使用OpenCV进行手部移动
为了执行视频追踪，算法分析顺序视频帧并输出帧之间的目标移动。有各种各样的算法，每个算法都有优点和缺点。考虑到预期用途在选择使用哪种算法时很重要。视觉跟踪系统有两个主要组件：目标表示和本地化，以及过滤和数据关联。
视频跟踪是使用摄像头随着时间的推移定位移动对象（或多个对象）的过程。它有多种用途，其中一些是：人机交互，安全和监视，视频通信和压缩，增强现实，流量控制，医学成像和视频编辑。
这是您需要重现它的所有Python代码：
import numpy as np
import cv2
import argparse
from collections import deque
cap=cv2.VideoCapture(0)
pts = deque(maxlen=64)
Lower_green = np.array([110,50,50])
Upper_green = np.array([130,255,255])
while True:
ret, img=cap.read()
hsv=cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
kernel=np.ones((5,5),np.uint8)
mask=cv2.inRange(hsv,Lower_green,Upper_green)
mask = cv2.erode(mask, kernel, iterations=2)
mask=cv2.morphologyEx(mask,cv2.MORPH_OPEN,kernel)
#mask=cv2.morphologyEx(mask,cv2.MORPH_CLOSE,kernel)
mask = cv2.dilate(mask, kernel, iterations=1)
res=cv2.bitwise_and(img,img,mask=mask)
cnts,heir=cv2.findContours(mask.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)[-2:]
center = None
if len(cnts) > 0:
c = max(cnts, key=cv2.contourArea)
((x, y), radius) = cv2.minEnclosingCircle(c)
M = cv2.moments(c)
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
if radius > 5:
cv2.circle(img, (int(x), int(y)), int(radius),(0, 255, 255), 2)
cv2.circle(img, center, 5, (0, 0, 255), -1)
pts.appendleft(center)
for i in xrange (1,len(pts)):
if pts[i-1]is None or pts[i] is None:
continue
thick = int(np.sqrt(len(pts) / float(i + 1)) * 2.5)
cv2.line(img, pts[i-1],pts[i],(0,0,225),thick)
cv2.imshow("Frame", img)
cv2.imshow("mask",mask)
cv2.imshow("res",res)
k=cv2.waitKey(30) & 0xFF
if k==32:
break
# cleanup the camera and close any open windows
cap.release()
cv2.destroyAllWindows()
54行代码。很简单!你需要在你的电脑上安装OpenCV。
嗜睡检测OpenCV
依赖
CV2
immutils
DLIB
SciPy
算法
每只眼睛由6个（x，y）坐标表示，从眼睛的左角开始（就好像你在看人一样），然后在眼睛周围顺时针工作。
条件
它会检查20个连续帧，如果眼睛纵横比小于0.25，则会生成警报。
关系
综合起来
Python代码：
from scipy.spatial import distance
from imutils import face_utils
import imutils
import dlib
import cv2
def eye_aspect_ratio(eye):
A = distance.euclidean(eye[1], eye[5])
B = distance.euclidean(eye[2], eye[4])
C = distance.euclidean(eye[0], eye[3])
ear = (A + B) / (2.0 * C)
return ear
thresh = 0.25
frame_check = 20
detect = dlib.get_frontal_face_detector()
predict = dlib.shape_predictor("C:\Users\akshaybahadur21\Documents\GitHub\Drowsiness_Detection|\shape_predictor_68_face_landmarks.dat")# Dat file is the crux of the code
(lStart, lEnd) = face_utils.FACIAL_LANDMARKS_IDXS["left_eye"]
(rStart, rEnd) = face_utils.FACIAL_LANDMARKS_IDXS["right_eye"]
cap=cv2.VideoCapture(0)
flag=0
while True:
ret, frame=cap.read()
frame = imutils.resize(frame, width=450)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
subjects = detect(gray, 0)
for subject in subjects:
shape = predict(gray, subject)
shape = face_utils.shape_to_np(shape)#converting to NumPy Array
leftEye = shape[lStart:lEnd]
rightEye = shape[rStart:rEnd]
leftEAR = eye_aspect_ratio(leftEye)
rightEAR = eye_aspect_ratio(rightEye)
ear = (leftEAR + rightEAR) / 2.0
leftEyeHull = cv2.convexHull(leftEye)
rightEyeHull = cv2.convexHull(rightEye)
cv2.drawContours(frame, [leftEyeHull], -1, (0, 255, 0), 1)
cv2.drawContours(frame, [rightEyeHull], -1, (0, 255, 0), 1)
if ear < thresh:
flag += 1
print (flag)
if flag >= frame_check:
cv2.putText(frame, "****************ALERT!****************", (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
cv2.putText(frame, "****************ALERT!****************", (10,325),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2)
#print ("Drowsy")
else:
flag = 0
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
if key == ord("q"):
break
cv2.destroyAllWindows()
cap.stop()
使用Softmax回归的数字识别
此代码可帮助您使用softmax回归对不同的数字进行分类。您可以安装Conda for python，它解决了机器学习的所有依赖关系。
描述
Softmax回归（同义词：多项Logistic，最大熵分类器，或者仅仅是多级Logistic回归）是逻辑回归的泛化，我们可以用于多类分类（假设类是互斥的）。相反，我们在二元分类任务中使用（标准）Logistic回归模型。
Python实现
所使用的数据集是MNIST，其图像大小为28×28，并且这里的计划是使用Logistic回归，浅网络和深度神经网络将数字从0分类到9。
这里最好的部分之一是他使用Numpy编码了三个模型，包括优化，前向传播和后向传播以及一切。
对于Logistic回归：
import numpy as np
import matplotlib.pyplot as plt
def softmax(z):
z -= np.max(z)
sm = (np.exp(z).T / np.sum(np.exp(z), axis=1))
return sm
def initialize(dim1, dim2):
"""
:param dim: size of vector w initilazied with zeros
:return:
"""
w = np.zeros(shape=(dim1, dim2))
b = np.zeros(shape=(10, 1))
return w, b
def propagate(w, b, X, Y):
"""
:param w: weights for w
:param b: bias
:param X: size of data(no of features, no of examples)
:param Y: true label
:return:
"""
m = X.shape[1] # getting no of rows
# Forward Prop
A = softmax((np.dot(w.T, X) + b).T)
cost = (-1 / m) * np.sum(Y * np.log(A))
# backwar prop
dw = (1 / m) * np.dot(X, (A - Y).T)
db = (1 / m) * np.sum(A - Y)
cost = np.squeeze(cost)
grads = {"dw": dw,
"db": db}
return grads, cost
def optimize(w, b, X, Y, num_iters, alpha, print_cost=False):
"""
:param w: weights for w
:param b: bias
:param X: size of data(no of features, no of examples)
:param Y: true label
:param num_iters: number of iterations for gradient
:param alpha:
:return:
"""
costs = []
for i in range(num_iters):
grads, cost = propagate(w, b, X, Y)
dw = grads["dw"]
db = grads["db"]
w = w - alpha * dw
b = b - alpha * db
# Record the costs
if i % 50 == 0:
costs.append(cost)
# Print the cost every 100 training examples
if print_cost and i % 50 == 0:
print("Cost after iteration %i: %f" % (i, cost))
params = {"w": w,
"b": b}
grads = {"dw": dw,
"db": db}
return params, grads, costs
def predict(w, b, X):
"""
:param w:
:param b:
:param X:
:return:
"""
# m = X.shape[1]
# y_pred = np.zeros(shape=(1, m))
# w = w.reshape(X.shape[0], 1)
y_pred = np.argmax(softmax((np.dot(w.T, X) + b).T), axis=0)
return y_pred
def model(X_train, Y_train, Y,X_test,Y_test, num_iters, alpha, print_cost):
"""
:param X_train:
:param Y_train:
:param X_test:
:param Y_test:
:param num_iterations:
:param learning_rate:
:param print_cost:
:return:
"""
w, b = initialize(X_train.shape[0], Y_train.shape[0])
parameters, grads, costs = optimize(w, b, X_train, Y_train, num_iters, alpha, print_cost)
w = parameters["w"]
b = parameters["b"]
