shen/Intelligent-Elderly-Care
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refine function

Browse Source
This commit is contained in:
Tang1705
2020-07-06 17:05:50 +08:00
parent 80bb3c7f70
commit 1a089c878b
6 changed files with 251 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

BIN
Class.zip Normal file
View File

Binary file not shown.

49
Class/collect_data/face_reco_from_camera.py
View File

@@ -8,6 +8,7 @@ import os
import time
from PIL import Image, ImageDraw, ImageFont
start_time = 0
# 1. Dlib 正向人脸检测器
# detector = dlib.get_frontal_face_detector()
@@ -75,11 +76,9 @@ class Face_Recognizer:
def return_euclidean_distance(feature_1, feature_2):
feature_1 = np.array(feature_1)
feature_2 = np.array(feature_2)
dist = np.sqrt(np.sum(np.square(feature_1 - feature_2)))
dist = np.sqrt(np.sum((feature_1 - feature_2) ** 2))
return dist
# TODO th
# 更新 FPS
def update_fps(self):
now = time.time()
@@ -111,7 +110,7 @@ class Face_Recognizer:
# TODO 数据库 ID
# Default known name: person_1, person_2, person_3
self.name_known_list[0] = '唐麒'.encode('utf-8').decode()
# self.name_known_list[1] ='李四'.encode('utf-8').decode()
self.name_known_list[1] = '段海燕'.encode('utf-8').decode()
# self.name_known_list[2] ='xx'.encode('utf-8').decode()
# self.name_known_list[3] ='xx'.encode('utf-8').decode()
# self.name_known_list[4] ='xx'.encode('utf-8').decode()
@@ -122,6 +121,7 @@ class Face_Recognizer:
if self.get_face_database():
while stream.isOpened():
flag, img_rd = stream.read()
img_with_name = img_rd
kk = cv2.waitKey(1)
# 按下 q 键退出
if kk == ord('q'):
@@ -164,7 +164,8 @@ class Face_Recognizer:
# greater than the minimum confidence
if confidence < 0.5:
continue
print("##### camera person", k + 1, "#####")
self.faces_cnt+=1
# print("##### camera person", k + 1, "#####")
# 让人名跟随在矩形框的上方
# 确定人名的位置坐标
# 先默认所有人不认识，是 unknown
@@ -175,30 +176,31 @@ class Face_Recognizer:
box = faces[0, 0, k, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
self.pos_camera_list.append(tuple(
[int(startX+5), int(startY - 30)]))
[int(startX + 5), int(startY - 30)]))
# 5. 对于某张人脸，遍历所有存储的人脸特征
e_distance_list = []
for i in range(len(self.features_known_list)):
# 如果 person_X 数据不为空
if str(self.features_known_list[i][0]) != '0.0':
print("with person", str(i + 1), "the e distance: ", end='')
# print("with person", str(i + 1), "the e distance: ", end='')
e_distance_tmp = self.return_euclidean_distance(self.features_camera_list[k],
self.features_known_list[i])
print(e_distance_tmp)
# print(e_distance_tmp)
e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
e_distance_list.append(999999999)
# 6. 寻找出最小的欧式距离匹配
similar_person_num = e_distance_list.index(min(e_distance_list))
print("Minimum e distance with person", self.name_known_list[similar_person_num])
# print("Minimum e distance with person", self.name_known_list[similar_person_num])
if min(e_distance_list) < 0.4:
if min(e_distance_list) < 1:
self.name_camera_list[k] = self.name_known_list[similar_person_num]
print("May be person " + str(self.name_known_list[similar_person_num]))
# print("May be person " + str(self.name_known_list[similar_person_num]))
else:
print("Unknown person")
pass
# print("Unknown person")
# 矩形框
for kk, d in enumerate(faces):
@@ -207,23 +209,24 @@ class Face_Recognizer:
(0, 255, 0), 2)
cv2.rectangle(img_rd, tuple([startX, startY - 35]), tuple([endX, startY]),
(0, 255, 0), cv2.FILLED)
print('\n')
self.faces_cnt = len(faces)
# 7. 在这里更改显示的人名
self.modify_name_camera_list()
# 8. 写名字
# self.draw_name(img_rd)
img_with_name = self.draw_name(img_rd)
# print('\n')
# self.faces_cnt = faces.shape[2]
# if len(self.name_camera_list) > 0:
# 7. 在这里更改显示的人名
self.modify_name_camera_list()
# 8. 写名字
# self.draw_name(img_rd)
img_with_name = self.draw_name(img_rd)
else:
img_with_name = img_rd
print("Faces in camera now:", self.name_camera_list, "\n")
# print("Faces in camera now:", self.name_camera_list, "\n")
cv2.imshow("camera", img_with_name)
if len(img_with_name):
cv2.imshow("camera", img_with_name)
# 9. 更新 FPS / Update stream FPS
self.update_fps()
# self.update_fps()
# OpenCV 调用摄像头并进行 process
def run(self):

