Uni-Logo
You are here: Home Staff
Articleactions

Deep 3D Perception of People and Their Mobility Aids

This website presents our work about detecting people and characterizing them according to the mobility aids they use. It also provides our annotated dataset that contains five classes: pedestrian, person in wheelchair, pedestrian pushing a person in a wheelchair, person using crutches and person using a walking frame.

The left image shows the detection of people and categorization in the image. The bottom visualizes the estimated 3D position of people. Our approach operates on image data only, the displayed point cloud only serves as a reference and is not used by our approach. On the right image, we show the position and class tracking capabilities of our proposed pipeline.

Publications

  • Andres Vasquez, Marina Kollmitz, Andreas Eitel, Wolfram Burgard
    Deep Detection of People and their Mobility Aids for a Hospital Robot
    IEEE European Conference on Mobile Robots (ECMR), Paris, France, 2017
    Download BibTeX

Videos

The following video shows the performance of our pipeline on our MobilityAids dataset and explains some of the underlying concepts.

Here we show a real-world experiment with our robot Canny, guiding visitors to the professor's office. If the robot perceives that the person is using a walking aid, it guides them to the elevator at a lower travel velocity. People without walking aids are guided to the closer staircase.

MobilityAids Code

Our people detection code is available as a ROS node on GitHub.

MobilityAids Dataset

We collected a hospital dataset with over 17'000 annotated RGB-D images, containing people categorized according to the mobility aids they use: pedestrians, people in wheelchairs, people in wheelchairs with people pushing them, people with crutches and people using walking frames. The images were collected in the facilities of the Faculty of Engineering of the University of Freiburg and in a hospital in Frankfurt.

The following image shows example frames of the dataset. On the right, we show successful classifications of our pipeline. On the left, you can see some failure cases with our approach. The top images are DepthJet examples, the bottom images RGB examples.

Dataset Download

This dataset is provided for research purposes only. Any commercial use is prohibited. If you use the dataset please cite our paper:

  @INPROCEEDINGS{vasquez17ecmr,
  author = {Andres Vasquez and Marina Kollmitz and Andreas Eitel and Wolfram Burgard},
  title = {Deep Detection of People and their Mobility Aids for a Hospital Robot},
  booktitle={Proceedings of the IEEE European Conference on Mobile Robotics (ECMR)},
  year = 2017
  }
  
Download RGB images 960x540 12.2GB
Download depth images 960x540 3.8GB
Download depth-jet images 960x540 1.4GB

Download annotations for RGB
Download annotations for RGB test set 2 (occlusions)
Download annotations for depth
Download annotations for depth test set 2 (occlusions)

Download image set textfiles
Download camera calibration
Download README file