LIBRE: The Multiple 3D LiDAR Dataset

Carballo, Alexander; Lambert, Jacob; Monrroy, Abraham; Wong, David; Narksri, Patiphon; Kitsukawa, Yuki; Takeuchi, Eijiro; Kato, Shigeo; Takeda, Kazuya

doi:10.1109/iv47402.2020.9304681

Cited by 88 publications

(67 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Setting up multiple lidar systems looking at the same scene can cause direct or indirect cross-talk between the sensors and produce artifacts in the pointclouds, thus leading to undesired measurements [36]. To avoid such phenomena and to achieve the most consistent results, the sensors are powered one by one so that they are recorded individually and do not influence each other.…”

Section: Methodsmentioning

confidence: 99%

A Quantitative Analysis of Point Clouds from Automotive Lidars Exposed to Artificial Rain and Fog

et al. 2021

View full text Add to dashboard Cite

Light Detection And Ranging sensors (lidar) are key to autonomous driving, but their data is severely impacted by weather events (rain, fog, snow). To increase the safety and availability of self-driving vehicles, the analysis of the phenomena of the consequences at stake is necessary. This paper presents experiments performed in a climatic chamber with lidars of different technologies (spinning, Risley prisms, micro-motion and MEMS) that are compared in various artificial rain and fog conditions. A specific target with calibrated reflectance is used to make a first quantitative analysis. We observe different results depending on the sensors, and unexpected behaviors in the analysis with artificial rain are seen where higher rain rates do not necessarily mean higher degradations on lidar data.

show abstract

Section: Methodsmentioning

confidence: 99%

A Quantitative Analysis of Point Clouds from Automotive Lidars Exposed to Artificial Rain and Fog

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent years, adverse weather conditions got a lot more attention and there are many other works worth mentioning that look into the degradation of LiDAR data in different adverse weather conditions [45,9,21,17,14,44,24,22]. Very recently, in 2020, the authors of LIBRE [4] test several LiDAR sensors in a weather chamber under rain and fog. Thereby they provide great and valuable insights on the robustness of individual sensors of this time on challenging weather conditions.…”

Section: Effects Of Adverse Weather On Lidarmentioning

confidence: 99%

“…Despite the benefit of measuring exact depth information, LiDAR has a significant drawback. The light pulses that LiDAR sensors emit in the invisible near infrared (NIR) spectrum (typically at 850 and 903 to 905 nm wavelength [4]) do not penetrate water particles, as opposed to automotive radars. This means as soon as there are water particles in the form of fog in the air, light pulses emitted by the sensor will undergo backscattering and attenuation.…”

Section: Introductionmentioning

confidence: 99%

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

Hahner

Sakaridis

Dai

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

This work addresses the challenging task of LiDARbased 3D object detection in foggy weather. Collecting and annotating data in such a scenario is very time, labor and cost intensive. In this paper, we tackle this problem by simulating physically accurate fog into clear-weather scenes, so that the abundant existing real datasets captured in clear weather can be repurposed for our task. Our contributions are twofold: 1) We develop a physically valid fog simulation method that is applicable to any LiDAR dataset. This unleashes the acquisition of large-scale foggy training data at no extra cost. These partially synthetic data can be used to improve the robustness of several perception methods, such as 3D object detection and tracking or simultaneous localization and mapping, on real foggy data. 2) Through extensive experiments with several state-of-theart detection approaches, we show that our fog simulation can be leveraged to significantly improve the performance for 3D object detection in the presence of fog. Thus, we are the first to provide strong 3D object detection baselines on the Seeing Through Fog dataset. Our code is available at www.trace.ethz.ch/lidar fog simulation.

show abstract

“…However, the LiDAR sensor has some disadvantages, namely, it is still expensive technology compared to other solutions, it is affected by some specific atmospheric weather conditions, as in the case of fog and smoke presence. Research work [4] has shown that recent LiDAR sensors (higher angle resolution) perform well in rainy conditions. However, there are still several weather conditions requiring analysis; freezing rain, sticky snow, as well the temperature LiDAR range are some examples of variables that have not been considered in these LiDAR benchmarks studies.…”

Section: Introductionmentioning

confidence: 99%

“…Perception is here described as the autonomous vehicle ability to detect objects in the surrounding environment in a real-time manner. However, this is a very challenging task due to the sparse and unstructured nature of the high dimensional data contained in point clouds, the number of points in a point cloud (which typically comprises more than 120,000 points [4]) and the limitations in computation power and power supply as expected in real-case applications, where vehicle setups do not contain a GPU-based server. Turning the task of accomplishing a perception algorithm able to meet the requirements imposed by the application, where it is expected for solutions to deliver outputs in a real-time manner (often, the target inference time is set as 10 Hz) [6], almost impractical.…”

Section: Introductionmentioning

confidence: 99%

Real-Time 3D Object Detection and SLAM Fusion in a Low-Cost LiDAR Test Vehicle Setup

Fernandes

Afonso²,

Girão³

et al. 2021

Sensors

View full text Add to dashboard Cite

Recently released research about deep learning applications related to perception for autonomous driving focuses heavily on the usage of LiDAR point cloud data as input for the neural networks, highlighting the importance of LiDAR technology in the field of Autonomous Driving (AD). In this sense, a great percentage of the vehicle platforms used to create the datasets released for the development of these neural networks, as well as some AD commercial solutions available on the market, heavily invest in an array of sensors, including a large number of sensors as well as several sensor modalities. However, these costs create a barrier to entry for low-cost solutions for the performance of critical perception tasks such as Object Detection and SLAM. This paper explores current vehicle platforms and proposes a low-cost, LiDAR-based test vehicle platform capable of running critical perception tasks (Object Detection and SLAM) in real time. Additionally, we propose the creation of a deep learning-based inference model for Object Detection deployed in a resource-constrained device, as well as a graph-based SLAM implementation, providing important considerations, explored while taking into account the real-time processing requirement and presenting relevant results demonstrating the usability of the developed work in the context of the proposed low-cost platform.

show abstract

LIBRE: The Multiple 3D LiDAR Dataset

Cited by 88 publications

References 13 publications

A Quantitative Analysis of Point Clouds from Automotive Lidars Exposed to Artificial Rain and Fog

A Quantitative Analysis of Point Clouds from Automotive Lidars Exposed to Artificial Rain and Fog

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

Real-Time 3D Object Detection and SLAM Fusion in a Low-Cost LiDAR Test Vehicle Setup

Contact Info

Product

Resources

About