scene-actor-extraction/src/config.hpp

#pragma once
#include "inference/backend_config.hpp"
#include <string>

inline const std::string kDefaultDetectorModel = std::string(SAE_MODELS_DIR) + "/scrfd_500m_bnkps.onnx";
inline const std::string kDefaultArcfaceModel  = std::string(SAE_MODELS_DIR) + "/LVFace-B_Glint360K.onnx";
inline const std::string kDefaultSceneModel    = std::string(SAE_MODELS_DIR) + "/transnetv2.onnx";

enum class Verbosity {
    minimal,   // actor names + merged time windows only
    standard,  // per-frame detail: bbox, similarity, unknowns logged
    xray,      // Jellyfin-Xray format: {"second": ["Actor", ...], ...}
};
// debug verbosity = compile with -DSAE_DEBUG → scene_analyze_debug binary

struct Config {
    // ── Input ─────────────────────────────────────────────────────────────────
    std::string movie_path;
    std::string gallery_path;
    // TRACES: IR-002 | SR-003
    // "global" (matched against the whole library) or "limited" (this title's
    // credited cast only). The strongest single quality signal when two
    // manifests compete for the same cut: identical gallery_size can mean very
    // different recall depending on which was used.
    std::string gallery_scope{"global"};    // gallery.json produced by build_gallery

    // ── Output ───────────────────────────────────────────────────────────────
    std::string output_path;     // annotations.json
    Verbosity   verbosity{Verbosity::minimal};

    // When set, tee the embedder output to an HDF5 dump (schema:
    // scripts/optimizer/SCHEMA.md) for offline threshold-sweep replay via sae_kpn.
    std::string dump_embeddings_path;

    // ── Sampling ─────────────────────────────────────────────────────────────
    float  sample_fps{1.0f};     // frames to analyse per second of movie
    float  max_decode_fps{0.f};  // wall-clock cap on source decode rate (0 = uncapped)
    double start_sec{0.0};       // seek to this timestamp before sampling
    double end_sec{-1.0};        // stop at this timestamp (-1 = end of file)

    // ── Detection (SCRFD-500MF via cv::dnn::Net) ──────────────────────────────
    std::string detector_model;
    std::string detector_engine;       // optional path to pre-built TRT engine; bypasses ORT
    int         max_faces{10};         // pipeline cap: keep only the N largest faces
    float       min_face_px{40.f};    // discard detections narrower or shorter than this
    float       detector_conf{0.5f};
    float       detector_nms{0.4f};

    /// TRACES: GR-004 | SR-001
    // Gallery ↔ embedder binding. A gallery built with a different model than the
    // one loaded here is a hard error, always. This flag additionally promotes
    // "cannot prove they match" (unstamped legacy gallery, or a name-only match
    // because the ONNX could not be hashed) from a loud warning to a hard error.
    // Also settable via SAE_REQUIRE_GALLERY_STAMP=1. Measurement runs want it on.
    bool require_gallery_stamp{false};   // --require-gallery-stamp

    // ── Recognition (ArcFace ONNX) ────────────────────────────────────────────
    std::string arcface_model;
    std::string arcface_engine;        // optional path to a pre-built TRT engine; bypasses ORT
    int         embed_batch_size{4};    // max faces per ORT Run() call — bounds per-call latency
    float       match_prior{0.5f};        // base-rate prior; 0.5 = use calibrated sigmoid directly
    // prob_threshold tuned by Differential Evolution against Amazon X-Ray per-scene
    // presence over 4 films, per-second metric (see docs/rep4-optimizer-results.md).
    // Best model+mode: LVFace-B_Glint360K, full gallery, expansion on. Supersedes the
    // earlier 9-film scene-union-metric tuning (0.76) — that metric is now known to
    // have hidden out-of-cast false positives (see docs/optimizer-experiments.md).
    float       prob_threshold{0.754f};   // posterior P(match | sim, prior) threshold
    float       match_threshold{0.45f};   // cosine distance hard ceiling fallback (no calibration)
    float       match_ratio{0.80f};       // ratio test fallback: accept if best/second < ratio
    float       match_ratio_ceil{0.65f};  // ratio test only fires below this absolute distance

    // ── Cut detection ────────────────────────────────────────────────────────
    float cut_threshold{0.70f};         // grayscale histogram correlation below this → hard cut

    // ── Scene detection (TransNetV2, opt-in) ─────────────────────────────────
    // When enabled, the source decodes densely (native FPS) and a decimator
    // splits the stream: full-res 1-FPS frames to the face pipeline, and a
    // downscaled dense stream to the TransNetV2 scene detector. Shot boundaries
    // it finds are surfaced as Frame::is_scene_boundary. This is separate from
    // the always-on histogram cut, which flags intra-scene camera-angle changes.
    bool        scene_detect{false};        // master switch (--scene-detect)
    std::string scene_model;                // TransNetV2 .onnx (default set in main)
    std::string scene_engine;               // optional pre-built TRT .engine; bypasses ORT
    float       scene_threshold{0.60f};     // sigmoid boundary prob above this → boundary
                                            //   (this export's non-boundary baseline sits
                                            //    at ~0.50; real boundaries spike to ~0.7+)
    int         scene_stride{50};           // frames advanced between windows (≤ kWindow)

