• Publications
  • Influence
Switchable constraints for robust pose graph SLAM
TLDR
We propose a robust back-end formulation for SLAM using switchable constraints that can deal with up to 1000 false positive loop closure constraints on various datasets. Expand
  • 212
  • 27
  • PDF
BRIEF-Gist - closing the loop by simple means
TLDR
The ability to recognize known places is an essential competence of any intelligent system that operates autonomously over longer periods of time. Expand
  • 146
  • 21
  • PDF
Towards a robust back-end for pose graph SLAM
TLDR
We propose a novel formulation of the pose graph SLAM problem that allows the back-end to change parts of the topological structure of the graph during the optimization process. Expand
  • 156
  • 18
  • PDF
Compact Watershed and Preemptive SLIC: On Improving Trade-offs of Superpixel Segmentation Algorithms
TLDR
We present two new super pixel segmentation algorithms, based on existing algorithms, that provide better balanced trade-offs between various performance measures. Expand
  • 64
  • 11
  • PDF
A vision based onboard approach for landing and position control of an autonomous multirotor UAV in GPS-denied environments
TLDR
We describe our work on multirotor UAVs and focus on our method for autonomous landing and position control in the absence of GPS signals by using a dedicated optical flow sensor. Expand
  • 184
  • 8
  • PDF
Appearance change prediction for long-term navigation across seasons
TLDR
We propose a novel approach to learn to predict the changes in an environment by learning how the visual appearance of an environment changes over time. Expand
  • 108
  • 4
  • PDF
Switchable constraints vs. max-mixture models vs. RRR - A comparison of three approaches to robust pose graph SLAM
TLDR
This paper compares three very recently published approaches to robust pose graph SLAM, namely switchable constraints, max-mixture models and the RRR algorithm. Expand
  • 49
  • 4
  • PDF
Genetically optimized neural network classifiers for bankruptcy prediction-an empirical study
TLDR
The use of financial statement data to predict the future financial health of an economic entity is generally considered a complex problem where non-linear pattern recognition methods such as neural networks (NN) can provide a performance advantage. Expand
  • 29
  • 4
  • PDF
Visual Odometry Using Sparse Bundle Adjustment on an Autonomous Outdoor Vehicle
TLDR
Visual Odometry is the process of estimating the movement of a (stereo) camera through its environment by matching point features between pairs of consecutive image frames. Expand
  • 95
  • 3
  • PDF
Beyond Holistic Descriptors, Keypoints, and Fixed Patches: Multiscale Superpixel Grids for Place Recognition in Changing Environments
TLDR
In this letter, we present a novel local region detector, SP-Grid, that is particularly suited for the combination of severe appearance and viewpoint changes. Expand
  • 25
  • 2
  • PDF