我正在嘗試進行手部檢測，但我只想顯示沒有背景的手部地標。
通常它會用你的真手輸出，但我希望它只帶有手部地標，這樣我的房間和真手就不會出現。
我希望它看起來如何：
它的外觀：
和我正在使用的代碼
#credits: https://github.com/kulin-patel/Hand-Tracking
import cv2
import mediapipe as mp
import time
frameWidth = 1280
frameHeight = 720
cap = cv2.VideoCapture(0)
cap.set(3, frameWidth)
cap.set(4, frameHeight)
mpHands=mp.solutions.hands
hands=mpHands.Hands()
mpDraw = mp.solutions.drawing_utils
pTime = 0
cTime = 0
while True:
success, img = cap.read()
img= cv2.flip(img,1)
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
results = hands.process(imgRGB)
#print(results.multi_hand_landmarks)
if results.multi_hand_landmarks:
for handLms in results.multi_hand_landmarks:
#handLMs are 21 points. so we need conection too-->mpHands.HAND_CONNECTIONS
for id, lm in enumerate(handLms.landmark):
#print(id, lm)
#lm = x,y cordinate of each landmark in float numbers. lm.x, lm.y methods
#So, need to covert in integer
h, w, c =img.shape
cx, cy = int(lm.x * w), int(lm.y * h)
#print(id, cx, cy)
# if id == 4: #(To draw 4th point)
#cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS) #drawing points and lines(=handconections)
#Write frame rate
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, "FPS= " str(int(fps)), (10, 20), cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 0), 1)
cv2.imshow('image', img)
if cv2.waitKey(1)==27:
break
uj5u.com熱心網友回復：
您可以為此使用 numpy。
import numpy as np
在您的 line 之后img= cv2.flip(img,1)，創建與以下相同形狀的白色影像（背景）img
img_w = np.empty(img.shape)
img_w.fill(255)
然后img_w在您曾經用來img顯示標記的地方使用它，即在這 4 行中。
cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
mpDraw.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS)
cv2.putText(img, "FPS= " str(int(fps)), (10, 20), cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 0), 1)
cv2.imshow('image', img)
轉載請註明出處，本文鏈接：https://www.uj5u.com/caozuo/345429.html