|
|
import cv2
|
|
|
import mediapipe as mp
|
|
|
import numpy as np
|
|
|
|
|
|
class MediaPipeDetector:
|
|
|
def __init__(self, model_complexity=1, min_detection_confidence=0.5):
|
|
|
self.mp_pose = mp.solutions.pose
|
|
|
self.pose = self.mp_pose.Pose(
|
|
|
static_image_mode=False,
|
|
|
model_complexity=model_complexity,
|
|
|
enable_segmentation=False,
|
|
|
min_detection_confidence=min_detection_confidence
|
|
|
)
|
|
|
self.mp_drawing = mp.solutions.drawing_utils
|
|
|
|
|
|
def detect(self, image):
|
|
|
"""Возвращает словарь с ключами: success, landmarks (33,4), pose_landmarks (для отрисовки)"""
|
|
|
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
|
|
results = self.pose.process(rgb)
|
|
|
|
|
|
if results.pose_landmarks:
|
|
|
h, w, _ = image.shape
|
|
|
landmarks = []
|
|
|
for lm in results.pose_landmarks.landmark:
|
|
|
x = lm.x * w
|
|
|
y = lm.y * h
|
|
|
z = lm.z
|
|
|
v = lm.visibility
|
|
|
landmarks.append([x, y, z, v])
|
|
|
landmarks = np.array(landmarks, dtype=np.float32)
|
|
|
return {'success': True, 'landmarks': landmarks, 'pose_landmarks': results.pose_landmarks}
|
|
|
else:
|
|
|
return {'success': False, 'landmarks': None, 'pose_landmarks': None}
|
|
|
|
|
|
def draw_landmarks(self, image, pose_landmarks):
|
|
|
"""Рисует скелет на копии изображения и возвращает её"""
|
|
|
if pose_landmarks is None:
|
|
|
return image.copy()
|
|
|
vis = image.copy()
|
|
|
self.mp_drawing.draw_landmarks(vis, pose_landmarks, self.mp_pose.POSE_CONNECTIONS)
|
|
|
return vis
|