使用Python+OpenCV實現(xiàn)姿態(tài)估計
OpenCV
什么是Mediapipe？
使用Mediapipe的最先進的ML模型
-
人臉檢測 -
多手跟蹤 -
頭發(fā)分割 -
目標檢測與追蹤 -
Objectron：3D對象檢測和跟蹤 -
AutoFlip：自動視頻裁剪管道 -
姿態(tài)估計
姿態(tài)估計
import cv2
import mediapipe as mp
import time
mpPose = mp.solutions.pose
pose = mpPose.Pose()
mpDraw = mp.solutions.drawing_utils
#cap = cv2.VideoCapture(0)
cap = cv2.VideoCapture('a.mp4')
pTime = 0
while True:
success, img = cap.read()
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
results = pose.process(imgRGB)
print(results.pose_landmarks)
if results.pose_landmarks:
mpDraw.draw_landmarks(img, results.pose_landmarks, mpPose.POSE_CONNECTIONS)
for id, lm in enumerate(results.pose_landmarks.landmark):
h, w,c = img.shape
print(id, lm)
cx, cy = int(lm.x*w), int(lm.y*h)
cv2.circle(img, (cx, cy), 5, (255,0,0), cv2.FILLED)
cTime = time.time()
fps = 1/(cTime-pTime)
pTime = cTime
cv2.putText(img, str(int(fps)), (50,50), cv2.FONT_HERSHEY_SIMPLEX,1,(255,0,0), 3)
cv2.imshow("Image", img)
cv2.waitKey(1)
姿勢界標
-
x和y：這些界標坐標分別通過圖像的寬度和高度歸一化為[0.0，1.0]。 -
z：通過將臀部中點處的深度作為原點來表示界標深度，并且z值越小，界標與攝影機越近。z的大小幾乎與x的大小相同。 -
可見性：[0.0，1.0]中的值，指示界標在圖像中可見的可能性。
import cv2
import mediapipe as mp
import time
class PoseDetector:
def __init__(self, mode = False, upBody = False, smooth=True, detectionCon = 0.5, trackCon = 0.5):
self.mode = mode
self.upBody = upBody
self.smooth = smooth
self.detectionCon = detectionCon
self.trackCon = trackCon
self.mpDraw = mp.solutions.drawing_utils
self.mpPose = mp.solutions.pose
self.pose = self.mpPose.Pose(self.mode, self.upBody, self.smooth, self.detectionCon, self.trackCon)
def findPose(self, img, draw=True):
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
self.results = self.pose.process(imgRGB)
#print(results.pose_landmarks)
if self.results.pose_landmarks:
if draw:
self.mpDraw.draw_landmarks(img, self.results.pose_landmarks, self.mpPose.POSE_CONNECTIONS)
return img
def getPosition(self, img, draw=True):
lmList= []
if self.results.pose_landmarks:
for id, lm in enumerate(self.results.pose_landmarks.landmark):
h, w, c = img.shape
#print(id, lm)
cx, cy = int(lm.x * w), int(lm.y * h)
lmList.append([id, cx, cy])
if draw:
cv2.circle(img, (cx, cy), 5, (255, 0, 0), cv2.FILLED)
return lmList
def main():
cap = cv2.VideoCapture('videos/a.mp4') #make VideoCapture(0) for webcam
pTime = 0
detector = PoseDetector()
while True:
success, img = cap.read()
img = detector.findPose(img)
lmList = detector.getPosition(img)
print(lmList)
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, str(int(fps)), (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 3)
cv2.imshow("Image", img)
cv2.waitKey(1)
if __name__ == "__main__":
main()
import cv2
import time
import PoseModule as pm
cap = cv2.VideoCapture(0)
pTime = 0
detector = pm.PoseDetector()
while True:
success, img = cap.read()
img = detector.findPose(img)
lmList = detector.getPosition(img)
print(lmList)
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, str(int(fps)), (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 0), 3)
cv2.imshow("Image", img)
cv2.waitKey(1)
個人微信（如果沒有備注不拉群！） 請注明：地區(qū)+學校/企業(yè)+研究方向+昵稱
下載1：何愷明頂會分享
在「AI算法與圖像處理」公眾號后臺回復：何愷明，即可下載。總共有6份PDF，涉及 ResNet、Mask RCNN等經(jīng)典工作的總結(jié)分析
下載2：終身受益的編程指南：Google編程風格指南
在「AI算法與圖像處理」公眾號后臺回復：c++，即可下載。歷經(jīng)十年考驗，最權(quán)威的編程規(guī)范！
下載3 CVPR2021
在「AI算法與圖像處理」公眾號后臺回復：CVPR，即可下載1467篇CVPR 2020論文 和 CVPR 2021 最新論文
點亮 
，告訴大家你也在看
評論
圖片
表情