def runIt():
print("track_eye")
cam5procs.logLine("track_eye")
clock = time.clock()
framecount = 0
ledState = 0
ledCounter = 0
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
face_cascade = image.HaarCascade("frontalface", stages=25)
eyes_cascade = image.HaarCascade("eye", stages=24)
#print(face_cascade,eyes_cascade)
while not cam5procs.receive_packet():
ledCounter += 1
if ((ledCounter % 5) == 0):
if (ledState == 0):
ledState = 1
cam5procs.ledShowColour([0, 0, 255])
else:
ledState = 0
cam5procs.ledShowColour([0, 0, 0])
clock.tick()
img = sensor.snapshot() # Capture snapshot
# Find faces.
# Note: Lower scale factor scales-down the image more and detects smaller objects.
# Higher threshold results in a higher detection rate, with more false positives.
faces = img.find_features(face_cascade, threshold=0.75, scale=1.35)
# Draw objects
framecount += 1
for face in faces[:4]:
img.draw_rectangle(face)
# Now find eyes within each face.
# Note: Use a higher threshold here (more detections) and lower scale (to find small objects)
eyes = img.find_features(eyes_cascade,
threshold=0.5,
scale=1.2,
roi=face)
for e in eyes[:2]:
img.draw_rectangle(e)
tracked = [
framecount & 0xff, 0, 0, e[0], e[1], e[0] + e[2],
e[1] + e[3]
]
#print("fps: ", clock.fps(),tracked)
cam5procs.send_packet(tracked, 7, cam5procs.TRK_BLOB)
# Print FPS.
# Note: Actual FPS is higher, streaming the FB makes it slower.
return True
def FaceTest():
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((320, 240))
#sensor.set_framesize(sensor.QVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
#sensor.set_framerate(2<<9|3<<11)
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
clock = time.clock()
for i in range(250):
clock.tick()
img = sensor.snapshot()
objects = img.find_features(face_cascade,
threshold=0.75,
scale_factor=1.25)
fID = 0
for r in objects:
img.draw_rectangle(r, color=(0, 0, 0), thickness=3)
#img.draw_rectangle(r[0], r[1], 48, 10, fill=True, color=(0,0,0))
fID += 1
s = 'face %d' % (fID)
img.draw_string(r[0], r[1], s)
print(clock.fps())
def face_detection(data):
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QVGA)
faces = sensor.snapshot().gamma_corr(contrast=1.5).find_features(image.HaarCascade("frontalface"))
if not faces: return bytes() # No detections.
for f in faces: sensor.get_fb().draw_rectangle(f, color = (255, 255, 255))
out_face = max(faces, key = lambda f: f[2] * f[3])
return struct.pack("<HHHH", out_face[0], out_face[1], out_face[2], out_face[3])
def face_recog(calc_time, vi_ip):
pin = pyb.millis()
print(pin)
print(calc_time)
cc = 0
#pyb.elapsed_millis(start)
while pyb.elapsed_millis(pin) < calc_time:
print("top of face recog function")
#snapshot on face detection
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset() # Initialize the camera sensor.
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.HQVGA) # or sensor.QQVGA (or others)
#sensor.alloc_extra_fb()
sensor.skip_frames(time=2000) # Let new settings take affect.
face_cascade = image.HaarCascade("frontalface", stages=25)
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000) # Give the user time to get ready.
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10 # We'll say we detected a face after 10 frames.
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(img.width(), img.height(),
sensor.GRAYSCALE)
faces = img.find_features(face_cascade,
threshold=0.5,
scale_factor=1.5)
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(pin)) > calc_time:
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(
pic_name) # Save Pic. to root of SD card -- uos.chdir("/")
pyb.delay(100)
facial_recog(pic_name, vi_ip)
gc.collect()
except Exception as go:
print("we are in exception")
pyb.LED(BLUE_LED_PIN).off()
gc.collect()
def unittest(data_path, temp_path):
import image
# Load Haar Cascade
cascade = image.HaarCascade(data_path + "/frontalface.cascade")
# Load image and find keypoints
img = image.Image(data_path + "/dennis.pgm", copy_to_fb=True)
# Find objects
objects = img.find_features(cascade, threshold=0.75, scale_factor=1.25)
return (objects and objects[0] == (189, 53, 88, 88)
and objects[1] == (12, 11, 107, 107))
def face_detect(init_start, calc_time):
print("~~~~~~~~~~~~~~~~FACE_DETECT~~~~~~~~~~~~~~~~~~~~~~")
gc.collect() #garbage collection
while pyb.elapsed_millis(init_start) < calc_time: #while time not expired
#snapshot on face detection
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset() # Initialize the camera sensor.