    // Dense-decode throughput knobs (only active with scene_detect). Dense decode
    // of every native-rate frame is the pipeline's cost driver; these trade a
    // little boundary precision for a large speedup.
    //   scene_decode_fps: rate the source decodes at in dense mode. Lower =
    //     fewer frames decoded. TransNetV2 tolerates ~12fps; boundary timestamps
    //     stay correct (keyed off each frame's real timestamp). 0 = native fps.
    //   dense_scale: downscale factor applied to decoded frames in dense mode
    //     (0<f≤1; e.g. 0.5 = half size). Cheaper sws_scale + smaller frames
    //     through the fanout. NOTE: also shrinks what the face detector sees —
    //     keep ≥0.5 on 1080p sources so SCRFD still resolves small faces. 1 = off.
    float       scene_decode_fps{12.0f};    // dense decode rate (0 = native)
    float       dense_scale{1.0f};          // dense-mode frame downscale (1 = off)

    // ── Face tracking (frame-to-frame) ───────────────────────────────────────
    /// TRACES: AR-007, AR-008, AR-024 | SR-002
    // track_alpha is the *base* weight, used on ordinary frames. It is
    // frame-dependent (AR-007): on is_cut / is_scene_boundary, and for any track
    // that is no longer on screen, it drops to 0 (embedding only), because
    // position carries no information across a viewpoint change or a gap.
    float track_alpha{0.4f};            // base cost weight: 0=embedding only, 1=spatial only
    float track_min_iou{0.1f};          // IoU below which spatial link alone is rejected
    // Minimum P(same person) for an association to be admissible on appearance
    // alone. This replaces track_max_embed_dist (a raw cosine distance, AR-024).
    // 0.5 is not a tuned constant: it is the decision boundary. Below it the pair
    // is more likely two people than one, and no amount of IoU makes that a link
    // worth asserting on identity grounds.
    float track_assoc_min_prob{0.5f};
    // How long a track that has gone off screen stays available for association
    // before the registry reaps it and emits its presence claim (AR-013).
    // Replaces track_max_frames_missing: a frame count silently changed meaning
    // with sample_fps, and the same number had to be guessed twice (once for an
    // ordinary miss, once for a cut). Seconds mean one thing at any sample rate.
    double track_extinction_sec{5.0};

    // ── Scene tracking ────────────────────────────────────────────────────────
    // extinction_sec re-tuned by DE against X-Ray per-second presence, 4-film rep4
    // matrix (docs/rep4-optimizer-results.md). Reverses the earlier "short is better"
    // finding: with a stricter prob_threshold, a long extinction window bridges real
    // presence gaps (occlusion, turned face) instead of just smearing FPs — every
    // model's best config pushed to ~90%+ of the search ceiling (tried up to 60s).
    // The ceiling kept getting hit, so treat 60 as "good enough", not a proven optimum.
    double extinction_sec{57.4};  // keep actor active this many seconds after last detection
    // anneal_sec: previously found INSENSITIVE at a 1–30s range; the wider rep4 sweep
    // (1–60s) also pushed this to the ceiling alongside extinction_sec (see above).
    double anneal_sec{35.5};      // merge actor windows separated by less than this into one epoch

    // ── Per-film gallery expansion ────────────────────────────────────────────
    // Within one uncut track every face is the same physical person — a free
    // same-identity label the baked gallery lacks. When a track is confidently
    // owned by an actor, its gallery-far (pose-varied) embeddings are validated
    // new reference views; they are promoted into a per-film, in-memory annex so
    // later frames/tracks of that actor at similar poses recognise. See
    // gallery/track_gallery.hpp.
    // Default ON: rep4 matrix (docs/rep4-optimizer-results.md) found expansion helps
    // recall on the full (unrestricted) gallery for the winning model/mode — the
    // opposite of the earlier assumption that it only helps restricted galleries.
    bool   expand_gallery{true};         // master switch
    int    expand_buffer_size{20};       // per-track diversity buffer capacity
    float  expand_novelty_sim{0.55f};    // promote only embeddings whose best sim to the
                                         //   actor's refs is below this (gallery-far / novel)
    float  expand_track_spread_max{0.60f}; // reject promotion if the retained buffer's
                                           //   internal spread (1 - min pairwise sim) exceeds
                                           //   this — guards track-ID collisions / two people
    int    expand_min_anchor_frames{3};  // require ≥N accepted frames naming the actor before
                                         //   the track is confirmed and its buffer promoted
    std::string expand_debug_dir;        // if set, dump promoted mugshots + embeddings here

    // ── Inference backend tuning ────────────────────────────────────────────
    // Consumed by the compiled-in inference backend (ORT or TRT).
    // INT8 is unsafe for ArcFace without a calibration table.
    BackendConfig trt{};   // fp16=true, int8=false, cache_dir="./trt_cache"

    // ── Debug output (only used when SAE_DEBUG is defined) ───────────────────
#ifdef SAE_DEBUG
    std::string debug_dir{"debug_frames"};
    float       crop_context{1.5f};   // bbox expansion factor for context crop
#endif
};