50
Class/collect_data/get_faces_from_camera.py
View File

@@ -7,7 +7,15 @@ import cv2
import os
import shutil # 读写文件
import time
import face_recognition
from PIL import ImageDraw, ImageFont
from PIL import Image
action_list = ['look_ahead', 'look_left', 'look_right', 'rise_head', 'bow_head', 'blink', 'open_mouth', 'smile', 'over']
action_map = {'look_ahead': '请看前方', 'blink': '请眨眼', 'open_mouth': '请张嘴',
'smile': '请笑一笑', 'rise_head': '请抬头',
'bow_head': '请低头', 'look_left': '请看左边',
'look_right': '请看右边', 'over': '录入完成'}
# Dlib 正向人脸检测器
# detector = dlib.get_frontal_face_detector()
@@ -30,6 +38,8 @@ class Face_Register:
self.save_flag = 1
# 之后用来检查是否先按 'n' 再按 's'，即先新建文件夹再保存
self.press_n_flag = 0
# 之后用来提示动作的计数器
self.index = 0
self.frame_time = 0
self.frame_start_time = 0
@@ -76,6 +86,8 @@ class Face_Register:
# 生成的 cv2 window 上面添加说明文字
def draw_note(self, img_rd):
# 添加说明
# cv2.putText(img_rd, action_map[action_list[index]].encode('utf-8').decode(), (20, 250), self.font, 1,
# (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Face Register", (20, 40), self.font, 1, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "FPS: " + str(self.fps.__round__(2)), (20, 100), self.font, 0.8, (0, 255, 0), 1,
cv2.LINE_AA)
@@ -84,6 +96,18 @@ class Face_Register:
cv2.putText(img_rd, "S: Save current face", (20, 400), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
cv2.putText(img_rd, "Q: Quit", (20, 450), self.font, 0.8, (255, 255, 255), 1, cv2.LINE_AA)
font = ImageFont.truetype("simsun.ttc", 30, index=1)
img_rd = Image.fromarray(cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img_rd)
if self.index <= 7:
draw.text((20, 230), text=action_map[action_list[self.index]].encode('utf-8').decode(), font=font,
fill=(0, 255, 0))
else:
draw.text((20, 230), text=action_map[action_list[8]].encode('utf-8').decode(), font=font,
fill=(0, 255, 0))
img_rd = cv2.cvtColor(np.array(img_rd), cv2.COLOR_RGB2BGR)
return img_rd
# 获取人脸
def process(self, stream):
# 1. 新建储存人脸图像文件目录
@@ -96,6 +120,7 @@ class Face_Register:
self.check_existing_faces_cnt()
while stream.isOpened():
self.faces_cnt = 0
flag, img_rd = stream.read() # Get camera video stream
kk = cv2.waitKey(1)
@@ -115,6 +140,7 @@ class Face_Register:
print("新建的人脸文件夹 / Create folders: ", current_face_dir)
self.ss_cnt = 0 # 将人脸计数器清零
self.index = 0
self.press_n_flag = 1 # 已经按下 'n'
# 5. 检测到人脸
@@ -129,6 +155,8 @@ class Face_Register:
if confidence < 0.5:
continue
self.faces_cnt += 1
# compute the (x, y)-coordinates of the bounding box for the
# object
box = faces[0, 0, i, 3:7] * np.array([w, h, w, h])
@@ -165,18 +193,20 @@ class Face_Register:
# 检查有没有先按'n'新建文件夹
if self.press_n_flag:
self.ss_cnt += 1
for ii in range(height * 2):
for jj in range(width * 2):
img_blank[ii][jj] = img_rd[startY - hh + ii][startX - ww + jj]
cv2.imwrite(current_face_dir + "/img_face_" + str(self.ss_cnt) + ".jpg", img_blank)
print("写入本地 / Save into：",
str(current_face_dir) + "/img_face_" + str(self.ss_cnt) + ".jpg")
if self.index<=7:
for ii in range(height * 2):
for jj in range(width * 2):
img_blank[ii][jj] = img_rd[startY - hh + ii][startX - ww + jj]
cv2.imwrite(current_face_dir + "/img_face_" + str(self.ss_cnt) + ".jpg", img_blank)
print("写入本地 / Save into：",
str(current_face_dir) + "/img_face_" + str(self.ss_cnt) + ".jpg")
self.index += 1
else:
print("请先按 'N' 来建文件夹, 按 'S' / Please press 'N' and press 'S'")
self.faces_cnt = len(faces)
# self.faces_cnt = len(faces)
# 9. 生成的窗口添加说明文字
self.draw_note(img_rd)
img_rd = self.draw_note(img_rd)
# 10. 按下 'q' 键退出
if kk == ord('q'):
@@ -200,4 +230,4 @@ def main():
if __name__ == '__main__':
main()
main()

