Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
- URL: http://arxiv.org/abs/2405.10575v1
- Date: Fri, 17 May 2024 07:00:58 GMT
- Title: Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory
- Authors: Jonas Kälble, Sascha Wirges, Maxim Tatarchenko, Eddy Ilg,
- Abstract summary: We show that techniques to convert LiDAR scans into occupancy grid maps yield very low quality.
We then present a novel approach using evidence theory that yields more accurate reconstructions.
We use the improved occupancy maps to train a state-of-the-art occupancy prediction method and demonstrate that it improves the MAE by 25% on nuScenes.
- Score: 4.837623051835053
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Automated driving fundamentally requires knowledge about the surrounding geometry of the scene. Modern approaches use only captured images to predict occupancy maps that represent the geometry. Training these approaches requires accurate data that may be acquired with the help of LiDAR scanners. We show that the techniques used for current benchmarks and training datasets to convert LiDAR scans into occupancy grid maps yield very low quality, and subsequently present a novel approach using evidence theory that yields more accurate reconstructions. We demonstrate that these are superior by a large margin, both qualitatively and quantitatively, and that we additionally obtain meaningful uncertainty estimates. When converting the occupancy maps back to depth estimates and comparing them with the raw LiDAR measurements, our method yields a MAE improvement of 30% to 52% on nuScenes and 53% on Waymo over other occupancy ground-truth data. Finally, we use the improved occupancy maps to train a state-of-the-art occupancy prediction method and demonstrate that it improves the MAE by 25% on nuScenes.
Related papers
- Producing and Leveraging Online Map Uncertainty in Trajectory Prediction [30.190497345299004]
We extend state-of-the-art online map estimation methods to additionally estimate uncertainty.
In doing so, we find that incorporating uncertainty yields up to 50% faster training convergence and up to 15% better prediction performance.
arXiv Detail & Related papers (2024-03-25T05:58:33Z) - OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments [77.0399450848749]
We propose an OccNeRF method for training occupancy networks without 3D supervision.
We parameterize the reconstructed occupancy fields and reorganize the sampling strategy to align with the cameras' infinite perceptive range.
For semantic occupancy prediction, we design several strategies to polish the prompts and filter the outputs of a pretrained open-vocabulary 2D segmentation model.
arXiv Detail & Related papers (2023-12-14T18:58:52Z) - Pre-training on Synthetic Driving Data for Trajectory Prediction [64.16991399882477]
We aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability.
We take advantage of graph representations of HD-map and apply vector transformations to reshape the maps.
We employ a rule-based model to generate trajectories based on augmented scenes.
arXiv Detail & Related papers (2023-09-18T19:49:22Z) - Enhancing Mapless Trajectory Prediction through Knowledge Distillation [19.626383744807068]
High-definition maps (HD maps) may suffer from the high cost of annotation or restrictions of law that limits their widespread use.
In this paper, we tackle the problem of improving the consistency of multi-modal prediction trajectories and the real road topology.
Our solution is generalizable for common trajectory prediction networks and does not bring extra computation burden.
arXiv Detail & Related papers (2023-06-25T09:05:48Z) - PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map [58.53373202647576]
We propose PreTraM, a self-supervised pre-training scheme for trajectory forecasting.
It consists of two parts: 1) Trajectory-Map Contrastive Learning, where we project trajectories and maps to a shared embedding space with cross-modal contrastive learning, and 2) Map Contrastive Learning, where we enhance map representation with contrastive learning on large quantities of HD-maps.
On top of popular baselines such as AgentFormer and Trajectron++, PreTraM boosts their performance by 5.5% and 6.9% relatively in FDE-10 on the challenging nuScenes dataset.
arXiv Detail & Related papers (2022-04-21T23:01:21Z) - Embedding Earth: Self-supervised contrastive pre-training for dense land
cover classification [61.44538721707377]
We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery.
We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method.
We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
arXiv Detail & Related papers (2022-03-11T16:14:14Z) - FPPN: Future Pseudo-LiDAR Frame Prediction for Autonomous Driving [30.18167579599365]
We propose the first future pseudo-LiDAR frame prediction network.
We first predict a future dense depth map based on dynamic motion information coarsely.
We refine the predicted dense depth map using static contextual information.
The future pseudo-LiDAR frame can be obtained by converting the predicted dense depth map into corresponding 3D point clouds.
arXiv Detail & Related papers (2021-12-08T16:46:18Z) - MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the
Edge [72.16021611888165]
This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for accurate and fast execution on edge devices.
The proposed MEST framework consists of enhancements by Elastic Mutation (EM) and Soft Memory Bound (&S)
Our results suggest that unforgettable examples can be identified in-situ even during the dynamic exploration of sparsity masks.
arXiv Detail & Related papers (2021-10-26T21:15:17Z) - Updating Street Maps using Changes Detected in Satellite Imagery [28.25061267734934]
We propose a novel method that leverages the progression of satellite imagery over time to substantially improve accuracy.
Our approach first compares satellite images captured at different times to identify portions of the physical road network that have visibly changed.
We show that our change-based approach reduces map update error rates four-fold.
arXiv Detail & Related papers (2021-10-13T02:50:26Z) - SLPC: a VRNN-based approach for stochastic lidar prediction and
completion in autonomous driving [63.87272273293804]
We propose a new LiDAR prediction framework that is based on generative models namely Variational Recurrent Neural Networks (VRNNs)
Our algorithm is able to address the limitations of previous video prediction frameworks when dealing with sparse data by spatially inpainting the depth maps in the upcoming frames.
We present a sparse version of VRNNs and an effective self-supervised training method that does not require any labels.
arXiv Detail & Related papers (2021-02-19T11:56:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.