Hasil Pencarian  ::  Simpan CSV :: Kembali

"In this paper, we present a 3D shape modeling system based on Tsai Shah shape from shading (SFS) algorithm. This SFS provides partial 3D shapes, as depth maps of the object to be reconstructed. Our previously developed Projected Polygon Representation Neural Network (PPRNN) performed the reconstruction process. This neural network is able to successively refine the polygon vertices parameter of an initial 3D shape based on 2D images taken from multiple views. The reconstuction is finalized by mapping the texture of object image to the 3 D initial shape. It is known from static stereo analysis that even though multiple view images are used, obtaining 3D structure without considering of base-distance information, i.e. focal separation between different camera positions, is impossible. Unless there is something else is known about the scene. Here we propose the use of shading features to extrat the 3D depth maps by using a fasat SFS algortihm, instead of rendering the object based on bare 2D images. A beginning result of reconstructing human (mannequin) head and face is presented. From our experiment, it was shown that using only 2D images would result a poor reconstruction. While using the depth-maps provides a smoother and more realistic 3D object. "

"Salah satu pergeseran paradigma terbesar dalam dunia kedokteran saat ini adalah pergeseran model pelayanan kesehatan dari disease-centric care menjadi patient-centric care. Bedah plastik rekonstruksi dan estetik menjadi spesialis kedokteran yang membutuhkan implementasi model tersebut, didorong oleh rendahnya tingkat konversi pasien di tahap pre-operatif, teknik operasi tanpa panduan di tahap intra-operatif, dan masih tingginya tingkat permintaan revisi operasi di tahap pasca-operatif. Saat ini, implementasi patient-centric care melalui penggunaan model spesifik-pasien, yaitu replika anatomis bagian wajah atau tubuh pasien yang dapat digunakan dokter sebagai simulator bedah dan alat visualisasi pasien, menjadi instrumen paling efektif dalam memecahkan masalah tersebut. Namun, model spesifik-pasien yang ada di pasaran saat ini masih menggunakan modalitas pemindai yang rumit, mahal, dan model spesifik-pasien masih sulit diakses khususnya untuk negara berkembang. Oleh karena itu, dalam skripsi ini penulis mengusulkan sebuah rancang bangun model spesifik-pasien yang dikhususkan pada bagian maxillofacial untuk pemandu operasi dengan metode pemindaian 3D berbasis smartphone dengan sensor TrueDepth™ dan pemodelan 3D berbasis Growing Neural Gas yang jauh lebih sederhana, murah, dan terjangkau. Akurasi model spesifik-pasien yang dirancang diukur nilai indeks similaritasnya sebesar 0,2101 terhadap topologi wajah subjek asli yang dinilai cukup akurat.

---

One of the biggest paradigm shifts in medicine today is the shift in health care models from “disease-centric care” to “patient-centric care”. Plastic and aesthetic surgery become one of the medical field who urgently need this model implementation, driven by the low conversion rates of patients in pre-surgery phase, unguided surgery technique encountered in intra-operative phase, and high surgery revision demand in postoperative phase. Currently, patient-centric care implemented through patient-specific models, which is an anatomical replica of the patient's face or body which surgeons can use as a surgical simulator and patient visualization tool, this instrument proven to be the most effective in solving those mentioned problems. However, patient-specific models on the market today still use complex and expensive scanning modalities and the patient-specific models that are still difficult to access, especially in developing countries. Therefore, in this research the author propose a patient-specific model prototype for surgical guidance in maxillofacial region with 3D scanning methodology which utilized smartphone with TrueDepth™ sensor and Growing Neural Gas-based 3D modelling methodology which more simple, low-cost, and accessible. The accuracy of patient-specific model measured in similarity index against the subject’s real face topology resulted in the amount of 0,2101 which sufficiently accurate."

