We may earn an affiliate commission when you visit our partners.
Course image
Antonio López Peña, Ernest Valveny, and Maria Vanrell

¿Te interesa la visión por computador? ¿Te gustaría conocer qué métodos puedes utilizar para detectar y reconocer objetos en una imagen?

Read more

¿Te interesa la visión por computador? ¿Te gustaría conocer qué métodos puedes utilizar para detectar y reconocer objetos en una imagen?

En este curso te introducirás en los principios básicos de cualquier sistema automático de detección y reconocimiento de objetos en imágenes. A lo largo del curso analizaremos diferentes métodos de representación y clasificación que te permitirán abordar casos de aplicación de complejidad creciente.

El contenido del curso se estructura a partir de un esquema básico de detección y reconocimiento de objetos que sirve de guía para ir introduciendo tanto los diferentes métodos de extracción de características y representación de la imagen como diferentes alternativas para clasificar una imagen y para localizar todas las instancias de un objeto en la imagen. El temario incluye conceptos básicos de formación de la imagen, la convolución y su aplicación a la detección de contornos, características de regiones, descriptores de imagen (Local Binary Pattern, Histogram of Oriented Gradients, características de Haar) y varios métodos de clasificación (clasificador lineal, Support Vector Machine, Adaboost, Random Forest, Convolutional Neural Network).

Finalizar el curso te permitirá:

• Diseñar, a partir de un esquema básico común, soluciones adaptadas para diferentes problemas de detección y reconocimiento de objetos en una imagen,

• Conocer las principales técnicas para la descripción y clasificación de una imagen,

• Conocer las herramientas que permiten el desarrollo de aplicaciones reales de detección y reconocimiento de objetos, para que seas capaz de desarrollar tus propios sistemas de detección y reconocimiento de objetos en múltiples aplicaciones.

El curso está orientado tanto a estudiantes universitarios de algún grado relacionado con la informática, la ingeniería o las matemáticas, como a otros estudiantes con conocimientos de programación, interesados en aprender cómo utilizar técnicas de visión por computador para extraer información de las imágenes.

INICIO: 1 de Diciembre de 2015

Enroll now

What's inside

Syllabus

INTRODUCCIÓN A LA DETECCIÓN DE OBJETOS
En esta primera semana explicaremos los fundamentos de un detector de objetos. Empezaremos introduciendo los conceptos básicos de la formación y el análisis de imágenes, para aplicarlos en el diseño de detectores simples basados en las características de los píxeles de la imagen. Finalmente, explicaremos los conceptos de correlación y convolución y veremos cómo se pueden utilizar en la detección de objetos.
Read more
CLASIFICACIÓN DE OBJETOS
En esta semana explicaremos el concepto de clasificador de ventana como forma de decidir si una ventana candidata contiene una instancia del objeto que queremos detectar o no. Lo ilustraremos utilizando LBP como descriptor de la imagen y la regresión logística cómo método de clasificación. Nos fijaremos tanto en la parte de aprendizaje del clasificador como en su utilización para determinar el contenido de una ventana.
DETECCIÓN DE OBJETOS
En esta semana nos centraremos primero en la fase de detección de posibles candidatos en la imagen. El conjunto de candidatos que se detecten serán analizados por el clasificador que explicamos en la semana 2 para determinar la presencia del objeto. Además, explicaremos también los pasos necesarios para poder preparar correctamente todos los datos que se utilizan en el aprendizaje y evaluación del detector. Finalmente, veremos cómo podemos evaluar de forma objetiva el rendimiento del detector.
DETECTOR BASADO EN HOG/SVM
En esta semana veremos un segundo ejemplo de sistema de detección de objetos que se basará en la utilización de HOG como descriptor de la imagen y SVM como clasificador.
DETECTOR BASADO EN HAAR/ADABOOST
En esta semana veremos un tercer sistema de detección basado en las características de Haar para describir la imagen y Adaboost como clasificador. Para poder explicar las características de Haar explicaremos también el concepto de imagen integral. Veremos cómo entrenar un clasificador con Adaboost que nos permita seleccionar el mejor subconjunto de las características de Haar. Finalmente, explicaremos cómo combinar varios clasificadores en una cascada para poder implementar un sistema completo de detección.
TÉCNICAS AVANZADAS
En las semanas anteriores hemos visto los métodos más habituales para la detección de objetos. En esta última semana explicaremos algunas técnicas más avanzadas que se pueden utilizar en diferentes fases de la detección y que pueden ser útiles en problemas de detección más complejos. Entre estas técnicas están los modelos no holísticos (DPM, Random Forests), métodos de adaptación de dominio, la utilización de redes neuronales convolucionales, explotar la multi-modalidad en las imágenes y técnicas alternativas para la generación de candidatos.

