• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.3
• /
• pp.611-618
• /
• 2000

This paper presents a shape classification method of dynamic image based on adaptive fuzzy inference. It describes the design scheme of fuzzy inference algorithm which makes it suitable for low speed systems such as conveyor, uninhabited transportation. In the first Discrete Wavelet Transform(DWT) is utilized to extract the motion vector in a sequential images. This approach provides a mechanism to simple but robust information which is desirable when dealing with an unknown environment. By using feature parameters of moving object, fuzzy if - then rule which can be able to adapt the variation of circumstances is devised. Then applying the implication function, shape classification processes are performed. Experimental results are presented to testify the performance and applicability of the proposed algorithm.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.585-590
• /
• 2006

Although motion estimation Plays an important role in digital video compression, complex search procedure is required to find an optimal motion vector. To reduce the search time, the search start point should be set up properly md efficient search pattern is needed. If the overall motion of the torrent block can be predicted, motion estimation can be performed efficiently. In this paper. block types are classified using candidate vectors and the motion activity of the block is predicted which leads to the search start point close to the optimal motion vector. The proposed method proves to be about 1.5$\sim$7 times faster than existing methods with about 0.02$\sim$0.2(dB) improvement of picture quality in images with large movements.

• The Journal of Korean Physical Therapy
• /
• v.27 no.4
• /
• pp.214-220
• /
• 2015

Purpose: The purpose of this study was to investigate the availability of software for rehabilitation with the Kinect sensor by presenting an efficient algorithm based on machine learning when classifying the motion data of the PNF pattern if the subjects were wearing a patient gown. Methods: The motion data of the PNF pattern for upper extremities were collected by Kinect sensor. The data were obtained from 8 normal university students without the limitation of upper extremities. The subjects, wearing a T-shirt, performed the PNF patterns, D1 and D2 flexion, extensions, 30 times; the same protocol was repeated while wearing a patient gown to compare the classification performance of algorithms. For comparison of performance, we chose four algorithms, Naive Bayes Classifier, C4.5, Multilayer Perceptron, and Hidden Markov Model. The motion data for wearing a T-shirt were used for the training set, and 10 fold cross-validation test was performed. The motion data for wearing a gown were used for the test set. Results: The results showed that all of the algorithms performed well with 10 fold cross-validation test. However, when classifying the data with a hospital gown, Hidden Markov model (HMM) was the best algorithm for classifying the motion of PNF. Conclusion: We showed that HMM is the most efficient algorithm that could handle the sequence data related to time. Thus, we suggested that the algorithm which considered the sequence of motion, such as HMM, would be selected when developing software for rehabilitation which required determining the correctness of the motion.

• Proceedings of the ESK Conference
• /
• 1998.04a
• /
• pp.31-35
• /
• 1998

Many reaearchers have reproted that poor body postures are associated with pains or symptoms of musculoskeletal dissoders. Therefore, the ergonomic evaluation of postural stresses as well as biomechanical stresses is important when a job such as automobile assembly tasks involves highly repetitive and/or prolonged poor body postures. A macropostural classification shema was developed to characterise various body postures occurring in automobile assembly tasks in the study. To specify a postural code and stress level to each body posture, perceived joint discomforts were subjectively evaluated in the lab experiments for the full range of motion in five human body joints. Based on the reaults, a postural classification scheme was developed where the full range of motion in each body joint was classified into several codes repressenting different stress levels. The automobile tasks were clustered into 12 types based on the result walk-in-surveillance and the possible posture codes for each task type are defined. I was exposed that the poor postural problems in automobile assembly tasks were concerned in most part with arms, trunk and neck. Application of te developed schema to seven operations in automobile assembly tasks showed that the schema can be used as a tool to identify the operations and tasks involving highly stressful body postures. The schema can also be utilised as a basis to prioritise the candidate assembly operations for redesign of work methods.

