This column in Cloud Continuum is titled “Frontiers in Software, Architecture, and Standards” or “Frontiers” for short. It will cover emerging design and implementation patterns being used to lay the software, architecture, and standards groundwork for new functional capabilities in the cloud-to-edge continuum. In it, we'll use articles, interviews, and contributions from leading proponents for new cloud tools to explain how they are being developed and designed to work together and the capabilities they provide. Wherever possible, we'll focus on areas that include opportunities for open source development and community involvement in carrying out these advances.

Video analytics frameworks often rely on Neural Networks to perform their tasks. For example, a “You Only Look Once” object detection algorithm applies a single neural network to each image, divides the image into regions, and predicts bounding boxes (weighted by the predicted probabilities) with probabilities for each region. Those algorithms often run more efficiently on hardware accelerators. Libraries which use CUDA enabled GPUs can achieve tremendous advances in speed for those functionalities. Frequently, video analytic researchers develop large solutions to allow them to solve problems with complex setup procedures for other researchers to be able to duplicate their efforts. Here we present a software solution that can be run on multiple computer environments without having to customize systems and software, and support the measurement of the performance of machine learning algorithms on disparate datasets. In this publication, we introduce a common base container that provides GPU-optimized access to common Computer Vision (CV) and Machine Learning (ML) libraries, and can be used as the building container (think Docker FROM) for complex analytics to be interactively designed and tested, and as the base for Docker container images that can be shared between analytics researchers.

Due to its availability, cloud computing is the de facto platform of choice for Big Data, where Big Data as a Service is believed to be the next best thing. In this chapter we will first introduce cloud computing, defining the advantages it provides in a Big Data context. Similarly, we will then establish the benefits of using private clouds, before focusing on selected open source cloud environments, studying their architecture. We will constrain our scope to some of the most prominent ones, in particular in view of Big Data processing. We will then establish how some Big Data applications can greatly benefit from the use of accelerators, and how those accelerators can be integrated with private clouds. Finally, we will present a case study, using an On-Premise Private Cloud, to demonstrate the implementation of one such environment.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. TRECVID 2017: Evaluating Ad-hoc and Instance Video Search, Events Detection, Video Captioning, and Hyperlinking George Awad, Asad Butt, Jonathan Fiscus, David Joy, Andrew Delgado, Willie Mcclinton, Martial Michel, Alan Smeaton, Yvette Graham, Wessel Kraaij, et al.

This article examines foundational issues in data science including current challenges, basic research questions, and expected advances, as the basis for a new data science research program (DSRP) and associated data science evaluation (DSE) series, introduced by the National Institute of Standards and Technology (NIST) in the fall of 2015. The DSRP is designed to facilitate and accelerate research progress in the field of data science and consists of four components: evaluation and metrology, standards, compute infrastructure, and community outreach. A key part of the evaluation and measurement component is the DSE. The DSE series aims to address logistical and evaluation design challenges while providing rigorous measurement methods and an emphasis on generalizability rather than domain- and application-specific approaches. Toward that end, each year the DSE will consist of multiple research tracks and will encourage the application of tasks that span these tracks. The evaluations are intended to facilitate research efforts and collaboration, leverage shared infrastructure, and effectively address crosscutting challenges faced by diverse data science communities. Multiple research tracks will be championed by members of the data science community with the goal of enabling rigorous comparison of approaches through common tasks, datasets, metrics, and shared research challenges. The tracks will permit us to measure several different data science technologies in a wide range of fields and will address computing infrastructure, standards for an interoperability framework, and domain-specific examples. This article also summarizes lessons learned from the data science evaluation series pre-pilot that was held in fall of 2015.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. TRECVID 2016: Evaluating Video Search, Video Event Detection, Localization, and Hyperlinking George Awad, Jonathan Fiscus, David Joy, Martial Michel, Alan Smeaton, Wessel Kraaij, Maria Eskevich, Robin Aly, Roeland Ordelman, Marc Ritter, et al.

