20. Mediapipe 활용(2) | 자세 랜드마크 감지

1. 자세 랜드마크 감지

 

◼  Mediapipe 사이트 

✔링크: https://ai.google.dev/edge/mediapipe/solutions/guide?hl=ko

MediaPipe 솔루션 가이드  |  Google AI Edge  |  Google AI for Developers

✔ 코랩파일 : https://colab.research.google.com/github/googlesamples/mediapipe/blob/main/examples/pose_landmarker/python/%5BMediaPipe_Python_Tasks%5D_Pose_Landmarker.ipynb?hl=ko#scrollTo=_JVO3rvPD4RN

 

 

◼ model bundle 설치 (vscode_terminal_cmd 입력)

curl -o pose_landmarker.task https://storage.googleapis.com/mediapipe-models/pose_landmarker/pose_landmarker_heavy/float16/1/pose_landmarker_heavy.task

 

 

◼ 시각화 하기

#@markdown To better demonstrate the Pose Landmarker API, we have created a set of visualization tools that will be used in this colab. These will draw the landmarks on a detect person, as well as the expected connections between those markers.             from mediapipe import solutions             from mediapipe.framework.formats import landmark_pb2             import numpy as np             def draw_landmarks_on_image(rgb_image, detection_result):             pose_landmarks_list = detection_result.pose_landmarks             annotated_image = np.copy(rgb_image)             # Loop through the detected poses to visualize.             for idx in range(len(pose_landmarks_list)):                 pose_landmarks = pose_landmarks_list[idx]                 # Draw the pose landmarks.                 pose_landmarks_proto = landmark_pb2.NormalizedLandmarkList()                 pose_landmarks_proto.landmark.extend([                 landmark_pb2.NormalizedLandmark(x=landmark.x, y=landmark.y, z=landmark.z) for landmark in pose_landmarks                 ])                 solutions.drawing_utils.draw_landmarks(                 annotated_image,                 pose_landmarks_proto,                 solutions.pose.POSE_CONNECTIONS,                 solutions.drawing_styles.get_default_pose_landmarks_style())             return annotated_image

 

 

 

◼ 이미지 다운로드 (주소창 입력)

https://cdn.pixabay.com/photo/2019/03/12/20/39/girl-4051811_960_720.jpg

 

 

◼ 추론 실행 및 결과 시각화

# STEP 1: Import the necessary modules.             import mediapipe as mp             from mediapipe.tasks import python             from mediapipe.tasks.python import vision             # STEP 2: Create an PoseLandmarker object.             base_options = python.BaseOptions(model_asset_path='pose_landmarker.task')             options = vision.PoseLandmarkerOptions(                 base_options=base_options,                 output_segmentation_masks=True)             detector = vision.PoseLandmarker.create_from_options(options)             # STEP 3: Load the input image.             image = mp.Image.create_from_file("image2.jpg")             # STEP 4: Detect pose landmarks from the input image.             detection_result = detector.detect(image)             # STEP 5: Process the detection result. In this case, visualize it.             annotated_image = draw_landmarks_on_image(image.numpy_view(), detection_result)             cv2.imshow('Annotated image', cv2.cvtColor(annotated_image, cv2.COLOR_RGB2BGR))             cv2.waitKey(0)             cv2.destroyAllWindows()

 

 

◼ 다양한 사진 넣어보기 

# STEP 3: Load the input image.         image = mp.Image.create_from_file("image.png") --> 이 부분 변경

 

 

◼ 웹캡으로 인식해보기

import mediapipe as mp         from mediapipe import solutions         from mediapipe.framework.formats import landmark_pb2         import numpy as np         from mediapipe.tasks import python         from mediapipe.tasks.python import vision         import cv2         def draw_landmarks_on_image(rgb_image, detection_result):         pose_landmarks_list = detection_result.pose_landmarks         annotated_image = np.copy(rgb_image)         # Loop through the detected poses to visualize.         for idx in range(len(pose_landmarks_list)):             pose_landmarks = pose_landmarks_list[idx]             # Draw the pose landmarks.             pose_landmarks_proto = landmark_pb2.NormalizedLandmarkList()             pose_landmarks_proto.landmark.extend([             landmark_pb2.NormalizedLandmark(x=landmark.x, y=landmark.y, z=landmark.z) for landmark in pose_landmarks             ])             solutions.drawing_utils.draw_landmarks(             annotated_image,             pose_landmarks_proto,             solutions.pose.POSE_CONNECTIONS,             solutions.drawing_styles.get_default_pose_landmarks_style())         return annotated_image         ## 캠 연결         cap = cv2.VideoCapture(0)         if not cap.isOpened():             print("웹캠을 열 수 없습니다.")             exit()         while True:             # 프레임 읽기             ret, frame = cap.read()             if not ret:                 print("프레임을 가져올 수 없습니다.")                 break             # STEP 2: Create an PoseLandmarker object.             base_options = python.BaseOptions(model_asset_path='pose_landmarker.task')             options = vision.PoseLandmarkerOptions(                 base_options=base_options,                 output_segmentation_masks=True)             detector = vision.PoseLandmarker.create_from_options(options)             # STEP 3: Load the input image.             frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)             mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=frame_rgb)             # STEP 4: Detect pose landmarks from the input image.             detection_result = detector.detect(mp_image)             # STEP 5: Process the detection result. In this case, visualize it.             annotated_image = draw_landmarks_on_image(mp_image.numpy_view(), detection_result)             cv2.imshow('test',cv2.cvtColor(annotated_image, cv2.COLOR_RGB2BGR))             if cv2.waitKey(1) & 0xFF == ord('q'):                 break