Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Computer Vision for Public Transportation - Phase 2
Overview Architecture concepts Solution architecture Validation Sizing the solution
Sizing the solution
Overview
Depot sizes
Sizing guidelines
Sizing example
Scaling guidelines
Depot scaling 5G scaling Data center scaling
Conclusions References

Overview

Home > Workload Solutions > Computer Vision > Guides > Computer Vision for Public Transportation - Phase 2 > Overview

Overview

  • There are a whole number of factors that can influence the sizing of a solution for transportation. Some of these factors are:

    Table 2. Sizing factors
    Factor Reason
    The number of cameras per bus Each camera needs storage on the bus and in the depot
    What quality of video is running on the bus High quality consumes more space
    What bandwidth has been secured for private 5G communications Defines how many concurrent offloads can happen
    The number of buses that use a depot Consumes 5G bandwidth and Depot storage
    What sort of retention period is there for bus video Defines the data center storage requirements

    We looked to answer some of these questions to help with building an example of sizing a system and here are the results:

    • Buses are looking to run up analytics on up to 9 cameras at once
    • Typical quality would be 1080 with 15-20 FPS. The output would be less than 2 Mb/s
    • The Bandwidth used in our test lab was 1Gb/s (1024 Mb/s) transfer rate
    • The number of buses per depot can vary see below
    • We can assume30 days as a minimum value for retention but much longer can be the case in different geographic locations