VXG makes video analytics cost-effective, scalable, and flexible. Cloud VMS provides a variety of pre-processing functions and interfaces an interface for integration with outside AI and making AI processing cost efficient.
Filtering and sampling
The operations are performed in 3 steps:
Filtering based on camera events (motion, etc.).
Sampling and preparation of data in the most efficient format.
Interfacing with AI.
...
As the result of the first two steps, VXG significantly reduces the load on AI engines and the bandwidth, making AI operations cost-efficient.
Processing modes
VXG extracts data and makes it available in the following formats:
Timer-based images.
Event-based images.
Continuous video.
Event-based video.
Supported AI services
As the last step, VXG interfaces the data with AI engines. VXG is integrated with a variety of AI engines includingengines.
To make the AI operations cost-efficient, VXG will first filter video by events, such as motion detection. Then sample data - extract short clips and images and then send this to AI engines. This will result in the processing of a fraction of data compared to the input streams.
You can connect the same camera to multiple AI engines, or switch between different AI engines based on certain conditions. This provides unmatched flexibility to video analytics.
Event filtering and data sampling are key operations for Cloud video analytics, they make Cloud AI scalable and cost-efficient.
...
Filtering
Event filtering is usually done by motion events generated on a camera. It can also be any type of event produced by a camera, external sensor, or software service. VXG Cloud VMS can process millions of events simultaneously and filter data based on selected criteria per camera.
Sampling
Sampling is a process of extracting video fragments and/or images from videos that contain the most significant information. VXG Cloud VMS can extract images and clips from 100s of thousands of cameras simultaneously.
Data flow
After video from a camera was filtered by events and then sampled (extracted images or short clips) we’ll get a small fraction of data that will be processed by a Cloud AI.
As a rule, Cloud AI engines only charge for actually processed data. If after filtering and sampling, we’ll get 10 images in a day, we’ll only pay for the processing of these 10 images.
For example, when we need to detect a person in a front yard, we’ll first filter video by motion, then from each video duration with motion we’ll extract several images and send these images to Cloud AI for object detection. If Cloud AI returned “human” as one of the objects then we’ll trigger an alarm.
Cloud AI services
VXG is pre-integrated with the following AI engines:
Amazon Rekognition
Google Vision AI
Azure Cognitive Services
YOLO (hosted by VXG)
The 3-step approach results in huge cost and bandwidth savings.
...
open source)
Cloud VMS comes with an API for integration with new AI services.
Features of Cloud AI services
For the full list of AI features please visit the corresponding AI services websites:
...