Alef Stream Processing & Smart Surveillance

Learn how Alef Stream Processing & Smart Surveillance can impact your video uploads.

Reference Documentation

Brochures

Why Alef Stream Processing & Smart Surveillance?

The Smart Surveillance and Stream Processing Industry is exploding.  The ability to process disparate video streams from IoT devices, video surveillance cameras, cameras on machinery etc. to create actionable insights in real-time has created new possibilities for the market. The devices used for the generation of video streams for Smart Surveillance and other Stream Processing use cases are generally regular IP cameras that are continuously generating video streams. Consumer demands are not as stringent as Enterprises demands, therefore, the market needs solutions to meet Enterprise requirements for real-time stream processing.

The Alef Smart Surveillance and Stream Processing solution creates real-time actionable insights based on video uploads while keeping data secure. The solution enables Enterprises to send their video streams to an Edge compute platform with Alef’s Stream Processing engine situated at a Micro Edge location to create actionable decisions.

The solution can be leveraged to identify defective products in an assembly line of a manufacturing plant with a camera recording the assembly line and sending video to a Stream Processing platform for real time processing. The video is uploaded to the Edge for processing.  Using AI the defective product can be identified in real-time, and the assembly line can be altered or the defective product pulled out of the manufacturing process altogether.

What is Alef Stream Processing & Smart Surveillance?

Alef’s Stream Processing platform has applications in Industrial IoT and video surveillance. An example is in the Oil/Gas industry. At present the Oil/Gas industry captures video from multiple oil wells every day and uploads this data to a server that is part of a cloud infrastructure. The video stream is then analyzed using an object detection algorithm and its statistics and critical information are generated. This process is time consuming and costly as the oil well has to upload videos streams of massive size, typically in the terabytes, daily.

With Alef’s Stream Processing solution running on the Edge on Alef’s Software-Defined Mobile Edge (SD-ME) platform, industries do not need to stream their videos onto cloud servers anymore. Video streams will instead be brought to the Edge and processing is completed directly on Alef’s local Edge server running its entire software stack. Alef applies object detection algorithms (e.g. Tensorflow AI from Google) on video streams and generates key insights from it. Alef sends all insights in the form of metadata to a central dashboard server. Customers have access to these insights via a dashboard.

Alef’s Stream Processing solution also provides an audit feature for the verification of insights generated from the AI engine. Alef stores video files of 1 minute in duration each. These video files can be used for verification of insights generated, should the need arise.

The main components of Alef’s Stream Processing solution are:

  1. Cloud Dashboard Components – These components are deployed on an EC2 instance in AWS.
  2. Upload API – Upload API’s is a node server that exposes APIs to store stream insight data and to retrieve them as well.
  3. Dashboard API – This component is used for the show insights feature, directly through a web browser.
  4. SD-ME Components – All the services listed below are part of the SD-ME framework at an Edge location and are containerized.
  5. Node Media Server – The Node Media server accepts the video streams. It is used for publishing live streams. It takes input from an incoming stream and publishes it on live stream.
  6. Detection Server – Alef currently uses the Tensorflow Object detection algorithm for real time object detection. Tensorflow Object detection API is an open source framework built on top of Tensorflow that makes it easy to construct, train and deploy object detection models. It also provides a collection of detection models which are pre-trained on different datasets. The Tensorflow API’s object detection component loads frame-by-frame live streaming data to generate insights. These insights/stats are sent to the cloud API server.
  7. Audit Server – The audit server is used to ensure accuracy of the generated stats. This module uses FFmpeg to store streaming data in 60-second MP4 files. An audit server starts capturing streaming data as soon as live streaming starts. It will capture videos of 1-minute duration until streaming stops. Audit data will currently be available until the next live streaming begins. After the start of new live streaming, it will override audit data of a previous stream with the latest one.

Benefits of Alef Stream Processing & Smart Surveillance

Alef Smart Surveillance and Stream Processing is an easy solution to deploy that will create an open environment for an Enterprise to securely process video uploads and use Alef’s Stream Processing platform to obtain real-time actionable insights. By using Alef’s open and modular APIs bundled together as Alef Smart Surveillance and Stream Processing, an Enterprise enhances and extends its application capabilities

By connecting cameras already in place within the Enterprise and any new cameras that are implemented to Alef’s SD-ME platform, the cameras gain a processing and compute environment in close proximity to the camera. The Edge enables the streams to be processed and intelligence gathered from the AI algorithms running on the SD-ME platform. The insights can range from a security threat within the Enterprise, security authentication to a building or to different locations, ensuring quality control of products and goods being produced, etc. The possibilities are endless when an Enterprise can securely create real-time actionable insights within its premises (See Alef AdVision as a reference on secure, real-time actionable insights that can be leveraged to play a targeted ad with low latency from the Edge). Video streams processed at the SD-ME location stay secure within the Edge network thanks to Alef’s stringent Edge security protocols and threat-based models implemented.

Scroll back up for downloads and more information.

Dr Ganesh Sundaram wins Biggest Individual Contribution to Edge Computing Development

This award recognizes the Edge Computing Ambassadors, those individuals who are instrumental in driving edge computing development and who have been particularly active over the last 12 months in ensuring the continued progression of edge computing research, development and trials.