The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset

Barnes, Dan; Gadd, Matthew; Murcutt, Paul; Newman, Paul; Posner, Ingmar

doi:10.48550/arxiv.1909.01300

Cited by 17 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We held this device to collect two sequences (RHD01lab and RHD02garden) with an average speed of 2m/s. • Oxford Robocar (OR) [36] is a vehicle equipped with two HDL-32E 2 . Datasets were recorded by driving the car on urban roads at an average speed of 10m/s.…”

Section: A Implementation Detailsmentioning

confidence: 99%

Greedy-Based Feature Selection for Efficient LiDAR SLAM

Jiao¹,

Zhu²,

Ye³

et al. 2021

Preprint

View full text Add to dashboard Cite

Modern LiDAR-SLAM (L-SLAM) systems have shown excellent results in large-scale, real-world scenarios. However, they commonly have a high latency due to the expensive data association and nonlinear optimization. This paper demonstrates that actively selecting a subset of features significantly improves both the accuracy and efficiency of an L-SLAM system. We formulate the feature selection as a combinatorial optimization problem under a cardinality constraint to preserve the information matrix's spectral attributes. The stochasticgreedy algorithm is applied to approximate the optimal results in real-time. To avoid ill-conditioned estimation, we also propose a general strategy to evaluate the environment's degeneracy and modify the feature number online. The proposed feature selector is integrated into a multi-LiDAR SLAM system. We validate this enhanced system with extensive experiments covering various scenarios on two sensor setups and computation platforms. We show that our approach exhibits low localization error and speedup compared to the state-of-the-art L-SLAM systems. To benefit the community, we have released the source code: https://ram-lab.com/file/site/m-loam.

show abstract

Section: A Implementation Detailsmentioning

confidence: 99%

Greedy-Based Feature Selection for Efficient LiDAR SLAM

Jiao¹,

Zhu²,

Ye³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The Oxford Radar RobotCar dataset (Barnes et al, 2019) is available for scene understanding analysis. The radar used for data collection offers much finer resolution and higher range than typical automotive radars.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The lack of publicly available radar datasets could be seen as the primary reason for the smaller amount of literature in this field. This issue is partially addressed by novel datasets with radar observations (Barnes et al, 2019) (Nowruzi et al, 2020) that have recently been introduced to enable the scientific community to expand the boundaries of knowledge in this field.…”

Section: Introductionmentioning

confidence: 99%

PolarNet: Accelerated Deep Open Space Segmentation Using Automotive Radar in Polar Domain

Nowruzi¹,

Kolhatkar²,

Kapoor³

et al. 2021

Preprint

View full text Add to dashboard Cite

Camera and Lidar processing have been revolutionized with the rapid development of deep learning model architectures. Automotive radar is one of the crucial elements of automated driver assistance and autonomous driving systems. Radar still relies on traditional signal processing techniques, unlike camera and Lidar based methods. We believe this is the missing link to achieve the most robust perception system. Identifying drivable space and occupied space is the first step in any autonomous decision making task. Occupancy grid map representation of the environment is often used for this purpose. In this paper, we propose PolarNet, a deep neural model to process radar information in polar domain for open space segmentation. We explore various input-output representations. Our experiments show that PolarNet is a effective way to process radar data that achieves state-of-the-art performance and processing speeds while maintaining a compact size.

show abstract

“…Next, we evaluate line descriptors by estimating a camera pose in 3D line maps. The evaluations were performed using the ScanNet [30] and Oxford Radar RobotCar [31] datasets for indoor and outdoor experiments. For indoor environments, we trained our networks in supervised learning, and initialized them with the homography estimation's weights.…”

Section: B Visual Localizationmentioning

confidence: 99%

“…2) Outdoor: The Oxford Radar RobotCar dataset [31] is built upon the Oxford RobotCar dataset [33]. We selected two sequences (2019-01-11-12-26-55 and 2019-01-16-13-09-37) for our reference and query sets.…”

Section: B Visual Localizationmentioning

confidence: 99%

Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

Yoon

Kim

2021

Preprint

View full text Add to dashboard Cite

Along with feature points for image matching, line features provide additional constraints to solve visual geometric problems in robotics and computer vision (CV). Although recent convolutional neural network (CNN)-based line descriptors are promising for viewpoint changes or dynamic environments, we claim that the CNN architecture has innate disadvantages to abstract variable line length into the fixed-dimensional descriptor. In this paper, we effectively introduce Line-Transformers dealing with variable lines. Inspired by natural language processing (NLP) tasks where sentences can be understood and abstracted well in neural nets, we view a line segment as a sentence that contains points (words). By attending to well-describable points on a line dynamically, our descriptor performs excellently on variable line length. We also propose line signature networks sharing the line's geometric attributes to neighborhoods. Performing as group descriptors, the networks enhance line descriptors by understanding lines' relative geometries. Finally, we present the proposed line descriptor and matching in a Point and Line Localization (PL-Loc). We show that the visual localization with feature points can be improved using our line features. We validate the proposed method for homography estimation and visual localization.

show abstract

The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset

Cited by 17 publications

References 15 publications

Greedy-Based Feature Selection for Efficient LiDAR SLAM

Greedy-Based Feature Selection for Efficient LiDAR SLAM

PolarNet: Accelerated Deep Open Space Segmentation Using Automotive Radar in Polar Domain

Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization

Contact Info

Product

Resources

About