AutoGraph: Predicting Lane Graphs from Traffic Observations
- URL: http://arxiv.org/abs/2306.15410v3
- Date: Fri, 10 Nov 2023 08:44:23 GMT
- Title: AutoGraph: Predicting Lane Graphs from Traffic Observations
- Authors: Jannik Z\"urn and Ingmar Posner and Wolfram Burgard
- Abstract summary: We propose to use the motion patterns of traffic participants as lane graph annotations.
Based on the location of these tracklets, we predict the successor lane graph from an initial position.
In a subsequent stage, we show how the individual successor predictions can be aggregated into a consistent lane graph.
- Score: 35.73868803802196
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: Lane graph estimation is a long-standing problem in the context of autonomous
driving. Previous works aimed at solving this problem by relying on
large-scale, hand-annotated lane graphs, introducing a data bottleneck for
training models to solve this task. To overcome this limitation, we propose to
use the motion patterns of traffic participants as lane graph annotations. In
our AutoGraph approach, we employ a pre-trained object tracker to collect the
tracklets of traffic participants such as vehicles and trucks. Based on the
location of these tracklets, we predict the successor lane graph from an
initial position using overhead RGB images only, not requiring any human
supervision. In a subsequent stage, we show how the individual successor
predictions can be aggregated into a consistent lane graph. We demonstrate the
efficacy of our approach on the UrbanLaneGraph dataset and perform extensive
quantitative and qualitative evaluations, indicating that AutoGraph is on par
with models trained on hand-annotated graph data. Model and dataset will be
made available at redacted-for-review.
Related papers
- nuScenes Knowledge Graph -- A comprehensive semantic representation of
traffic scenes for trajectory prediction [6.23221362105447]
Trajectory prediction in traffic scenes involves accurately forecasting the behaviour of surrounding vehicles.
It is crucial to consider contextual information, including the driving path of vehicles, road topology, lane dividers, and traffic rules.
This paper presents an approach that utilizes knowledge graphs to model the diverse entities and their semantic connections within traffic scenes.
arXiv Detail & Related papers (2023-12-15T10:40:34Z) - Deep Prompt Tuning for Graph Transformers [55.2480439325792]
Fine-tuning is resource-intensive and requires storing multiple copies of large models.
We propose a novel approach called deep graph prompt tuning as an alternative to fine-tuning.
By freezing the pre-trained parameters and only updating the added tokens, our approach reduces the number of free parameters and eliminates the need for multiple model copies.
arXiv Detail & Related papers (2023-09-18T20:12:17Z) - Prior Based Online Lane Graph Extraction from Single Onboard Camera
Image [133.68032636906133]
We tackle online estimation of the lane graph from a single onboard camera image.
The prior is extracted from the dataset through a transformer based Wasserstein Autoencoder.
The autoencoder is then used to enhance the initial lane graph estimates.
arXiv Detail & Related papers (2023-07-25T08:58:26Z) - Learning and Aggregating Lane Graphs for Urban Automated Driving [26.34702432184092]
Lane graph estimation is an essential and highly challenging task in automated driving and HD map learning.
We propose a novel bottom-up approach to lane graph estimation from aerial imagery that aggregates multiple overlapping graphs into a single consistent graph.
We make our large-scale urban lane graph dataset and code publicly available at http://urbanlanegraph.cs.uni-freiburg.de.
arXiv Detail & Related papers (2023-02-13T08:23:35Z) - Model Inversion Attacks against Graph Neural Networks [65.35955643325038]
We study model inversion attacks against Graph Neural Networks (GNNs)
In this paper, we present GraphMI to infer the private training graph data.
Our experimental results show that such defenses are not sufficiently effective and call for more advanced defenses against privacy attacks.
arXiv Detail & Related papers (2022-09-16T09:13:43Z) - Unboxing the graph: Neural Relational Inference for Mobility Prediction [15.4049962498675]
Graph Networks (GNNs) have been widely applied on non-euclidean spatial data.
In this paper, we use Neural Inference, a dynamically learn the optimal graph model.
arXiv Detail & Related papers (2022-01-25T13:26:35Z) - Lane Graph Estimation for Scene Understanding in Urban Driving [34.82775302794312]
We propose a novel approach for lane geometry estimation from bird's-eye-view images.
We train a graph estimation model on multimodal bird's-eye-view data processed from the popular NuScenes dataset.
Our model shows promising performance for most evaluated urban scenes and can serve as a step towards automated generation of HD lane annotations for autonomous driving.
arXiv Detail & Related papers (2021-05-01T08:38:18Z) - LaneRCNN: Distributed Representations for Graph-Centric Motion
Forecasting [104.8466438967385]
LaneRCNN is a graph-centric motion forecasting model.
We learn a local lane graph representation per actor to encode its past motions and the local map topology.
We parameterize the output trajectories based on lane graphs, a more amenable prediction parameterization.
arXiv Detail & Related papers (2021-01-17T11:54:49Z) - Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset
for Intelligent Vehicles [72.04891523115535]
We propose road scene graph,a special scene-graph for intelligent vehicles.
It provides not only object proposals but also their pair-wise relationships.
By organizing them in a topological graph, these data are explainable, fully-connected, and could be easily processed by GCNs.
arXiv Detail & Related papers (2020-11-27T07:33:11Z)
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.