Towards 3D LiDAR-based semantic scene understanding of 3D point cloud sequences: The SemanticKITTI Dataset

Behley, Jens; Garbade, Martin; Milioto, Andres; Quenzel, Jan; Behnke, Sven; Gall, Jürgen; Stachniss, Cyrill

doi:10.1177/02783649211006735

Cited by 93 publications

(33 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both the X-zero and the Z-zero algorithms require the LIDAR to be in a parallel position with respect to the road surface. Although this is a common sensor setup [ 34 , 35 , 36 , 37 , 38 , 39 ] and our vehicles were equipped this way, there are notable cases where it is recommended to set it up differently. For instance, [ 38 ] has LIDAR systems both straight (parallel to the road) and tilted.…”

Section: Discussionmentioning

confidence: 99%

Real-Time LIDAR-Based Urban Road and Sidewalk Detection for Autonomous Vehicles

Horváth

Pozna

Unger

2021

Sensors

View full text Add to dashboard Cite

Road and sidewalk detection in urban scenarios is a challenging task because of the road imperfections and high sensor data bandwidth. Traditional free space and ground filter algorithms are not sensitive enough for small height differences. Camera-based or sensor-fusion solutions are widely used to classify drivable road from sidewalk or pavement. A LIDAR sensor contains all the necessary information from which the feature extraction can be done. Therefore, this paper focuses on LIDAR-based feature extraction. For road and sidewalk detection, the current paper presents a real-time (20 Hz+) solution. This solution can also be used for local path planning. Sidewalk edge detection is the combination of three algorithms working parallelly. To validate the result, the de facto standard benchmark dataset, KITTI, was used alongside our measurements. The data and the source code to reproduce the results are shared publicly on our GitHub repository.

show abstract

Section: Discussionmentioning

confidence: 99%

Real-Time LIDAR-Based Urban Road and Sidewalk Detection for Autonomous Vehicles

Horváth

Pozna

Unger

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Experiments are conducted in three datasets. KITTI [24] and SemanticKITTI [25] are used to measure the accuracy of the 3D object detection and ground segmentation, respectively. The detection algorithm is trained on KITTI training set.…”

Section: Methodsmentioning

confidence: 99%

No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets

Seppänen¹,

Alamikkotervo²,

Ojala³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper presents a novel architecture for point cloud road user detection, which is based on a classical point cloud proposal generator approach, that utilizes simple geometrical rules. New methods are coupled with this technique to achieve extremely small computational requirement, and mAP that is comparable to the state-of-the-art. The idea is to specifically exploit geometrical rules in hopes of faster performance. The typical downsides of this approach, e.g. global context loss, are tackled in this paper, and solutions are presented. This approach allows real-time performance on a single core CPU, which is not the case with endto-end solutions presented in the state-of-the-art. We have evaluated the performance of the method with the public KITTI dataset, and with our own annotated dataset collected with a small mobile robot platform. Moreover, we also present a novel ground segmentation method, which is evaluated with the public SemanticKITTI dataset.

show abstract

“…Object Detection and Tracking. Due to recent advances in supervised deep learning [26] and community efforts in dataset collection and benchmarking [4,6,12,16,47], the research community has witnessed rapid improvement in LiDAR-based 3D object detection [27,39,44,45], tracking [48,53], and segmentation [3,4,54]. Several methods [44,45] follow a well-established two-stage object detection pipeline using point-cloud encoder backbones and a 3D variant of a region proposal network [40], or detect objects as points, followed by classification and bounding box regression [53].…”

Section: Related Workmentioning

confidence: 99%

Forecasting from LiDAR via Future Object Detection

Peri¹,

Luiten²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Object detection and forecasting are fundamental components of embodied perception. These two problems, however, are largely studied in isolation by the community. In this paper, we propose an end-to-end approach for detection and motion forecasting based on raw sensor measurement as opposed to ground truth tracks. Instead of predicting the current frame locations and forecasting forward in time, we directly predict future object locations and backcast to determine where each trajectory began. Our approach not only improves overall accuracy compared to other modular or end-to-end baselines, it also prompts us to rethink the role of explicit tracking for embodied perception. Additionally, by linking future and current locations in a many-toone manner, our approach is able to reason about multiple futures, a capability that was previously considered difficult for end-to-end approaches. We conduct extensive experiments on the popular nuScenes dataset and demonstrate the empirical effectiveness of our approach. In addition, we investigate the appropriateness of reusing standard forecasting metrics for an end-to-end setup, and find a number of limitations which allow us to build simple baselines to game these metrics. We address this issue with a novel set of joint forecasting and detection metrics that extend the commonly used AP metrics from the detection community to measuring forecasting accuracy. Our code is available on GitHub.

show abstract

Towards 3D LiDAR-based semantic scene understanding of 3D point cloud sequences: The SemanticKITTI Dataset

Cited by 93 publications

References 34 publications

Real-Time LIDAR-Based Urban Road and Sidewalk Detection for Autonomous Vehicles

Real-Time LIDAR-Based Urban Road and Sidewalk Detection for Autonomous Vehicles

No GPU? No problem: an ultra fast 3D detection of road users with a simple proposal generator and energy-based out-of-distribution PointNets

Forecasting from LiDAR via Future Object Detection

Contact Info

Product

Resources

About