sensor.set_contrast(3) #set to highest contrast setting
sensor.set_gainceiling(16)
sensor.set_pixformat(
sensor.GRAYSCALE) #grayscale for facial recognition
sensor.set_framesize(sensor.HQVGA)
sensor.skip_frames(time=2000) # Let new settings take affect.
face_cascade = image.HaarCascade(
"frontalface",
stages=25) #Using Frontal Face Haar Cascade Classifier
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000) # Give the user time to get ready.
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10 # We'll say we detected a face after 10 frames.
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(
img.width(), img.height(),
sensor.GRAYSCALE) #allocate more space for image
faces = img.find_features(
face_cascade, threshold=0.5,
scale_factor=1.5) #detecting face features
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(init_start)
) > calc_time: #if time is expired, leave function
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(pic_name) # Save Pic. to root of SD card
pyb.delay(100)
gc.collect() #garbage collection
return pic_name
except Exception as go:
print("exception - time expired")
pyb.LED(BLUE_LED_PIN).off()
gc.collect() #garbage collection
class postProcess:
faceCascade = image.HaarCascade('frontalface')
def applyFilter(fid, img):
f = [None, lambda i: i.gaussian(1), lambda i: i.histeq(), lambda i: i.mean(1),
lambda i: i.mean(1), lambda i: i.erode(2),
lambda i: i.dilate(2), lambda i: i.chrominvar() if i.format() == 2 else i,
lambda i: i.illuminvar() if i.format() == 2 else i]
return f[fid](img)
def detectFace(img):
f = img.find_features(postProcess.faceCascade, 0.9)
if f:
img.draw_rectangle(*f)
def face_detect(init_start, calc_time):
print("~~~~~~~~~~~~~~~~FACE_DETECT~~~~~~~~~~~~~~~~~~~~~~")
gc.collect()
while pyb.elapsed_millis(init_start) < calc_time:
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset()
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.HQVGA)
sensor.skip_frames(time=2000)
face_cascade = image.HaarCascade("frontalface", stages=25)
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000)
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10
try:
while (diff):
img = sensor.snapshot()
sensor.alloc_extra_fb(img.width(), img.height(),
sensor.GRAYSCALE)
faces = img.find_features(face_cascade,
threshold=0.5,
scale_factor=1.5)
sensor.dealloc_extra_fb()
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
elif (pyb.elapsed_millis(init_start)) > calc_time:
raise Exception
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(pic_name)
pyb.delay(100)
gc.collect()
return pic_name
except Exception as go:
print("exception - time expired")
pyb.LED(BLUE_LED_PIN).off()
gc.collect()
def FaceTest(loopCnt=220, barLen=120):
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
#sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
#sensor.set_framesize(sensor.VGA)
#sensor.set_windowing((320,240))
sensor.set_framesize(sensor.VGA)
sensor.set_windowing((320, 240))
sensor.set_pixformat(sensor.GRAYSCALE)
#sensor.set_auto_gain(False)
#sensor.set_auto_whitebal(True) # must be turned off for color tracking
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
clock = time.clock()
avg = 0.0
startTick = time.ticks()
while (True):
if time.ticks() - startTick > loopCnt:
break
clock.tick()
img = sensor.snapshot()
img.draw_string(4, 4, 'Face Detect', color=(0, 0, 0))
t0 = time.ticks()
objects = img.find_features(face_cascade,
threshold=0.75,
scale_factor=1.25)
t1 = time.ticks() - t0
avg = avg * 0.90 + t1 * 0.10
fID = 0
lnLen = (barLen * (loopCnt - (time.ticks() - startTick))) // loopCnt
DrawPgsBar(img, barLen, loopCnt, startTick)
for r in objects:
img.draw_rectangle(r, thickness=3)
img.draw_rectangle(r[0], r[1], 48, 10, fill=True)
fID += 1
s = 'face %d' % (fID)
img.draw_string(r[0], r[1], s, color=(0, 0, 0))
print('algo time cost : %.2f ms' % (avg))
def runIt():
print("track_face")
cam5procs.logLine("track_face")
clock = time.clock()
ledState = 0
ledCounter = 0
framecount = 0
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
while not cam5procs.receive_packet():
ledCounter += 1
if ((ledCounter % 5) == 0):
if (ledState == 0):
ledState = 1
cam5procs.ledShowColour([0, 0, 255])
else:
ledState = 0
cam5procs.ledShowColour([0, 0, 0])
clock.tick()
img = sensor.snapshot() # Capture snapshot
# Find faces.
# Note: Lower scale factor scales-down the image more and detects smaller objects.
# Higher threshold results in a higher detection rate, with more false positives.
faces = img.find_features(face_cascade, threshold=0.75, scale=1.35)
# Draw objects
framecount += 1
for r in faces[:8]:
img.draw_rectangle(r)
tracked = [
framecount & 0xff, 0, 0, r[0], r[1], r[0] + r[2], r[1] + r[3]
]
cam5procs.send_packet(tracked, 7, cam5procs.TRK_BLOB)
# Print FPS.
# Note: Actual FPS is higher, streaming the FB makes it slower.
return True
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time=2000)
clock = time.clock()
net = tf.load("trained.tflite", load_to_fb=True)
labels = [l.rstrip('\n') for l in open("labels.txt")]
while (True):
clock.tick()
# Take a picture and brighten things up for the frontal face detector.
img = sensor.snapshot().gamma_corr(contrast=1.5)
# Returns a list of rects (x, y, w, h) where faces are.
faces = img.find_features(image.HaarCascade("frontalface"))
for f in faces:
# Classify a face and get the class scores list
scores = net.classify(img, roi=f)[0].output()
# Find the highest class score and lookup the label for that
label = labels[scores.index(max(scores))]
# Draw a box around the face
img.draw_rectangle(f)
# Draw the label above the face
img.draw_string(f[0] + 3, f[1] - 1, label, mono_space=False)
def face_recog(calc_time):
pin = pyb.millis()
print(pin)
cc = 0
#pyb.elapsed_millis(start)
while pyb.elapsed_millis(pin) < calc_time:
print("top of face recog function")
#snapshot on face detection
RED_LED_PIN = 1
BLUE_LED_PIN = 3
sensor.reset() # Initialize the camera sensor.
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.HQVGA) # or sensor.QQVGA (or others)
sensor.skip_frames(time=2000) # Let new settings take affect.
face_cascade = image.HaarCascade("frontalface", stages=25)
uos.chdir("/")
pyb.LED(RED_LED_PIN).on()
print("About to start detecting faces...")
sensor.skip_frames(time=2000) # Give the user time to get ready.
pyb.LED(RED_LED_PIN).off()
print("Now detecting faces!")
pyb.LED(BLUE_LED_PIN).on()
diff = 10 # We'll say we detected a face after 10 frames.
while (diff):
img = sensor.snapshot()
faces = img.find_features(face_cascade,
threshold=0.5,
scale_factor=1.5)
if faces:
diff -= 1
for r in faces:
img.draw_rectangle(r)
pyb.LED(BLUE_LED_PIN).off()
print("Face detected! Saving image...")
pic_name = "snapshot-person.pgm"
sensor.snapshot().save(
pic_name) # Save Pic. to root of SD card -- uos.chdir("/")
pyb.delay(100)
snap_img = image.Image(pic_name).mask_ellipse()
d0 = snap_img.find_lbp((0, 0, snap_img.width(), snap_img.height()))
# face recognition
pyb.LED(2).on()
name_lbp_list = []
uos.chdir(
"/Faces"
) # change directory to where all the webex photos from tcp are stored
for filename in uos.listdir("/Faces"):
if filename.endswith(".pgm"):
try:
img = None
img = image.Image(filename).mask_ellipse()
d1 = img.find_lbp((0, 0, img.width(), img.height()))
dist = image.match_descriptor(d0, d1, 50)
word = filename
#print(filename)
und_loc = word.index('_')
word = word[0:(und_loc)]
name_lbp_list.append(word)
name_lbp_list.append(dist)
continue
except Exception as e:
print(e)
print("error reading file")
else:
print("ERROR")
print(name_lbp_list)
#print(len(name_lbp_list))
end = 0
name_avg = []
i = 0
start = 0
while i < len(name_lbp_list):
if ((i + 2) < len(name_lbp_list)) and (name_lbp_list[i] !=
name_lbp_list[i + 2]):
end = i + 2
#print(start)
#print(end)
face = []
face = name_lbp_list[start:end]
print(face)
j = 1
sum_lbp = 0
while j < len(face):
sum_lbp += face[j]
j += 2
name_avg.append(face[0])
name_avg.append(sum_lbp / (len(face) / 2))
start = i + 2
i += 2
face = []
face = name_lbp_list[(end):(len(name_lbp_list))]
print(face)
j = 1
sum_lbp = 0
while j < len(face):
sum_lbp += face[j]
j += 2
name_avg.append(face[0])
name_avg.append(sum_lbp / (len(face) / 2))
print(name_avg)
lbps = []
k = 1
while k < len(name_avg):
lbps.append(name_avg[k])
k += 2
print(lbps)
#print(len(lbps))
min_lbp = min(lbps)
print(min_lbp)
ind = lbps.index(min(lbps))
#print(ind)
ind += 1
found_person = name_avg[2 * ind - 2]
id_name = "The person you are looking at is: " + found_person
print(id_name)
#delete snapshot of person
uos.remove("/snapshot-person.pgm")
pyb.LED(2).off()
cc += 1
print(cc)
def __init__(self):
global_value.flag_disp_line = 1
self.row = global_value.row
global_value.row = global_value.row + 1
self.face_cascade = image.HaarCascade("frontalface", stages=25)
red_led = LED(1)
# Reset sensor
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.skip_frames()
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=30)
eyes_cascade = image.HaarCascade("eye", stages=24)
print(face_cascade, eyes_cascade)
# FPS clock
clock = time.clock()
def circle_from_rect(rect):
x = round(rect[2] / 2) + rect[0]
y = round(rect[3] / 2) + rect[1]
r = round(rect[3] / 2)
return (x, y, r)
notFound = True
import sensor, time, image
# Reset sensor
sensor.reset()
sensor.set_contrast(1)
sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
#注意人脸识别只能用灰度图哦
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade('frontalface', stages=25)
#image.HaarCascade(path, stages=Auto)加载一个haar模型。haar模型是二进制文件，
#这个模型如果是自定义的，则引号内为模型文件的路径；也可以使用内置的haar模型，
#比如“frontalface” 人脸模型或者“eye”人眼模型。
#stages值未传入时使用默认的stages。stages值设置的小一些可以加速匹配，但会降低准确率。
print(face_cascade)
clock = time.clock()
while (True):
clock.tick()
# Capture snapshot
img = sensor.snapshot()
# Find objects.
# Keypoint extractor threshold, range from 0 to any number.
# This threshold is used when extracting keypoints, the lower
# the threshold the higher the number of keypoints extracted.
KEYPOINTS_THRESH = 3
# Keypoint-level threshold, range from 0 to 100.
# This threshold is used when matching two keypoint descriptors, it's the
# percentage of the distance between two descriptors to the max distance.
# In other words, the minimum matching percentage between 2 keypoints.
MATCHING_THRESH = 85
# Number of maximum keypoints
KEYPOINTS_MAX = 80
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface")
# First set of keypoints
leo_kpts = None
andy_kpts = None
taiga_kpts = None
aya_kpts = None
# load faces!
img_andy = image.Image("/andy11.pgm", copy_to_fb=True)
andy_objects = img_andy.find_features(face_cascade, threshold=0.7, scale=1.3)
if andy_objects:
print("Andy's face loaded!")
