iot-connected-camera

End-to-end V2N reference application: camera capture → DRP-AI inference → MQTT/TLS publish + LVGL UI overlay. Demonstrates <alp/camera.h>, <alp/inference.h>, <alp/iot.h>, <alp/security.h>, and <alp/gui.h> in one app.

Source: examples/iot-connected-camera/.

What it shows

The full vision-IoT pipeline on V2N:

1. Capture — MIPI CSI-2 frame via <alp/camera.h> from the V2N's connected camera module.
2. Infer — TFLite Micro model dispatched through <alp/inference.h> to the on-die DRP-AI3 NPU.
3. Publish — Detection results serialised to JSON, published over MQTT with TLS via <alp/iot.h> + <alp/security.h>.
4. Display — Live preview + bounding-box overlay rendered with <alp/gui.h> (LVGL).

Wi-Fi credentials + MQTT broker config come from a per-device JSON file written into the on-module storage at factory provisioning.

board.yaml

schema_version: 2

som:
  sku: E1M-V2N101

carrier:
  name: E1M-X-EVK

cores:
  a55_cluster:
    os: yocto
    app: ./linux
    image: alp-image-edge
    peripherals: [i2c, spi]
    libraries: [lvgl, mbedtls]
    iot: { wifi: true, mqtt: true, tls: true }
    inference: { backend: drpai, tensor_arena_kb: 4096 }

chips:
  - gd32g553
  - optiga_trust_m

diagnostics:
  log_level: info

Build

cd alp-workspace
west alp-build alp-sdk/examples/iot-connected-camera
west alp-image

See also

• <alp/inference.h> reference — DRP-AI dispatcher
• <alp/iot.h> reference — Wi-Fi + MQTT
• <alp/security.h> reference
• Tutorial 11 — MQTT TLS publish
• Examples overview