What's the best structurer/components to implement my project?

[tormentally]

I have a IOT system (described below) need to implement which requires ai model for vision.
I am thinking about using ESP32-CAM and my windows laptop as MTTQ broker.
Now can ESP32-CAM controller motors, sensors, while same time send video stream to my laptop so my laptop can do the python script for vision?

system that will determine the right height of a painting given the height of the visitor. The system will include a proximity sensor (an ITR sensor for instance) to determine the presence of a visitor, a camera, to determine the visitor's height and a controller that will activate two mini motors for controlling the height of the painting that will hang on retractable metal cords. In this case, whenever a visitor approaches the painting, the suggested by us system is designed to identify the visitor positioned in front of the artwork and measure their eye level. Subsequently, it will calculate the optimal delta value, that should be made to raise or lower the exhibit. The calculated delta value, along with the specified direction (either upward or downward), will then be transmitted to the engine to facilitate the precise repositioning of the artwork. As a result, the height of the painting will be adjusted, if needed, and returned to its initial position once the visitor moves on.

Here's the image https://prnt.sc/0RQUHB3ftfJO