Efficient feature extraction from wide-area motion imagery by MapReduce in Hadoop

Abstract

Wide-Area Motion Imagery (WAMI) feature extraction is important for applications such as target tracking, traffic management and accident discovery. With the increasing amount of WAMI collections and feature extraction from the data, a scalable framework is needed to handle the large amount of information. Cloud computing is one of the approaches recently applied in large scale or big data. In this paper, MapReduce in Hadoop is investigated for large scale feature extraction tasks for WAMI. Specifically, a large dataset of WAMI images is divided into several splits. Each split has a small subset of WAMI images. The feature extractions of WAMI images in each split are distributed to slave nodes in the Hadoop system. Feature extraction of each image is performed individually in the assigned slave node. Finally, the feature extraction results are sent to the Hadoop File System (HDFS) to aggregate the feature information over the collected imagery. Experiments of feature extraction with and without MapReduce are conducted to illustrate the effectiveness of our proposed Cloud-Enabled WAMI Exploitation (CAWE) approach.

Evaluation of Open-Source Tools for Big Data Processing

“…There exist a lot of big data analytics open-source tools to process and analyse huge data and some of which are here discussed with some techniques for analysing big data with emphasis on three emerging open-source tools namely: Hadoop, Spark, and Presto (Chenga, 2015). Majority of these tools focuses on batch and stream processing, as well as interactive analysis as most of these tools are built on Apache Hadoop.…”

A container-based elastic cloud architecture for real-time full-motion video (FMV) target tracking

“…However, capacity overhead and actuation delays in virtualization layers occur due to dynamic resource reallocation/rescheduling. These weaknesses make hypervisor-based virtualization technology unable to meet requirements of real-time performance and elastic, high efficient resource utility, which are essential to dynamic resource management (DRM) [6]. In this work, we propose an elastic information fusion cloud that is built on the container-based virtualization technology, which possesses multiple user favorable features including near-native performance, resource provisioning to live virtual environments (VEs), and execution flexibility to compensate for uneven job parallelism.…”