4 papers
Through the Perspective of LiDAR: A Feature-Enriched and Uncertainty-Aware Annotation Pipeline for Terrestrial Point Cloud Segmentation
Fei Zhang, Rob Chancia, Josie Clapp +4
Accurate semantic segmentation of terrestrial laser scanning (TLS) point clouds is limited by costly manual annotation. We propose a semi-automated, uncertainty-aware pipeline that…
Deep Imbalanced Multi-Target Regression: 3D Point Cloud Voxel Content Estimation in Simulated Forests
Amirhossein Hassanzadeh, Bartosz Krawczyk, Michael Saunders +4
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 inf…
Uncertainty Quantification In Surface Landmines and UXO Classification Using MC Dropout
Sagar Lekhak, Emmett J. Ientilucci, Dimah Dera +1
Detecting surface landmines and unexploded ordnances (UXOs) using deep learning has shown promise in humanitarian demining. However, deterministic neural networks can be vulnerable…
SUPER-Net: Trustworthy Image Segmentation via Uncertainty Propagation in Encoder-Decoder Networks
Giuseppina Carannante, Nidhal C. Bouaynaya, Dimah Dera +2
Deep Learning (DL) holds great promise in reshaping the industry owing to its precision, efficiency, and objectivity. However, the brittleness of DL models to noisy and out-of-dist…