A university degree in which you will progress in the robotics industry under the guidance of experts with long professional careers"

The mobility and autonomy of robots depends largely on the technical ability to improve their artificial vision by making their movements much more precise and more human-like. A complex task that requires highly qualified engineering professionals. This Postgraduate certificate, taught by a team of experts in Robotics, will delve over 12 weeks in the algorithms that allow image processing and analysis in robots. 

An education in which students will acquire advanced and comprehensive knowledge about the efficient operation of mobile robots in complex environments, decision making and performing tasks without human intervention, i.e. everything that pertains to robotic navigation. A program with a theoretical approach, but with great practical application so that the professional can progress in a sector on the rise in recent years thanks to the improvement of techniques and the different advanced digital tools that allow the configuration of algorithms that affect artificial vision. 

An excellent opportunity for the engineering professional who wishes to progress with a university degree taught entirely in 100% online mode. A teaching method that you can study comfortably and flexibly, since you only need a device with an internet connection to access all the multimedia content that makes up this Postgraduate certificate, without fixed timetable sessions and with the complete content of the program from the first day. A method that will allow you to reconcile your personal responsibilities while acquiring an education that is at the forefront of the academic world. 

A university program that brings you the most innovative multimedia content in the field of robotics and machine vision"

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 

The Relearning system of this 100% online teaching will facilitate your learning and reduce the long hours of study"

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. 

Its 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 an immersive education programmed to learn in real situations. 

The design of this program focuses on Problem-Based Learning, by means of which the professional must try to solve the different professional practice situations that are presented throughout the academic course. For this purpose, the student will be assisted by an innovative interactive video system created by renowned experts. 

With this program, you can go deeper into Bayesian models and 3D segmentation with the most up-to-date tools"

Solve the main problems of Robot localization thanks to this Postgraduate certificate. Enroll now"

This Postgraduate certificate consists of a syllabus that has been developed by a teaching team specialized in the field of Robotics, which will allow the engineering professional to deepen during 300 teaching hours in Machine Vision. Thus, students will acquire a thorough knowledge of computer vision, optical sensors, mathematical tools and the different vision learning methods used. The video summaries, the specialized readings and the real cases provided by the teaching staff will serve to acquire a comprehensive and agile learning process.

The real cases presented in this course will facilitate the creation of Neural Networks in robots"

Module 1. Computer 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

Take the step to get up to date on the latest developments in Computer Vision Algorithms in Robotics: Image Processing and Analysis"