Machine Vision Security (MaViS) system

The Machine Vision Security (MaViS) system is a machine learning based security platform that automatically monitors and detects people in a scene, and then alerts the user in real time by sending an image and video to their email. The system is enabled through a combination of edge computing and cloud infrastructure. The edge platform used was the Nvidia Jetson Nano 4GB Developer Kit, and the cloud infrastructure was built using Amazon Web Services (AWS).

MaViS was build using JetPack 4.5.1 and DeepStream SDK 5.1.

For further details, please see the following:


Hello Friend

I am interested in knowing how do you capture a single image /frame of the person(intruder) from the video stream which has many frames

I want to use Deepstream-app for this but I am told it may not be possible to do this with Deepstream app

Right now my implementation saves any frame with a positive detection.

You can do a search for folder_name in to see how and when I write to the output folder.

I hope this helps.

1 Like

Hi Friend, can you tell me if it is possible to store data about last seen, first seen and also video images into a file (dat file, csv file…) that can be uploaded to postgres so that it can be called out when the client request for it, and how to do it, i’m having some trouble with this, can you help me, thank you and have a good day heal.