Input
- Video - From Downloaded Files, or
- Webcam
Output
Run the Code:
#Created by MediaPipe
#Modified by Augmented Startups 2021
#Hand-Pose-Estimation in 5 Minutes
#Watch 5 Minute Tutorial at www.augmentedstartups.info/YouTube
import cv2
import mediapipe as mp
mp_drawing = mp.solutions.drawing_utils
mp_hands = mp.solutions.hands
import time
# For static images:
with mp_hands.Hands(
static_image_mode=True,
max_num_hands=2,
min_detection_confidence=0.5) as hands:
# Read an image, flip it around y-axis for correct handedness output (see
# above).
image = cv2.imread('hand.jpg') #Insert your Image Here
# Convert the BGR image to RGB before processing.
results = hands.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
if not results.multi_hand_landmarks:
print("Continue")
# Print handedness and draw hand landmarks on the image.
print('Handedness:', results.multi_handedness)
image_height, image_width, _ = image.shape
annotated_image = image.copy()
for hand_landmarks in results.multi_hand_landmarks:
print('hand_landmarks:', hand_landmarks)
print(
f'Index finger tip coordinates: (',
f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x * image_width}, '
f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y * image_height})'
)
mp_drawing.draw_landmarks(
annotated_image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
cv2.imwrite(r'hands.png', annotated_image)
## For webcam input:
cap = cv2.VideoCapture(0)
prevTime = 0
with mp_hands.Hands(
min_detection_confidence=0.5, #Detection Sensitivity
min_tracking_confidence=0.5) as hands:
while cap.isOpened():
success, image = cap.read()
if not success:
print("Ignoring empty camera frame.")
# If loading a video, use 'break' instead of 'continue'.
continue
# Flip the image horizontally for a later selfie-view display, and convert
# the BGR image to RGB.
image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)
# To improve performance, optionally mark the image as not writeable to
# pass by reference.
image.flags.writeable = False
results = hands.process(image)
# Draw the hand annotations on the image.
image.flags.writeable = True
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
if results.multi_hand_landmarks:
for hand_landmarks in results.multi_hand_landmarks:
mp_drawing.draw_landmarks(
image, hand_landmarks, mp_hands.HAND_CONNECTIONS)
currTime = time.time()
fps = 1 / (currTime - prevTime)
prevTime = currTime
cv2.putText(image, f'FPS: {int(fps)}', (20, 70), cv2.FONT_HERSHEY_PLAIN, 3, (0, 196, 255), 2)
cv2.imshow('MediaPipe Hands', image)
if cv2.waitKey(5) & 0xFF == 27:
break
cap.release()
# Learn more AI in Computer Vision by Enrolling in our AI_CV Nano Degree:
# https://bit.ly/AugmentedAICVPRO
