Samad Barri Khojasteh

I am a researcher at the University of Alcalá (UAH) in Spain, where I work under the supervision of Daniel Pizarro and Adrien Bartoli. In 2025, I visited the EnCoV Research Group at the University of Clermont Auvergne, France, where I worked on deformable registration with Adrien Bartoli. Previously, I was a research intern at the University of Oviedo, Spain, under the Erasmus+ program, supervised by José Ramón Villar and Víctor M. Gonzalez.

Email  /  Scholar  /  LinkedIn  /  Github

profile photo

Research

My research interests lie in applying machine learning and deep learning techniques to real-world healthcare challenges. I am currently working on Non-Rigid Structure from Motion (NRSfM), 3D reconstruction, and deformable modeling for medical imaging, with a particular focus on Neural Radiance Fields (NeRF) and non-rigid registration. My research aims to develop high-fidelity and robust methods for reconstruction and registration in minimally invasive surgery (MIS). Previously, I worked on Human Activity Recognition (HAR), with an emphasis on fall detection for elder people and monitoring.

Selected Publications

MIS-NeRF: neural radiance fields in minimally-invasive surgery
Samad Barri Khojasteh, David Fuentes-Jimenez, Daniel Pizarro , Yamid Espinel, Adrien Bartoli
IPCAI, 2025
project page / paper

MIS-NeRF improves AR-based lesion localization by facilitating accurate 3D model registration to multiple MIS images.

Neuron Characterization in Complex Cultures Using a Combined YOLO and U-Net Segmentation Approach
Paula Puerta, Berke Öztürk, Samad Barri Khojasteh, Víctor M. González, José R. Villar, Esther Serrano-Pertierra, Antonello Novelli, M.Teresa Fernández-Sánchez, Ángel Río-Álvarez,
SOCO, 2023
project page / paper

Neuron detection in complex cultures by YOLO and U-Net Segmentation.

Autonomous on-wrist acceleration-based fall detection systems: unsolved challenges Approach
José R. Villar, Camelia Chira, Enrique de la Cal, Víctor M. González, Javier Sedano, Samad Barri Khojasteh,
Neurocomputing, 2022
project page / paper

Evaluation autonomous on-wrist wearable devices using different trained machine learning models, where a single dataset is used for training and multiple independent datasets are used for validation.

Mixing user-centered and generalized models for Fall Detection Approach
Mirko Fáñez, José R. Villar, Enrique de la Cal, Víctor M. González, Javier Sedano, Samad Barri Khojasteh,
Neurocomputing, 2022
project page / paper

This paper proposes a hybrid fall detection method combining personalized and generalized models. The approach improves robustness and accuracy across different users compared to single-model method

Evaluation of a Wrist-Based Wearable Fall Detection Method Approach
Samad Barri Khojasteh, José R. Villar, Enrique de la Cal, Víctor M. González, Javier Sedano, Harun Reşit Yazggan,
HAIS, 2018
project page / paper

This paper evaluates a fall detection system based on improved feature extraction and data balancing techniques to enhance classification performance..

Improving Fall Detection Using an On-Wrist Wearable Accelerometer Approach
Samad Barri Khojasteh, José R. Villar, Camelia Chira, Víctor M. González, Enrique De la Cal,
SENSORS, 2018
project page / paper

Propose the low-cost computation fall detection system on wearable accelerometer.

A Stochastic Programming Model for Decision-Making Concerning Medical Supply Location and Allocation in Disaster Management Approach
Samad Barri Khojasteh, Irfan Macit ,
Cambridge, 2017
project page / paper

Stochastic programming model as a solution for optimizing the problem of locating and allocating medical supplies.


This website is adapted from Jon Barron's template.