Universität Bonn: Autonomous Intelligent SystemsInstitute for Computer Science VI: Autonomous Intelligent Systems

Lab Vision Systems - Learning Vision Systems on Graphics Cards  MA-INF 4308

Prof. Dr. Sven Behnke, Dr. Seongyong Koo

weekly, dates by agreement, work on the final project will be possible in the lecture-free time in the summer

First Meeting Wednesday: 1.6.2016, 13:00, room I.28, Friedrich-Ebert-Allee 144

Content

Due to the availability of general purpose programming interfaces like CUDA, the immense speed of graphics cards can be put to work for a multitude of parallel tasks. Algorithms for the analysis of images mostly work independently on different regions of an image. These algorithms are therefore inherently parallel and can greatly profit from parallel hardware.

Speedup factors in the order of two magnitudes make it possible to process and extract information from huge datasets, for example the images of the ImageNet Large Scale Visual Recognition Challenge. When experimenting with learning algorithms, the experiment duration is drastically reduced.

In the lab, we learn how to implement learning algorithms from the area of visual pattern recognition and accelerate them using the CUDA C++ extension. It will be split into two parts. In the first part, you will first aquire knowledge of CUDA by programming and accelerating simple algorithms using parallel programming. In the second part, we implement learning algorithms with the help of an existing CUDA library.

Prerequisites

Slides and assignments

Application Domain: Pascal Object Recognition Challenge

Pascal Object Categorization Challenge

Our three Titan CUDA computers with a total of 34.560 CUDA cores and 96GB DDR5 RAM

CUDA-Supercomputer

Universität Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI