momentry_core/scripts/mediapipe_pose_processor.py

#!/opt/homebrew/bin/python3.11
"""
MediaPipe Pose Processor - Using MediaPipe Pose Landmarker

Detects human pose with 33 keypoints, including face landmarks (nose, eyes).
Coordinates are normalized (0-1), converted to pixel coordinates.

Usage:
    python3 scripts/mediapipe_pose_processor.py --video /path/to/video.mp4 --file-uuid <uuid> --output-dir /path/to/output

Output:
    {uuid}.pose.mediapipe.json
"""

import argparse
import json
import os
import sys
import time
from pathlib import Path

try:
    import cv2
    import mediapipe as mp
    import numpy as np
    from mediapipe.tasks.python.vision import PoseLandmarker, PoseLandmarkerOptions
    from mediapipe.tasks.python.core.base_options import BaseOptions
except ImportError as e:
    print(f"Missing dependency: {e}", file=sys.stderr)
    sys.exit(1)


# MediaPipe Pose landmark names (33 keypoints)
LANDMARK_NAMES = [
    "nose", "left_eye_inner", "left_eye", "left_eye_outer",
    "right_eye_inner", "right_eye", "right_eye_outer",
    "left_ear", "right_ear", "mouth_left", "mouth_right",
    "left_shoulder", "right_shoulder", "left_elbow", "right_elbow",
    "left_wrist", "right_wrist", "left_pinky", "right_pinky",
    "left_index", "right_index", "left_thumb", "right_thumb",
    "left_hip", "right_hip", "left_knee", "right_knee",
    "left_ankle", "right_ankle", "left_heel", "right_heel",
    "left_foot_index", "right_foot_index",
]


def process_video(
    video_path: str,
    output_path: str,
    file_uuid: str,
    sample_interval: int = 3,  # Match Apple Vision default
) -> dict:
    """
    Process video with MediaPipe Pose.
    
    Args:
        video_path: Path to video file
        output_path: Output JSON path
        file_uuid: File UUID
        sample_interval: Process every N frames
    
    Returns:
        Dict with pose data
    """
    # Download model if not exists
    model_path = os.path.expanduser("~/.mediapipe/models/pose_landmarker_heavy.task")
    if not os.path.exists(model_path):
        os.makedirs(os.path.dirname(model_path), exist_ok=True)
        print(f"[mediapipe_pose] Downloading model...")
        import urllib.request
        url = "https://storage.googleapis.com/mediapipe-models/pose_landmarker/pose_landmarker_heavy/float16/1/pose_landmarker_heavy.task"
        urllib.request.urlretrieve(url, model_path)
        print(f"[mediapipe_pose] Model downloaded to {model_path}")
    
    # Initialize Pose Landmarker
    options = PoseLandmarkerOptions(
        base_options=BaseOptions(model_asset_path=model_path),
        running_mode=mp.tasks.vision.RunningMode.VIDEO,
    )
    detector = PoseLandmarker.create_from_options(options)
    
    # Open video
    cap = cv2.VideoCapture(video_path)
    if not cap.isOpened():
        print(f"[mediapipe_pose] Cannot open video: {video_path}", file=sys.stderr)
        return {"error": "Cannot open video"}
    
    fps = cap.get(cv2.CAP_PROP_FPS)
    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
    
    print(f"[mediapipe_pose] Video: {total_frames} frames, {fps:.2f} fps, {width}x{height}")
    print(f"[mediapipe_pose] Processing every {sample_interval} frames...")
    
    frames_data = []
    frame_num = 0
    processed_count = 0
    
    start_time = time.time()
    
    while True:
        ret, frame = cap.read()
        if not ret:
            break
        
        # Process every N frames
        if frame_num % sample_interval == 0:
            # Convert BGR to RGB
            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            
            # Create MediaPipe Image
            mp_image = mp.Image(mp.ImageFormat.SRGB, rgb_frame)
            
            # Detect pose
            results = detector.detect_for_video(mp_image, int(frame_num * 1000 / fps))
            
            if results.pose_landmarks:
                for pose_landmarks in results.pose_landmarks:
                    keypoints = []
                    face_keypoints = []
                    
                    for idx, landmark in enumerate(pose_landmarks):
                        name = LANDMARK_NAMES[idx] if idx < len(LANDMARK_NAMES) else f"landmark_{idx}"
                        kp = {
                            "name": name,
                            "x": landmark.x * width,
                            "y": landmark.y * height,
                            "z": landmark.z if hasattr(landmark, 'z') else 0,
                            "confidence": landmark.visibility if hasattr(landmark, 'visibility') else 1.0,
                        }
                        keypoints.append(kp)
                        
                        if name in ["nose", "left_eye", "right_eye"]:
                            face_keypoints.append(kp)
                    
                    # Calculate bbox from all keypoints
                    valid_kps = [kp for kp in keypoints if kp["confidence"] > 0.3]
                    if valid_kps:
                        x_coords = [kp["x"] for kp in valid_kps]
                        y_coords = [kp["y"] for kp in valid_kps]
                        bbox = {
                            "x": min(x_coords),
                            "y": min(y_coords),
                            "width": max(x_coords) - min(x_coords),
                            "height": max(y_coords) - min(y_coords),
                        }
                    else:
                        bbox = {"x": 0, "y": 0, "width": 0, "height": 0}
                    
                    frames_data.append({
                        "frame": frame_num,
                        "timestamp": frame_num / fps,
                        "persons": [{
                            "keypoints": keypoints,
                            "bbox": bbox,
                            "face_keypoints": face_keypoints,
                        }],
                    })
                    
                    processed_count += 1
                    
                    if processed_count % 100 == 0:
                        elapsed = time.time() - start_time
                        print(f"[mediapipe_pose] Processed {processed_count} poses ({elapsed:.1f}s)")
        
        frame_num += 1
    
    cap.release()
    detector.close()
    
    elapsed = time.time() - start_time
    
    # Build output
    output = {
        "file_uuid": file_uuid,
        "processor": "mediapipe_pose",
        "fps": fps,
        "frame_count": total_frames,
        "sample_interval": sample_interval,
        "total_poses": len(frames_data),
        "elapsed_seconds": round(elapsed, 2),
        "frames": frames_data,
    }
    
    # Save
    with open(output_path, "w") as f:
        json.dump(output, f)
    
    print(f"[mediapipe_pose] Saved: {output_path}")
    print(f"[mediapipe_pose] Total poses: {len(frames_data)}")
    print(f"[mediapipe_pose] Elapsed: {elapsed:.1f}s")
    
    return output


def main():
    parser = argparse.ArgumentParser(description="MediaPipe Pose Processor")
    parser.add_argument("--video", "-v", required=True, help="Video file path")
    parser.add_argument("--file-uuid", "-u", required=True, help="File UUID")
    parser.add_argument("--output-dir", "-o", default="/Users/accusys/momentry/output", help="Output directory")
    parser.add_argument("--sample-interval", "-s", type=int, default=3, help="Process every N frames")
    args = parser.parse_args()
    
    output_path = Path(args.output_dir) / f"{args.file_uuid}.pose.mediapipe.json"
    
    result = process_video(
        args.video,
        str(output_path),
        args.file_uuid,
        args.sample_interval,
    )
    
    if "error" not in result:
        print(f"\n[mediapipe_pose] Done. Output: {output_path}")


if __name__ == "__main__":
    main()