English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Due to the rapid development of remote sensing (RS) technology in recent years, high-quality images shot by Unmanned Aerial Vehicle (UAV) have become so widespread in the usage of environmental observation and record. Then further RS image processing works can be done by standalone software, ex. ENVI, but there are two bottlenecks in processing a large amount of RS images: limitation of computation and capacity of storage. Therefore, researchers have developed many kinds of variants in parallel algorithms, and most of them are implemented by using MPI or MapReduce. In this paper, we propose and implement a framework of novel K-means algorithm based on MapReduce architectures. The observer on the ground can lay their finger to decide central points (centroids) of real-time images shot by UAV in person by tablet computer. The clustered result is completed by our proposed cloud computing environment and appeared by color blocks in front of tablet computer within the acceptable time. From our experiment, human intervention (man-made centroid) can get faster convergence better than random centroid selection. Finally, this service can be used in our UAV business and become software of a service (SaaS) in hadoop environment.

The Framework of Novel k-means Embedded Cloud Computing Platform for Real-time Unmanned Aerial Vehicle (UAV) Remote Sensing Images Processing