SIBGRAPI 2014 - Tutorials

All SIBIGRAPI 2014 tutorials will take place on Wednesday, August 27, from 9:00 to 17:30. Attendees have the option of registering only for the tutorials at special rates. See registration for more information.

Visual Computing and Machine Learning Techniques for Digital Forensics

  • Tutorial 1 - Auditorium 12th floor - 09:00 - 12:30
  • Tutorial Level: intermediate
  • Language: Portuguese
  • Estimated Time: 3 hours.
  • Material for download

Authors: - Tiago Carvalho, (Unicamp, Campinas - Brazil) - Hélio Pedrini, (Unicamp, Campinas - Brazil) - Anderson Rocha, (Unicamp, Campinas - Brazil)

Abstract: In this tutorial, we will give an overview of digital forensics, in special digital image analysis. We present some of the main concepts associated with digital forensics and, complementary, we will present some recent and powerful techniques relying on computer graphics, image processing, computer vision and machine learning concepts for detecting forgeries in photographs. Finally, we will present the challenges and open problems in digital image forensics in order for the audience to get acquainted with the myriad of opportunities available for research.

Introduction to the Smart Surveillance Framework

  • Tutorial 2 - Room 1013 - 14:00 - 17:30
  • Tutorial Level: intermediate.
  • Language: Portuguese
  • Estimated Time: 3 hours.
  • Material for Download

Authors: - William Robson Schwartz (UFMG, Belo Horizonte, Brazil) - Victor Hugo Cunha Melo, (UFMG, Belo Horizonte, Brazil) - Antonio C. Nazare Jr., (UFMG, Belo Horizonte, Brazil)

Abstract: Computer Vision problems applied to Visual Surveillance have been studied for several years aiming at finding accurate and efficient solutions, required to allow the execution of surveillance systems in real environments. The main goal of such systems is to analyze the scene focusing on the detection and recognition of suspicious activities performed by humans in the scene, so that the security personnel can pay closer attention to these preselected activities. To accomplish that, several problems have to be solved first, for instance background subtraction, person detection, tracking and re-identification, face recognition, and action recognition. Even though surveillance related problems have been researched in the past decades, they are hardly considered in a sequence, each one is usually solved individually. However, in real surveillance scenarios, the such problems have to be solved in sequence considering only videos as the input. Some surveillance systems were proposed in the literature, being largely commercial systems, which hindering its use in academia. Recently, was developed a open framework, called Smart Surveillance Framework (SSF), to allow researchers to implement their solutions to the surveillance problems as a sequence of processing modules that communicate through a shared memory. This tutorial focuses on the concepts of visual surveillance and on the application of the SSF. It is structured in four parts. First, the description of the main concepts regarding visual surveillance. Second, the presentation of the Smart Surveillance Framework (SSF) and its resources. Third, an example of application of the SSF. Finally, a step-by-step demonstration of how the framework can be used by researchers working on surveillance and video analysis problems. At the end of this tutorial, the audience will understand the concepts of the Smart Surveillance Framework and its workflow, as well as, be able to implement modules and use the data provided by modules already available in the framework.

SciPy and OpenCV as an interactive computing environment for computer vision

  • Tutorual 3 - FGV´s Cultural Center - 09:00 - 17:30
  • Tutorial Level: intermediate.
  • Language: English
  • Estimated Time: 6 hours.
  • Material for Download

Author: - Thiago T. Santos, (Embrapa Agricultural Informatics - Campinas SP)

Abstract: In research and development (R&D), interactive computing environments are a frequently employed alternative for data exploration, algorithm development and prototyping. In the last twelve years, a popular scientific computing environment flourished around the Python programming language. Most of this environment is part of (or built over) a software stack named the SciPy Stack. Combined to the OpenCV Python interface, this environment raises as a powerful alternative for current computer vision R&D. This course will introduce this environment and show how it addresses different steps on computer vision research, from initial data exploration to prototyping employing machine learning and parallel computing.

Developing Mobile Multimedia Apps, Botanic: A Case Study

  • Tutorial 4 - Auditorium 12th floor - 14:00 - 17:30
  • Tutorial Level: intermediate
  • Language: English
  • Estimated Time: 3 hours.
  • Material for Download

Author: - Luiz Velho, (VISGRAF/IMPA, Rio de Janeiro, Brazil)

Abstract:This tutorial presents a methodology for the development of multimedia mobile applications. It describes the complete process of creating this type of App, going through all the stages of its life cycle, from initial concept to final deployment and usage. The underlying theory and abstract notions are illustrated by a practical example: Jobim Botanic — a project developed by the VISGRAF Laboratory in collaboration with the Instituto Antonio Carlos Jobim.

Graphics for 3D Printing

  • Tutorial 5 - Room 1332 - 14:00 - 17:30
  • Tutorial Level: intermediate
  • Language: English
  • Estimated Time: 3 hours.

Authors: - Karina Rodriguez Echavarria, (University of Brighton, Brighton, UK) - Derek Covill, (University of Brighton, Brighton, UK) - Asla Medeiros e Sá, (FGV/EMAp, Rio de Janeiro, Brazil)

Abstract: 3D printing is becoming of importance to different knowledge areas and sectors due to their increasing affordability and efficiency. This trend is supported by the wider availability of 3D content that has resulted from advances on digitalization technologies. Consequently, innovative technologies are required for taking advantage of the availability of 3D content in order to turn this information into 3D printed products which can support a wide range of purposes. This tutorial will describe the workflow for acquiring 3D content and using printing technologies for different applications. In particular, it will describe how graphic algorithms can support this workflow. Finally, we will present application examples in the Cultural Heritage area.