• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.1
• /
• pp.174-184
• /
• 1997

This paper presents a robust force tracking control of a smart flexible gripper featured by a piezoceramic actuator characterizing its durability and quick response time. A mathematical governing equation for the proposed gripper structure is derived by employing Hamilton's principle and a state space control model is subsequently obtained through model analysis. Uncertain system parameters such as frequency variation are included in the control model. A sliding mode control theory which has inherent robustness to the sys- tem uncertainties is adopted to design a force tracking controller for the piezoceramic actuator. Using out- put information from the tip force sensor, a full-order observer is constructed to estimate state variables of the system. Force tracking performances for desired trajectories represented by sinusoidal and step func- tions are evaluated by undertaking both simulation and experimental works. In addition, in order to illustrate practical feasibility of the proposed method, a two-fingered gripper is constructed and its performance is demonstrated by showing a capability of holding an object.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2846-2866
• /
• 2022

Caenorhabditis elegans exhibits sophisticated chemotaxis behavior through two parallel strategies, klinokinesis and klinotaxis, executed entirely by a small nervous circuit. It is therefore suitable for inspiring fast and energy-efficient solutions for autonomous navigation. As a random search strategy, the Lévy walk is optimal for diverse animals when foraging without external chemical cues. In this study, by combining these biological strategies for the first time, we propose a spiking neural network model for search and contour tracking of specific concentrations of environmental variables. Specifically, we first design a klinotaxis module using spiking neurons. This module works in conjunction with a klinokinesis module, allowing rapid searches for the concentration setpoint and subsequent contour tracking with small deviations. Second, we build a random exploration module. It generates a Lévy walk in the absence of concentration gradients, increasing the chance of encountering gradients. Third, considering local extrema traps, we develop a termination module combined with an escape module to initiate or terminate the escape in a timely manner. Experimental results demonstrate that the proposed model integrating these modules can switch strategies autonomously according to the information from a single sensor and control steering through output spikes, enabling the model worm to efficiently navigate across various scenarios.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2483-2503
• /
• 2016

Traffic congestion is a severe problem in many modern cities around the world. Real-time and accurate traffic congestion identification can provide the advanced traffic management systems with a reliable basis to take measurements. The most used data sources for traffic congestion are loop detector, GPS data, and video surveillance. Video based traffic monitoring systems have gained much attention due to their enormous advantages, such as low cost, flexibility to redesign the system and providing a rich information source for human understanding. In general, most existing video based systems for monitoring road traffic rely on stationary cameras and multiple vehicle tracking method. However, most commonly used multiple vehicle tracking methods are lack of effective track initiation schemes. Based on the motion of the vehicle usually obeys constant velocity model, a novel vehicle recognition method is proposed. The state of recognized vehicle is sent to the GM-PHD filter as birth target. In this way, we relieve the insensitive of GM-PHD filter for new entering vehicle. Combining with the advanced vehicle detection and data association techniques, this multiple vehicle tracking method is used to identify traffic congestion. It can be implemented in real-time with high accuracy and robustness. The advantages of our proposed method are validated on four real traffic data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.192-203
• /
• 2016

Uganda is a country blessed with the biggest number of mountain Gorillas in the whole world. These animals contribute at least 12% in revenue generation to the Tourism sector through tracking by both local and foreign tourists who pay for the tracking permits. However, Gorilla tracking is also a big challenge even in the presence of highly skilled and well-trained game rangers. Development and implementation of a secure Computer and Mobile based Gorilla Tracking (GT) system that uses GIS and GPS technologies would be the most ideal technology to use. Therefore, this study aimed to find out the critical factors that would affect the Behavioral Intention of the would-be users to successfully decide to use such GIS/GPS-GT system. We used the existing UTAUT model to integrate six factors such as Performance Expectancy, Effort Expectancy, Employee Peer Influence, Facilitating Conditions, Behavioral Intention and System Use. However, Infrastructure Availability and Non-Technical Facilitating Conditions were added to reflect Ugandan ICT context. This amended UTAUT model was used to carry out the survey. The questionnaire was emailed to 220 government employees in the fields of ICT, Tour and Travel, Environmental Groups officials and Farmers who garden near the game reserves. A total of 133 were obtained fully completed, whereas 127 were deemed usable thus yielding a response rate of 58%. The analysis results show that except for non-technical facilitating conditions, effort expectancy, peer influence, performance expectancy and infrastructure availability positively affects behavioral Intention to use GIS/GPS-GT. This indicates that people in Uganda don't bother about regulations and rules in regard to using information system. As long as the system does what they want it to, anything else does not matter. As an employee in an organization is told to use a system by their supervisor, they have no objection to otherwise they risk losing their job. This implies that, supervisors have a great responsibility in the process of developing, implementing and using the system in Uganda.