We examine foundational issues in data science including current challenges, basic research questions, and expected advances, as the basis for a new Data Science Initiative and evaluation series, introduced by the National Institute of Standards and Technology (NIST) in the fall of 2015. The evaluations will facilitate research efforts, collaboration, leverage shared infrastructure, and effectively address cross-cutting challenges faced by diverse data science communities. The evaluations will have multiple research tracks championed by members of the data science community, and will enable rigorous comparison of approaches through common tasks, datasets, metrics, and shared research challenges. The tracks will measure several different data science technologies in a wide range of fields, starting with a pre-pilot. In addition to developing data science evaluation methods and metrics, it will address computing infrastructure, standards for an interoperability framework, and domain-specific examples.

We examine foundational issues in data science including current challenges, basic research questions, and expected advances, as the basis for a new Data Science Research Program and evaluation series, introduced by the Information Access Division (IAD) of the National Institute of Standards and Technology (NIST) in the fall of 2015. The evaluations will facilitate research efforts, collaboration, leverage shared infrastructure, and effectively address cross-cutting challenges faced by diverse data science communities. The evaluations will have multiple research tracks championed by members of the data science community, and will enable rigorous comparison of approaches through common tasks, datasets, metrics, and shared research challenges. The tracks will measure several different data science technologies in a wide range of fields, starting with a pre-pilot. In addition to developing data science evaluation methods and metrics, it will address computing infrastructure, standards for an interoperability framework, and domain-specific examples.

Reconstructing three dimensional (3D) crime scenes is an important aspect of forensic investigation. With installations of large-scale camera networks, multiple videos of a crime may be collected. Video analytics technologies are helpful for data reduction, identifying which video sources have the most useful forensic data for a crime, and generating an understanding of the scene by piecing together video and imagery from many different cameras. It is especially crucial to accurately localize and track the positions of people and objects in the physical world across all videos collected. We present accurate camera calibration techniques and proposed a 3D ground-truth annotation system. Given the single view or multi-view of videos with camera calibration parameters, the system projects the locations of objects from cameras into the 3D physical world. We perform multiple experiments using our methods. They show that the prototype system provides localization and tracking results with high accuracy. A 3D groundtruth annotation system can be used for 3D crime scene reconstruction, cross camera tracking etc. Forensic scientists can reconstruct the crime scene and analyze line of sight, bullet trajectories (with other techniques), provide a 3D virtual tour to verify witness testimony or evaluate hypotheses, and provide 2D and 3D evidence for courtroom presentation. Presenter: John Garofolo Information Access Division Information Technology Laboratory Tel.: 301 975 3193 Email: john.garofolo@nist.gov

The TREC Video Retrieval Evaluation (TRECVID) 2011 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in content-based exploitation of digital video via open, metrics-based evaluation. Over the last ten years this effort has yielded a better understanding of how systems can effectively accomplish such processing and how one can reliably benchmark their performance. TRECVID is funded by the National Institute of Standards and Technology (NIST) and other US government agencies. Many organizations and individuals worldwide contribute significant time and effort

The main goal of the TREC Video Retrieval Evaluation (TRECVID) is to promote progress in content-based analysis of and retrieval from digital video via open, metrics-based evaluation. TRECVID is a laboratory-style evaluation that attempts to model real world situations or significant component tasks involved in such situations. Six tasks were proposed in 2011: Semantic indexing (SIN), Known-item search (KIS), Content-based copy detection (CCD), Surveillance event detection (SED), Instance search (pilot) (INS) and Multimedia event detection (MED). 60 teams from various research organizations -- 25 from Asia, 18 from Europe, 12 from North America, 2 from South America, and 3 from Australia -- completed one or more of six proposed tasks. Further details about each particular group's approach and performance for each task can be found in that group's paper in the TRECVID publications webpage: http://www-nlpir.nist.gov/projects/tv2011/tv2011.html.

The TREC Video Retrieval Evaluation (TRECVID) 2012 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in content-based exploitation of digital video via open, metrics-based evaluation. Over the last ten years this effort has yielded a better understanding of how systems can effectively accomplish such processing and how one can reliably benchmark their performance. TRECVID is funded by the NIST and other US government agencies. Many organizations and individuals worldwide contribute significant time and effort.