Garuda - Garba Rujukan Digital

Remo Dance Motion Estimation with Markerless Motion Capture Using The Optical Flow Method Kurniati, Neny; Basuki, Achmad; Pramadihanto, Dadet
EMITTER International Journal of Engineering Technology Vol 3, No 1 (2015)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Motion capture has been developed and applied in various fields, one of them is dancing. Remo dance is a dance from East Java that tells the struggle of a prince who fought on the battlefield. Remo dancer does not use body-tight costume. He wears a few costume pieces and accessories, so required a motion detection method that can detect limb motion which does not damage the beauty of the costumes and does not interfere motion of the dancer. The method is Markerless Motion Capture. Limbs motions are partial behavior. This means that all limbs do not move simultaneously, but alternately. It required motion tracking to detect parts of the body moving and where the direction of motion. Optical flow is a method that is suitable for the above conditions. Moving body parts will be detected by the bounding box. A bounding box differential value between frames can determine the direction of the motion and how far the object is moving. The optical flow method is simple and does not require a monochrome background. This method does not use complex feature extraction process so it can be applied to real-time motion capture. Performance of motion detection with optical flow method is determined by the value of the ratio between the area of the blob and the area of the bounding box. Estimate coordinates are not necessarily like original coordinates, but if the chart of estimate motion similar to the chart of the original motion, it means motion estimation it can be said to have the same motion with the original.Keywords: Motion Capture, Markerless, Remo Dance, Optical Flow

An Implementation of Error Minimization Position Estimate in Wireless Inertial Measurement Unit using Modification ZUPT Darmawan, Adytia; Dewanto, Sanggar; Pramadihanto, Dadet
EMITTER International Journal of Engineering Technology Vol 4, No 2 (2016)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Position estimation using WIMU (Wireless Inertial Measurement Unit) is one of emerging technology in the field of indoor positioning systems. WIMU can detect movement and does not depend on GPS signals. The position is then estimated using a modified ZUPT (Zero Velocity Update) method that was using Filter Magnitude Acceleration (FMA), Variance Magnitude Acceleration (VMA) and Angular Rate (AR) estimation. Performance of this method was justified on a six-legged robot navigation system. Experimental result shows that the combination of VMA-AR gives the best position estimation.

Remo Dance Motion Estimation with Markerless Motion Capture Using The Optical Flow Method Kurniati, Neny; Basuki, Achmad; Pramadihanto, Dadet
EMITTER International Journal of Engineering Technology Vol 3, No 1 (2015)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v3i1.33

Motion capture has been developed and applied in various fields, one of them is dancing. Remo dance is a dance from East Java that tells the struggle of a prince who fought on the battlefield. Remo dancer does not use body-tight costume. He wears a few costume pieces and accessories, so required a motion detection method that can detect limb motion which does not damage the beauty of the costumes and does not interfere motion of the dancer. The method is Markerless Motion Capture. Limbs motions are partial behavior. This means that all limbs do not move simultaneously, but alternately. It required motion tracking to detect parts of the body moving and where the direction of motion. Optical flow is a method that is suitable for the above conditions. Moving body parts will be detected by the bounding box. A bounding box differential value between frames can determine the direction of the motion and how far the object is moving. The optical flow method is simple and does not require a monochrome background. This method does not use complex feature extraction process so it can be applied to real-time motion capture. Performance of motion detection with optical flow method is determined by the value of the ratio between the area of the blob and the area of the bounding box. Estimate coordinates are not necessarily like original coordinates, but if the chart of estimate motion similar to the chart of the original motion, it means motion estimation it can be said to have the same motion with the original.Keywords: Motion Capture, Markerless, Remo Dance, Optical Flow

Teen-Size Humanoid âFLoWâ Complete Analytical Kinematics Yanto, Luky; Dewanto, Raden Sanggar; Pramadihanto, Dadet; Binugroho, Eko Henfri
EMITTER International Journal of Engineering Technology Vol 5, No 2 (2017)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Humanoid research in Indonesia is quite a lot, but in reality only limited in kid-size proportional size, while for the Teen-Size is still rare. Research on the Teen-Size Humanoid robot requires more joints to be able to perform the movement compared to the size of Kid-Size, therefore required more complex modeling to determine the movement. With complete kinematics anlysis, the movement of the robot can be solved. With kinematic forward-invers, researchers can determine the movement of robots by controlling the motor parts that function as a joint on the robot. In this study, the modeling uses D-H parameter, because this modeling has been widely used, besides the calculation can be solved by computing. And then for the simulation can be done with V-REP software. Forward-invers kinematics can be implemented on the PID algorithm, in order to generate speed on the motor that can form an angle on the motor to make the movement. The result of this research is to obtain equation of matrix transformation from all body parts of robot. With the creation of this Humanoid Teen-Size robot, it is hoped that the research on Humanoid robot in Indonesia will be increasingly diverse and increasing, and can be used as a support and reference in the development of Humanoid Teen-Size next.

An Embedded System for applying High Performance Computing in Educational Learning Activity Wina Rachmawan, Irene Erlyn; Fahmi, Nurul; Widodo, Edi Wahyu; Huda, Samsul; Pamenang, M. Unggul; Roziqin, M. Choirur; W., Andri Permana; Sukaridhoto, Stritusta; Pramadihanto, Dadet
EMITTER International Journal of Engineering Technology Vol 4, No 1 (2016)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

HPC (High Performance Computing) has become more popular in the last few years. With the benefits on high computational power, HPC has impact on industry, scientific research and educational activities. Implementing HPC as a curriculum in universities could be consuming a lot of resources because well-known HPC system are using Personal Computer or Server. By using PC as the practical moduls it is need great resources and spaces.Â This paper presents an innovative high performance computing cluster system to support education learning activities in HPC course with small size, low cost, and yet powerful enough. In recent years, High Performance computing usually implanted in cluster computing and require high specification computer and expensive cost. It is not efficient applying High Performance Computing in Educational research activiry such as learning in Class. Therefore, our proposed system is created with inexpensive component by using Embedded System to make High Performance Computing applicable for leaning in the class. Students involved in the construction of embedded system, built clusters from basic embedded and network components, do benchmark performance, and implement simple parallel case using the cluster. Â In this research we performed evaluation of embedded systems comparing with i5 PC, the results of our embedded system performance of NAS benchmark are similar with i5 PCs. We also conducted surveys about student learning satisfaction that with embedded system students are able to learn about HPC from building the system until making an application that use HPC system.

Face RGB-D Data Acquisition System Architecture for 3D Face Identification Technology Ismail, Aldi Bayu Kreshnanda; Muharram, Ihsan Fikri Abdurahman; Pramadihanto, Dadet; Besari, Adnan Rachmat Anom
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

The three-dimensional approach in face identification technology had gained prominent significance as the state-of-the-art breakthrough due to its ability to address the currently developing issues of identification technology (illumination, deformation and pose variance). Consequently, this trend is also followed by rapid development of the three-dimensional face identification architectures in which some of them, namely Microsoft Kinect and Intel RealSense, have become somewhat today's standard because of its popularity. However, these architectures may not be the most accessible to all due to its limited customisation nature being a commercial product. This research aims to propose an architecture as an alternative to the pre-existing ones which allows user to fully customise the RGB-D data by involving open source components, and serving as a less power demanding architecture. The architecture integrates Microsoft LifeCam and Structure Sensor as the input components and other open source libraries which are OpenCV and Point Cloud Library (PCL). The result shows that the proposed architecture can successfully perform the intended tasks such as extracting face RGB-D data and selecting out region of interest in the face area.

Further Investigation on Building and Benchmarking A Low Power Embedded Cluster for Education Sukaridhoto, Sritrusta; Subhan Khalilullah, Achmad; Pramadihanto, Dadet
IPTEK Journal of Proceedings Series Vol 1, No 1 (2014): International Seminar on Applied Technology, Science, and Arts (APTECS) 2013
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j23546026.y2014i1.355

Embedded parallel computing become popular, and the future of innovation in the semiconductor industry will be in ubiquitous computing. Many researchers built embedded cluster system with limited number of devices, but we utilize the device from embedded classroom to build more number of parallel computing unit. In this paper we built low power cluster consisting 32 ARM boards with low-cost customized power supply for high performance computing class for education purpose, tested with several benchmarks on embedded cluster system and analyse the raw performance.

