Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation

@article{Hrmann2018ObjectDO,
  title={Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation},
  author={Stefan H{\"o}rmann and Philipp Henzler and M. Bach and K. Dietmayer},
  journal={2018 IEEE Intelligent Vehicles Symposium (IV)},
  year={2018},
  pages={826-833}
}
  • Stefan Hörmann, Philipp Henzler, +1 author K. Dietmayer
  • Published 2018
  • Computer Science
  • 2018 IEEE Intelligent Vehicles Symposium (IV)
  • We tackle the problem of object detection and pose estimation in a shared space downtown environment. [...] Key Method A single-stage deep convolutional neural network is trained to provide object hypotheses comprising of shape, position, orientation and an existence score from a single input DOGMa. Furthermore, an algorithm for offline object extraction was developed to automatically label several hours of training data. The algorithm is based on a two-pass trajectory extraction, forward and backward in time…Expand Abstract
    14 Citations
    Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs
    • 7
    • PDF
    Offline Object Extraction from Dynamic Occupancy Grid Map Sequences
    • 8
    • PDF
    Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks
    • 31
    • PDF
    Predicting Objects of Interest with Deep Learning
    Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks
    • 2
    • PDF
    Dynamic Occupancy Grid Mapping with Recurrent Neural Networks
    An Online Multi-lidar Dynamic Occupancy Mapping Method
    • 4
    Fast Radar Motion Estimation with a Learnt Focus of Attention using Weak Supervision
    • 20
    • PDF
    Dynamic Environment Prediction in Urban Scenes using Recurrent Representation Learning
    • 2
    • PDF
    Distant Vehicle Detection Using Radar and Vision
    • 21
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Dynamic Occupancy Grid Prediction for Urban Autonomous Driving: A Deep Learning Approach with Fully Automatic Labeling
    • 59
    • PDF
    Fully convolutional neural networks for dynamic object detection in grid maps
    • 13
    • PDF
    Focal Loss for Dense Object Detection
    • 2,829
    SSD: Single Shot MultiBox Detector
    • 8,817
    • PDF
    You Only Look Once: Unified, Real-Time Object Detection
    • 9,373
    • PDF
    Object tracking based on evidential dynamic occupancy grids in urban environments
    • 28
    • PDF
    Deep tracking in the wild: End-to-end tracking using recurrent neural networks
    • 56
    • PDF
    Hybrid sampling Bayesian Occupancy Filter
    • 43
    • PDF
    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    • 19,566
    • Highly Influential
    • PDF
    Occupancy grid map-based extended object tracking
    • 21