105
Class/detection/algorithm_fall.py
View File

@@ -6,44 +6,45 @@ import numpy as np
import statistics
import queue
import math
from PIL import ImageDraw, ImageFont
from PIL import Image
def fall_detect(cnts, defined_min_area, frame, prevX, prevY, xList, yList, centerV, alert):
for c in cnts:
#exclusion
# exclusion
if cv2.contourArea(c) < defined_min_area:
continue
# outer bounding box
(x_b, y_b, w_b, h_b) = cv2.boundingRect(c)
cv2.rectangle(frame, (x_b, y_b), (x_b + w_b, y_b + h_b), (0, 255, 255), 2) # 黄色矩形
cv2.rectangle(frame, (x_b, y_b), (x_b + w_b, y_b + h_b), (0, 255, 255), 2) # 黄色矩形
#rotating bounding box
rect = cv2.minAreaRect(c) # 得到最小外接矩形的（中心(x,y), (宽,高), 旋转角度）
box = cv2.boxPoints(rect) # 获取最小外接矩形的4个顶点坐标
# rotating bounding box
rect = cv2.minAreaRect(c) # 得到最小外接矩形的（中心(x,y), (宽,高), 旋转角度）
box = cv2.boxPoints(rect) # 获取最小外接矩形的4个顶点坐标
box = np.int0(box)
cv2.drawContours(frame,[box],0,(0,0,255),2)
cv2.drawContours(frame, [box], 0, (0, 0, 255), 2)
#averaging line
rows,cols = frame.shape[:2]
[vx,vy,x,y] = cv2.fitLine(c, cv2.DIST_L2, 0, 0.01, 0.01)
lefty = (-x * vy/vx) + y
righty =((cols-x) * vy/vx)+y
cv2.line(frame,(cols-1,righty),(0,lefty),(255,0,0),2)
# averaging line
rows, cols = frame.shape[:2]
[vx, vy, x, y] = cv2.fitLine(c, cv2.DIST_L2, 0, 0.01, 0.01)
lefty = (-x * vy / vx) + y
righty = ((cols - x) * vy / vx) + y
cv2.line(frame, (cols - 1, righty), (0, lefty), (255, 0, 0), 2)
#ellipse
# ellipse
elps = cv2.fitEllipse(c)
(x, y), (MA, ma), angle = cv2.fitEllipse(c)
cv2.ellipse(frame, elps,(255,0,0),3) #red
cv2.ellipse(frame, elps, (255, 0, 0), 3) # red
#Aspect Ratio
AR = MA/ma
# Aspect Ratio
AR = MA / ma
#Center Speed - acceleration
# Center Speed - acceleration
prevX = 0.0
prevY = 0.0
centerSpeed =0
centerSpeed = 0
if xList.full():
prevX = statistics.median(list(xList.queue))
prevY = statistics.median(list(yList.queue))
@@ -54,49 +55,57 @@ def fall_detect(cnts, defined_min_area, frame, prevX, prevY, xList, yList, cente
yList.put(elps[0][1])
X = statistics.median(list(xList.queue))
Y = statistics.median(list(yList.queue))
if xList.full():
dx = abs(prevX-X)
dy = abs(prevY-Y)
centerV = math.sqrt(dx**2+dy**2)
# calculate probabilities for the 4 features
pAngle = (abs(angle-90)-50)/10
pAngle = 1 / (math.exp(pAngle)+1)
pAR = 10*AR - 5
pAR = 1 / (math.exp(pAR) + 1)
ACS = centerV - 9
ACS = 1 / (math.exp(ACS) + 1)
if xList.full():
dx = abs(prevX - X)
dy = abs(prevY - Y)
centerV = math.sqrt(dx ** 2 + dy ** 2)
# calculate probabilities for the 4 features
pAngle = (abs(angle - 90) - 50) / 10
pAngle = 1 / (math.exp(pAngle) + 1)
pAR = 10 * AR - 5
pAR = 1 / (math.exp(pAR) + 1)
ACS = centerV - 9
try:
ACS = 1 / (math.exp(ACS) + 1)
except:
ACS = 1 / (float('inf') + 1)
# print("pAngle : ", pAngle)
# print("pAR : ", pAR)
# print("ACS : ", ACS)
#confidence
# confidence
P_FALL = pAngle * pAR * ACS + 0.5
# print("P_FALL1 : ", P_FALL)
P_FALL = 1/ (math.exp(-(P_FALL-0.65)*10)+1)
P_FALL = 1 / (math.exp(-(P_FALL - 0.65) * 10) + 1)
# print("P_FALL2: ", P_FALL)
#status display
cv2.putText(frame, "Status : ", (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
cv2.putText(frame, "Fall Confidence: {0:.2f} ".format(P_FALL), (10,50),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 128, 255), 2)
# status display
# cv2.putText(frame, "Status : ", (10, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
# cv2.putText(frame, "Fall Confidence: {0:.2f} ".format(P_FALL), (10, 50), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
# (0, 128, 255), 2)
# cv2.putText(frame, "Angle: {0:.2f}".format(angle), (10, 220),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
# cv2.putText(frame, "AR: {0:.2f}".format(AR), (10, 237),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
# cv2.putText(frame, "Center Speed: {0:.2f}".format(centerV), (10, 256),cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 2)
#fall
# fall
if P_FALL > 0.88:
if alert >= 8:
print("fall")
cv2.putText(frame, " Fall Detected", (82, 20),cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
if alert >3:
# print("fall")
font = ImageFont.truetype("simsun.ttc", 30, index=1)
img_rd = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img_rd)
draw.text((10, 10), text="Fall Detected", font=font,
fill=(255, 0, 0))
frame = cv2.cvtColor(np.array(img_rd), cv2.COLOR_RGB2BGR)
# cv2.imwrite("report.jpg", frame)
# send_alert.SendMail("report.jpg")
alert = alert + 1
else:
alert = alert + 1
return alert
return frame,alert

