© 2020 by visual globe


    The road to success is as follows - 

    Jump Start for ALL Data Discovery:

    Our team will identify and obtain current, legacy and siloed data sources as it relates to all utility poles.  Propegating this data provides a complete understanding of the various data sets in preparation for our data fusion process.  We collaborate on data mapping from structured and unstructured sources including but not limited to internal, 3rdparty and public. These efforts create a common language and holistic overview which acts as a foundation for any joint engagements related to the assets defined.




















    Phase 2

    Data Fusion: ]

    Our data fusion platform links all types of data feeds from unstructured e.g. excel spreadsheets, IOT field sensors, legacy PDFs with structured data e.g. SAP, Oracle, ERP. Thus breaking down communication barriers and bringing a common language for all orginizations to digist, Data Transparency. 














    Phase 3 Imagery

    In an effort to reduce exposure and limit the need to provide redundant perspectives related to the same asset, the collection methodology and requirements can be dictated by the state of the utility partners existing imagery.  We have developed an agnostic approach to acquire imagery from disparate sources including previously funded collection programs to capatilize on existing data prior to recreating the status quo. Imagery data can be collected using a low cost provider with limited exposre to the specifics of joint use as our Phase 4 feature extraction becomes the subject matter expert. 


    Source imagery examples:


    • Engineering As-builts

    • Permit to attach 

    • Pole Loading 

    • Joint use audits

    • Pole structure testing

    • Pole transfer/ double wood

    • Ownership descrepency


















    Phase 4

    Artificial Intelligence/Machine Learning for Automated Feature Extraction:

    Our Artificial Intelligence and Machine learning algorithms require structured data, and through this process we have written algorithms for feature extractions. Machine learning algorithms are built to “learn” to do things by understanding labeled data, then use it to produce further outputs to progressively extract higher level features from the raw input.


















    Our  learning methodology utilizes photo images collected from aerial and terrestrial imagery. Then machine learning creates a permanent library of asset attributes and establishes a set of baselines in a library for feature extraction using AI (Artificial Intelligence). 


    The unique library has the ability to transform your data and provide a baseline that can be utilized for current and future programs.  Improving the auditing process by using change detection simplifies the process and isolated the joint use challenges, compares the past to the present and reports back on where changes actually occurred.
















    The Visual Globe Value Proposition

    The value Visual Globe brings to utility companies is by fusing  multiple data sets to bridge the data communications gap and streamline the physical asset attribute collection and visibility. Because we have transcended the boundaries of siloed data communication and asset visualization by developing a platform this will connect all organizational domains with a common language.


    With our advancement in deep learning through artificial intelligence, the telcom and power industry can set a new precedence in understanding  what assets they have and compare those assets to the past all in a common language of things.


    The proposed cost for using the advanced approach portrayed above is $2.80 a pole.


    We are excited and look forward to showing you best practices and success stories form the many utility companies who have capatilized on this approach.