Skip to content
Computer Vision & AI

ESP-WHO

Computer vision and image recognition framework designed for ESP32-S3 and ESP32-CAM devices.

Language
C / C++
ESP Image Processing & Vision Framework
Category
Computer Vision & AI
Main purpose
Face detection, face recognition, human presence and cat/dog detection on microcontrollers

Key features

  • Optimized neural networks for Xtensa LX7 and vector instructions
  • Face detection and recognition pipelines
  • Support for DVP and MIPI-CSI camera sensors (OV2640, OV3660, OV5640)
  • Works with PSRAM for image buffering and tensor storage
  • Real-time processing directly on device

When to use

  • Smart video doorbells and access control
  • Human presence detection for energy saving
  • Edge camera monitoring systems
  • Vision-guided robotics

Code example

Starter snippet in C / C++. Adjust pins and configuration for your board.

ESP-WHOC / C++
1