y_prediction_train = predict(w, b, X_train)
y_prediction_test = predict(w, b, X_test)
print("Train accuracy: {} %", sum(y_prediction_train == Y) / (float(len(Y))) * 100)
print("Test accuracy: {} %", sum(y_prediction_test == Y_test) / (float(len(Y_test))) * 100)
d = {"costs": costs,
"Y_prediction_test": y_prediction_test,
"Y_prediction_train": y_prediction_train,
"w": w,
"b": b,
"learning_rate": alpha,
"num_iterations": num_iters}
# Plot learning curve (with costs)
#costs = np.squeeze(d['costs'])
#plt.plot(costs)
#plt.ylabel('cost')
#plt.xlabel('iterations (per hundreds)')
#plt.title("Learning rate =" + str(d["learning_rate"]))
#plt.plot()
#plt.show()
#plt.close()
#pri(X_test.T, y_prediction_test)
return d
def pri(X_test, y_prediction_test):
example = X_test[2, :]
print("Prediction for the example is ", y_prediction_test[2])
plt.imshow(np.reshape(example, [28, 28]))
plt.plot()
plt.show()
对于神经网络：
import numpy as np
import matplotlib.pyplot as plt
def softmax(z):
z -= np.max(z)
sm = (np.exp(z).T / np.sum(np.exp(z),axis=1))
return sm
def layers(X, Y):
"""
:param X:
:param Y:
:return:
"""
n_x = X.shape[0]
n_y = Y.shape[0]
return n_x, n_y
def initialize_nn(n_x, n_h, n_y):
"""
:param n_x:
:param n_h:
:param n_y:
:return:
"""
np.random.seed(2)
W1 = np.random.randn(n_h, n_x) * 0.01
b1 = np.random.rand(n_h, 1)
W2 = np.random.rand(n_y, n_h)
b2 = np.random.rand(n_y, 1)
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
def forward_prop(X, parameters):
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
Z1 = np.dot(W1, X) + b1
A1 = np.tanh(Z1)
Z2 = np.dot(W2, A1) + b2
A2 = softmax(Z2.T)
cache = {"Z1": Z1,
"A1": A1,
"Z2": Z2,
"A2": A2}
return A2, cache
def compute_cost(A2, Y, parameters):
m = Y.shape[1]
W1 = parameters['W1']
W2 = parameters['W2']
logprobs = np.multiply(np.log(A2), Y)
cost = - np.sum(logprobs) / m
cost = np.squeeze(cost)
return cost
def back_prop(parameters, cache, X, Y):
m = Y.shape[1]
W1 = parameters['W1']
W2 = parameters['W2']
A1 = cache['A1']
A2 = cache['A2']
dZ2 = A2 - Y
dW2 = (1 / m) * np.dot(dZ2, A1.T)
db2 = (1 / m) * np.sum(dZ2, axis=1, keepdims=True)
dZ1 = np.multiply(np.dot(W2.T, dZ2), 1 - np.square(A1))
dW1 = (1 / m) * np.dot(dZ1, X.T)
db1 = (1 / m) * np.sum(dZ1, axis=1, keepdims=True)
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
def update_params(parameters, grads, alpha):
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
dW1 = grads['dW1']
db1 = grads['db1']
dW2 = grads['dW2']
db2 = grads['db2']
W1 = W1 - alpha * dW1
b1 = b1 - alpha * db1
W2 = W2 - alpha * dW2
b2 = b2 - alpha * db2
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
def model_nn(X, Y,Y_real,test_x,test_y, n_h, num_iters, alpha, print_cost):
np.random.seed(3)
n_x,n_y = layers(X, Y)
parameters = initialize_nn(n_x, n_h, n_y)
W1 = parameters['W1']
b1 = parameters['b1']
W2 = parameters['W2']
b2 = parameters['b2']
costs = []
for i in range(0, num_iters):
A2, cache = forward_prop(X, parameters)
cost = compute_cost(A2, Y, parameters)
