One week after the initial idea: a functional app on two Samsung flagships, 27\/27 tests green, APK under 30 MB. What happened on the way there.<\/p>\n
For AI traffic light recognition, there are several YOLO variants. I started with the 640px model – detection quality good, latency on the S23 Ultra around 215 ms. Too slow for live use. The 320px model achieves ~88 ms on the S23 Ultra, ~50 ms on the S25 Ultra. Usable.<\/p>\n
APK size was initially 52 MB. arm64-only ABI filter and removal of the 640px asset reduced this to 28 MB. Better.<\/p>\n
Light and Pro are not two separate apps, but one. The CV model is always included (~28 MB) but locked. Upon the first Pro launch, a real benchmark runs on the device: the app measures inference latency under real conditions, not on a test image. If the average is below 150 ms, Pro is unlocked. If it is above, CV remains deactivated – ensuring no poor experience on weak hardware.<\/p>\n
Purchase is currently a stub – unlockable locally. Play Billing will be implemented when the store rollout occurs.<\/p>\n
Dual-load soak for 20 minutes on the S23 Ultra: camera, GPS, and display running in parallel. Thermal equilibrium at ~43 \u00b0C, CV latency stable at ~88 ms, no crash. GPS on real drives: 3-meter accuracy, excellent.<\/p>\n
Hazard warning runs on offline OSM data (1,102 saved points in Hessen), speed limit from a local index with 921,000 points – loads for a few seconds upon first launch, then instant.<\/p>\n
Traffic light CV during real driving: ~30 detections, but no confirmed color. Detection works, but smoothing at distance and motion is not yet good enough. This is the next open topic. Requires a proper camera mount for testing.<\/p>\n
Status quo and next steps: tomorrow.<\/p>","protected":false},"excerpt":{"rendered":"