Hy-Seg: A Hybrid Method for Ground Segmentation Using Point Clouds

Qian, Yeqiang; Wang, Xiaoliang; Chen, Ziqing; Wang, Chunxiang; Yang, Ming

doi:10.1109/tiv.2022.3187008

Cited by 14 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the high strength, corrosion resistance, weldability and high surface finishing the 5xxx series aluminium alloys are widely used as a structural material in the automotive and aerospace industries [1]. The microstructure of Al-Mg-Si cast alloys, such as AlMg5Si2Mn alloy, consist of α(Al) dendrites, primary Mg2Si particles and/or eutectic α(Al)+Mg2Si brittle Chinese script eutectic structures [2]. The sharp corner of primary Mg2Si is easier to generate stress concentration, which deeply damages the mechanical strength of the alloys and severely limit their development and applications.…”

Section: Introductionmentioning

confidence: 99%

Effect of Al10Sr and TiB on the Microstructure and Solidification Behavior of AlMg5Si2Mn Alloy

Snopiński

2021

SSP

View full text Add to dashboard Cite

In the first stage of the experiment, the effect of Al10Sr modification and Al5TiB grain refiner and interaction of both additions on the microstructure of AlMg5Si2Mn alloy and Mg2Si phase morphology was investigated. Then the influence of Al10Sr and Al5TiB addition on nucleation temperatures of various intermetallic phases formed in AlMg5Si2Mn alloy also have been interpreted by the formation of distinct peaks in the first derivative cooling curve and microstructural observations. It was found that modification has a meaningful influence on the microstructure of the investigated alloy as well as the crystallization process

show abstract

Section: Introductionmentioning

confidence: 99%

Effect of Al10Sr and TiB on the Microstructure and Solidification Behavior of AlMg5Si2Mn Alloy

Snopiński

2021

SSP

View full text Add to dashboard Cite

show abstract

“…Point cloud semantic segmentation is one of the most 209 fundamental tasks for autonomous driving [3], [15] For the range-based methods: RangeNet++ [47] proposed a 224 deep-learning-supported approach to exploit the potential of 225 range images and 2D convolutions, and a GPU-accelerated 226 post-processing K-Nearest-Neighbor (KNN) approach is fur-227 ther proposed to recover consistent semantic information dur-228 ing inference for entire LiDAR scans. KPRNet [48] improved 229 the convolutional neural network architecture for the feature 230 extraction of the range image, and the commonly used post-231 processing techniques such as KNN were replaced with KP-232 Conv [49], which is a learnable pointwise component and 233 allows for more accurate semantic class prediction.…”

mentioning

confidence: 99%

Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation

Qiu,

Chen,

Lai

et al. 2024

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Existing data augmentation approaches on LiDAR 1 point cloud are mostly developed on rigid transformation, such 2 as rotation, flipping, or copy-based and mix-based methods, 3 lacking the capability to generate diverse samples that depict 4 smooth deformations in real-world scenarios. In response, we 5 propose a novel and effective LiDAR point cloud augmentation 6 approach with smooth deformations that can enrich the diversity 7 of training data while keeping the topology of instances and 8 scenes simultaneously. The whole augmentation pipeline can 9 be separated into two different parts: scene augmentation and 10 instance augmentation. To simplify the selection of deformation 11 functions and ensure control over augmentation outcomes, we 12 propose three effective strategies: residual mapping, space decou-13 pling, and function periodization, respectively. We also propose 14 an effective prior-based location sampling algorithm to paste 15 instances on a more reasonable area in the scenes. Extensive ex-16 periments on both the SemanticKITTI and nuScenes challenging 17 datasets demonstrate the effectiveness of our proposed approach 18 across various baselines. The codes are publicly available at 19 https://github.com/skyshoumeng/SmoothDA.20

show abstract

An efficient ground segmentation approach for LiDAR point cloud utilizing adjacent grids

Dong,

Liu,

Dong

et al. 2024

Machine Vision and Applications

View full text Add to dashboard Cite

Hy-Seg: A Hybrid Method for Ground Segmentation Using Point Clouds

Cited by 14 publications

References 33 publications

Effect of Al10Sr and TiB on the Microstructure and Solidification Behavior of AlMg5Si2Mn Alloy

Effect of Al10Sr and TiB on the Microstructure and Solidification Behavior of AlMg5Si2Mn Alloy

Leveraging Smooth Deformation Augmentation for LiDAR Point Cloud Semantic Segmentation

An efficient ground segmentation approach for LiDAR point cloud utilizing adjacent grids

Contact Info

Product

Resources

About