This is the documentation for the latest (main) development branch of HPM SDK. If you are looking for the documentation of previous releases, use the drop-down menu on the left and select the desired version.

21.1. TensorFlowLiteMicro-PersonDetection

21.1.1. Overview

The TFLM example demos the use of a camera to capture an image, perform human detection via the integrated TFLM machine learning platform, and display the results on screen

21.1.2. Configurations

• Connect the camera device to the CAM interface on the board

• Connect LCD to the LCD interface on the board

• Click DRV-LV50A-MP1907 Motor Driver Board section and configure

21.1.3. Code Options

• Add sdk_compile_options("-mabi=ilp32f") sdk_compile_options("-march=rv32gc") set(CONFIG_HPM_MATH_NN_RVP32 1) to the project’s CMakeLists.txt to get a higher performance

Warning

Please use flash_sdram_xip option for compilation due

21.1.4. Running the example

When the example runs successfully, The LCD will display the live screen, the processed image and the recognition result, while the serial terminal will output the score of whether someone is present or not

person score:-23 no person score 23