Research Projects
- Show Keywords
- 3D Computer Vision 3D reconstruction Aerial Vision Augmented Reality Augmented Video Best Paper Award Biometrics Caleydo Computer Graphics Computer Vision Convex Optimization Coordinate transformations detection face Fingerprint Georeferencing GPU GUI HOG Human Computer Interaction Image Labelling Industrial Applications Information Visualization integral imaging Interaction Interaction Design Machine Learning Medical computer vision Medical Visualization Mixed Reality Mobile computing Mobile phone Model Multi-Display Environments Multiple Perspectives Object detection Object recognition Object reconstruction Object Tracking On-Line Learning Robotics Segmentation Shape analysis shape from focus SLAM Software Projects Structure from Motion Surveillance SVM Symmetry Tracking Fusion Tracking, Action Recognition User Interfaces Variational Methods Virtual reality and augmented reality Visual Tracking Visualization
| Title | Abstract |
Start
|
End |
|---|---|---|---|
|
CONSTRUCT: Construction Site Monitoring and Change Detection using UAVs
(details) |
The goal of the project is to develop methods for modeling and surveying large construction sites. The project will make use of unmanned aerial vehicles and existing stationary or pan-tilt zoom cameras at the construction site. The goal is to provide accurate 3D models on a regular basis of the whole site. This will generate a 4D data set (3D+time). This data can then be used for documentation, visualization (we will use a mobile augmented reality system to overlay e.g. the plan or a model of the building) as well as measurement (e.g., how much material has been transported). From a scientific point of view we will have to solve following tasks:
|
2011 | 2014 |
|
HOLISTIC: Holistic Aerial Scene Understanding Using Highly Redundant Data
(details) |
The aim of this research project is holistic scene understanding in large aerial datasets, consisting of thousands of massively redundant high-resolution images. Holistic scene understanding is one of the major problems in computer vision and photogrammetry and has recently got a lot of attention. The problem of holistic image understanding includes two fundamental tasks: 3D scene reconstruction and semantic interpretation of the imaged content at the level of pixels. The tight interaction between semantic classification and 3D reconstruction is often ignored by state of the art aerial image processing workflows, due to the lack of computational power, the absence of efficient algorithms or the enormous effort of manual intervention. However, these tasks are mutually informative and should be solved jointly as a correct class labelling is a valuable source of information for reconstruction, and 3D information can help to improve the semantic interpretation. For instance, a correct classification is a valuable source of information for reconstruction in regions where dense matching methods fail (e.g. sheets of water and reflecting windows / facades), and 3D information can be used as a prior to improve classification (e.g. building and road detection). The high resolution and redundancy due to large overlaps of aerial images requires massive processing power which will be handled by taking advantage of graphic processing units that have proved to give a significant speedup compared to single core machines. In particular, we will focus on algorithms based on variational methods, which provide a high degree of parallelization capability. In order to reduce cost-intensive manual interaction, we further will exploit publicly available user-data from the Internet to improve both interpretation and 3D reconstruction. In the HOLISTIC project we will provide a flexible framework for scene classification and 3D reconstruction from aerial images that outperforms current state-of-the art and delivers interpretable models at highest possible accuracy. To achieve this goal, we will focus our attention on the following two research subjects: (i) the joint optimization of geometry and semantic classification from aerial images in a unified framework, and (ii) the exploitation of existing geographic information systems and web data to support these two sub-tasks. In addition, we will use web-based standard to efficiently represent the obtained results for fast modeling and data parsing. |
2011 | 2014 |
|
PEGASUS: Autonomous Inspection of Overhead Power Lines using an Unmanned Aerial Vehicle
(details) |
The aim of the PEGASUS project is to develop a mobile vision system for overhead power line inspection to be mounted on an unmanned aerial vehicle (UAV). The long term goal is to develop a fully autonomous aerial vehicle which is able to perform power line inspection in an automated manner. This goal requires innovative solutions to a number of problems such as visual navigation, visual tracking and obstacle detection, model-based inspection under harsh conditions etc. In addition, due to the use of a small scale UAV (e.g. a quad-rotor helicopter) we have restricted computational resources for algorithms that need to be executed on the UAV (especially for navigation and tracking). Within PEGASUS we want to make significant progress towards this long term goal. In particular, PEGASUS will provide a set of tools for the inspector. The project is organized in four phases: First, an inspection system for a single power tower is developed. Used in ground-based inspection, the UAV provides close-up views of all points of interest from an optimal viewpoint. Second, we want to implement an automatic visual inspection system which highlights possible faulty components. In a third step, the system is extended towards multiple towers (still in the sight of the operator). Finally, the system will be used as a handheld system in manned helicopters by power line inspectors, where it should dramatically reduce the time needed for inspection. From a research perspective we will develop novel solutions for model-based recognition and pose estimation, visual navigation including obstacle avoidance and automated model-based visual inspection. All of these problems are extremely challenging because of the uncontrolled conditions (illumination etc.) and the real-time requirements. If successful, the methods developed in PEGASUS will be usable beyond the task of power line inspection. |
2010 | 2013 |