# Expand the ROI by 31 pixels in each direction (half the pattern scale)
andy_face = (andy_objects[0][0] - 31, andy_objects[0][1] - 31,
andy_objects[0][2] + 31 * 2, andy_objects[0][3] + 31 * 2)
import sensor, time, image, tf
def sort_preds(pred):
return pred[1]
sensor.reset()
img = image.Image("/temp/licenseplate.bmp", copy_to_fb=True)
plates = image.HaarCascade("plate/cascade.cascade", stages=10)
zero_cascade = image.HaarCascade("plate/0_cascade.cascade", stages=10)
five_cascade = image.HaarCascade("plate/5_cascade.cascade", stages=10)
six_cascade = image.HaarCascade("plate/6_cascade.cascade", stages=10)
s_cascade = image.HaarCascade("plate/s_cascade.cascade", stages=10)
g_cascade = image.HaarCascade("plate/g_cascade.cascade", stages=10)
net = "/plate/trained.tflite"
labels = [line.rstrip('\n') for line in open("/plate/labels.txt")]
found_plate = img.find_features(plates, threshold=1, scale_factor=1.5)
for f in found_plate:
(x, y, w, h) = f
f = (x, y, w, int(h * 1.2))
img.draw_rectangle(f)
import sensor, image, time
#Reset sensor
sensor.reset()
sensor.set_contrast(3)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.VGA)
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.skip_frames(time = 2000)
# Load Haar Cascade
# 默认情况下，这将使用所有阶段，较低的阶段更快但不太准确。
face_cascade = image.HaarCascade('FRONTALFACE',stages = 25)
print(face_cascade)
kpts1 = None
while(kpts1 == None):
img = sensor.snapshot()
img.draw_string(0,0,"Looking for a face....")
# Find faces
objects = img.find_features(face_cascade,threshold = 0.5,scale = 1.25)
if objects:
#在每个方向上将ROI扩大31个像素
face = (objects[0][0]-31,objects[0][-1]-31,objects[0][2]+31*2,objects[0][3]+31*2)
#使用检测面大小作为ROI提取关键点
kpts1 = img.find_keypoints(threshold = 10,scale_factor = 1.1 ,max_keypoints= 100,roi= face)
# Draw a rectangle around the first face
#翻译和注释：01Studio
import sensor, time, image
# Reset sensor
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
# 加载 Haar Cascade 模型
# 默认使用全部stages,提高识别的准确率.
face_cascade = image.HaarCascade("frontalface", stages=25) #定义人脸模型
eyes_cascade = image.HaarCascade("eye", stages=24) #定义眼球模型
print(face_cascade, eyes_cascade)
# FPS clock
clock = time.clock()
while (True):
clock.tick()
# Capture snapshot
img = sensor.snapshot()
# 人脸检测
objects = img.find_features(face_cascade, threshold=0.5, scale_factor=1.5)
except:
HAVE_LCD_MODULE = False
print("lcd init error")
try:
os.listdir('desc')
except:
print('mkdir desc')
os.mkdir('desc')
try:
os.listdir('photo')
except:
print('mkdir photo')
os.mkdir('photo')
face_cascade = image.HaarCascade("frontalface", stages=HAAR_FACE_STAGES)
def loadFaceCascade():
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
# face_cascade = image.HaarCascade("frontalface", stages=HAAR_FACE_STAGES)
# # print(face_cascade)
# return face_cascade
global face_cascade
return face_cascade
# https://github.com/opencv/opencv/tree/master/data/haarcascades
# https://github.com/openmv/openmv/blob/master/ml/haarcascade/cascade_convert.py
# https://github.com/atduskgreg/opencv-processing/tree/master/lib/cascade-files #这数据太大了
# カメラを初期化
sensor.reset()
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QVGA)
sensor.run(1)
# コントラスト設定
sensor.set_contrast(3)
# ゲイン設定
sensor.set_gainceiling(16)
##################################################
# main
##################################################
# カスケード情報を取得(顔)
cascade_frontalface = image.HaarCascade("frontalface")
# カスケード情報を取得(目)
cascade_eye = image.HaarCascade("eye")
while True:
# カメラ画像を取得
img = sensor.snapshot()
# 特徴を検出(顔)
res_frontalface = img.find_features(cascade_frontalface)
# 結果が存在する場合
if res_frontalface:
