Identification of Ghost Moving Detections in Automotive Scenarios with Deep Learning
- Resource Type
- Conference
- Authors
- Garcia, Javier Martinez; Prophet, Robert; Michel, Juan Carlos Fuentes; Ebelt, Randolf; Vossiek, Martin; Weber, Ingo
- Source
- 2019 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM) Microwaves for Intelligent Mobility (ICMIM), 2019 IEEE MTT-S International Conference on. :1-4 Apr, 2019
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Fields, Waves and Electromagnetics
Transportation
Radar
Automotive engineering
Semantics
Deep learning
Feature extraction
Convolution
Image segmentation
77 GHz
automotive radar
classification
deep learning
ghost detection
- Language
We introduce a method to classify ghost moving detections in automotive radar sensors for advanced driver assistance systems. A fully connected network is used to distinguish between real and false moving detections in the occupancy gridmaps. By using this architecture, we combine the local Doppler information, along with the spatial context of the surrounding scenario to classify the moving detections. A proof of concept experiment shows promising results with data from a test drive in an urban scenario.