Skip to main content

ai-camera-viewer

[UNTESTED] — v0.5 paper-correct

Builds clean on native_sim/native/64. Real OV5640 capture + Ethos-U dispatch + Vela-compiled model land in v0.6 alongside AEN HiL bring-up.

Headline edge-AI demo: an E1M-AEN module captures camera frames, runs a person-detect model on the on-die Ethos-U NPU, and renders the preview + bounding boxes on a 240×240 LVGL display.

Source: examples/ai-camera-viewer/.

Pipeline​

OV5640 → <alp/camera.h> → <alp/inference.h> → post-process → LVGL
(SCCB+MIPI)   RGB565 frame     person-detect          bbox list +
                               (uint8 quantised)      per-frame latency

board.yaml​

schema_version: 2

som:
  sku: E1M-AEN701

carrier:
  name: E1M-EVK

cores:
  m55_hp:
    os: zephyr
    app: ./src
    peripherals: [i2c, spi]
    libraries: [lvgl]
    inference: { backend: ethos_u, tensor_arena_kb: 512 }

chips:
  - ov5640
  - st7789

diagnostics:
  log_level: info

See also​

Questions about this page? Discuss in Community Forum