Learned Enrichment of Top-View Grid Maps Improves Object Detection
This work addresses object detection for autonomous systems using sensor data, but it is incremental as it builds on existing methods by adding a regularization task.
The paper tackles the problem of improving object detection in top-view grid maps by jointly training a model to generate enriched inputs, which enhances generalization without requiring manual annotations. The result is an improvement in object detection performance, though specific numerical gains are not provided.
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.