# Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps

arXiv: https://arxiv.org/abs/2410.14799 · HTML: https://mlsanity.com/paper/2410.14799/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 13 of 13)

- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [A Random Finite Set Approach for Dynamic Occupancy Grid Maps with Real-Time Application](https://mlsanity.com/paper/1605.02406/) (2016)
- [A Multi-Task Recurrent Neural Network for End-to-End Dynamic Occupancy Grid Mapping](https://mlsanity.com/paper/2202.04461/) (2022)
- [Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs](https://mlsanity.com/paper/1805.08986/) (2018)
- [Fully Convolutional Neural Networks for Dynamic Object Detection in Grid Maps](https://mlsanity.com/paper/1709.03139/) (2017)
- [Object Detection on Dynamic Occupancy Grid Maps Using Deep Learning and Automatic Label Generation](https://mlsanity.com/paper/1802.02202/) (2018)
- [Environment Perception Framework Fusing Multi-Object Tracking, Dynamic Occupancy Grid Maps and Digital Maps](https://mlsanity.com/paper/1812.08449/) (2018)
- [Single-Stage Object Detection from Top-View Grid Maps on Custom Sensor Setups](https://mlsanity.com/paper/2002.00667/) (2020)
- [Deep Radar Inverse Sensor Models for Dynamic Occupancy Grid Maps](https://mlsanity.com/paper/2305.12409/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beam-Wise Statistical Background Subtraction for Static Roadside LiDAR: A Cross-Sensor Benchmark Study](https://mlsanity.com/paper/2608.14868/) (2026)

## Abstract (arXiv)

This paper describes a method to detect generic dynamic objects for automated driving. First, a LiDAR-based dynamic grid is generated online. Second, a deep learning-based detector is trained on the dynamic grid to infer the presence of dynamic objects of any type, which is a prerequisite for safe automated vehicles in arbitrary, edge-case scenarios. The Rotation-equivariant Detector (ReDet) - originally designed for oriented object detection on aerial images - was chosen due to its high detection performance. Experiments are conducted based on real sensor data and the benefits in comparison to classic dynamic cell clustering strategies are highlighted. The false positive object detection rate is strongly reduced by the proposed approach.