Human Point Cloud Data Segmentation based on Normal Vector Estimation using PCA-SVD Approaches for Elderly Activity Daily Living Detection

Budiyanta, Nova Eka; Yuniarno, Eko Mulyanto; Purnomo, Mauridhi Hery

doi:10.1109/tencon54134.2021.9707317

Cited by 4 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have investigated many approaches to tackle the challenges in processing point cloud data, such as through point cloud segmentation [49] and motion detection [50]. Due to the data's dispersed nature, it requires preprocessing before the utilization in computational models.…”

Section: B Previous 3d Point Cloud Processingmentioning

confidence: 99%

“…The method described in a previous study [70] can be employed to remove flat surfaces. This method builds upon the ground plane segmentation technique [49]. The investigation entails examining numerous sources on cluster formation, such as Random Sample Consensus (RANSAC) [71] and Density-based Spatial Clustering of Applications with Noise (DBSCAN) [72].…”

Section: D To 3d Projectionmentioning

confidence: 99%

“…Subsequently, a ground plane elimination procedure was conducted to eliminate the flat surface in the image, yielding a more precise depiction of the object's relative position. The ground plane removal strategy utilized the outcomes of prior research by using the discoveries of normal vector analysis through the application of SVD on the PCA plane generated by kdTreeNN [49], [70].…”

Section: E 2d Pixel To 3d Lidar Point Cloud Object Back-projectionmentioning

confidence: 99%

See 2 more Smart Citations

Utilizing a Single-Stage 2D Detector in 3D LiDAR Point Cloud With Vertical Cylindrical Coordinate Projection for Human Identification

Eka Budiyanta,

Mulyanto Yuniarno,

Usagawa

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Exploiting sensitive human data in human visual monitoring system violates individual's privacy. Hence, this study utilized a Light Detection and Ranging (LiDAR)-generated three-dimensional (3D) point cloud instead of an RGB camera as it captures the human object without detailed imagery. Given their dispersed nature, processing 3D LiDAR point cloud is economically inefficient as it requires some preliminary actions. Alternatively, this study applied a single-stage detection process using only one data type, namely 3D LiDAR point cloud with vertical axis direct projection. This approach utilized the 3D LiDAR cylindrical coordinates features to project the data onto two-dimensional (2D) image space with various computational capabilities and back-projection algorithm to restore the identified object on the 2D plane onto 3D LiDAR point cloud coordinates. This model also implemented the YOLOv5 series due to their varied sizes. The evaluation of this approach utilized accuracy metric which was the average of mean average precision (mAP) value based on different intersections over union (IoU) thresholds. The proposed methodology effectively employed a vertical projection technique to identify human objects. Notably, this approach distinguishes itself from previous methods such as PIXOR, BirdNet, BirdNet+, BevDetNet, and Frustum-PointPillars, offering a novel perspective in the field. In addition, the best and worst performing models had the accuracy values of 44.35% and 79.83%, with inference speeds of 3.7 ms and up to 25 ms, respectively. Further, the inference speeds of all models were less than 33.33 ms. Thus, the monitored objects were identified before the LiDAR system enters the next azimuth rotation.

show abstract

Section: B Previous 3d Point Cloud Processingmentioning

confidence: 99%