This video demonstrates an example of face detection using the ESP32-S3-EYE board, where the AI model is embedded within the device or runs independently (without interaction with a server processing the model). Here, we use the ESP-DL Standard model format. This format is similar to ONNX but uses FlatBuffers instead of Protobuf, making it more lightweight and supporting zero-copy deserialization, with a file extension of .espdl. If you need other object detection capabilities using specialized devices without an Internet connection, we can provide the solutions, please contact us.
