Python?OpenCV實(shí)現(xiàn)姿態(tài)識(shí)別的詳細(xì)代碼
更新時(shí)間：2022年02月23日 11:39:33 作者：SlowFeather
這篇文章主要介紹了Python?OpenCV實(shí)現(xiàn)姿態(tài)識(shí)別的方法，本文通過截圖實(shí)例代碼相結(jié)合給大家介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或工作具有一定的參考借鑒價(jià)值,需要的朋友可以參考下
前言
想要使用攝像頭實(shí)現(xiàn)一個(gè)多人姿態(tài)識(shí)別
環(huán)境安裝
下載并安裝 Anaconda
官網(wǎng)連接 https://anaconda.cloud/installers
安裝 Jupyter Notebook
檢查Jupyter Notebook是否安裝
Tip：這里涉及到一個(gè)切換Jupyter Notebook內(nèi)核的問題，在我這篇文章中有提到
AnacondaNavigator Jupyter Notebook更換Python內(nèi)核http://www.dbjr.com.cn/article/238496.htm
生成Jupyter Notebook項(xiàng)目目錄
打開Anaconda Prompt切換到項(xiàng)目目錄
輸入Jupyter notebook在瀏覽器中打開 Jupyter Notebook
并創(chuàng)建新的記事本
下載訓(xùn)練庫(kù)
圖片以及訓(xùn)練庫(kù)都在下方鏈接
https://github.com/quanhua92/human-pose-estimation-opencv
將圖片和訓(xùn)練好的模型放到項(xiàng)目路徑中graph_opt.pb為訓(xùn)練好的模型
單張圖片識(shí)別
導(dǎo)入庫(kù)
import cv2 as cv import os import matplotlib.pyplot as plt
加載訓(xùn)練模型
net=cv.dnn.readNetFromTensorflow("graph_opt.pb")初始化
inWidth=368
inHeight=368
thr=0.2
BODY_PARTS = { "Nose": 0, "Neck": 1, "RShoulder": 2, "RElbow": 3, "RWrist": 4,
"LShoulder": 5, "LElbow": 6, "LWrist": 7, "RHip": 8, "RKnee": 9,
"RAnkle": 10, "LHip": 11, "LKnee": 12, "LAnkle": 13, "REye": 14,
"LEye": 15, "REar": 16, "LEar": 17, "Background": 18 }
POSE_PAIRS = [ ["Neck", "RShoulder"], ["Neck", "LShoulder"], ["RShoulder", "RElbow"],
["RElbow", "RWrist"], ["LShoulder", "LElbow"], ["LElbow", "LWrist"],
["Neck", "RHip"], ["RHip", "RKnee"], ["RKnee", "RAnkle"], ["Neck", "LHip"],
["LHip", "LKnee"], ["LKnee", "LAnkle"], ["Neck", "Nose"], ["Nose", "REye"],
["REye", "REar"], ["Nose", "LEye"], ["LEye", "LEar"] ]
載入圖片
img = cv.imread("image.jpg")顯示圖片
plt.imshow(img)
調(diào)整圖片顏色
plt.imshow(cv.cvtColor(img,cv.COLOR_BGR2RGB))
姿態(tài)識(shí)別
def pose_estimation(frame):
frameWidth=frame.shape[1]
frameHeight=frame.shape[0]
net.setInput(cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))
out = net.forward()
out = out[:, :19, :, :] # MobileNet output [1, 57, -1, -1], we only need the first 19 elements
assert(len(BODY_PARTS) == out.shape[1])
points = []
for i in range(len(BODY_PARTS)):
# Slice heatmap of corresponging body's part.
heatMap = out[0, i, :, :]
