Logo de Freelancer Cómo funcionaBusca trabajos
Iniciar sesión Registrarse
Publica un proyecto
EXPLORAR
AI (Artificial Intelligence) HW/SW
Algorithm
Machine Learning (ML)
Matlab and Mathematica
Python
Foto de portada de perfil
Ahora estás siguiendo a
Error al seguir a usuario.
Este usuario no permite que los usuarios lo sigan.
Ya estás siguiendo a este usuario.
Tu plan de membresía solo permite 0 seguimientos. Mejora tu membresía aquí.
Dejaste de seguir correctamente a
Error al dejar de seguir al usuario.
Has recomendado exitosamente a
Error al recomendar al usuario.
Algo salió mal. Por favor, actualiza la página e intenta de nuevo.
Email verificado correctamente.
Avatar del usuario
$30 USD / hora
Bandera de GERMANY
lingen, germany
$30 USD / hora
Aquí son las 8:38 p. m.
Se unió el enero 24, 2023
0 recomendaciones

Natalia S.

@pofc2023

 5,0 (3 comentarios)
4,5
4,5
100%
100%
$30 USD / hora
Bandera de GERMANY
lingen, germany
$30 USD / hora
100 %
Trabajos finalizados
100 %
Dentro del presupuesto
100 %
A tiempo
33 %
Tasa de recontratación

PhD in Geoinformatics, Computer Vision, ML

We are the team of 5 experts: mathematician, physicist and 3 software developers. Our team has a strong mathematical background and many years of professional experience in software development and data processing.
Freelancer Python Developers Germany
Ver todo Python Developers en Germany

Contacta Natalia S. sobre tu trabajo

Inicia sesión para comentar cualquier detalle por chat.

Portafolio

10755724
The task was to develop an algorithm that covers a figure of arbitrary shape with a set of non-overlapping rectangles. The shape of the rectangle was restricted by the minimum and maximum side length. The algorithm had to try to generate as few rectangles as possible. To solve the problem, a completely new algorithm was developed and implemented in Python. The video shows the iterative filling of the given shape with rectangles.
Fitting a sequence of rectangles into an arbitrary figure.
10755672
The goal of the project was to improve the efficiency of group exercises by analyzing video data by means of Deep Learning. The exercises were filmed with an RGB camera. Body position and face keypoints were detected on the video frames. Based on the obtained data, the statistical characteristic values were calculated. The statistical values were used to estimate the efficiency of group exercises.
Increasing the effectiveness of exercises in group training.
10754720
The goal of the project was to anonimize (remove sensitive data) RGB video stream by converting video images into depth maps. The MiDaS model was used for the conversion (https://pytorch.org/hub/intelisl_midas_v2/). The depth maps are used further for estimating body pose, counting people, inspecting objects, etc. Depth modeling was installed on the server and integrated into the back-end solution.
Anonimization of video information using depth mapping
10754587
The aim of the project was to validate and choose the best method for multimodal synthesis of photorealistic images from a sketch. As a result of the validation, the pixe2style2pixel method was selected. The method is described in the paper: Elad Richardson, Yuval Alaluf, Or Patashnik, Yotam Nitzan, Yaniv Azar, Stav Shapiro, Daniel Cohen-Or "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" The resulting code was successfully integrated into a back-end solution.
Multi-modal synthesis of images from a sketch.
10755724
The task was to develop an algorithm that covers a figure of arbitrary shape with a set of non-overlapping rectangles. The shape of the rectangle was restricted by the minimum and maximum side length. The algorithm had to try to generate as few rectangles as possible. To solve the problem, a completely new algorithm was developed and implemented in Python. The video shows the iterative filling of the given shape with rectangles.
Fitting a sequence of rectangles into an arbitrary figure.
10755672
The goal of the project was to improve the efficiency of group exercises by analyzing video data by means of Deep Learning. The exercises were filmed with an RGB camera. Body position and face keypoints were detected on the video frames. Based on the obtained data, the statistical characteristic values were calculated. The statistical values were used to estimate the efficiency of group exercises.
Increasing the effectiveness of exercises in group training.
10754720
The goal of the project was to anonimize (remove sensitive data) RGB video stream by converting video images into depth maps. The MiDaS model was used for the conversion (https://pytorch.org/hub/intelisl_midas_v2/). The depth maps are used further for estimating body pose, counting people, inspecting objects, etc. Depth modeling was installed on the server and integrated into the back-end solution.
Anonimization of video information using depth mapping
10754587
The aim of the project was to validate and choose the best method for multimodal synthesis of photorealistic images from a sketch. As a result of the validation, the pixe2style2pixel method was selected. The method is described in the paper: Elad Richardson, Yuval Alaluf, Or Patashnik, Yotam Nitzan, Yaniv Azar, Stav Shapiro, Daniel Cohen-Or "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" The resulting code was successfully integrated into a back-end solution.
Multi-modal synthesis of images from a sketch.

Comentarios

Cambios guardados
Mostrando 1 - 3 de 3 reseñas
 Filtrar reseñas por:
5,0
$10,00 USD
Project for Natalia S.
Natalia is an expert in python, image processing and Machine learning techniques. She is very smart and professional, good to work with, and understood the project clearly from the start and delivered on time. Excellent work !
Python
Matlab and Mathematica
Algorithm
Machine Learning (ML)
+1 más
Avatar del usuario
Bandera de Mahmut R.
@Mahmutr
•
hace 1 año
5,0
$200,00 USD
Python coding
Exellect skills and expertise extended. Highly recommend. Would love to work with her again. Thank you.
Engineering
Python
Software Architecture
S
Bandera de Kaoru Y.
@skytree634
•
hace 1 año
5,0
$10,00 USD
fit rectangles into a 2D shape within an image using either Matlab or Python -- 2
Natalia is very professional and quick, and wrote a clear code to get the job done. I am surely going to work with Natalia in the future and strongly recommend.
Python
Matlab and Mathematica
Algorithm
Machine Learning (ML)
Image Processing
Avatar del usuario
Bandera de Mahmut R.
@Mahmutr
•
hace 1 año

Contacta Natalia S. sobre tu trabajo

Inicia sesión para comentar cualquier detalle por chat.

Verificaciones

Freelancer preferente
Identidad verificada
Pago verificado
Teléfono verificado
Email verificado
Facebook conectado

Principales habilidades

Python 4
Matlab and Mathematica 3
Algorithm 3
Machine Learning (ML) 2
AI (Artificial Intelligence) HW/SW 1

Explorar freelancers similares

Python Developers in Germany
Python Developers
Matlab and Mathematica Engineers
Algorithm Experts

Explorar galerías similares

Python
Matlab and Mathematica
Algorithm
Machine Learning (ML)
Usuario anterior Usuario siguiente
¡Invitación enviada correctamente!
¡Gracias! Te hemos enviado un enlace para reclamar tu crédito gratuito.
Algo salió mal al enviar tu correo electrónico. Por favor, intenta de nuevo.
Logo de Freelancer Chile / Español Ayuda y soporte Freelancer CategoríasProyectos Concursos Freelancers Empresarial MembresíaPrograma de Freelancers Preferentes Gestión del proyecto Trabajos localesPhoto Anywhere GaleríaAPI para desarrolladoresVerifícate Software de escritorio Información Quiénes somos Cómo funciona Seguridad Inversionista Mapa del sitio Historias NoticiasEquipoPremiosComunicados de prensaEmpleos Términos Política de privacidadTérminos y condicionesPolítica de derechos de autorCódigo de conductaCargos y TarifasSociosEscrow.comLoadshiftWarrior Forum Apps Logo de "App Store" de AppleLogo de Google Play
Falló el copiado al portapapeles. Intenta de nuevo después de ajustar tus permisos.
Copiado al portapapeles.
Usuarios registrados Total de empleos publicados
Freelancer ® is a registered Trademark of Freelancer Technology Pty Limited (ACN 142 189 759)
Copyright © 2024 Freelancer Technology Pty Limited (ACN 142 189 759)
Cargando visualización previa
Permiso concedido para Geolocalización.
Tu sesión de acceso ha expirado y has sido desconectado. Por favor, inica sesión nuevamente.