Enhancing Building Point Cloud Reconstruction from RGB UAV Data with Machine-Learning-Based Image Translation.

The performance of three-dimensional (3D) point cloud reconstruction is affected by dynamic features such as vegetation. Vegetation can be detected by near-infrared (NIR)-based indices; however, the sensors providing multispectral data are resource intensive. To address this issue, this study proposes a two-stage framework to firstly improve the performance of the 3D point cloud generation of buildings with a two-view SfM algorithm, and secondly, reduce noise caused by vegetation.

Improving GIS-based Landslide Susceptibility Assessments with Multi-temporal Remote Sensing and Machine Learning.

This study developed a systematic approach with machine learning (ML) to apply the satellite remote sensing images, geographic information system (GIS) datasets, and spatial analysis for multi-temporal and event-based landslide susceptibility assessments at a regional scale. Random forests (RF) algorithm, one of the ML-based methods, was selected to construct the landslide susceptibility models. Different ratios of landslide and non-landslide samples were considered in the experiments.

A Novel Approach to Relative Radiometric Calibration on Spatial and Temporal Variations for FORMOSAT-5 RSI Imagery.

Unlabelled: Radiometric calibration for imaging sensors is a crucial procedure to ensure imagery quality. One of the challenges in relative radiometric calibration is to correct detector-level artifacts due to the fluctuation in discrepant responses (spatial) and electronic instability (temporal). In this paper, the integration of the empirical mode decomposition (EMD) with Hilbert⁻Huang transform (HHT) in relative radiometric calibration was explored for a new sensor, FS-5 RSI (remote sensing instrument onboard the FORMOSAT-5 satellite).

Vanishing Point Extraction and Refinement for Robust Camera Calibration.

This paper describes a flexible camera calibration method using refined vanishing points without prior information. Vanishing points are estimated from human-made features like parallel lines and repeated patterns. With the vanishing points extracted from the three mutually orthogonal directions, the interior and exterior orientation parameters can be further calculated using collinearity condition equations.

A reduced-complexity data-fusion algorithm using belief propagation for location tracking in heterogeneous observations.

This paper presents a low-complexity and high-accuracy algorithm to reduce the computational load of the traditional data-fusion algorithm with heterogeneous observations for location tracking. For the location-estimation technique with the data fusion of radio-based ranging measurement and speed-based sensing measurement, the proposed tracking scheme, based on the Bayesian filtering concept, is handled by a state space model. The location tracking problem is divided into many mutual-interaction local constraints with the inherent message- passing features of factor graphs.