110
Class/detection/check_smile_from_camera.py Normal file
View File

@@ -0,0 +1,110 @@
from sklearn.externals import joblib
import ML_ways_sklearn
import dlib
import numpy as np
import cv2
detector = dlib.get_frontal_face_detector()
# OpenCV DNN face detector
# detector = cv2.dnn.readNetFromCaffe("data/data_opencv/deploy.prototxt.txt",
# "data/data_opencv/res10_300x300_ssd_iter_140000.caffemodel")
predictor = dlib.shape_predictor('data/data_dlib_model/shape_predictor_68_face_landmarks.dat')
# OpenCV 调用摄像头
cap = cv2.VideoCapture(0)
# 设置视频参数
cap.set(3, 480)
def get_features(img_rd):
# 输入: img_rd: 图像文件
# 输出: positions_lip_arr: feature point 49 to feature point 68, 20 feature points / 40D in all
# 取灰度
img_gray = cv2.cvtColor(img_rd, cv2.COLOR_RGB2GRAY)
# 计算68点坐标
positions_68_arr = []
faces = detector(img_gray, 0)
landmarks = np.matrix([[p.x, p.y] for p in predictor(img_rd, faces[0]).parts()])
for idx, point in enumerate(landmarks):
# 68点的坐标
pos = (point[0, 0], point[0, 1])
positions_68_arr.append(pos)
positions_lip_arr = []
# 将点 49-68 写入 CSV
# 即 positions_68_arr[48]-positions_68_arr[67]
for i in range(48, 68):
positions_lip_arr.append(positions_68_arr[i][0])
positions_lip_arr.append(positions_68_arr[i][1])
return positions_lip_arr
while cap.isOpened():
# 480 height * 640 width
flag, img_rd = cap.read()
kk = cv2.waitKey(1)
img_gray = cv2.cvtColor(img_rd, cv2.COLOR_RGB2GRAY)
# 人脸数 faces
faces = detector(img_gray, 0)
# 检测到人脸
if len(faces) != 0:
# 提取单张40维度特征
positions_lip_test = get_features(img_rd)
# path of models
path_models = "data/data_models/"
# ######### LR ###########
LR = joblib.load(path_models+"model_LR.m")
ss_LR = ML_ways_sklearn.model_LR()
X_test_LR = ss_LR.transform([positions_lip_test])
y_predict_LR = str(LR.predict(X_test_LR)[0]).replace('0', "no smile").replace('1', "with smile")
print("LR:", y_predict_LR)
# ######### LSVC ###########
LSVC = joblib.load(path_models+"model_LSVC.m")
ss_LSVC = ML_ways_sklearn.model_LSVC()
X_test_LSVC = ss_LSVC.transform([positions_lip_test])
y_predict_LSVC = str(LSVC.predict(X_test_LSVC)[0]).replace('0', "no smile").replace('1', "with smile")
print("LSVC:", y_predict_LSVC)
# ######### MLPC ###########
MLPC = joblib.load(path_models+"model_MLPC.m")
ss_MLPC = ML_ways_sklearn.model_MLPC()
X_test_MLPC = ss_MLPC.transform([positions_lip_test])
y_predict_MLPC = str(MLPC.predict(X_test_MLPC)[0]).replace('0', "no smile").replace('1', "with smile")
print("MLPC:", y_predict_MLPC)
# ######### SGDC ###########
SGDC = joblib.load(path_models+"model_SGDC.m")
ss_SGDC = ML_ways_sklearn.model_SGDC()
X_test_SGDC = ss_SGDC.transform([positions_lip_test])
y_predict_SGDC = str(SGDC.predict(X_test_SGDC)[0]).replace('0', "no smile").replace('1', "with smile")
print("SGDC:", y_predict_SGDC)
print('\n')
# 按下 'q' 键退出
if kk == ord('q'):
break
# 窗口显示
# cv2.namedWindow("camera", 0) # 如果需要摄像头窗口大小可调
cv2.imshow("camera", img_rd)
# 释放摄像头
cap.release()
# 删除建立的窗口
cv2.destroyAllWindows()

