International Journal on Semantic Web and Information Systems · 2022 · 52 citations · 31 references
ComputingComputer ScienceComputer VisionMachine LearningMachine Vision3D Imaging3D ReconstructionDeep LearningImage RegistrationObject RecognitionPoint Cloud Processing3D Point Cloud ProcessingCentral Limit TheoremsCustomer ExperienceData AugmentationIterative Closest PointOperational SafetyPoint Cloud Data AugmentationPoint Cloud Representation
3D sensors such as Kinect and LiDAR have spurred widespread use of 3D data in manufacturing, healthcare, and retail, yet object recognition still struggles with illumination, pose, and scale variations. The study proposes three sub‑sampling based data augmentation methods for 3D point clouds. The authors validate the augmentations by comparing ICP registration errors among sub‑samples and parents and by applying the Central Limit Theorem to confirm preserved characteristics.
Due to the availability of cheap 3D sensors such as Kinect and LiDAR, the use of 3D data in various domains such as manufacturing, healthcare, and retail to achieve operational safety, improved outcomes, and enhanced customer experience has gained momentum in recent years. In many of these domains, object recognition is being performed using 3D data against the difficulties posed by illumination, pose variation, scaling, etc present in 2D data. In this work, we propose three data augmentation techniques for 3D data in point cloud representation that use sub-sampling. We then verify that the 3D samples created through data augmentation carry the same information by comparing the Iterative Closest Point Registration Error within the sub-samples, between the sub-samples and their parent sample, between the sub-samples with different parents and the same subject, and finally, between the sub-samples of different subjects. We also verify that the augmented sub-samples have the same characteristics and features as those of the original 3D point cloud by applying the Central Limit Theorem.
31
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
3D ShapeNets: A deep representation for volumetric shapes
Zhirong Wu, Shuran Song, Aditya Khosla et al. · 2015 · 4.7K citations · Full text
Fast Point Feature Histograms (FPFH) for 3D registration
Radu Bogdan Rusu, Nico Blodow, Michael Beetz · 2009 · 3.8K citations