# Originally, we try to find all the local maximums. To simplify a sample
# we just find a global one. However only a single pose at the same time
# could be detected this way.
_, conf, _, point = cv.minMaxLoc(heatMap)
x = (frameWidth * point[0]) / out.shape[3]
y = (frameHeight * point[1]) / out.shape[2]
# Add a point if it's confidence is higher than threshold.
points.append((int(x), int(y)) if conf > thr else None)
for pair in POSE_PAIRS:
partFrom = pair[0]
partTo = pair[1]
assert(partFrom in BODY_PARTS)
assert(partTo in BODY_PARTS)
idFrom = BODY_PARTS[partFrom]
idTo = BODY_PARTS[partTo]
# 繪制線條
if points[idFrom] and points[idTo]:
cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
t, _ = net.getPerfProfile()
freq = cv.getTickFrequency() / 1000
cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
return frame
# 處理圖片
estimated_image=pose_estimation(img)
# 顯示圖片
plt.imshow(cv.cvtColor(estimated_image,cv.COLOR_BGR2RGB))
視頻識(shí)別
Tip：與上面圖片識(shí)別代碼是銜接的
視頻來自互聯(lián)網(wǎng)，侵刪
cap = cv.VideoCapture('testvideo.mp4')
cap.set(3,800)
cap.set(4,800)
if not cap.isOpened():
cap=cv.VideoCapture(0)
raise IOError("Cannot open vide")
while cv.waitKey(1) < 0:
hasFrame,frame=cap.read()
if not hasFrame:
cv.waitKey()
break
frameWidth=frame.shape[1]
frameHeight=frame.shape[0]
net.setInput(cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))
out = net.forward()
out = out[:, :19, :, :] # MobileNet output [1, 57, -1, -1], we only need the first 19 elements
assert(len(BODY_PARTS) == out.shape[1])
points = []
for i in range(len(BODY_PARTS)):
# Slice heatmap of corresponging body's part.
heatMap = out[0, i, :, :]
# Originally, we try to find all the local maximums. To simplify a sample
# we just find a global one. However only a single pose at the same time
# could be detected this way.
_, conf, _, point = cv.minMaxLoc(heatMap)
x = (frameWidth * point[0]) / out.shape[3]
y = (frameHeight * point[1]) / out.shape[2]
# Add a point if it's confidence is higher than threshold.
points.append((int(x), int(y)) if conf > thr else None)
for pair in POSE_PAIRS:
partFrom = pair[0]
partTo = pair[1]
assert(partFrom in BODY_PARTS)
assert(partTo in BODY_PARTS)
idFrom = BODY_PARTS[partFrom]
idTo = BODY_PARTS[partTo]
if points[idFrom] and points[idTo]:
cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
t, _ = net.getPerfProfile()
freq = cv.getTickFrequency() / 1000
cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv.imshow('Video Tutorial',frame)實(shí)時(shí)攝像頭識(shí)別
Tip：與上面圖片識(shí)別代碼是銜接的
cap = cv.VideoCapture(0)
cap.set(cv.CAP_PROP_FPS,10)
cap.set(3,800)
cap.set(4,800)
if not cap.isOpened():
cap=cv.VideoCapture(0)
raise IOError("Cannot open vide")
while cv.waitKey(1) < 0:
hasFrame,frame=cap.read()
if not hasFrame:
cv.waitKey()
break
frameWidth=frame.shape[1]
frameHeight=frame.shape[0]
net.setInput(cv.dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (127.5, 127.5, 127.5), swapRB=True, crop=False))
out = net.forward()
out = out[:, :19, :, :] # MobileNet output [1, 57, -1, -1], we only need the first 19 elements
assert(len(BODY_PARTS) == out.shape[1])
points = []
for i in range(len(BODY_PARTS)):
# Slice heatmap of corresponging body's part.
heatMap = out[0, i, :, :]
# Originally, we try to find all the local maximums. To simplify a sample
# we just find a global one. However only a single pose at the same time
# could be detected this way.
_, conf, _, point = cv.minMaxLoc(heatMap)
x = (frameWidth * point[0]) / out.shape[3]
y = (frameHeight * point[1]) / out.shape[2]
# Add a point if it's confidence is higher than threshold.
points.append((int(x), int(y)) if conf > thr else None)
for pair in POSE_PAIRS:
partFrom = pair[0]
partTo = pair[1]
assert(partFrom in BODY_PARTS)
assert(partTo in BODY_PARTS)
idFrom = BODY_PARTS[partFrom]
idTo = BODY_PARTS[partTo]
if points[idFrom] and points[idTo]:
cv.line(frame, points[idFrom], points[idTo], (0, 255, 0), 3)
cv.ellipse(frame, points[idFrom], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
cv.ellipse(frame, points[idTo], (3, 3), 0, 0, 360, (0, 0, 255), cv.FILLED)
t, _ = net.getPerfProfile()
freq = cv.getTickFrequency() / 1000
cv.putText(frame, '%.2fms' % (t / freq), (10, 20), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
cv.imshow('Video Tutorial',frame)參考
DeepLearning_by_PhDScholar
Human Pose Estimation using opencv | python | OpenPose | stepwise implementation for beginners
https://www.youtube.com/watch?v=9jQGsUidKHs
到此這篇關(guān)于Python OpenCV實(shí)現(xiàn)姿態(tài)識(shí)別的文章就介紹到這了,更多相關(guān)Python姿態(tài)識(shí)別內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！
相關(guān)文章
Python中的文件和目錄操作實(shí)現(xiàn)代碼
對(duì)于文件和目錄的處理，雖然可以通過操作系統(tǒng)命令來完成，但是Python語言為了便于開發(fā)人員以編程的方式處理相關(guān)工作，提供了許多處理文件和目錄的內(nèi)置函數(shù)。重要的是，這些函數(shù)無論是在Unix、Windows還是Macintosh平臺(tái)上，它們的使用方式是完全一致的。2011-03-03
很多朋友一直使用pip list來查詢,但如果想知道單個(gè),應(yīng)該怎么使用呢,在Python中,可以使用多種方法來查看已安裝包的版本號(hào),本文給大家詳細(xì)介紹了Python查看已安裝包的版本號(hào)的多種方法,需要的朋友可以參考下2024-02-02
Numpy 多維數(shù)據(jù)數(shù)組的實(shí)現(xiàn)
這篇文章主要介紹了Numpy 多維數(shù)據(jù)數(shù)組的實(shí)現(xiàn)，文中通過示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值，需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2020-06-06
本文主要介紹了Python中l(wèi)oguru日志庫(kù)的使用，文中通過示例代碼介紹的非常詳細(xì)，對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值，需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2023-03-03
PIL庫(kù)支持圖像存儲(chǔ)、顯示和處理,它能夠處理幾乎所有圖片格式,可以完成對(duì)圖像的縮放、剪裁、疊加以及向圖像添加線條、圖像和文字等操作,下面這篇文章主要給大家介紹了關(guān)于Python使用PIL.image保存圖片的相關(guān)資料,需要的朋友可以參考下2022-12-12
在本篇內(nèi)容中我們給大家整理了關(guān)于python安裝Scrapy框架的圖文詳細(xì)步驟，需要的朋友們跟著學(xué)習(xí)下。2019-05-05
防截圖是指一組技術(shù)或方法,用于防止他人在未經(jīng)允許的情況下在屏幕上截取或記錄圖像,這是一個(gè)重要的安全措施,它可以防止竊取敏感信息或監(jiān)視個(gè)人信息,本文為大家整理了6種python可以防截圖的方法,需要的可以參考下2023-10-10
這篇文章主要介紹了Python寫的英文字符大小寫轉(zhuǎn)換代碼示例,本文例子相對(duì)簡(jiǎn)單,本文直接給出代碼實(shí)例,需要的朋友可以參考下2015-03-03
簡(jiǎn)單分析python的類變量、實(shí)例變量
在本篇文章中小編給大家整理的是關(guān)于python類變量、實(shí)例變量的知識(shí)點(diǎn)內(nèi)容，有需要的朋友們可以學(xué)習(xí)下。2019-08-08
這篇文章主要介紹了Python OS模塊,結(jié)合實(shí)例形式總結(jié)分析了Python使用OS解析文件路徑、判斷文件、目錄等相關(guān)操作技巧,需要的朋友可以參考下2019-04-04