Implement Phase 1: Raspberry Pi reference pipeline - #1
Merged
Conversation
Capture, detection, fusion, state, and control now work end to end: - events: FrameEvent/AudioEvent/DetectorVote/MuteDecision/AdSegment - config: TOML loading, validation, device-profile inheritance - capture: deterministic file_replay (.npz fixtures + ffmpeg media) and live hdmi_uvc (V4L2 + ALSA via ffmpeg subprocesses) - detectors: black_frame, silence (spectral-flatness aware), loudness (K-weighted short-term level vs. frozen-while-elevated baseline) - fusion: constant-mass weighted combination with Schmitt hysteresis; no single detector can trigger a mute alone - state: PROGRAM -> SUSPECT_AD -> AD -> RECOVERY with asymmetric dwell, full-confidence AD entry, and a hard max-mute ceiling - control: rs232_sharp (AQUOS discrete mute + state readback, injectable serial link) and ir_lirc (discrete or toggle via irsend) - engine: offline replay and live threaded loop, plus separate mute-onset/unmute-onset precision-recall scoring (ADR 0004) - cli: run, replay (labeled-ground-truth scoring), doctor, ir-test Tests: 66 passing (unit per module + labeled file_replay integration), ruff and strict mypy clean; mypy added to CI. Default loudness window shortened to 1.5 s so unmute latency stays under ~2 s. Co-Authored-By: Claude <[email protected]> Claude-Session: https://claude.ai/code/session_01BcfLmuUiHYY3PbRUskf3t4
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Capture, detection, fusion, state, and control now work end to end:
live hdmi_uvc (V4L2 + ALSA via ffmpeg subprocesses)
(K-weighted short-term level vs. frozen-while-elevated baseline)
no single detector can trigger a mute alone
full-confidence AD entry, and a hard max-mute ceiling
serial link) and ir_lirc (discrete or toggle via irsend)
mute-onset/unmute-onset precision-recall scoring (ADR 0004)
Tests: 66 passing (unit per module + labeled file_replay integration),
ruff and strict mypy clean; mypy added to CI. Default loudness window
shortened to 1.5 s so unmute latency stays under ~2 s.
Co-Authored-By: Claude [email protected]
Claude-Session: https://claude.ai/code/session_01BcfLmuUiHYY3PbRUskf3t4