In this video, I show how I made an esp32 stereo camera, which can be used for object detection and distance estimation, with quite good results. The camera consists of two esp32-cams, a perf board, some female header pins, some wires, a battery shield (with 5v output and charger) and a battery. The camera streams into a python notebook, and uses the mask-rcnn model from the pytorch library for segmentation of left and right images. Then it matches the objects from the left image to the objects from the right image and does distance estimation.

GitHub code:
https://github.com/jonathanrandall/esp32_stereo_camera

Artificial Intelligence graduate certificate that I am doing:
https://www.latrobe.edu.au/courses/graduate-certificate-in-artificial-intelligence

And graduate diploma:
https://www.latrobe.edu.au/courses/graduate-diploma-in-artificial-intelligence

Daniel Rossi’s ESP32-CAM Python stream OpenCV project:
https://www.hackster.io/onedeadmatch/esp32-cam-python-stream-opencv-example-1cc205

Battery Shield
https://www.aliexpress.com/item/32870411748.html

source