• Korean Journal of Applied Biomechanics
• /
• v.13 no.3
• /
• pp.181-197
• /
• 2003

The Purpose of this study was to examine the kinematic analysis of the upper-limb motion of wheelchair basketball free throw shooting. Three-dimensional kinematic data were obtained from 8 male wheelchair basketball players performing a successful free throw. Players were divided into three groups, according to their IWBF classification(Group 1: 1 point players, Group 2: 2-2.5point players and Group 3:3.5-4 point players) Wheelchair basketball free throw motions were taken by video camera. The three-dimensional coordinates was processed by DLT. Players from Group 1 and 2 tended to release the ball from a lower height, with greater velocity and release angle. Players from Group 1 showed greater shoulder horizontal adduction and horizontal abduction angle, wrist ulnar flexion and radial flexion angle, and trunk angle. but players from Group 2 appeared lower shoulder abduction. Upper limb angular velocity showed most greatly in hands from Group 1, upperarm from Group 2, and forearm from Group 3.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.477-481
• /
• 2010

In this paper, we try to classify behavior patterns of a person around a bed based on a wireless sensor network system. We define five behavioral patterns and three states of a person around a bed which is described by a state machine. We collected data sensed by motion detection and vibration sensors installed around a bed from which a feature vector was extracted. Based on feature vector corresponding to behavioral patterns and the state machine, we established a model for behavioral patterns. To validate the model, experiments on subjects were performed and the model was fixed. These experimental results revealed that behavior patterns of a person around a bed can be classified well.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3769-3789
• /
• 2018

Social pedestrian groups are the basic elements that constitute a crowd; therefore, detection of such groups is scientifically important for modeling social behavior, as well as practically useful for crowd video understanding. A social group refers to a cluster of members who tend to keep similar motion state for a sustained period of time. One of the main challenges of social group detection arises from the complex dynamic variations of crowd patterns. Therefore, most works model dynamic groups to analysis the crowd behavior, ignoring the existence of stationary groups in crowd scene. However, in this paper, we propose a novel unified framework for detecting social pedestrian groups in crowd videos, including dynamic and stationary pedestrian groups, based on spatiotemporal-oriented energy measurements. Dynamic pedestrian groups are hierarchically clustered based on energy flow similarities and trajectory motion correlations between the atomic groups extracted from principal spatiotemporal-oriented energies. Furthermore, the probability distribution of static spatiotemporal-oriented energies is modeled to detect stationary pedestrian groups. Extensive experiments on challenging datasets demonstrate that our method can achieve superior results for social pedestrian group detection and crowd video classification.

• Journal of Korea Multimedia Society
• /
• v.10 no.5
• /
• pp.559-568
• /
• 2007

Anchor-person scene detection is of significance for video shot semantic parsing and indexing clues extraction in content-based news video indexing and retrieval system. This paper proposes an efficient algorithm extracting anchor ranges that exist in sports news video for unit structuring of sports news. To detect anchor person scenes, first, anchor person candidate scene is decided by DCT coefficients and motion vector information in the MPEG4 compressed video. Then, from the candidate anchor scenes, image processing method is utilized to classify the news video into anchor-person scenes and non-anchor(sports) scenes. The proposed scheme achieves a mean precision and recall of 98% in the anchor-person scenes detection experiment.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.2
• /
• pp.15-20
• /
• 2000

In this paper, we presents a new MCDI(motion compensated difference image) coding method using CVQ(classifled vector quantization) whoes MCD(motion compensated difference) block is classified by proposed classifier using motion vector and compensated block The variance of MCD block is closely related with the magnitude of motion vector as well as the variance of compensated block, so using this property, we propose a new classifier. This scheme has no side information of the classifier what sub-codebook is selected, and simulation results show that the proposed method exhibits a good performance even when compared with a conventional method that requires classification bits.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.211-220
• /
• 2002

In this paper, we propose an efficient algorithm to compress simple computer cell animation at very low bit rate. The structure of proposed algorithm consists of intra frame coding and inter frame coding. In inter frame coding, animation is encoded by color quantization using a palette, rearrangement of index, ADPCM used in JPEG-LS, mapping, classification, and entropy coding. In interframe coding, classifying the characteristics of motion, animation is encoded by block based motion replenishment. Experimental results show that the proposed methods turns out to outperform conventional methods including Flash, FLC, Motion-JPEG, MPEG-1, and MPEG-4.