small VLSI size. The proposed systolic array is optimized memory access time because of iterative reuse of input data on search block and become independent of problem size due to increase of algorithm's parallelism and total processing elements connection is localized spatial and temporal. The designed systolic array is reduced O(N6) time complexity to O(N3) on moving vector and has O(N) input/output pin size.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.4
• /
• pp.722-727
• /
• 2009

The technology of distinguishing human motion states is required in the areas of measuring and analyzing biosignals changing according to physical activities, diagnosing sleep disorder, screening the effect of treatment, examining chronic patients' kinetic state, prescribing exercise therapy, etc. The present study implemented a fuzzy inference system based on fuzzy rules that distinguish human motion states (tying, sitting, walking, and running) by acquiring and processing data of LAA, TAA, L-MAD, and T-MAD using ADXL202AE of Analog Devices embedded in an armband. The membership degree and fuzzy rules in each area of input (LAA, TAA, L-MAD, and T-MAD) and output (tying, sitting, walking, and running) data used here were determined using numeric data obtained from experiment. In the results of analyzing data for simulation generated in order of tying$\rightarrow$walking$\rightarrow$running$\rightarrow$tying, the sorting rate for motion states tying, sitting, walking, and running was 100% for each motion.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.213-214
• /
• 2012

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.10
• /
• pp.57-63
• /
• 2019

Motion errors which are caused by several reasons, non-ideal path, errors of navigation systems, and radar system errors, have to be corrected. Motion compensation methods can compensate the motion error, but not exactly. To correct these residual errors, several autofocus methods are invented. A popular method is phase gradient autofocus (PGA). PGA does not assume specific circumstances, such as isolated point targets and shapes of errors. PGA is an iterative and adaptive method, so that the processing time is the main problem for the real time processing. In this paper, the improved method to select targets for PGA is proposed to reduce processing time. The variances of image pixels are used to select targets with high SNR. The processing of PGA with these targets diminishes the processing time and iterations effectively. The processed results with real radar data, obtained by flight tests, show that the proposed method compensates errors well, and reduce working time.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.663-668
• /
• 2003

This paper presents a new observation system which is useful to observe the scene of the remote controlled robot vision. This system is composed of a motionless camera and head motion detector with a motion sensor. The motionless camera has a fish eye lens and is for observing a hemisphere space. The head motion detector has a motion sensor is for defining an arbitrary subspace of the hemisphere space from fish eye lens. Thus processing the angular information from the motion sensor appropriately, the direction of face is estimated. However, since the fisheye image is distorted, it is unclear image. The partial domain of a fish eye image is selected by head motion, and this is converted to perspective image. However, since this conversion enlarges the original image spatially and is based on discrete data, crevice is generated in the converted image. To solve this problem, interpolation based on an intensity of the image is performed for the crevice in the converted image (space problem). This paper provides the experimental results of the proposed observation system with the head motion detector and perspective image conversion using the proposed conversion and interpolation methods, and the adequacy and improving point of the proposed techniques are discussed.