History

chunyexixiaoyu bea5eda2e0 APP_Framework/Applications:update face detect and instrusion detect ,the version had been tested for long time,and its's stable. At the same time,rt-thread and kendryte-sdk-source both sub module must be updated.		2021-10-14 14:15:09 +08:00
..
Kconfig	APP_Framework/lib/:add cJSON library	2021-08-04 16:26:37 +08:00
README.md	docs(knowing app): add README for face detect	2021-08-13 14:42:18 +08:00
SConscript	APP_Framework/Applications/:add face detect application	2021-07-21 16:39:36 +08:00
detect.json	fix(knowing apps): adapting new cjson lib usage and some little bug fix	2021-08-05 15:05:36 +08:00
detect.kmodel	feat(knowing app): update json config and upload model for 3 k210 apps	2021-08-13 14:42:18 +08:00
face_detect.c	APP_Framework/Applications:update face detect and instrusion detect ,the version had been tested for long time,and its's stable.	2021-10-14 14:15:09 +08:00

README.md

Face detection demo

A face object detection task demo. Running MobileNet-yolo on K210-based edge devices.

Training

kmodel from GitHub.

Deployment

compile and burn

Use (scons --)menuconfig in bsp folder (Ubiquitous/RT_Thread/bsp/k210), open:

More Drivers --> ov2640 driver
Board Drivers Config --> Enable LCD on SPI0
Board Drivers Config --> Enable SDCARD (spi1(ss0))
Board Drivers Config --> Enable DVP(camera)
RT-Thread Components --> POSIX layer and C standard library --> Enable pthreads APIs
APP_Framework --> Framework --> support knowing framework --> kpu model postprocessing --> yolov2 region layer
APP_Framework --> Applications --> knowing app --> enable apps/face detect

scons -j(n) to compile and burn in by kflash.

json config and kmodel

Copy json config for deployment o SD card /kmodel. Example config file is detect.json in this directory. Copy final kmodel to SD card /kmodel either.

Run

In serial terminal, face_detect to start a detection thread, face_detect_delete to stop it. Detection results can be found in output.