A Lightweight 3D Convolutional Network for
Hyperspectral–LiDAR Patch Classification

A Lightweight 3D Convolutional Network for
Hyperspectral–LiDAR Patch Classification

imagery, LiDAR, 3D-CNN, data
fusion, patch classification, class imbalance, remote sensing

We propose a simple yet effective threedimensional convolutional neural network (3D-CNN) for urban
land-cover classification using co-registered hyperspectral
imagery (HSI) and LiDAR data. The network treats the entire
spectral-LiDAR stack as a three-dimensional volume and uses a
series of 3×3×3 convolutions to capture both spectral and spatial
context simultaneously. LiDAR elevation data is added as an
extra channel in the input. During preprocessing, each
hyperspectral band and LiDAR DSM are normalized to zero
mean and unit variance. Training uses small local patches (P×P)
centered on labeled pixels, with random flips and 90-degree
rotations, called dihedral augmentation, applied across all
channels. To address class imbalance, inverse-frequency class
weighting and label smoothing are included in the cross-entropy
loss. Evaluation on the Houston2013 dataset shows that the
model achieves high accuracy, a single model reaches an Overall
Accuracy (OA) of about 0.90 and an Average Accuracy (AA) of
about 0.92 over five runs. An ensemble of five runs improves
these results to OA ≈ 0.912, AA ≈ 0.928, and a kappa coefficient
(κ) of approximately 0.904. Classes with distinctive spectral and
spatial signatures, like water, synthetic grass, and tennis courts,
reach nearly 100% recall. Meanwhile, classes with similar
appearances, such as highway and road, show higher confusion,
with highway recall around 46.9%. These results confirm that
combining spectral and three-dimensional structural information
significantly enhances accuracy in urban classification

Junhua Ku

https://ijcit.com/index.php/ijcit/article/view/538

Qiongtai Normal University, Haikou, China

september 2025

Fajar bagus W

PDF

English

Text