grads = back_prop(parameters, cache, X, Y)
if (i > 1500):
alpha1 = 0.95*alpha
parameters = update_params(parameters, grads, alpha1)
else:
parameters = update_params(parameters, grads, alpha)
if i % 100 == 0:
costs.append(cost)
if print_cost and i % 100 == 0:
print("Cost after iteration for %i: %f" % (i, cost))
predictions = predict_nn(parameters, X)
print("Train accuracy: {} %", sum(predictions == Y_real) / (float(len(Y_real))) * 100)
predictions=predict_nn(parameters,test_x)
print("Train accuracy: {} %", sum(predictions == test_y) / (float(len(test_y))) * 100)
#plt.plot(costs)
#plt.ylabel('cost')
#plt.xlabel('iterations (per hundreds)')
#plt.title("Learning rate =" + str(alpha))
#plt.show()
return parameters
def predict_nn(parameters, X):
A2, cache = forward_prop(X, parameters)
predictions = np.argmax(A2, axis=0)
return predictions
最后是深度神经网络：
import numpy as np
import matplotlib.pyplot as plt
def softmax(z):
cache = z
z -= np.max(z)
sm = (np.exp(z).T / np.sum(np.exp(z), axis=1))
return sm, cache
def relu(z):
"""
:param z:
:return:
"""
s = np.maximum(0, z)
cache = z
return s, cache
def softmax_backward(dA, cache):
"""
:param dA:
:param activation_cache:
:return:
"""
z = cache
z -= np.max(z)
s = (np.exp(z).T / np.sum(np.exp(z), axis=1))
dZ = dA * s * (1 - s)
return dZ
def relu_backward(dA, cache):
"""
:param dA:
:param activation_cache:
:return:
"""
Z = cache
dZ = np.array(dA, copy=True) # just converting dz to a correct object.
dZ[Z <= 0] = 0
return dZ
def initialize_parameters_deep(dims):
"""
:param dims:
:return:
"""
np.random.seed(3)
params = {}
L = len(dims)
for l in range(1, L):
params['W' + str(l)] = np.random.randn(dims[l], dims[l - 1]) * 0.01
params['b' + str(l)] = np.zeros((dims[l], 1))
return params
def linear_forward(A, W, b):
"""
:param A:
:param W:
:param b:
:return:
"""
Z = np.dot(W, A) + b
cache = (A, W, b)
return Z, cache
def linear_activation_forward(A_prev, W, b, activation):
"""
:param A_prev:
:param W:
:param b:
:param activation:
:return:
"""
if activation == "softmax":
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = softmax(Z.T)
elif activation == "relu":
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = relu(Z)
cache = (linear_cache, activation_cache)
return A, cache
def L_model_forward(X, params):
"""
:param X:
:param params:
:return:
"""
caches = []
A = X
L = len(params) // 2 # number of layers in the neural network
# Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
for l in range(1, L):
A_prev = A
A, cache = linear_activation_forward(A_prev,
params["W" + str(l)],
params["b" + str(l)],
activation='relu')
caches.append(cache)
A_last, cache = linear_activation_forward(A,
params["W" + str(L)],
params["b" + str(L)],
activation='softmax')
caches.append(cache)
return A_last, caches
def compute_cost(A_last, Y):
"""
:param A_last:
:param Y:
:return:
"""
m = Y.shape[1]
cost = (-1 / m) * np.sum(Y * np.log(A_last))
cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).