26
Class/detection/fall_detection.py
View File

@@ -9,6 +9,9 @@ from sys import platform
import argparse
import numpy as np
from PIL import ImageDraw, ImageFont
from PIL import Image
from imutils.video import VideoStream
import datetime
import imutils
@@ -39,7 +42,7 @@ try:
raise e
# cap = cv2.VideoCapture(0)
cap = cv2.VideoCapture("demo1.mp4")
cap = cv2.VideoCapture("test4.mp4")
_, frame = cap.read()
cv2.imwrite('fall_detection.jpg', frame)
@@ -113,6 +116,7 @@ try:
imageToProcess = cv2.imread(args[0].image_path)
datum.cvInputData = imageToProcess
opWrapper.emplaceAndPop([datum])
img_rd = datum.cvOutputData
# Display Image
# print("Body keypoints: \n" + str(datum.poseKeypoints))
@@ -147,7 +151,7 @@ try:
np.array(height0))):
couter += 1
# print("alarm by v and a")
elif (width > height and (x[8] != 0 or x[9] != 0 or x[12] != 0)):
elif (width > height and (x[8] != 0 or x[9] != 0 or x[12] != 0) and v < 0.41):
couter += 1
# print("alarm by w and h")
else:
@@ -157,8 +161,15 @@ try:
couter = 0
error = 0
if couter > 2:
print("alarm")
if couter > 3:
font = ImageFont.truetype("simsun.ttc", 30, index=1)
img_rd = Image.fromarray(cv2.cvtColor(datum.cvOutputData, cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img_rd)
draw.text((10, 10), text="Fall Detected", font=font,
fill=(255, 0, 0))
img_rd = cv2.cvtColor(np.array(img_rd), cv2.COLOR_RGB2BGR)
# print("fall")
# update variables
frame_start_time = now
@@ -183,8 +194,8 @@ try:
cnts = frame_process.get_contours(firstFrame, gray)
defined_min_area = 3000
alert = algorithm_fall.fall_detect(cnts, defined_min_area, frame, prevX, prevY, xList, yList,
centerV, alert)
frame, alert = algorithm_fall.fall_detect(cnts, defined_min_area, frame, prevX, prevY, xList, yList,
centerV, alert)
# cv2.putText(frame, datetime.datetime.now().strftime("%A %d %B %Y %I:%M:%S%p"),
# (10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.35, (255, 255, 255), 1)
@@ -192,9 +203,8 @@ try:
cv2.imshow("OpenPose 1.6.0 - Tutorial Python API", frame)
continue
cv2.imshow("OpenPose 1.6.0 - Tutorial Python API", datum.cvOutputData)
cv2.imshow("OpenPose 1.6.0 - Tutorial Python API", img_rd)
cap.release()
cv2.destroyAllWindows()
except Exception as e:
print(e)
sys.exit(-1)