# 全ての結果に対して実行
for i in res_frontalface:
print(i)
# 矩形を描画(顔)
img.draw_rectangle(i)
sensor.reset()
sensor.set_pixformat(sensor.GRAYSCALE)
sensor.set_framesize(sensor.QQVGA)
sensor.skip_frames(time = 2000)
clock = time.clock()
while(True):
clock.tick()
img = sensor.snapshot()
#print(clock.fps())
#eye_position = img.find_eye([0, 0, img.width(), img.height()])
#img.draw_circle(eye_position[0], eye_position[1], 5)
x = img.find_features(image.HaarCascade('eye'))
for feature in x:
print(x)
img.draw_rectangle(feature[0], feature[1], feature[2], feature[3])
eye_position = img.find_eye(feature)
print(eye_position)
img.draw_circle(eye_position[0], eye_position[1], 5)
#if x:
#print(x)
#img.draw_circle(x[0][0], x[0][1], 5)
# 1. Zaczac od wczytania w roznych formatach (DLA QVGA - 320x240)
# TYP - Terminal (GUI)
# Note: This script does not detect a face first, use it with the telephoto lens.
import sensor, time, image
# Reset sensor
sensor.reset()
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.QQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
eyes_cascade = image.HaarCascade("eye", stages=24)
print(eyes_cascade)
# FPS clock
clock = time.clock()
while (True):
clock.tick()
# Capture snapshot
img = sensor.snapshot()
# Find eyes !
# Note: Lower scale factor scales-down the image more and detects smaller objects.
# Higher threshold results in a higher detection rate, with more false positives.
eyes = img.find_features(eyes_cascade, threshold=0.5, scale=1.5)
# Find iris
# Use this script to gather face images for building a TensorFlow dataset. This script automatically
# zooms in the largest face in the field of view which you can then save using the data set editor.
import sensor, image, time
sensor.reset()
sensor.set_pixformat(sensor.RGB565)
sensor.set_framesize(sensor.QVGA)
sensor.skip_frames(time=2000)
clock = time.clock()
largest_face = None
largest_face_timeout = 0
while (True):
clock.tick()
faces = sensor.snapshot().gamma_corr(contrast=1.5).find_features(
image.HaarCascade("frontalface"))
if faces:
largest_face = max(faces, key=lambda f: f[2] * f[3])
largest_face_timeout = 20
if largest_face_timeout > 0:
sensor.get_fb().crop(roi=largest_face)
largest_face_timeout -= 1
print(clock.fps())
# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
# Skip a few frames to allow the sensor settle down
# Note: This takes more time when exec from the IDE.
#for i in range(0, 10):
# img = sensor.snapshot()
# img.draw_string(0, 0, "Please wait...")
# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
print(face_cascade)
# First set of keypoints
hzy_kpts = None
hjf_kpts = None
hmy_kpts = None
sf_kpts = None
# load faces!
img_hjf = image.Image("/hjfface2-hqvga.bmp",copy_to_fb=True)
#img = img2
#img.draw_string(0, 0, "Looking for a face...")
# Find faces
hjf_objects = img_hjf.find_features(face_cascade, threshold=0.7, scale=1.5)
if hjf_objects:
self.isCounted = isCounted
self.direction = direction
self.prev_dir = prev_dir
sensor.reset() # Reset and initialize the sensor.
sensor.set_pixformat(
sensor.GRAYSCALE) # Set pixel format to RGB565 (or GRAYSCALE)
sensor.set_framesize(sensor.QVGA) # Set frame size to QVGA (320x240)
sensor.set_windowing((240, 240)) # Set 240x240 window.
sensor.skip_frames(time=2000) # Let the camera adjust.
clock = time.clock()
print("Loading model")
person_cascade = image.HaarCascade(
"/PeopleCounting/people_counting_cascade.cascade", stages=25)
height = None
width = None
count = 0
direction = 0
isCounted = False
i = 1
j = 1
b_boxes = []
vid = image.ImageReader("/PeopleCounting/walking.bin")
while (True):
