.png){kind=icon}
.png){kind=icon}
Return
Deep Imbalanced Multitarget Regression: 3-D Point Cloud Voxel Content Estimation in Simulated Forests
.png){kind=icon}
PRE
AI
DOI：10.1109/tgrs.2026.3713799.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Voxelization is an effective approach to reduce the computational cost of processing light detection and ranging (LiDAR) data; yet, it results in a loss of fine-scale structural information. This study explores whether low-level voxel content information, specifically target occupancy percentage within a voxel, can be inferred from high-level voxelized LiDAR point cloud data collected from Digital Imaging and Remote Sensing Image Generation (DIRSIG) software. In our study, the targets include bark, leaf, soil, and miscellaneous materials. We propose a multitarget regression approach in the context of imbalanced learning using kernel point convolutions (KPConvs). Our research leverages cost-sensitive learning to address class imbalance called density-based relevance (DBR). We employ weighted mean squared error (WMSE), focal regression (FocalR), and regularization to improve the optimization of KPConv. This study performs a sensitivity analysis on the voxel size (0.25–2 m) to evaluate the effect of various grid representations in capturing the nuances of the forest. This sensitivity analysis reveals that larger voxel sizes (e.g., 2 m) result in lower errors due to reduced variability, while smaller voxel sizes (e.g., 0.25 or 0.5 m) exhibit higher errors, particularly within the canopy, where variability is greatest. For bark and leaf targets, error values at smaller voxel size datasets (0.25 and 0.5 m) were significantly higher than those in larger voxel size datasets (2 m), highlighting the difficulty in accurately estimating within-canopy voxel content at fine resolutions. This suggests that the choice of voxel size is application-dependent. Our work fills the gap in deep imbalance learning models for multitarget regression and simulated datasets for 3-D LiDAR point clouds of forests.
Keywords:
Forest
imbalance
light detection and ranging (LiDAR)
multitarget
point cloud
regression
simulation
voxel
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W
View more organizations