• Journal of KIISE:Software and Applications
• /
• v.34 no.10
• /
• pp.937-944
• /
• 2007

In this paper, we propose multiple human tracking with an moving stereo camera. The tracking process is based on mean shift algorithm which is using color information of the target. Color based tracking approach is invariant to translation and rotation of the target but, it has several problems. Because of mean shift uses color distribution, it is sensitive to color distribution of background and targets. In order to solve this problem, we combine color and depth information of target. Also, we build human body part model to handle occlusions and we have created adaptive box scale. As a result, the proposed method is simple and efficient to track multiple humans in real time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.4
• /
• pp.241-253
• /
• 2006

In modem societies, a monitoring system is required to automatically detect and track persons from several cameras scattered in a wide area. Combining multiple cameras with non-overlapping views and a tracking technique, we propose a method that tracks automatically the target persons in one camera and transfers the tracking information to other networked cameras through a server. So the proposed method tracks thoroughly the target persons over the cameras. In this paper, we use a person model to detect and distinguish the corresponding person and to transfer the person's tracking information. A movement of the tracked persons is defined on FOV lines of the networked cameras. The tracked person has 6 statuses. The proposed system was experimented in several indoor scenario. We achieved 91.2% in an averaged tracking rate and 96% in an averaged status rate.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.3
• /
• pp.411-418
• /
• 2005

This paper discusses an output-tracking control design method for Takagi-Sugeno fuzzy systems with parametric uncertainties. We first represent the concerned system as a set of uncertain linear systems. The tracking problem is then converted into a stabilization problem thereby leading to a more feasible control design procedure. A sufficient condition for robust practical output tracking is derived in terms of a set of linear matrix inequalities. A numerical example for a flexible-joint robot-arm model has been demonstrated, to convincingly show effectiveness of the proposed system modeling and control design.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.4 s.316
• /
• pp.86-92
• /
• 2007

A discrete dynamic model for tracking feature points in 2D images is developed. Conventional snake approaches deform a contour to lock onto features of interest within an image by finding a minimum of its energy functional, composed of internal and external forces. The neighborhood around center snaxel is a space matrix, typically rectangular. The structure of the model proposed in this paper is a set of connected vertices. Energy model is designed for its local minima to comprise the set of alternative solutions available to active process. Block on tracking is one dimension, line type. Initial starting points are defined to the satisfaction of indent states, which is then automatically modified by an energy minimizing process. The track is influenced by curvature constraints, ascent/descent or upper/lower points. The advantages and effectiveness of this layer approach may also be applied to feature points tracking of digital image whose pixels have one directional properties with high autocorrelation between adjacent data lines, vertically or horizontally. The test image is the ultrasonic carotid artery image of human body, and we have verified its effect on intima/adventitia starting points tracking.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3136-3150
• /
• 2015

A vision-based 3D tracking of articulated human hand is one of the major issues in the applications of human computer interactions and understanding the control of robot hand. This paper presents an improved approach for tracking and recovering the 3D position and orientation of a human hand using the Kinect sensor. The basic idea of the proposed method is to solve an optimization problem that minimizes the discrepancy in 3D shape between an actual hand observed by Kinect and a hypothesized 3D hand model. Since each of the 3D hand pose has 23 degrees of freedom, the hand articulation tracking needs computational excessive burden in minimizing the 3D shape discrepancy between an observed hand and a 3D hand model. For this, we first created a 3D hand model which represents the hand with 17 different parts. Secondly, Random Forest classifier was trained on the synthetic depth images generated by animating the developed 3D hand model, which was then used for Haar-like feature-based classification rather than performing per-pixel classification. Classification results were used for estimating the joint positions for the hand skeleton. Through the experiment, we were able to prove that the proposed method showed improvement rates in hand part recognition and a performance of 20-30 fps. The results confirmed its practical use in classifying hand area and successfully tracked and recovered the 3D hand pose in a real time fashion.