• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1377-1381
• /
• 2003

This paper describes real time object tracking of 3D objects in 2D image sequences. The moving objects are segmented from the image sequence using morphological operations. The moving objects are segmented by the method of differential image followed by the process of morphological dilation. The moving objects are recognized and tracked using statistical moments. The direction of moving objects are determined by the Hough transform. The straight lines in the moving objects are found with the help of Hough transform. The direction of the moving object is calculated from the orientation of the straight lines in the direction of the principal axes of the moving objects. The direction of the moving object and the displacement of the object in the image sequence is used to calculate the velocity of the moving objects. The simulation results of the proposed method are promising on the test images.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.11
• /
• pp.1053-1059
• /
• 2007

This paper presents a target sate estimator(TSE) with low pass filter for improving the gun driving command. The ballistic computer uses target information such as predicted range, velocity, acceleration of a target to generate the gun command. We adopt the finite impulse response(FIR) filter as our TSE to shorten calculation time for the driving command and due to its inherent stability property. We also introduce a post-processing filter to reduce the high frequency components in the output signal of a TSE which may cause instability of gun driving. The first order low pass filter has been designed based on $H{\infty}$ criteria considering the noise characteristics. To show the validity of the present scheme, simulation results are given for the overall gun driving system including aircraft target information.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.7-10
• /
• 2000

There are many Problems such as low detection ratio, velocity and increase of false hit ratio on the detection of gradual scene changes with the previous shot transition detection algorithms. In this paper, we Propose an improved dissolve detection method using color information on low-frequency subband and edge elements on high-frequency subband. The Possible dissolve transition are found by analyzing the edge change ratio in the high-frequency subband with edge elements of each direction. Using the double chromatic difference on the lowest frequency subband, we have the improvement of the dissolve detection ratio. The simulation results show that the performance of the proposed algorithm is better than the conventional one for dissolve detection on a diverse set of uncompressed video sequences.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.33-36
• /
• 2000

To create a more realistic soccer game derived from TV images, we are developing an image synthesis system that generates 3D image sequence from TV images. We propose the method for the team and the pose recognition of players in TV images. The representation includes camera calibration method, team recognition method and pose recognition method. To find the location of a player on the field, a field model is constructed and a player's field position is transformed by 4-feature points. To recognize the team information of players, we compute RGB mean values and standard deviations of a player in TV images. Finally, to recognize pose of a player, this system computes the velocity and the ratio of player(height/width). Experimental results are included to evaluate the performance of the team and the pose recognition.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.119-120
• /
• 2016

줄넘기와 같은 반복적인 운동들의 개수 측정은 가속도 센서의 가속도 값과 자이로 센서의 각속도 값의 특징을 추출하고 선택하여 개수를 판단한다. 하지만 잡음과 진동에 취약한 가속도와 드리프트 현상이 발생하는 각속도의 문제점으로 인하여 줄넘기 개수를 세는데 정확도가 떨어지는 문제가 발생한다. 본 논문에서는 6축 가속도 자이로 센서에 상보필터를 적용하여 가속도와 각속도 값의 오류를 최소화하여 보다 정확한 개수를 측정하는 방법을 제안한다. 제안하는 방법은 센서 값의 특징만을 보고 판단하는 방법에 비해 정확하게 개수를 측정하는 것을 실험 결과를 통해 확인할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.117-118
• /
• 2016

줄넘기는 줄을 돌리는 손동작과 뛰어오르는 동작이 결합된 운동으로 정확한 카운트를 위해서는 두 동작을 함께 고려해야 한다. 이전의 연구들에서는 단순 반복적인 운동인 윗몸일으키기, 팔굽혀펴기, 아령 운동과 함께 치부하여 하나의 동작만을 체크하여 카운트 하였다. 이것은 실제 줄넘기 동작과는 차이가 있으며 두 동작 중 하나의 동작만을 하고 있다면 확인해내지 못하는 문제가 있다. 본 논문에서는 6축 가속도 자이로 센서를 이용하여 두 동작을 모두 확인하고 카운트하는 방법을 제안한다. 가속도 센서를 이용하여 뛰어오르는 동작을 확인하며 자이로 센서를 이용하여 손동작을 확인한다. 이때 확인되는 값의 파형을 이용하여 줄넘기 횟수를 카운트하게 된다. 제안하는 방법은 실제 실험을 통하여 카운트 방법의 성능을 확인할 수 있다.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1561-1564
• /
• 2003

Intelligent Wearable Module is intelligent system that arises when a human is part of the feedback loop of a computational process like a certain control system. Applied system is mobile robot. This paper represents the mobile robot control system remote controlled by Intelligent Wearable Module. So far, owing to the development of 802.l1b technologies, lots of remote control methods through internet have been proposed. To control a mobile robot through internet and guide it under unknown environment. The information about the direction and velocity of the mobile robot feedbacks to the PDA and the PDA send new control method produced from the combination of Neuro and Hierarchical Fuzzy Algorithm

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.304-306
• /
• 2003

In this paper, we propose the intelligent robot control technique for mobile robot using personal digital assistants (PDA). With the proposed technique, the mobile rebot can trace human at regular intervals by the remote control method with PDA. The mobile robot can recognize the distances between it and human whom the robot must follow with both multi-ultrasonic sensors and PC-camera and then, can inference the direction and velocity of itself to keep the given regular distances. In the first place, the mobile robot acquires the information about circumstances using ultrasonic sensor and PC-camera then secondly, transmits the data to PDA using wireless LAN communication. Finally, PDA recognizes the status of circumstances using the fuzzy logic and neural network and gives the command to mobile robot again.

• ETRI Journal
• /
• v.40 no.4
• /
• pp.499-510
• /
• 2018

A vector space based augmented structural kinematic (VSASK) feature descriptor is proposed for human activity recognition. An action descriptor is built by integrating the structural and kinematic properties of the actor using vector space based augmented matrix representation. Using the local or global information separately may not provide sufficient action characteristics. The proposed action descriptor combines both the local (pose) and global (position and velocity) features using augmented matrix schema and thereby increases the robustness of the descriptor. A multiclass support vector machine (SVM) is used to learn each action descriptor for the corresponding activity classification and understanding. The performance of the proposed descriptor is experimentally analyzed using the Weizmann and KTH datasets. The average recognition rate for the Weizmann and KTH datasets is 100% and 99.89%, respectively. The computational time for the proposed descriptor learning is 0.003 seconds, which is an improvement of approximately 1.4% over the existing methods.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11c
• /
• pp.749-756
• /
• 2000

Chemical application, one of the most important crop management processes happened to cause spray drift, that would threaten farmers in field as well as dwellers in rural region. Spray drift was affected by micro-meteorological parameters. In Korea, a boom sprayer was introduced but good effects of a boom sprayer was not evaluated. A study to evaluate short distance drift characteristics of a boom sprayer in paddy fields has been undergoing and determining wind characteristics in paddy field was the main purpose of this paper. Micro-meteorological information has been pre-requisite information for evaluating drift in both long and short distances or in both theoretical and experimental ways. Wind velocity, Reynolds stresses, turbulence intensity, skewness, kurtosis etc. were evaluated with height from the ground using a 2-dimensional probe and a hot wire anemometer system.