Learned Enrichment of Top-View Grid Maps Improves Object Detection
Authors:
- 20 September 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
We propose an object detector for top-view grid maps which is additionally trained to generate an enriched version of its input. Our goal in the joint model is to improve generalization by regularizing towards structural knowledge in form of a map fused from multiple adjacent range sensor measurements. This training data can be generated in an automatic fashion, thus does not require manual annotations. We present an evidential framework to generate training data, investigate different model architectures and show that predicting enriched inputs as an additional task can improve object detection performance.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentationNeural Networks, 2020
- SuMa++: Efficient LiDAR-based Semantic SLAM2019
- Fusion of range measurements and semantic estimates in an evidential frameworkTM - Technisches Messen, 2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019
- PointPillars: Fast Encoders for Object Detection From Point Clouds2019
- Object Detection and Classification in Occupancy Grid Maps Using Deep Convolutional Networks2018
- A random finite set approach for dynamic occupancy grid maps with real-time applicationThe International Journal of Robotics Research, 2018
- Evidential Occupancy Grid Map Augmentation using Deep Learning2018
- Focal Loss for Dense Object Detection2017
- Object scene flow for autonomous vehicles2015