AWS Rekognition/General Questions

Hoping someone can help me out, have a couple of questions.

First, I have been using Node-RED as a "middleware" solution to integrate several different system into a video management system that offers a ton of API/SDK tools and docs. I have all sorts of stuff working that I never thought possible....just can't wrap my head around this.....
So I can request virtually any format of video stream or thumbnail from my VMS.....I have several video and audio analytics running that when triggered can push these streams or images into an "HTTP in" node, I've also just sent a HTTP message into Node.RED that pushes an API out requesting whatever I need from the VMS......I have recently setup an AWS account and have been playing around, got Node.RED running on EC2 and used the Rekognition demo.....what I would like to do is take my video stream or thumbnails and push them up to AWS for Rekognition......I have installed the AWS Rekognition node but it offers little to know documentation. How would I go about receiving the stream/image in Node.RED and pushing it up for Rekognition? My VMS has a SDK example that aids in building a plugin, this plugin will allow me to take these responses and create searchable events....I can also utilize the bounding boxes......any guidance, tips or tricks anyone may have to offer would be beyond appreciated.

While i'm at it have 1 more thing absolutely driving me nuts...... Using the Alexa-remote2 node I am controlling all sorts of devices, mainly lighting.....I have created a pretty decent dashboard to control the lights, on/off buttons, brightness sliders and color pickers......what would be the best means of keeping the sliders and on/off buttons updated in the event another device or system changes these settings? I know I can have an inject node constantly checking status but kinda confused since Alexa is handling the direct connection....THANK YOU!!

I did use Rekognition earlier and it was working fine & fast. However, back then I wrote a python script that took the images and pushed them to AWS from my video system

Since then I have skipped that. Benefit is also that you do not provide images to AWS. Instead I do local analysis using YOLO V3 full version. It is to my opinion very reliable but it depends I guess on what objects you target to detect. And it is good enough if you are checking individual images and have a reasonable powerful computer (I run it on an older good-enough laptop). But if you are looking for real time video streaming, I think you have to look for computers utilizing GPU's like Jetson Nano and it's inference engine or other usb stick based devices

If you just have the need to analyze images on certain (intrusion etc etc) events, you should certainly read this topic Object Detection using node-red-contrib-tfjs-coco-ssd

1 Like

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.