Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset
- URL: http://arxiv.org/abs/2504.17371v2
- Date: Fri, 25 Apr 2025 12:59:17 GMT
- Title: Highly Accurate and Diverse Traffic Data: The DeepScenario Open 3D Dataset
- Authors: Oussema Dhaouadi, Johannes Meier, Luca Wahl, Jacques Kaiser, Luca Scalerandi, Nick Wandelburg, Zhuolun Zhou, Nijanthan Berinpanathan, Holger Banzhaf, Daniel Cremers,
- Abstract summary: We introduce the DeepScenario Open 3D dataset (DSC3D) of 6 degrees of freedom bounding box trajectories acquired through a novel monocular camera drone tracking pipeline.<n>Our dataset includes more than 175,000 trajectories of 14 types of traffic participants and significantly exceeds existing datasets in terms of diversity and scale.<n>We demonstrate its utility across multiple applications including motion prediction, motion planning, scenario mining, and generative reactive traffic agents.
- Score: 25.244956737443527
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Accurate 3D trajectory data is crucial for advancing autonomous driving. Yet, traditional datasets are usually captured by fixed sensors mounted on a car and are susceptible to occlusion. Additionally, such an approach can precisely reconstruct the dynamic environment in the close vicinity of the measurement vehicle only, while neglecting objects that are further away. In this paper, we introduce the DeepScenario Open 3D Dataset (DSC3D), a high-quality, occlusion-free dataset of 6 degrees of freedom bounding box trajectories acquired through a novel monocular camera drone tracking pipeline. Our dataset includes more than 175,000 trajectories of 14 types of traffic participants and significantly exceeds existing datasets in terms of diversity and scale, containing many unprecedented scenarios such as complex vehicle-pedestrian interaction on highly populated urban streets and comprehensive parking maneuvers from entry to exit. DSC3D dataset was captured in five various locations in Europe and the United States and include: a parking lot, a crowded inner-city, a steep urban intersection, a federal highway, and a suburban intersection. Our 3D trajectory dataset aims to enhance autonomous driving systems by providing detailed environmental 3D representations, which could lead to improved obstacle interactions and safety. We demonstrate its utility across multiple applications including motion prediction, motion planning, scenario mining, and generative reactive traffic agents. Our interactive online visualization platform and the complete dataset are publicly available at https://app.deepscenario.com, facilitating research in motion prediction, behavior modeling, and safety validation.
Related papers
- OnSiteVRU: A High-Resolution Trajectory Dataset for High-Density Vulnerable Road Users [41.63444034391952]
This study developed the OnSiteVRU datasets, which cover a variety of scenarios, including intersections, road segments, and urban villages.<n>The datasets provide trajectory data for motor vehicles, electric bicycles, and human-powered bicycles, totaling approximately 17,429 trajectories with a precision of 0.04 seconds.<n>The results demonstrate that VRU_Data outperforms traditional datasets in terms of VRU density and scene coverage, offering a more comprehensive representation of VRU behavioral characteristics.
arXiv Detail & Related papers (2025-03-30T08:44:55Z) - Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagery [4.387337528923525]
This paper presents a framework for extracting geo-referenced vehicle trajectories from high-altitude drone imagery.<n>The study was conducted in the Songdo International Business District, South Korea.
arXiv Detail & Related papers (2024-11-04T14:49:01Z) - InScope: A New Real-world 3D Infrastructure-side Collaborative Perception Dataset for Open Traffic Scenarios [13.821143687548494]
This paper introduces a new 3D infrastructure-side collaborative perception dataset, abbreviated as inscope.
InScope encapsulates a 20-day capture duration with 303 tracking trajectories and 187,787 3D bounding boxes annotated by experts.
arXiv Detail & Related papers (2024-07-31T13:11:14Z) - Empowering Urban Traffic Management: Elevated 3D LiDAR for Data Collection and Advanced Object Detection Analysis [4.831084635928491]
This paper presents a novel framework that transforms the detection and analysis of 3D objects in traffic scenarios by utilizing the power of elevated LiDAR sensors.
Due to the limitation in obtaining real-world traffic datasets, we utilize the simulator to generate 3D point cloud for specific scenarios.
arXiv Detail & Related papers (2024-05-21T21:12:09Z) - Argoverse 2: Next Generation Datasets for Self-Driving Perception and
Forecasting [64.7364925689825]
Argoverse 2 (AV2) is a collection of three datasets for perception and forecasting research in the self-driving domain.
The Lidar dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose.
The Motion Forecasting dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene.
arXiv Detail & Related papers (2023-01-02T00:36:22Z) - IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes [79.18349050238413]
Preparation and training of deploy-able deep learning architectures require the models to be suited to different traffic scenarios.
An unstructured and complex driving layout found in several developing countries such as India poses a challenge to these models.
We build a new dataset, IDD-3D, which consists of multi-modal data from multiple cameras and LiDAR sensors with 12k annotated driving LiDAR frames.
arXiv Detail & Related papers (2022-10-23T23:03:17Z) - DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and
Interconnected Self-driving [19.66714697653504]
Vehicle-to-Everything (V2X) network has enabled collaborative perception in autonomous driving.
The lack of datasets has severely blocked the development of collaborative perception algorithms.
We release DOLPHINS: dataset for cOllaborative Perception enabled Harmonious and INterconnected Self-driving.
arXiv Detail & Related papers (2022-07-15T17:07:07Z) - Weakly Supervised Training of Monocular 3D Object Detectors Using Wide
Baseline Multi-view Traffic Camera Data [19.63193201107591]
7DoF prediction of vehicles at an intersection is an important task for assessing potential conflicts between road users.
We develop an approach using a weakly supervised method of fine tuning 3D object detectors for traffic observation cameras.
Our method achieves vehicle 7DoF pose prediction accuracy on our dataset comparable to the top performing monocular 3D object detectors on autonomous vehicle datasets.
arXiv Detail & Related papers (2021-10-21T08:26:48Z) - One Million Scenes for Autonomous Driving: ONCE Dataset [91.94189514073354]
We introduce the ONCE dataset for 3D object detection in the autonomous driving scenario.
The data is selected from 144 driving hours, which is 20x longer than the largest 3D autonomous driving dataset available.
We reproduce and evaluate a variety of self-supervised and semi-supervised methods on the ONCE dataset.
arXiv Detail & Related papers (2021-06-21T12:28:08Z) - Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving.
We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
arXiv Detail & Related papers (2021-03-12T15:30:02Z) - End-to-end Interpretable Neural Motion Planner [78.69295676456085]
We propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios.
We design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations.
We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America.
arXiv Detail & Related papers (2021-01-17T14:16:12Z) - Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data
Augmentation [77.60050239225086]
We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images.
Our approach is fully automatic without any human interaction.
We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
arXiv Detail & Related papers (2020-12-15T03:03:38Z)
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.