Abstract
Herein, on the basis of a distributed AI cluster, a real-time video analysis system is proposed for edge computing. With ARM cluster server as the hardware platform, a distributed software platform is constructed. The system is characterized by flexible expansion, flexible deployment, data security, and network bandwidth efficiency, which makes it suited to edge computing scenarios. According to the measurement data, the system is effective in increasing the speed of AI calculation by over 20 times in comparison with the embedded single board and achieving the calculation effect that matches GPU. Therefore, it is considered suited to the application in heavy computing power such as real-time AI computing.
Highlights
According to an analysis of the annual shipments of surveillance cameras over the last 15 years, IHS Markit | Technology projects that there have been 770 million cameras put in service globally by the end of 2019
With multiple arm nodes applied in parallel processing, a real-time AI computing task is split into multiple single-frame image computing tasks
The definition of a task is as follows: a specified video stream is pulled and motion is monitored on the video stream, while the video frame is extracted for AI computing in case that a change is detected
Summary
According to an analysis of the annual shipments of surveillance cameras over the last 15 years, IHS Markit | Technology projects that there have been 770 million cameras put in service globally by the end of 2019. AI chips based on the ARM architecture have attracted increasing attention Such modules as CPU, GPU, ISP, and AI acceleration engine can be integrated by these purpose-built processors for AI computing. For mitigating the loss of bandwidth resource and ensuring data security, it is essential to deploy AI computing services at the edge, and diversified scenario puts forward higher requirements on the computing power performance of the device. In order to apply various AI algorithms such as pedestrian detection, obstacle detection, sign detection, and vehicle trajectory tracking, the use of distributed embedded AI cluster is proposed in this paper to connect the video stream of the existing surveillance cameras of the bridge. Edge computing contributes to the capability of processing data at the bottom and highly scalable distributed capabilities, while central computing leads to a sensible application architecture based on the business layer. Is the underlying computing and application system with "strongly distributed and loosely coupled" aligned with the developmental trend of information technology, it satisfies the demands for dynamic upgrades in future applications
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
