CVML Programming Short Course and Workshop on Deep Learning, Computer Vision and Big Data Analytics 2024

This Summer School offers a three-day short course that delivers an in-depth exploration of programming tools and techniques for addressing a variety of computer vision and deep learning challenges. The course focuses on the fundamentals of deep learning and its applications in Natural Disaster Management. The short course consists of three parts (A, B, C), each having lectures and programming workshops with hands-on lab exercises.

This course presents recent deep learning and computer vision advances as applied in Natural Disaster Management (Horizon Europe TEMA R&D project).

Part A will focus on Deep Learning and GPU programming. The lectures of this part provide a solid background on Deep Neural Networks (DNN) topics, notably convolutional NNs (CNNs) and deep learning for image classification and 2D object tracking. Two programming workshops will take place. The first one will be on image classification using CNNs, while the second how to use OpenCV (the most used library for computer vision) for target tracking.

Part B lectures will provide a basic understanding of two well-known methods in computer vision, object detection and image semantic segmentation. Participants will gain insights into how these methods address real-world challenges. Accompanied by programming courses, attendees will learn not only to comprehend but also to apply these techniques effectively. Furthermore, the programming lectures will demonstrate the training of deep neural networks on specialized datasets for Natural Disaster Management, such as fire detection and flood segmentation.

Part C will explore the application of Natural Language Processing (NLP) in Natural Disaster Management (NDM), complemented by a programming workshop focused on analyzing text data from social media platforms, such as Twitter, using deep neural networks (DNNs). Additionally, a lecture on the explainability of computer vision methods will offer participants insights into how these algorithms function and identify which parts of the input image are crucial for their decisions. In the practical component of this lecture, visualization techniques based on input images will be employed to illustrate what information is deemed significant by the neural networks.