mediaproc/tests/detect/manual/run_region_analysis.py

#!/usr/bin/env python3
"""
Run edge detection on test video frames — visual verification.

Uses a minimal 3-stage pipeline: extract_frames → filter_scenes → detect_edges.
No YOLO, OCR, or downstream stages.

Usage:
    python tests/detect/manual/run_region_analysis.py [--job JOB_ID] [--port PORT] [--local]

Opens: http://mpr.local.ar/detection/?job=<JOB_ID>

What to look for in the frame viewer:
  - "Edges" toggle appears (cyan)
  - Cyan boxes around horizontal line pairs (hoarding edges)
  - No boxes on players, ball, or sky
  - Boxes concentrated in the lower third of the frame
"""

import argparse
import logging
import os
import sys
import time as _time

parser = argparse.ArgumentParser()
parser.add_argument("--job", default=f"cv-{int(_time.time()) % 100000}")
parser.add_argument("--port", type=int, default=6379)
parser.add_argument("--local", action="store_true", help="Run CV locally (no inference server)")
args = parser.parse_args()

os.environ["REDIS_URL"] = f"redis://localhost:{args.port}/0"
if args.local:
    os.environ.pop("INFERENCE_URL", None)

logging.basicConfig(level=logging.DEBUG, format="%(levelname)-7s %(name)s — %(message)s")

sys.path.insert(0, ".")

from langgraph.graph import END, StateGraph

from core.detect import emit
from core.detect.models import PipelineStats
from core.detect.profile import get_profile
from core.detect.stages.frame_extractor import extract_frames
from core.detect.stages.scene_filter import scene_filter
from core.detect.stages.edge_detector import detect_edge_regions
from core.detect.state import DetectState

logger = logging.getLogger(__name__)

VIDEO = "media/mpr/out/chunks/95043d50-4df6-4ac8-bbd5-2ba873117c6e/chunk_0000.mp4"
INFERENCE_URL = os.environ.get("INFERENCE_URL")


# --- 3-stage pipeline ---

NODES = ["extract_frames", "filter_scenes", "detect_edges"]


def _emit_transition(job_id: str, node: str, status: str, node_states: dict):
    node_states[node] = status
    nodes = [{"id": n, "status": node_states.get(n, "pending")} for n in NODES]
    emit.graph_update(job_id, nodes)


def node_extract(state: DetectState) -> dict:
    job_id = state.get("job_id", "")
    ns = state.get("_node_states", {n: "pending" for n in NODES})
    _emit_transition(job_id, "extract_frames", "running", ns)

    profile = SoccerBroadcastProfile()
    config = profile.frame_extraction_config()
    frames = extract_frames(state["video_path"], config, job_id=job_id)

    _emit_transition(job_id, "extract_frames", "done", ns)
    return {"frames": frames, "stats": PipelineStats(frames_extracted=len(frames)), "_node_states": ns}


def node_filter(state: DetectState) -> dict:
    job_id = state.get("job_id", "")
    ns = state.get("_node_states", {})
    _emit_transition(job_id, "filter_scenes", "running", ns)

    profile = SoccerBroadcastProfile()
    config = profile.scene_filter_config()
    kept = scene_filter(state.get("frames", []), config, job_id=job_id)

    stats = state.get("stats", PipelineStats())
    stats.frames_after_scene_filter = len(kept)

    _emit_transition(job_id, "filter_scenes", "done", ns)
    return {"filtered_frames": kept, "stats": stats, "_node_states": ns}


def node_edges(state: DetectState) -> dict:
    job_id = state.get("job_id", "")
    ns = state.get("_node_states", {})
    _emit_transition(job_id, "detect_edges", "running", ns)

    profile = SoccerBroadcastProfile()
    config = profile.region_analysis_config()
    regions = detect_edge_regions(
        state.get("filtered_frames", []), config,
        inference_url=INFERENCE_URL, job_id=job_id,
    )
    total = sum(len(r) for r in regions.values())

    stats = state.get("stats", PipelineStats())
    stats.cv_regions_detected = total

    _emit_transition(job_id, "detect_edges", "done", ns)
    return {"edge_regions_by_frame": regions, "stats": stats, "_node_states": ns}


def build_3stage_graph() -> StateGraph:
    graph = StateGraph(DetectState)
    graph.add_node("extract_frames", node_extract)
    graph.add_node("filter_scenes", node_filter)
    graph.add_node("detect_edges", node_edges)
    graph.set_entry_point("extract_frames")
    graph.add_edge("extract_frames", "filter_scenes")
    graph.add_edge("filter_scenes", "detect_edges")
    graph.add_edge("detect_edges", END)
    return graph


def main():
    logger.info("Job: %s", args.job)
    logger.info("Mode: %s", "remote" if INFERENCE_URL else "local")
    logger.info("Pipeline: extract_frames → filter_scenes → detect_edges")
    logger.info("Open: http://mpr.local.ar/detection/?job=%s", args.job)
    input("\nPress Enter to start...")

    emit.set_run_context(run_id=args.job, parent_job_id=args.job, run_type="initial", log_level="DEBUG")

    graph = build_3stage_graph()
    pipeline = graph.compile()

    initial_state = {
        "video_path": VIDEO,
        "job_id": args.job,
        "profile_name": "soccer_broadcast",
    }

    result = pipeline.invoke(initial_state)

    # Print results
    regions = result.get("edge_regions_by_frame", {})
    total = sum(len(boxes) for boxes in regions.values())
    frames_with_regions = sum(1 for boxes in regions.values() if boxes)

    logger.info("Results:")
    logger.info("  Total edge regions: %d", total)
    logger.info("  Frames with regions: %d / %d",
                frames_with_regions, len(result.get("filtered_frames", [])))

    for seq, boxes in sorted(regions.items()):
        if boxes:
            labels = [f"{b.label}({b.confidence:.2f})" for b in boxes]
            logger.info("  Frame %d: %s", seq, ", ".join(labels))

    logger.info("Done. Check the frame viewer for cyan boxes.")
    logger.info("")

    # --- Parameter sensitivity ---
    logger.info("=== Parameter sensitivity (local debug) ===")

    from core.detect.stages.edge_detector import _load_cv_edges
    edges_mod = _load_cv_edges()

    filtered = result.get("filtered_frames", [])
    if filtered:
        sample = filtered[0]
        for canny_low in [20, 50, 80, 120]:
            dbg = edges_mod.detect_edges_debug(sample.image, canny_low=canny_low)
            logger.info(
                "  canny_low=%d → %d horizontals, %d pairs, %d regions",
                canny_low, dbg["horizontal_count"], dbg["pair_count"], len(dbg["regions"]),
            )

    logger.info("")
    logger.info("=== Editor test ===")
    logger.info("  Dashboard: http://mpr.local.ar/detection/?job=%s", args.job)
    logger.info("  Editor:    http://mpr.local.ar/detection/?job=%s#/editor/detect_edges", args.job)


if __name__ == "__main__":
    main()