return cost
def linear_backward(dZ, cache):
"""
:param dZ:
:param cache:
:return:
"""
A_prev, W, b = cache
m = A_prev.shape[1]
dW = (1. / m) * np.dot(dZ, cache[0].T)
db = (1. / m) * np.sum(dZ, axis=1, keepdims=True)
dA_prev = np.dot(cache[1].T, dZ)
return dA_prev, dW, db
def linear_activation_backward(dA, cache, activation):
"""
:param dA:
:param cache:
:param activation:
:return:
"""
linear_cache, activation_cache = cache
if activation == "relu":
dZ = relu_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
elif activation == "softmax":
dZ = softmax_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
return dA_prev, dW, db
def L_model_backward(A_last, Y, caches):
"""
:param A_last:
:param Y:
:param caches:
:return:
"""
grads = {}
L = len(caches) # the number of layers
m = A_last.shape[1]
Y = Y.reshape(A_last.shape) # after this line, Y is the same shape as A_last
dA_last = - (np.divide(Y, A_last) - np.divide(1 - Y, 1 - A_last))
current_cache = caches[-1]
grads["dA" + str(L)], grads["dW" + str(L)], grads["db" + str(L)] = linear_activation_backward(dA_last,
current_cache,
activation="softmax")
for l in reversed(range(L - 1)):
current_cache = caches[l]
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l + 2)], current_cache,
activation="relu")
grads["dA" + str(l + 1)] = dA_prev_temp
grads["dW" + str(l + 1)] = dW_temp
grads["db" + str(l + 1)] = db_temp
return grads
def update_params(params, grads, alpha):
"""
:param params:
:param grads:
:param alpha:
:return:
"""
L = len(params) // 2 # number of layers in the neural network
for l in range(L):
params["W" + str(l + 1)] = params["W" + str(l + 1)] - alpha * grads["dW" + str(l + 1)]
params["b" + str(l + 1)] = params["b" + str(l + 1)] - alpha * grads["db" + str(l + 1)]
return params
def model_DL( X, Y, Y_real, test_x, test_y, layers_dims, alpha, num_iterations, print_cost): # lr was 0.009
"""
Implements a L-layer neural network: [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID.
Arguments:
X -- data, numpy array of shape (number of examples, num_px * num_px * 3)
Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
layers_dims -- list containing the input size and each layer size, of length (number of layers + 1).
alpha -- learning rate of the gradient descent update rule
num_iterations -- number of iterations of the optimization loop
print_cost -- if True, it prints the cost every 100 steps
Returns:
params -- params learnt by the model. They can then be used to predict.
"""
np.random.seed(1)
costs = [] # keep track of cost
params = initialize_parameters_deep(layers_dims)
for i in range(0, num_iterations):
A_last, caches = L_model_forward(X, params)
cost = compute_cost(A_last, Y)
grads = L_model_backward(A_last, Y, caches)
if (i > 800 and i<1700):
alpha1 = 0.80 * alpha
params = update_params(params, grads, alpha1)
elif(i>=1700):
alpha1 = 0.50 * alpha
params = update_params(params, grads, alpha1)
else:
params = update_params(params, grads, alpha)
if print_cost and i % 100 == 0:
print("Cost after iteration %i: %f" % (i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
predictions = predict(params, X)
print("Train accuracy: {} %", sum(predictions == Y_real) / (float(len(Y_real))) * 100)
predictions = predict(params, test_x)
print("Test accuracy: {} %", sum(predictions == test_y) / (float(len(test_y))) * 100)
#plt.plot(np.squeeze(costs))
#plt.ylabel('cost')
#plt.xlabel('iterations (per tens)')
#plt.title("Learning rate =" + str(alpha))
#plt.show()
return params
def predict(parameters, X):
A_last, cache = L_model_forward(X, parameters)
predictions = np.argmax(A_last, axis=0)
return predictions
执行通过网络摄像头写入
要运行代码，请键入 python Dig-Rec.py