A Postgraduate certificate that will lead you to Computer Vision, a field that has undergone a great revolution in recent years. Don't fall behind, enroll now"

This Postgraduate certificate, aimed at IT professionals, delves into Computer Vision in Robotics, with special emphasis on image processing and analysis. An advanced knowledge taught by an expert teaching team in Robotics, which will show students the importance of a correct work to improve the mobility and autonomy of a machine. 

An online teaching that will focus on the complex world of robotic navigation. A learning where the students will be able to know perfectly the different techniques used by the scientific community in the area of Robotics to process the data that the machines collect, in order to obtain the most useful information for decision making of the robot itself. It will also delve into vision techniques based on Learning Systems, the use of Neural Networks, specifically Deep Neural Networks, which has revolutionized the way in which Computer Vision is used.

A program with a theoretical-practical approach with the most updated multimedia content for students to acquire a learning that will allow them to progress in their professional career in a field that has grown in recent years and whose future prospects are positive. It is, therefore, an excellent opportunity to acquire a quality and flexible education. Students only need an electronic device with internet connection to access the entire syllabus at any time of the day, without fixed schedules, and with the ease of distributing the teaching load according to their needs. 

You have at your disposal 24 hours a day the most up-to-date multimedia content in Robotics, so you can access it whenever and wherever you want"

This Postgraduate certificate in Computer Vision Algorithms in Robotics: Image Processing and Analysis contains the most complete and up-to-date program on the market. The most important features include:

• Case studies presented by experts in robotic engineering
• The graphic, schematic, and practical contents with which they are created, provide scientific and practical information on the disciplines that are essential for professional practice
• Practical exercises where self-assessment can be used to improve learning
• Its special emphasis on innovative methodologies 
• Theoretical lessons, questions to the expert, debate forums on controversial topics, and individual reflection assignments
• Content that is accessible from any fixed or portable device with an Internet connection

Acquire advanced knowledge in learning techniques for Localization and Mapping in Mobile Robotics with this Postgraduate certificate”

The program’s teaching staff includes professionals from the sector who contribute their work experience to this educational program, as well as renowned specialists from leading societies and prestigious universities.

The multimedia content, developed with the latest educational technology, will provide the professional with situated and contextual learning, i.e., a simulated environment that will provide immersive education programmed to learn in real situations.

This program is designed around Problem-Based Learning, whereby the professional must try to solve the different professional practice situations that arise during the academic year For this purpose, students will be assisted by an innovative, interactive video system created by renowned and experienced experts.

During 6 weeks you will learn the most used techniques and tools for 3D segmentation"

You will gain advanced knowledge in Deep Neural Networks and their application in Industry 4.0"

This Postgraduate certificate consists of 150 teaching hours where students can delve into the field of Computer Vision in Robotics with an up-to-date syllabus consisting of video summaries, specialized readings and real cases. All this will allow you to delve into the processing and analysis of images, learn the main techniques used to establish optical sensors, 3D vision systems, localization in robots or the different methods of learning the environment. The Relearning system, which TECH applies in each of its programs, will favor the foundation of knowledge in a more natural and progressive way.

The Relearning learning system, which TECH applies in its programs will allow you to reduce the long hours of study".

Module 1. Vision Techniques in Robotics: Image Processing and Analysis

1.1. Computer Vision

1.1.1. Computer Vision
1.1.2. Elements of a Computer Vision System
1.1.3. Mathematical Tools

1.2. Optical Sensors for Robotics

1.2.1. Passive Optical Sensors
1.2.2. Active Optical Sensors
1.2.3. Non-Optical Sensors

1.3. Image Acquisition

1.3.1. Image Representation
1.3.2. Color Space
1.3.3. Digitizing Process

1.4. Image Geometry

1.4.1. Lens Models
1.4.2. Camera Models
1.4.3. Camera Calibration

1.5. Mathematical Tools

1.5.1. Histogram of an Image
1.5.2. Convolution
1.5.3. Fourier Transform

1.6. Image Preprocessing

1.6.1. Noise Analysis
1.6.2. Image Smoothing
1.6.3. Image Enhancement

1.7. Image Segmentation

1.7.1. Contour-Based Techniques
1.7.3. Histogram-Based Techniques
1.7.4. Morphological Operations

1.8. Image Feature Detection

1.8.1. Point of Interest Detection
1.8.2. Feature Descriptors
1.8.3. Feature Matching

1.9. 3D Vision Systems

1.9.1. 3D Perception
1.9.2. Feature Matching between Images
1.9.3. Multiple View Geometry

1.10. Computer Vision based Localization

1.10.1. The Robot Localization Problem
1.10.2. Visual Odometry
1.10.3. Sensory Fusion

Module 2. Robot Visual Perception Systems with Machine Learning

2.1. Unsupervised Learning Methods applied to Computer Vision

2.1.1. Clustering
2.1.2. PCA
2.1.3. Nearest Neighbors
2.1.4. Similarity and Matrix Decomposition

2.2. Supervised Learning Methods Applied to Computer Vision

2.2.1. “Bag of Words” Concept
2.2.2. Support Vector Machine
2.2.3. Latent Dirichlet Allocation
2.2.4. Neural Networks

2.3. Deep Neural Networks: Structures, Backbones and Transfer Learning

2.3.1. Feature Generating Layers

2.3.3.1. VGG
2.3.3.2. Densenet
2.3.3.3. ResNet
2.3.3.4. Inception
2.3.3.5. GoogLeNet

2.3.2. Transfer Learning
2.3.3. The Data Preparation for Training

2.4. Computer Vision with Deep Learning I: Detection and Segmentation

2.4.1. YOLO and SSD Differences and Similarities
2.4.2. Unet
2.4.3. Other Structures

2.5. Computer Vision with Deep Learning II: Generative Adversarial Networks

2.5.1. Image Super-Resolution Using GAN
2.5.2. Creation of Realistic Images
2.5.3. Scene Understanding

2.6. Learning Techniques for Localization and Mapping in Mobile Robotics

2.6.1. Loop Closure Detection and Relocation
2.6.2. Magic Leap. Super Point and Super Glue
2.6.3. Depth from Monocular

2.7. Bayesian Inference and 3D Modeling

2.7.1. Bayesian Models and "Classical" Learning
2.7.2. Implicit Surfaces with Gaussian Processes (GPIS)
2.7.3. 3D Segmentation Using GPIS
2.7.4. Neural Networks for 3D Surface Modeling

2.8. End-to-End Applications of Deep Neural Networks

2.8.1. End-to-End System. Example of Person Identification
2.8.2. Object Manipulation with Visual Sensors
2.8.3. Motion Generation and Planning with Visual Sensors

2.9. Cloud Technologies to Accelerate the Development of Deep Learning Algorithms

2.9.1. Use of GPUs for Deep Learning
2.9.2. Agile Development with Google IColab
2.9.3. Remote GPUs, Google Cloud and AWS

2.10. Deployment of Neural Networks in Real Applications

2.10.1. Embedded Systems
2.10.2. Deployment of Neural Networks. Use
2.10.3. Network Optimizations in Deployment, Example with TensorRT

Enter the complex world of Computer Vision and learn about the latest techniques used. Enroll now”