Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Nasional Teknik Elektro dan Teknologi Informasi

Rekonstruksi Objek 3D dari Multiple Images Rachmawati; Risanuri Hidayat; Sunu Wibirama
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 2 No 1: Februari 2013
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1115.087 KB)

Abstract

Abstract - 3D reconstruction is a task of recovering 3D geometry and color information. There are two categories of 3D object reconstruction: active method, 3D model acquisition can be performed by laser scanner or structured light. Passive methods, reconstruct 3D models by image sequences from a single camera or multiple cameras. Object scanning often demand expensive equipment and special skill to operate. As a simple and low cost approach, 3D reconstruction based images became more popular among the researches. In this study apply passive reconstruction technique, the reconstruction of 3D objects made using images taken from different viewpoint leading to the same object using a digital camera.To determine the corresponding points of the two views used epipolar geometry and Direct Linear Triangulation algorithm (DLT). All required parameters are extracted from the image itself, without any calibration of the camera before. The reconstruction process can divided into four part: first, feature point extraction. Second estimate the fundamental matrix from point correspondences, third compute the camera matrix, and the end compute 3D point from image points. All the required parameters are recovered from the images. As objects of experiment used a miniatur of a statue. Experiment result show the residual error from estimation fundamental matrix is 9.9051 x10-04, and reprojection error 1.714 x 10-03 pixel. Visually, the reconstructed 3D model reseamble the shape of the original object. Intisari - Rekonstruksi 3D merupakan proses untuk memperoleh kembali informasi geometri 3D dan warna. Teknik rekonstruksi objek tiga dimensi terbagi menjadi 2 kategori, yaitu metode aktif: akuisisi model 3D dapat dilakukan dengan laser scanner atau cahaya terstruktur. Metode pasif: rekonstruksi model 3D dengan sekumpulan gambar dari sebuah atau beberapa kamera. Object scanning terkadang membutuhkan peralatan yang mahal dan keahlian khusus untuk mengoperasikan. Sebagai pendekatan yang sederhana dan murah, rekonstruksi objek berdasarkan gambar menjadi lebih popular bagi para peneliti. Pada penelitian ini menerapkan teknik rekonstruksi pasif, rekonstruksi objek 3D dilakukan dengan menggunakan citra yang diambil dari posisi yang berbeda yang mengarah ke obyek yang sama menggunakan sebuah kamera digital sederhana. Untuk menentukan titik-titik persamaan dari kedua citra tersebut digunakan epipolar geometry dan komputasi titik 3D menggunakan algoritma Direct Linear Triangulation (DLT). Semua parameter yang dibutuhkan diekstrak dari citra itu sendiri, tanpa dilakukan kalibrasi kamera sebelumnya. Tahapan rekonstruksi dapat dibagi menjadi empat bagian: pertama, ekstraksi titik fitur, kedua menghitung fundamental matrik dari titik – titik yang berkoresponden, ketiga menghitung matrik kamera dan terakhir mendapatkan titik-titik 3D untuk semua pasangan titik citra. Sebagai obyek penelitian adalah sebuah miniatur patung. Dari hasil rekonstruksi patung dari menggunakan citra dengan resolusi 1824 x 1368 pixel diperoleh residual error 9.9051 x 10-04 dan reproyeksi error 1.714 x 10-03. Secara visualisasi model 3D yang dihasilkan menyerupai bentuk obyek aslinya.
Rekonstruksi dan Visualisasi Objek 3-D Berbasis Algoritma Direct Linear Transformation Sunu Wibirama; Risanuri Hidayat
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 1 No 2: Mei 2012
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1205.227 KB)

Abstract

Visual reconstruction and modeling of three dimensional (3-D) object is an emerging research topic in computer vision and photogrammetry fields. Nowadays, many commercial products are developed to obtain 3-D model of rigid object, starting from small ancient heritages to city landscape. Such commercial tools are very expensive and not accessible for education and research purpose. This paper aims to present a low-cost approach to generate a 3-D model from geometry of multiple two-dimensional (2-D) images using consumer-level Digital Single Lens Reflection (DSLR) camera. Direct Linear Transformation (DLT) algorithm was used to obtain 3-D point cloud. Texturization of 3-D object was generated by implementing Convex Hull and Random Sample Consensus (RANSAC) algorithms. Experimental result of small Merlion Singapore statue and large Herz-Jesu building shows that the proposed low-cost method is able to visually reconstruct small and large objects by using 10-20% feature points detected on 2D images. Rekonstruksi visual dan pemodelan objek tiga dimensi (3-D) adalah sebuah topik penelitian yang sedang berkembang pesat dalam bidang computer vision dan fotogrametri. Saat ini, banyak produk komersial dikembangkan untuk melakukan pemodelan objek 3-D dengan struktur rigid, mulai dari warisan sejarah berukuran kecil sampai dengan bentang darat perkotaan. Alat-alat komersial tersebut biasanya berbiaya tinggi dan tidak terjangkau apabila digunakan untuk tujuan pendidikan dan penelitian. Paper ini memperkenalkan sebuah metode berbiaya rendah untuk melakukan proses rekonstruksi objek 3-D dari unsur geometri beberapa citra dua dimensi (2-D) dengan menggunakan kamera Digital Single Lens Reflection (DSLR) yang banyak dijumpai di pasaran. Algoritma Direct Linear Transformation (DLT) digunakan untuk menghasilkan titik-titik 3-D. Proses teksturisasi objek 3-D dilakukan dengan memanfaatkan algoritma Convex Hull dan Random Sample Consensus (RANSAC). Hasil percobaan pada objek patung miniatur Merlion Singapore dan bangunan Herz-Jesu menunjukkan bahwa metode berbiaya rendah ini mampu merekonstruksi objek miniatur dan objek berukuran besar secara visual dengan memanfaatkan 10-20% titik-titik fitur yang terdeteksi pada citra 2-D.
Kajian Eye-Tracking Pengaruh Gender Terhadap Proses Kognitif dalam Pembelajaran Multimedia AG Pradnya Sidhawara; Sunu Wibirama; Dwi Joko Suroso
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 2: Mei 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i2.5145

Abstract

Multimedia learning is defined as the process of forming a knowledge mental model from words and pictures. It is important to measure cognitive process during multimedia learning. Differences in learners’ capabilities can be investigated through cognitive processes to improve the learning process. However, conventional methods such as interviews or behavioural assessment do not provide an objective measurement of cognitive processes during multimedia learning. Some advance methods to measure cognitive processes takes into account learner’s eye movement during learning process. In such a case, eye-tracking can be used as an alternative method to measure cognitive processes because eye movement has become a major part of human cognitive function. Another issue is related to the learners with different gender, which might have different styles of interaction with the source of information. Unfortunately, the effect of gender disparities in multimedia learning has not been widely studied. To address this research gap, this study examines the effect of gender differences based on eye-tracking metrics during multimedia learning. Based on the experimental results, `time until first fixation` on the text-type area of interest (AOI), `number of fixations` on the image type AOI, and `transition` from text-type AOI to image-type as well as `transition` between Image AOIs provided notable distinctions for each gender group (p < 0.05). It was found that male learners preferred to access information from images. In contrast, female learners tended to do a thorough inspection on textual and pictorial information during multimedia learning. This study can be used as an alternative method for collecting cognitive process indicators in multimedia learning.