Anomaly Detection in Radar Data Using PointNets

@article{Griebel2021AnomalyDI,
  title={Anomaly Detection in Radar Data Using PointNets},
  author={Thomas Griebel and Dominik Authaler and Markus Horn and Matti Henning and Michael Buchholz and Klaus C. J. Dietmayer},
  journal={2021 IEEE International Intelligent Transportation Systems Conference (ITSC)},
  year={2021},
  pages={2667-2673}
}
For autonomous driving, radar is an important sensor type. On the one hand, radar offers a direct measurement of the radial velocity of targets in the environment. On the other hand, in literature, radar sensors are known for their robustness against several kinds of adverse weather conditions. However, on the downside, radar is susceptible to ghost targets or clutter which can be caused by several different causes, e.g., reflective surfaces in the environment. Ghost targets, for instance, can… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 16 REFERENCES
2D Car Detection in Radar Data with PointNets
TLDR
This work presents an approach to detect 2D objects solely depending on sparse radar data using PointNets, which facilitates a classification together with a bounding box estimation of objects using a single radar sensor. Expand
Ghost Target Detection in 3D Radar Data using Point Cloud based Deep Neural Network
TLDR
This work introduces the first point based deep learning approach for ghost target detection in 3D radar point clouds by extending the PointNet network architecture by modifying its input to include radar point features beyond location and introducing skip connetions. Expand
Automotive Radar in a UAV to Assess Earth Surface Processes and Land Responses
TLDR
This article developed with automotive radar technology a system with an integrated camera and sensors suitable for the usage in a UAV and future earth science research because of its autonomy, precision, and lightweight. Expand
Instantaneous Ghost Detection Identification in Automotive Scenarios
TLDR
An algorithm is presented, which uses a machine-learning-based classifier to distinguish between real and ghost detections, and shows success rates of 91% in real world experiments. Expand
Identification of Ghost Moving Detections in Automotive Scenarios with Deep Learning
TLDR
A fully connected network is used to distinguish between real and false moving detections in the occupancy gridmaps by using the local Doppler information, along with the spatial context of the surrounding scenario to classify themoving detections. Expand
Automotive Radar Multipath Propagation in Uncertain Environments
TLDR
A novel geometric model to determine the relative positions from surrounding targets and reflection surfaces assuming that every object moves on a circular path to a mutual center is presented. Expand
Semantic Segmentation on Radar Point Clouds
TLDR
This work demonstrates how this task can be performed and provides results on a large data set of manually labeled radar reflections, and eliminates the need for clustering algorithms and manually selected features. Expand
Ghost target identification by analysis of the Doppler distribution in automotive scenarios
TLDR
A model for describing ghost targets and a procedure to distinguish them from real targets using the orientation and the motion state of a vehicle is presented. Expand
Autonomous driving at Ulm University: A modular, robust, and sensor-independent fusion approach
TLDR
The sensor-independent fusion scheme allows for an efficient sensor replacement and realizes redundancy by using probabilistic and generic interfaces, and the performance of the experimental vehicle that was realized during the project is presented along with its software modules. Expand
Deep Learning for Anomaly Detection: A Survey
TLDR
This survey presents a structured and comprehensive overview of research methods in deep learning-based anomaly detection, grouping state-of-the-art deep anomaly detection research techniques into different categories based on the underlying assumptions and approach adopted. Expand
...
1
2
...