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Prepares students to design solutions adapted to different problems of object detection and recognition in an image
Suitable for students with programming knowledge, particularly those interested in computer vision
Provides a comprehensive overview of object detection and recognition principles
Taught by instructors recognized for their work in computer vision
Introduces essential concepts in image formation, convolution, and feature extraction
Covers various classification methods, including SVM, Adaboost, and Random Forest

Save this course

Save Detección de objetos to your list so you can find it easily later:
Save

Reviews summary

Practical object detection

This course covers the basics of object detection and pattern recognition, including practical applications. It provides a solid foundation for further research in advanced topics.
Provides practical applications of object detection.
"Una muy buena introducción al tema de la detección de objetos y reconocimiento de patrones, con buenas referencias para iniciar una investigación propia a los tópicos avanzados."

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Detección de objetos with these activities:
Organiza y revisa tus materiales de curso
Organiza y revisa tus notas, tareas, cuestionarios y exámenes para mejorar tu retención y comprensión.
Show steps
  • Recopila todos tus materiales de curso.
  • Organiza tus materiales en un sistema lógico.
  • Revisa tus materiales periódicamente.
Forma un grupo de estudio con tus compañeros
Forma un grupo de estudio con tus compañeros para discutir conceptos, resolver problemas y apoyarse mutuamente.
Show steps
  • Identifica compañeros que estén interesados en formar un grupo de estudio.
  • Establece un horario y un lugar regulares para reunirse.
  • Revisa el material del curso juntos.
  • Trabaja en problemas y proyectos juntos.
Show all two activities

Career center

Learners who complete Detección de objetos will develop knowledge and skills that may be useful to these careers:
Image Processing Engineer
Image Processing Engineers develop and implement image processing algorithms and systems. They also work on integrating image processing systems with other systems. This course helps build a foundation for Image Processing Engineers by teaching them image processing, analysis, and classification techniques.
Computer Vision Engineer
Computer Vision Engineers develop and implement computer vision algorithms and systems. They also work on integrating computer vision systems with other systems. This course helps build a foundation for Computer Vision Engineers by teaching image processing, analysis, and classification techniques.
Computer Vision Researcher
Computer Vision Researchers develop new computer vision algorithms and techniques. They also work on applying computer vision to new applications. This course helps build a foundation for Computer Vision Researchers by teaching them image processing, analysis, and classification techniques.
Geospatial Analyst
Geospatial Analysts use image processing, analysis, and classification techniques to extract insights from geospatial data. This course helps build a foundation for Geospatial Analysts by teaching them image processing, analysis, and classification techniques.
Machine Learning Engineer
Machine Learning Engineers design, develop, and maintain machine learning models. They also work on automating machine learning processes and integrating them with other systems. This course helps build a foundation for Machine Learning Engineers by providing them with a strong understanding of image processing, analysis, and classification techniques.
Autonomous Vehicle Engineer
Autonomous Vehicle Engineers design, develop, and maintain autonomous vehicles. They also work on integrating autonomous vehicles with other systems. This course helps build a foundation for Autonomous Vehicle Engineers by teaching them image processing, analysis, and classification techniques, which are essential for autonomous vehicles to perceive and interact with the world around them.
Remote Sensing Analyst
Remote Sensing Analysts use image processing, analysis, and classification techniques to extract insights from satellite and aerial images. This course helps build a foundation for Remote Sensing Analysts by teaching them image processing, analysis, and classification techniques.
Medical Imaging Analyst
Medical Imaging Analysts use image processing, analysis, and classification techniques to extract insights from medical images. This course helps build a foundation for Medical Imaging Analysts by teaching them image processing, analysis, and classification techniques.
Robotics Engineer
Robotics Engineers design, develop, and maintain robots. They also work on integrating robots with other systems. This course helps build a foundation for Robotics Engineers by teaching them image processing, analysis, and classification techniques, which are essential for robots to perceive and interact with the world around them.
Data Scientist
Data Scientists use scientific methods, processes, algorithms, and systems to extract knowledge and insights from structured and unstructured data. This course helps build a foundation for Data Scientists by teaching image processing, analysis, and classification techniques that can be applied to extract insights from images.
Biomedical Engineer
Biomedical Engineers design, develop, and maintain medical devices and systems. They also work on integrating medical devices and systems with other systems. This course helps build a foundation for Biomedical Engineers by teaching them image processing, analysis, and classification techniques, which are essential for medical devices and systems to perceive and interact with the world around them.
Data Analyst
Data Analysts use data to solve business problems. They also work on developing new products and services. This course may be useful for Data Analysts who are interested in using image processing, analysis, and classification techniques to solve business problems.
Software Engineer
Software Engineers design, develop, and maintain software systems. They also work on integrating software systems with other systems. This course may be useful for Software Engineers who are interested in developing software systems that use image processing, analysis, and classification techniques.
Business Analyst
Business Analysts help businesses improve their performance by identifying and solving problems. They also work on developing new products and services. This course may be useful for Business Analysts who are interested in using image processing, analysis, and classification techniques to solve business problems.
Product Manager
Product Managers are responsible for the development and launch of new products. They also work on managing the lifecycle of products. This course may be useful for Product Managers who are interested in developing products that use image processing, analysis, and classification techniques.

