• Publications
  • Influence
The Cityscapes Dataset for Semantic Urban Scene Understanding
TLDR
We introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Expand
  • 3,845
  • 1005
  • PDF
Semantic Stixels: Depth is not enough
TLDR
We present Semantic Stixels, a novel vision-based scene model geared towards automated driving. Expand
  • 66
  • 5
  • PDF
The Stixel World: A medium-level representation of traffic scenes
TLDR
We propose a medium-level model of the environment that is specifically designed to compress information about obstacles by leveraging the typical layout of outdoor traffic scenes. Expand
  • 34
  • 1
  • PDF
Fully convolutional neural networks for dynamic object detection in grid maps
TLDR
We present a methods that uses a deep convolutional neural network (CNN) to infer whether grid cells are covering a moving object or not based on the structural appearance in the grid map. Expand
  • 14
  • 1
  • PDF
Estimating high definition map parameters with convolutional neural networks
TLDR
In this paper, we present a method to estimate abstract parameters of high definition maps from sensor data. Expand
  • 6
  • 1
Intravenous levetiracetam in clinical practice – Results from an independent registry
PURPOSE Most common clinical studies with antiepileptic drugs do not reflect medical everyday practice due to their strict in- and exclusion criteria and specifications of treatment regimens. Here weExpand
  • 6
Tree-Structured Models for Efficient Multi-Cue Scene Labeling
TLDR
We propose a novel approach to semantic scene labeling in urban scenarios, which aims to combine excellent recognition performance with highest levels of computational efficiency. Expand
  • 11
Environment Estimation with Dynamic Grid Maps and Self-Localizing Tracklets
TLDR
A probabilistic solution based on a particle filter that combines two important perception tasks: fusing multi-sensor data into one estimator and stabilizing the residual errors in the position and speed estimation. Expand
  • 7
Combining Appearance, Depth and Motion for Efficient Semantic Scene Understanding
TLDR
This dissertation addresses the scene labeling problem in an automotive context by constructing a scene labeling concept around the "Stixel World" model of Pfeiffer (2011), which compresses dense information about the environment into a set of small "sticks" that stand upright, perpendicular to the ground plane. Expand
Holistic Grid Fusion Based Stop Line Estimation
TLDR
We propose a method that takes advantage of fused multi-sensory data including stereo camera and lidar as input and utilizes a carefully designed convolutional neural network architecture to detect stop lines. Expand