pyr0ball
0dcc25164d
- BlinkDetector: EAR-based blink detection (left/right/both), 6 tests - GazeEstimator: iris-to-eye-corner ratio gaze direction, frozen GazeDirection dataclass, 4 tests - HeadPoseEstimator: velocity-based nod/shake/tilt detection (stateful, no tests — daemon smoke test) - HandGestureDetector: normalize_hand + tip-distance open/pinch/fist classifier (no tests — daemon smoke test) - TDD: blink and gaze followed RED→GREEN cycle; Black applied to all 6 files
60 lines
1.8 KiB
Python
60 lines
1.8 KiB
Python
"""
|
|
Gaze direction estimation from MediaPipe Face Mesh iris landmarks.
|
|
|
|
Requires mediapipe to be run with refine_landmarks=True (enables iris tracking,
|
|
landmark indices 468-477).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
import numpy as np
|
|
|
|
_LEFT_IRIS_CENTER = 468
|
|
_RIGHT_IRIS_CENTER = 473
|
|
_LEFT_EYE_INNER = 133
|
|
_RIGHT_EYE_OUTER = 263
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class GazeDirection:
|
|
dx: float # [-1, 1] — negative = left, positive = right
|
|
dy: float # [-1, 1] — negative = up, positive = down
|
|
|
|
@property
|
|
def label(self) -> str:
|
|
if abs(self.dx) < 0.15 and abs(self.dy) < 0.15:
|
|
return "center"
|
|
if abs(self.dx) > abs(self.dy):
|
|
return "left" if self.dx < 0 else "right"
|
|
return "up" if self.dy < 0 else "down"
|
|
|
|
|
|
class GazeEstimator:
|
|
"""Estimate gaze direction from iris center relative to eye corners."""
|
|
|
|
def estimate(self, face_landmarks: np.ndarray) -> GazeDirection:
|
|
"""
|
|
Args:
|
|
face_landmarks: (478, 3) float32 — MediaPipe Face Mesh with iris refinement.
|
|
|
|
Returns:
|
|
GazeDirection with normalized (dx, dy).
|
|
"""
|
|
left_iris = face_landmarks[_LEFT_IRIS_CENTER]
|
|
right_iris = face_landmarks[_RIGHT_IRIS_CENTER]
|
|
iris_center = (left_iris + right_iris) / 2.0
|
|
|
|
left_inner = face_landmarks[_LEFT_EYE_INNER]
|
|
right_outer = face_landmarks[_RIGHT_EYE_OUTER]
|
|
eye_width = np.linalg.norm(right_outer - left_inner)
|
|
if eye_width < 1e-6:
|
|
return GazeDirection(dx=0.0, dy=0.0)
|
|
|
|
eye_center = (left_inner + right_outer) / 2.0
|
|
delta = iris_center - eye_center
|
|
return GazeDirection(
|
|
dx=float(delta[0] / eye_width),
|
|
dy=float(delta[1] / eye_width),
|
|
)
|