Reading list

We've selected ten books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Detección de objetos.
Provides a comprehensive overview of computer vision and applications. It covers a wide range of topics, from image processing to object detection and recognition. It valuable resource for students and researchers in computer vision.
Provides a comprehensive overview of pattern recognition and machine learning, covering a wide range of topics, from statistical models to neural networks, providing a solid theoretical foundation for understanding the principles of machine learning.
Provides a comprehensive overview of pattern recognition and machine learning. It covers a wide range of topics, from linear regression to neural networks. It valuable resource for students and researchers in computer vision.
Provides a comprehensive overview of computer vision. It covers a wide range of topics, from image formation and acquisition to object detection and recognition. It valuable resource for students and researchers in computer vision.
Provides a practical guide to using deep learning for computer vision tasks. It covers a wide range of topics, from image classification to object detection and segmentation, providing hands-on examples and code snippets that illustrate the implementation of deep learning algorithms in computer vision applications.
Provides a practical introduction to computer vision using OpenCV. It covers a wide range of topics, from image processing to object detection and recognition. It valuable resource for students and researchers in computer vision.
Provides a comprehensive overview of computer vision algorithms and their applications. It covers a wide range of topics, from image formation and representation to object detection and recognition, providing a solid theoretical foundation for understanding the principles of computer vision. As a textbook commonly used in academic institutions, it valuable reference for students and professionals seeking to deepen their knowledge in the field.
Provides a comprehensive and up-to-date overview of computer vision, covering a wide range of topics, from image formation and representation to object detection and recognition, providing a solid theoretical foundation for understanding the principles of computer vision.
Provides a comprehensive overview of computer vision models, learning, and inference, covering a wide range of topics, from image formation and representation to object detection and recognition, providing a solid theoretical foundation for understanding the principles of computer vision.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Detección de objetos.
Clasificación de imágenes: ¿cómo reconocer el contenido...
Most relevant
Introducción a Machine Learning
Most relevant
Docker - Guía práctica de uso para desarrolladores
Most relevant
Humanidades digitales
Most relevant
Big Data: procesamiento y análisis
Most relevant
Visión artificial contemporánea
Most relevant
Programar en Python
Most relevant
Fundamentos de la innovación empresarial
Most relevant
Haz sonar la alarma: Detección y respuesta
Most relevant
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser