Lightningnet: Fast and Accurate Semantic Segmentation for Autonomous Driving Based on 3D LIDAR Point Cloud

Yang, Kaihong; Bi, Sheng; Dong, Min

doi:10.1109/icme46284.2020.9102769

Cited by 10 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the distance between two clusters of points is less than those within individual point clouds, then a distance-based algorithm can classify the point clouds. This is the basis of the Euclidean distance-based clustering algorithm [31]. We perform Euclidean clustering on downsampled point cloud data, yielding various distinct point cloud features within the scene.…”

Section: Point Cloud Global Registrationmentioning

confidence: 99%

Construction of a digital twin model for vertical storage tank deformation assessment using terrestrial laser scanning technology

Wu,

Yang,

Sun

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The foundational settlement and deformation of vertical storage tanks are crucial factors influencing their safe operation. To enable rapid deformation assessment of storage tanks, this paper combines point cloud data acquired through terrestrial laser scanning with relevant data processing algorithms to construct a digital twin (DT) model. This achieves high-precision automated detection of tank deformation, facilitating the digital transformation of deformation assessment and offering an integrated detection strategy. First, Euclidean distance clustering is applied to the point cloud, and the point density within clusters is statistically analyzed using a Gaussian distribution. This results in a collection of point clusters within one standard deviation, effectively filtering out outliers and noise points, which facilitates the rapid global registration of the point cloud. Second, in order to quickly segment tank point clouds in the scene, back propagation neural network classification learning based on principal component analysis information is used. The point cloud model is combined with the fitting information of slices to generate a DT model, whose deformation can be evaluated through comparison with appropriate storage tank specifications, taking radial deformation, tank inclination, and foundation settlement as indicators.

show abstract

Section: Point Cloud Global Registrationmentioning

confidence: 99%

Construction of a digital twin model for vertical storage tank deformation assessment using terrestrial laser scanning technology

Wu,

Yang,

Sun

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Instead of densely distributing features along the ray, they predict a categorical distribution over discrete depth bins for each pixel indicating the contribution of each feature in the intermediate 3D representation. Pseudo-LiDAR approaches such as BEV-Seg (Ng et al, 2020) predict explicit dense depth from the monocular image, which is used to establish a one-to-one correspondence between image pixels and grid cells. Simple-BEV (Harley et al, 2023) and M2BEV (Xie et al, 2022) show that, while the feature lifting problem is well-researched, a uniform lifting approach (Roddick et al, 2019) can result in competitive performance and more gain can be achieved using RADAR sensor data (Harley et al, 2023) or a larger image backbone (Xie et al, 2022).…”

Section: Learning Semantics In Bev Representationmentioning

confidence: 99%

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Frey¹,

Hoeller²,

Khattak³

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image quality due to poor lighting and motion blur, as well as limited sparse geometric information available from LiDAR sensing when driving at high speeds. In this work, we present RoadRunner, a novel framework capable of predicting terrain traversability and an elevation map directly from camera and LiDAR sensor inputs. RoadRunner enables reliable autonomous navigation, by fusing sensory information, handling of uncertainty, and generation of contextually informed predictions about the geometry and traversability of the terrain while operating at low latency. In contrast to existing methods relying on classifying handcrafted semantic classes and using heuristics to predict traversability costs, our method is trained end-to-end in a self-supervised fashion. The RoadRunner network architecture builds upon popular sensor fusion network architectures from the autonomous driving domain, which embed LiDAR and camera information into a common Bird's Eye View perspective. Training is enabled by utilizing an existing traversability estimation stack to generate training data in hindsight in a scalable manner from realworld off-road driving datasets. Furthermore, RoadRunner improves the system latency by a factor of ∼ 4, from 500 ms to 140 ms, while improving the accuracy for traversability costs and elevation map predictions. We demonstrate the effectiveness of RoadRunner in enabling safe and reliable offroad navigation at high speeds in multiple real-world driving scenarios through unstructured desert environments.

show abstract

“…including autonomous driving [319][320][321][322][323] , dietary monitoring 324,325 , magnetic resonance images [326][327][328][329][330] , medical images [331][332][333] such as prenatal ultrasound [334][335][336][337] , and satellite image translation [338][339][340][341][342] . Most DNNs for semantic segmentation are trained with images segmented by humans.…”

Section: /98mentioning

confidence: 99%

Review: Deep Learning in Electron Microscopy

Ede

2020

Preprint

View full text Add to dashboard Cite

Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.

show abstract

Lightningnet: Fast and Accurate Semantic Segmentation for Autonomous Driving Based on 3D LIDAR Point Cloud

Cited by 10 publications

References 8 publications

Construction of a digital twin model for vertical storage tank deformation assessment using terrestrial laser scanning technology

Construction of a digital twin model for vertical storage tank deformation assessment using terrestrial laser scanning technology

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Review: Deep Learning in Electron Microscopy

Contact Info

Product

Resources

About