• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3599-3619
• /
• 2019

In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video features and unable to investigate the level of contribution of both (Static and Motion) components. Our work highlights this problem and proposes Static-Motion fused features descriptor (SMFD), which intelligently leverages both static and motion features in the form of descriptor. First, static features are learned by two-stream 3D convolutional neural network. Second, trajectories are extracted by tracking key points and only those trajectories have been selected which are located in central region of the original video frame in order to to reduce irrelevant background trajectories as well computational complexity. Then, shape and motion descriptors are obtained along with key points by using SIFT flow. Next, cholesky transformation is introduced to fuse static and motion feature vectors to guarantee the equal contribution of all descriptors. Finally, Long Short-Term Memory (LSTM) network is utilized to discover long-term temporal dependencies and final prediction. To confirm the effectiveness of the proposed approach, extensive experiments have been conducted on three well-known datasets i.e. UCF101, HMDB51 and YouTube. Findings shows that the resulting recognition system is on par with state-of-the-art methods.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.2
• /
• pp.11-19
• /
• 2020

When a character's pose changes, its center of mass(COM) also changes. The change of COM has distinctive patterns corresponding to various motion types like walking, running or sitting. Thus the motion type can be predicted by using COM movement. We propose a motion generator that uses character's center of mass information. This generator can generate various motions without annotated action type labels. Thus dataset for training and running can be generated full-automatically. Our neural network model takes the motion history of the character and its center of mass information as inputs and generates a full-body pose for the current frame, and is trained using simple Convolutional Neural Network(CNN) that performs 1D convolution to deal with time-series motion data.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.2
• /
• pp.131-140
• /
• 1994

Dynamics of AUV has heavy nonlinearities and many unknown parameters due to its bluff shape and low cruising speed. Intelligent algorithms, therefore, are required to overcome these nonlinearities and unknown system dynamics. Several identification techniques have been suggested for the application of control of underwater vehicles during last decade. This paper applies the neural network to identification and motion control problem of AUVs. Nonlinear dynamic systems of an AUV are identified using feedforward neural network. Simulation results show that the learned neural network can generate the motion of AUV. This paper, also, suggest an adaptive control scheme up-dates the controller weights with reference model and feedforward neural network using error back propagation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.1
• /
• pp.159-164
• /
• 2013

Recently the solution integrated of vision and motion controller which are important element in automatiomn system has been many developed. However typically such a solutions has a many case that integrated vision processing and motion control into network or organized two chip solution on one module. We implement one chip solution integrated into vision and motion controller using Zynq-7000 that is developed recently as extended processing platform. We also apply EtherCAT to motion control that is industrial Ethernet protocol which have compatibility for open standardization Ethernet in order to control of motion because EtherCAT has a secure to realtime control and can treat massive data.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.34 no.7
• /
• pp.63-70
• /
• 2006

This paper describes research of using area of artificial mark on vision based head tracker system. A head tracker system consists of the translational and rotational motions which are detected by web camera. Results of the motion are taken from image processing and neural network. Because of the characteristics of cockpit, the specific color on the helmet is tracked for translational motion. And rotational motion is tracked via neural network. Ratio of two different colored area on the helmet is used as input of network. Neural network algorithms used, such as back-propagation and RBFN (Radial Basis Function Network). Both back-propagation using a characteristic of feedback and RBFN using a characteristic of statistics have a good performances for the tracking of nonlinear system such as a head motion. Finally, this paper analyzes and compares with tracking performance.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.6 no.1
• /
• pp.67-73
• /
• 2012

In this paper, Artificial Neural Network(ANN) based motion classification algorithm is proposed to classify wrist motions using surface electromyograms(sEMG). surface EMGs are obtained from two electrodes placed on the flexor carpi ulnaris muscle and extensor carpi ulnaris muscle of 26 subjects under no strain condition during wrist motions and used to recognize wrist motions such as up, down, left, right, and rest. Feature is extracted from obtained EMG signals in time domain for fast processing and used to classify wrist motions using ANN. DAMV, DASDV, MAV, and RMS were used as features and accuracies of motion classification based on ANN were 98.03% for DAMV, 97.97% for DASDV, 96.95% for MAV, 96.82% for RMS.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.566-571
• /
• 1994

This paper presents in image-based visual servo control scheme for tracking a workpiece with a hand-eye coordinated robotic system using the fuzzy-neural-network. The goal is to control the relative position and orientation between the end-effector and a moving workpiece using a single camera mounted on the end-effector of robot manipulator. We developed a fuzzy-neural-network that consists of a network-model fuzzy system and supervised learning rules. Fuzzy-neural-network is applied to approximate the nonlinear mapping which transforms the features and theire change into the desired camera motion. In addition a control strategy for real-time relative motion control based on this approximation is presented. Computer simulation results are illustrated to show the effectiveness of the fuzzy-neural-network method for visual servoing of robot manipulator.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.5
• /
• pp.414-421
• /
• 2007

This paper presents a engine/brake integrated VDC(Vehicle Dynamic Control) system using neural network algorithm methods for wheel slip and yaw rate control. For stable performance of vehicle, not only is the lateral motion control(wheel slip control) important but the yaw motion control of the vehicle is crucial. The proposed NNPI(Neural Network Proportional-Integral) controller operates at throttle angle to improve the performance of wheel slip. Also, the suggested NNPID controller performs at brake system to improve steering performance. The proposed controller consists of multi-hidden layer neural network structure and PID control strategy for self-learning of gain scheduling. Computer Simulation have been performed to verify the proposed neural network based control scheme of 17 dof vehicle dynamic model which is implemented in MATLAB Simulink.

• Journal of Platform Technology
• /
• v.6 no.1
• /
• pp.3-8
• /
• 2018

This paper proposes a technique for recognizing online handwritten cursive data obtained by tracing a motion trajectory while a user is in the 3D space based on a convolution neural network (CNN) algorithm. There is a difficulty in recognizing the virtual character input by the user in the 3D space because it includes both the character stroke and the movement stroke. In this paper, we divide syllable into consonant and vowel units by using labeling technique in addition to the result of localizing letter stroke and movement stroke in the previous study. The coordinate information of the separated consonants and vowels are converted into image data, and Korean handwriting recognition was performed using a convolutional neural network. After learning the neural network using 1,680 syllables written by five hand writers, the accuracy is calculated by using the new hand writers who did not participate in the writing of training data. The accuracy of phoneme-based recognition is 98.9% based on convolutional neural network. The proposed method has the advantage of drastically reducing learning data compared to syllable-based learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1118-1133
• /
• 2017

Computer vision-based human activity recognition (HAR) has become very famous these days due to its applications in various fields such as smart home healthcare for elderly people. A video-based activity recognition system basically has many goals such as to react based on people's behavior that allows the systems to proactively assist them with their tasks. A novel approach is proposed in this work for depth video based human activity recognition using joint-based motion features of depth body shapes and Deep Belief Network (DBN). From depth video, different body parts of human activities are segmented first by means of a trained random forest. The motion features representing the magnitude and direction of each joint in next frame are extracted. Finally, the features are applied for training a DBN to be used for recognition later. The proposed HAR approach showed superior performance over conventional approaches on private and public datasets, indicating a prominent approach for practical applications in smartly controlled environments.