Hardware-Accelerated Video Analytics Training Course

This instructor-led, live training in the US (online or onsite) is aimed at beginner-level system administrators and IT professionals who wish to install, configure, manage, and troubleshoot CUDA environments.

By the end of this training, participants will be able to:

• Understand the architecture, components, and capabilities of CUDA.
• Install and configure CUDA environments.
• Manage and optimize CUDA resources.
• Debug and troubleshoot common CUDA issues.

This instructor-led, live training in the US (online or onsite) is aimed at developers who wish to use CUDA to build Python applications that run in parallel on NVIDIA GPUs.

By the end of this training, participants will be able to:

• Use the Numba compiler to accelerate Python applications running on NVIDIA GPUs.
• Create, compile and launch custom CUDA kernels.
• Manage GPU memory.
• Convert a CPU based application into a GPU-accelerated application.

OpenFace is Python and Torch based open-source, real-time facial recognition software based on Google's FaceNet research.

In this instructor-led, live training, participants will learn how to use OpenFace's components to create and deploy a sample facial recognition application.

By the end of this training, participants will be able to:

• Work with OpenFace's components, including dlib, OpenVC, Torch, and nn4 to implement face detection, alignment, and transformation
• Apply OpenFace to real-world applications such as surveillance, identity verification, virtual reality, gaming, and identifying repeat customers, etc.

Audience

• Developers
• Data scientists

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

This instructor-led, live training introduces the software, hardware, and step-by-step process needed to build a facial recognition system from scratch. Facial Recognition is also known as Face Recognition.

The hardware used in this lab includes Rasberry Pi, a camera module, servos (optional), etc. Participants are responsible for purchasing these components themselves. The software used includes OpenCV, Linux, Python, etc.

By the end of this training, participants will be able to:

• Install Linux, OpenCV and other software utilities and libraries on a Rasberry Pi.
• Configure OpenCV to capture and detect facial images.
• Understand the various options for packaging a Rasberry Pi system for use in real-world environments.
• Adapt the system for a variety of use cases, including surveillance, identity verification, etc.

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Note

• Other hardware and software options include: Arduino, OpenFace, Windows, etc. If you wish to use any of these, please contact us to arrange.

Fiji is an open-source image processing package that bundles ImageJ (an image processing program for scientific multidimensional images) and a number of plugins for scientific image analysis.

In this instructor-led, live training, participants will learn how to use the Fiji distribution and its underlying ImageJ program to create an image analysis application.

By the end of this training, participants will be able to:

• Use Fiji's advanced programming features and software components to extend ImageJ
• Stitch large 3d images from overlapping tiles
• Automatically update a Fiji installation on startup using the integrated update system
• Select from a broad selection of scripting languages to build custom image analysis solutions
• Use Fiji's powerful libraries, such as ImgLib on large bioimage datasets
• Deploy their application and collaborate with other scientists on similar projects

Format of the Course

• Interactive lecture and discussion.
• Lots of exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Marvin is an extensible, cross-platform, open-source image and video processing framework developed in Java.  Developers can use Marvin to manipulate images, extract features from images for classification tasks, generate figures algorithmically, process video file datasets, and set up unit test automation.

Some of Marvin's video applications include filtering, augmented reality, object tracking and motion detection.

In this instructor-led, live course participants will learn the principles of image and video analysis and utilize the Marvin Framework and its image processing algorithms to construct their own application.

Format of the Course

• The basic principles of image analysis, video analysis and the Marvin Framework are first introduced. Students are given project-based tasks which allow them to practice the concepts learned. By the end of the class, participants will have developed their own application using the Marvin Framework and libraries.

PaddlePaddle (PArallel Distributed Deep LEarning) is a scalable deep learning platform developed by Baidu.

In this instructor-led, live training, participants will learn how to use PaddlePaddle to enable deep learning in their product and service applications.

By the end of this training, participants will be able to:

• Set up and configure PaddlePaddle
• Set up a Convolutional Neural Network (CNN) for image recognition and object detection
• Set up a Recurrent Neural Network (RNN) for sentiment analysis
• Set up deep learning on recommendation systems to help users find answers
• Predict click-through rates (CTR), classify large-scale image sets, perform optical character recognition(OCR), rank searches, detect computer viruses, and implement a recommendation system.

Audience

• Developers
• Data scientists

Format of the course

• Part lecture, part discussion, exercises and heavy hands-on practice

Pattern Matching is a technique used to locate specified patterns within an image. It can be used to determine the existence of specified characteristics within a captured image, for example the expected label on a defective product in a factory line or the specified dimensions of a component. It is different from "Pattern Recognition" (which recognizes general patterns based on larger collections of related samples) in that it specifically dictates what we are looking for, then tells us whether the expected pattern exists or not.

Format of the Course

• This course introduces the approaches, technologies and algorithms used in the field of pattern matching as it applies to Machine Vision.

Scilab is a well-developed, free, and open-source high-level language for scientific data manipulation. Used for statistics, graphics and animation, simulation, signal processing, physics, optimization, and more, its central data structure is the matrix, simplifying many types of problems compared to alternatives such as FORTRAN and C derivatives. It is compatible with languages such as C, Java, and Python, making it suitable as for use as a supplement to existing systems.

In this instructor-led training, participants will learn the advantages of Scilab compared to alternatives like Matlab, the basics of the Scilab syntax as well as some advanced functions, and interface with other widely used languages, depending on demand. The course will conclude with a brief project focusing on image processing.

By the end of this training, participants will have a grasp of the basic functions and some advanced functions of Scilab, and have the resources to continue expanding their knowledge.

Audience

• Data scientists and engineers, especially with interest in image processing and facial recognition

Format of the course

• Part lecture, part discussion, exercises and intensive hands-on practice, with a final project