3D Object Detection Based on Point Cloud Data Sari, Dewi Mutiara; Dadet Pramadihanto; Alfan Rizaldy Pratama; Bayu Sandi Marta
Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi Vol. 7 No. 1 (2022)
Publisher : Universitas Dr. Soetomo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25139/inform.v7i1.4417

In the Industrial robotic, computer vision is an important part of the system. The popular object used in the industrial field is a 3D pipe. The problem that is currently being developed is how to detect an object. This research aims to estimate the object detection that is, in this case, is a 3D pipe in various lighting conditions. The camera used in this research is Time of Flight. The methods applied are Remove NaN data for Pre-processing, Random Sample Consensus (RANSAC) for Segmentation, Euclidean Distance for Clustering, and Viewpoint Feature Histogram (VFH) for the object detection. A study conducted on five different objects found that the system could detect each one with a success rate of 100% for the first object, 98.05 percent for the second object, 93.97 percent for the third object, 94 percent for the fourth object, and 99.48 percent for the fifth object. Overall, the system's accuracy in detecting the object is 97.1 percent when four different lighting conditions are applied to five different objects in total.

Implementation and design of new low-cost foot pressure sensor module using piezoelectric sensor in T-FLoW humanoid robot R. Dimas Pristovani; Dewanto Sanggar; Pramadihanto Dadet
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 1: February 2019
Publisher : Institute of Advanced Engineering and Science

Basically, human can sense the active body force trough the soles of their feet and can feel the position vector of zero moment point (ZMP) based on the center of pressure (CoP) from active body force. This behavior is adapted by T-FLoW humanoid robot using unique sensor which is piezoelectric sensor. Piezoelectric sensor has a characteristic which is non-continuous reading (record a data only a moment). Because of it, this sensor cannot be used to stream data such as flex sensor, loadcell sensor, and torque sensor like previous research. Therefore, the piezoelectric sensor still can be used to measure the position vector of ZMP. The idea is using this sensor in a special condition which is during landing condition. By utilizing 6 unit of piezoelectric sensor with a certain placement, the position vector of ZMP (X-Y-axis) and pressure value in Z-axis from action body force can be found. The force resultant method is used to find the position vector of ZMP from each piezoelectric sensor. Based on those final conclusions in each experiment, the implementation of foot pressure sensor modul using piezoelectric sensor has a good result (94%) as shown in final conclusions in each experiment. The advantages of this new foot pressure sensor modul is low-cost design and similar result with another sensor. The disadvantages of this sensor are because of the main characteristic of piezoelectric sensor (non-continuous read) sometimes the calculation has outlayer data.

Stereo vision-based obstacle avoidance module on 3D point cloud data Eko Purbo Wahyono; Endah Suryawati Ningrum; Raden Sanggar Dewanto; Dadet Pramadihanto
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 3: June 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i3.14829

This paper deals in building a 3D vision-based obstacle avoidance and navigation. In order for an autonomous system to work in real life condition, a capability of gaining surrounding environment data, interpret the data and take appropriate action is needed. One of the required capability in this matter for an autonomous system is a capability to navigate cluttered, unorganized environment and avoiding collision with any present obstacle, defined as any data with vertical orientation and able to take decision when environment update exist. Proposed in this work are two-step strategy of extracting the obstacle position and orientation from point cloud data using plane based segmentation and the resultant segmentation are mapped based on obstacle point position relative to camera using occupancy grid map to acquire obstacle cluster position and recorded the occupancy grid map for future use and global navigation, obstacle position gained in grid map is used to plan the navigation path towards target goal without going through obstacle position and modify the navigation path to avoid collision when environment update is present or platform movement is not aligned with navigation path based on timed elastic band method.

Title

Found 33 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 33 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 33 Documents
Search