Teaching

Bee polls recognition and quantity estimation

Status: about to be finishedSupervisor: Martin Kampel Start: as soon as possible Problem Statement In the project MIC-Cam a system for the automated detection of mites was developed. It monitors the bees by camera when departing and landing at the flight board of the bee hive to recognise attached mites in real time without restricting the … Continue reading Bee polls recognition and quantity estimation

Bee data recording from a bee hive in Banja Luka

Problem Statement & Goal We developed a prototype for recording bees when entering the bee hive. The images are used to analyse bee images in various ways: mite detection, pollen quantity estimation, bee counting, … In this practicum we want to record new bee data in bee hives from our partner in Banja Luka. The … Continue reading Bee data recording from a bee hive in Banja Luka

Shadow Removal in Satellite Images

Status: taken Supervisor: Sebastian Zambanini Problem Statement Shadows cast in remote sensing images complicate their analysis due to the low contrast in the poorly illuminated image regions. Shadow removal/compensation methods aim at automatically reducing shadow effects, either by a physical or learning-based  model. Goal The goal of this work is to explore and examine methods … Continue reading Shadow Removal in Satellite Images

Deep Learning Object Detection in Satellite Video

Status: available Supervisor: Roman Pflugfelder Problem Statement Object detection, i.e. the recognition and localization of objects, is very important in aerial imaging and remote sensing. Demanding applications can be found such as urban planning for smart cities, environment monitoring to reduce traffic and pollution. Object detection in aerial and satellite data is still challenging due to … Continue reading Deep Learning Object Detection in Satellite Video

Improving a Multispectral Imaging System

Status: available Supervisor: Simon Brenner Problem Statement The Computer Vision Lab has developed a Multispectral Imaging system for the imaging of ancient manuscripts (see Fig.1), which was continuously used and updated for the last 15 years. In this hands-on internship you will help us further improve the system, both in hard- and software. Goal In … Continue reading Improving a Multispectral Imaging System

Generative Adversarial Nets (GANs) for the Enhancement of Ancient Manusctripts

Status: available Supervisor: Simon Brenner Problem Statement Multispectral Imaging (MSI) has proven a powerful tool to recover degraded texts in historic manuscripts. In this context, the goal of image enhancement methods is to take the raw multispectral images as input and produce and output image with maximal visibility/legibility of a degraded text. Fig. 1 shows … Continue reading Generative Adversarial Nets (GANs) for the Enhancement of Ancient Manusctripts

3D Surface Structures of Ancient Manuscripts

Status: available Supervisor: Simon Brenner Problem Statement Naturally, historic manuscripts are valuable sources of information. However, not only the letters and drawings made with ink and pigments hold information, but also the three-dimensional structure of the material itself. Examples of interesting features are ruling lines or textual comments drawn with a hard tool (“hard point … Continue reading 3D Surface Structures of Ancient Manuscripts

Raiders of the Lost Writings – Investigating Ancient Manuscripts

Status: availableSupervisor: Simon Brenner Before continuing to read we strongly recommend to let this play in the background: https://www.youtube.com/watch?v=-bTpp8PQSog Introduction Uncountable ancient manuscripts lie in archives, libraries, monastaries and haunted tombs around the world. Unfortunately, the centuries took their toll: due to unsuitable storage conditions, fire- or water damage, clumsy librarians or the recycling of … Continue reading Raiders of the Lost Writings – Investigating Ancient Manuscripts