Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Rivero, Jose Roberto Vargas; Gerbich, Thiemo; Buschardt, Boris; Chen, Jia

doi:10.3390/s21134503

Cited by 11 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The images were categorized based on the level of disease severity: normal, mild, moderate, or severe. In addition, data augmentation techniques [ 34 ] were used to generate more training data, where affine transformations, such as a random rotation of ±20 and random translation of ±5 pixels in the horizontal/vertical direction, were applied to the original dataset. These data augmentations help avoid overfitting issues while training.…”

Section: Resultsmentioning

confidence: 99%

Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images

Rhyou

Yoo

2021

Sensors

View full text Add to dashboard Cite

Diagnosing liver steatosis is an essential precaution for detecting hepatocirrhosis and liver cancer in the early stages. However, automatic diagnosis of liver steatosis from ultrasound (US) images remains challenging due to poor visual quality from various origins, such as speckle noise and blurring. In this paper, we propose a fully automated liver steatosis prediction model using three deep learning neural networks. As a result, liver steatosis can be automatically detected with high accuracy and precision. First, transfer learning is used for semantically segmenting the liver and kidney (L-K) on parasagittal US images, and then cropping the L-K area from the original US images. The second neural network also involves semantic segmentation by checking the presence of a ring that is typically located around the kidney and cropping of the L-K area from the original US images. These cropped L-K areas are inputted to the final neural network, SteatosisNet, in order to grade the severity of fatty liver disease. The experimental results demonstrate that the proposed model can predict fatty liver disease with the sensitivity of 99.78%, specificity of 100%, PPV of 100%, NPV of 99.83%, and diagnostic accuracy of 99.91%, which is comparable to the common results annotated by medical experts.

show abstract

Section: Resultsmentioning

confidence: 99%

Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images

Rhyou

Yoo

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…However, LiDAR does present certain limitations, including susceptibility to atmospheric factors like fog, rain, and sandstorms, as well as interference from dust. These conditions can scatter the laser beam and lead to power attenuation, posing challenges in obtaining precise information about the target [65]. In situations demanding swift responses, such as emergency rescue operations, adverse weather conditions may impede the effective use of LiDAR.…”

Section: Light Detection and Ranging (Lidar)mentioning

confidence: 99%

Unmanned Aerial Vehicles (UAVs) in Landslide Investigation and Monitoring: A Review

Sun,

Yuan,

Song

et al. 2024

Drones

View full text Add to dashboard Cite

Over the past decade, Unmanned Aerial Vehicles (UAVs) have emerged as essential tools for landslide studies, particularly in on-site investigations. This paper reviews UAV applications in landslide studies, with a focus on static geological characteristics, monitoring temporal and spatial dynamics, and responses post-events. We discuss the functions and limitations of various types of UAVs and sensors (RGB cameras, multi-spectral cameras, thermal IR cameras, SAR, LiDAR), outlining their roles and data processing methods in landslide applications. This review focuses on the UAVs’ roles in landslide geology surveys, emphasizing landslide mapping, modeling and characterization. For change monitoring, it provides an overview of the temporal and spatial evolution through UAV-based monitoring, shedding light on dynamic landslide processes. Moreover, this paper underscores UAVs’ crucial role in emergent response scenarios, detailing strategies and automated detection using machine learning algorithms. The discussion on challenges and opportunities highlights the need for ongoing UAV technology advancements, addressing regulatory hurdles, hover time limitations, 3D reconstruction accuracy and potential integration with technologies like UAV swarms.

show abstract

“…However, their method has a limitation: the simulation only aims to reproduce measurements in a 30 m long fog chamber. The authors in [ 30 , 31 , 32 ] created LiDAR simulators to deal with adverse weather conditions based on physical models; however, their methods are limited, in that it is impossible to cover all parametric variations in the real world, due to characteristics of the physical models.…”

Section: Related Workmentioning

confidence: 99%

GAN-Based LiDAR Translation between Sunny and Adverse Weather for Autonomous Driving and Driving Simulation

Lee

Shiotsuka

Nishimori

et al. 2022

Sensors

View full text Add to dashboard Cite

Autonomous driving requires robust and highly accurate perception technologies. Various deep learning algorithms based on only image processing satisfy this requirement, but few such algorithms are based on LiDAR. However, images are only one part of the perceptible sensors in an autonomous driving vehicle; LiDAR is also essential for the recognition of driving environments. The main reason why there exist few deep learning algorithms based on LiDAR is a lack of data. Recent translation technology using generative adversarial networks (GANs) has been proposed to deal with this problem. However, these technologies focus on only image-to-image translation, although a lack of data occurs more often with LiDAR than with images. LiDAR translation technology is required not only for data augmentation, but also for driving simulation, which allows algorithms to practice driving as if they were commanding a real vehicle, before doing so in the real world. In other words, driving simulation is a key technology for evaluating and verifying algorithms which are practically applied to vehicles. In this paper, we propose a GAN-based LiDAR translation algorithm for autonomous driving and driving simulation. It is the first LiDAR translation approach that can deal with various types of weather that are based on an empirical approach. We tested the proposed method on the JARI data set, which was collected under various adverse weather scenarios with diverse precipitation and visible distance settings. The proposed method was also applied to the real-world Spain data set. Our experimental results demonstrate that the proposed method can generate realistic LiDAR data under adverse weather conditions.

show abstract

Data Augmentation of Automotive LIDAR Point Clouds under Adverse Weather Situations

Cited by 11 publications

References 30 publications

Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images

Cascaded Deep Learning Neural Network for Automated Liver Steatosis Diagnosis Using Ultrasound Images

Unmanned Aerial Vehicles (UAVs) in Landslide Investigation and Monitoring: A Review

GAN-Based LiDAR Translation between Sunny and Adverse Weather for Autonomous Driving and Driving Simulation

Contact Info

Product

Resources

About