"ABSTRAK On 26 December 2004. amd undersea seismic activity, with a magnitude of 9 on the Richter Scale occured in epicenter some 250 kilometers off the coast of Sumatera, Indonesia. It triggered a devastating tidal wave or "tsunami" measuring up to 10 meters high and traveling at 500 km/hour. Indonesia, Sri Lanka, India, Thailand, Myanmar, Bangladesh, Maldives, Seychelles, Yamen, Somalia, Kenya and Tanzania in the Indian Ocean were hit. It inflicted seroius damages to structures built close to the seashore, in particular Aceh and North Sumatera province where the damages were devastating. This paper will analyze the usage of GIS in assessing damages and rebuilding process. This paper will present a knowledge-based approach for recontruction. By combining the aerial image analysis with information from GIS maps and construction domain specific knowledge the compleity of the reconstruction process can be greatly reduced "

"Teknologi pemindaian dan rekonstruksi model tiga dimensi (3D) telah mengalami evolusi yang pesat, terutama dengan meningkatnya tren perkembangan teknologi LiDAR yang lebih portabel dan mudah dijangkau oleh pengguna awam, seperti yang terlihat pada perangkat genggam. Terlepas dari kemajuan di bidang perangkat keras, perkembangan perangkat lunak sebagai antarmuka pengguna dengan teknologi tersebut masih sangat terbatas dan belum dapat mengakomodasi kebutuhan dan pengetahuan yang dimiliki oleh masyarakat luas. Penelitian ini mengusulkan pengembangan sistem \textit{end-to-end} yang mampu memindai, memvisualisasikan, serta melakukan segmentasi aset 3D dari hasil rekaman lingkungan 3D. Pendekatan menggunakan teknik terbaru seperti 3D Gaussian Splatting dan Point Transformer tidak hanya dapat meningkatkan kualitas dan aksesibilitas segmentasi objek 3D, tetapi juga membuka jalan untuk adopsi yang lebih luas di berbagai bidang yang menargetkan pengguna awam.

---

Three-dimensional (3D) model scanning and reconstruction technology has undergone rapid evolution, especially with the increasing trend of developing LiDAR technology that is more portable and easily accessible to ordinary users, as seen in handheld devices. Despite the progress in hardware, the development of software as a user interface for the technology is still very limited and has not been able to accommodate the needs and knowledge possessed by the wider community. This research proposes the development of an end-to-end system capable of scanning, visualizing, and segmenting 3D assets from recorded 3D environments. The approach of using the latest techniques, such as 3D Gaussian Splatting and Point Transformer, can not only improve the quality and accessibility of 3D object segmentation but also pave the way for wider adoption in various fields targeting lay users."

"Teknologi pemindaian dan rekonstruksi model tiga dimensi (3D) telah mengalami evolusi yang pesat, terutama dengan meningkatnya tren perkembangan teknologi LiDAR yang lebih portabel dan mudah dijangkau oleh pengguna awam, seperti yang terlihat pada perangkat genggam. Terlepas dari kemajuan di bidang perangkat keras, perkembangan perangkat lunak sebagai antarmuka pengguna dengan teknologi tersebut masih sangat terbatas dan belum dapat mengakomodasi kebutuhan dan pengetahuan yang dimiliki oleh masyarakat luas. Penelitian ini mengusulkan pengembangan sistem \textit{end-to-end} yang mampu memindai, memvisualisasikan, serta melakukan segmentasi aset 3D dari hasil rekaman lingkungan 3D. Pendekatan menggunakan teknik terbaru seperti 3D Gaussian Splatting dan Point Transformer tidak hanya dapat meningkatkan kualitas dan aksesibilitas segmentasi objek 3D, tetapi juga membuka jalan untuk adopsi yang lebih luas di berbagai bidang yang menargetkan pengguna awam.

---

Three-dimensional (3D) model scanning and reconstruction technology has undergone rapid evolution, especially with the increasing trend of developing LiDAR technology that is more portable and easily accessible to ordinary users, as seen in handheld devices. Despite the progress in hardware, the development of software as a user interface for the technology is still very limited and has not been able to accommodate the needs and knowledge possessed by the wider community. This research proposes the development of an end-to-end system capable of scanning, visualizing, and segmenting 3D assets from recorded 3D environments. The approach of using the latest techniques, such as 3D Gaussian Splatting and Point Transformer, can not only improve the quality and accessibility of 3D object segmentation but also pave the way for wider adoption in various fields targeting lay users."