Performance Evaluation of Parallel Structure from Motion (SfM) Processing with Public Cloud Computing and an On-Premise Cluster System for UAS Images in Agriculture

Abstract

Thanks to sensor developments, unmanned aircraft systems (UASs) are now among the most promising modern technologies used to collect imagery datasets that can be utilized to develop agricultural applications. These datasets can grow exponentially due to the ultrafine spatial and high temporal resolution capabilities of UAS data. One of the main obstacles to processing UAS data is the intensive computational resource requirements. The structure from motion (SfM) is the most popular algorithm used to generate 3D point clouds, orthomosaic images and digital elevation models (DEMs) in agricultural applications. Recently, the SfM algorithm has been implemented in parallel to process big UAS data quicker for certain applications. This study evalu-ated the performance of parallel SfM processing on public cloud computing and on-premise cluster systems. The UAS datasets collected over cropping fields were used for evaluation. We used multiple computing nodes and centralized network storage with different network environments for the SfM workflow. In single-node processing, an instance with the most computing power in the cloud computing system performed approximately 20 and 35 percent faster than in the single-node processing with the most computing power in the on-premises cluster. The parallel processing results showed that the cloud-based system performed better in scalability in terms of speed-up and efficiency metrics, although the absolute processing time was faster in the on-premise cluster. The experimental results also showed that the public cloud computing system might be a good alternative computing environment in UAS data processing for agricultural applications.


Thanks to sensor developments, unmanned aircraft systems (UASs) are now among the most promising modern technologies used to collect imagery datasets that can be utilized to develop agricultural applications. These datasets can grow exponentially due to the ultrafine spatial and high temporal resolution capabilities of UAS data. One of the main obstacles to processing UAS data is the intensive computational resource requirements. The structure from motion (SfM) is the most popular algorithm used to generate 3D point clouds, orthomosaic images and digital elevation models (DEMs) in agricultural applications. Recently, the SfM algorithm has been implemented in parallel to process big UAS data quicker for certain applications. This study evalu-ated the performance of parallel SfM processing on public cloud computing and on-premise cluster systems. The UAS datasets collected over cropping fields were used for evaluation. We used multiple computing nodes and centralized network storage with different network environments for the SfM workflow. In single-node processing, an instance with the most computing power in the cloud computing system performed approximately 20 and 35 percent faster than in the single-node processing with the most computing power in the on-premises cluster. The parallel processing results showed that the cloud-based system performed better in scalability in terms of speed-up and efficiency metrics, although the absolute processing time was faster in the on-premise cluster. The experimental results also showed that the public cloud computing system might be a good alternative computing environment in UAS data processing for agricultural applications.

Description

Keywords

uas, structure from motion (sfm), cloud computing, uas, structure from motion (sfm), cloud computing

Sponsorship

Rights:

Attribution 4.0 International, Attribution 4.0 International

Citation

Chang, A.; Jung, J.; Landivar, J.; Landivar, J.; Barker, B.; Ghosh, R. Performance Evaluation of Parallel Structure from Motion (SfM) Processing with Public Cloud Computing and an On-Premise Cluster System for UAS Images in Agriculture. ISPRS Int. J. Geo-Inf. 2021, 10, 677. https://doi.org/10.3390/ijgi10100677
Chang, A.; Jung, J.; Landivar, J.; Landivar, J.; Barker, B.; Ghosh, R. Performance Evaluation of Parallel Structure from Motion (SfM) Processing with Public Cloud Computing and an On-Premise Cluster System for UAS Images in Agriculture. ISPRS Int. J. Geo-Inf. 2021, 10, 677. https://doi.org/10.3390/ijgi10100677