Research Projects (2010)
- Show Keywords
- 3D Computer Vision 3D reconstruction Aerial Vision Augmented Reality Augmented Video Best Paper Award Biometrics Caleydo Computational Photography 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
PEGASUS: Autonomous Inspection of Overhead Power Lines using an Unmanned Aerial Vehicle
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.