def __init__(self):
self.items = {}
self.items["button"] = {}
self.items["labels"] = {}
self.items["button"]["github"] = TextButton("Github Repo", 212, 382)
self.items["button"]["return"] = TextButton("Return", 212, 466)
self.items["labels"]["label1"] = Label("Made by", 32, 261, 231)
self.items["labels"]["label2"] = Label("Pedro Perpetua", 32, 172, 268)
def detect_lp(output_dir, loaded_models, Iorig_name):
imgs_paths = glob('%s/%s_*car.png' % (output_dir, Iorig_name))
print('Searching for license plates...')
for i, img_path in enumerate(imgs_paths):
bname = splitext(basename(img_path))[0]
lp_net, lp_meta, lp_threshold = loaded_models[1]
R, _ = detect(lp_net,
lp_meta,
img_path.encode('utf-8'),
thresh=lp_threshold)
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Llp = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Ilp = crop_region(Iorig, label)
Llp.append(label)
cv2.imwrite('%s/%s_lp.png' % (output_dir, bname), Ilp)
lwrite('%s/%s_lp.txt' % (output_dir, bname), Llp)
else:
print('No license plate found')
def detect_vehicles(self, img_path):
vehicle_threshold = 0.5
classes = ['car', 'bus', 'truck', 'motorcycle']
results, _ = dn.detect(self.vehicle_net,
self.vehicle_meta,
img_path,
thresh=vehicle_threshold)
results = [
result for result in results
if result[0].decode('utf-8') in classes
]
vehicles = []
if len(results):
image = cv2.imread(img_path)
WH = np.array(image.shape[1::-1], dtype=float)
for i, result in enumerate(results):
cx, cy, w, h = (np.array(result[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
vehicle = crop_region(image, label)
results[i] = (result[0], result[1], result[2], vehicle)
vehicles.append(label)
return vehicles
def on_any_event(event):
if event.is_directory:
return None
elif event.event_type == 'created':
# Take any action here when a file is first created.
print("Received created event - %s." % event.src_path)
try:
img_path = event.src_path
print('\tScanning %s' % img_path)
bname = basename(splitext(img_path)[0])
R, _ = detect(vehicle_net,
vehicle_meta,
img_path,
thresh=lp_threshold)
R = [r for r in R if r[0] in ['vehicle registration plate']]
print('\t\t%d plates found' % len(R))
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
height, width, _ = Icar.shape
print(height, width)
if height > 24:
cv2.imwrite(
'%s/%s_%dplate.png' % (output_dir, bname, i),
Icar)
else:
print(
'plate likely too small to OCR, high change of FP'
)
if os.path.exists(img_path):
os.remove(img_path)
else:
if os.path.exists(img_path):
os.remove(img_path)
except:
traceback.print_exc()
sys.exit(1)
elif event.event_type == 'modified':
# Taken any action here when a file is modified.
print("Received modified event - %s." % event.src_path)
def vehicle_detect(vehicle_net, vehicle_meta, vehicle_threshold, img):
print ('Searching for vehicles using YOLO...')
R,_ = detect2(vehicle_net, vehicle_meta, img, thresh=vehicle_threshold)
R = [r for r in R if r[0] in [b'car',b'bus']]
print ('\t\t%d cars found' % len(R))
Icars = []
Lcars = []
Tcars = []
Scars = []
Pcars = []
if len(R):
Iorig = img
WH = np.array(Iorig.shape[1::-1],dtype=float)
for i,r in enumerate(R):
# print ('\t\t\t%d %d %4.2f' % (r[2][2], r[2][3], r[1]))
cx,cy,w,h = (np.array(r[2])/np.concatenate( (WH,WH) )).tolist()
tl = np.array([cx - w/2., cy - h/2.])
br = np.array([cx + w/2., cy + h/2.])
label = Label(0,tl,br)
Icar = crop_region(Iorig,label)
if (r[2][2] > vehicle_width_threshold and r[2][3] > vehicle_height_threshold):
Icars.append(Icar)
Lcars.append(label)
Tcars.append(r[0])
Scars.append(r[1])
Pcars.append(r[2])
#cv2.imwrite('%s/%dcar.png' % (car_img_dir,i),Icar)
#lwrite('%s/cars.txt' % (car_img_dir),Lcars)
print ('\t\t%d cars chosen' % len(Icars))
return Icars, Lcars, Tcars, Scars, Pcars
def find_vehicle_one_img(img_path, veh_net, veh_meta, out_dir, veh_thd):
st = time.time()
print '\tScanning %s' % img_path
bname = basename(splitext(img_path)[0])
R, _ = dn.detect(veh_net, veh_meta, img_path, thresh=veh_thd)
# R: [name, prob, [x center, y center, width, height]]
R = [r for r in R if r[0] in ['car', 'bus']]
out_img = []
out_label_f = ""
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate((WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
p_img = '%s/%s_%dcar.png' % (out_dir, bname, i)
cv2.imwrite(p_img, Icar)
out_img.append(p_img)
out_label_f = '%s/%s_cars.txt' % (out_dir, bname)
lwrite(out_label_f, Lcars)
print '\t\t%d cars found, runtime: %.1fs' % (len(R), time.time() - st)
return out_img, out_label_f
def genOutput(img_path, output_dir, bname):
I = cv2.imread(img_path)
detected_cars_labels = '%s/%s_cars.txt' % (output_dir, bname)
Lcar = lread(detected_cars_labels)
sys.stdout.write('%s' % bname)
if Lcar:
for i, lcar in enumerate(Lcar):
draw_label(I, lcar, color=YELLOW, thickness=3)
lp_label = '%s/%s_%dcar_lp.txt' % (output_dir, bname, i)
lp_label_str = '%s/%s_%dcar_lp_str.txt' % (output_dir, bname, i)
if isfile(lp_label):
Llp_shapes = readShapes(lp_label)
pts = Llp_shapes[0].pts * lcar.wh().reshape(
2, 1) + lcar.tl().reshape(2, 1)
ptspx = pts * np.array(I.shape[1::-1], dtype=float).reshape(
2, 1)
draw_losangle(I, ptspx, RED, 3)
if isfile(lp_label_str):
with open(lp_label_str, 'r') as f:
lp_str = f.read().strip()
llp = Label(0, tl=pts.min(1), br=pts.max(1))
write2img(I, llp, lp_str)
sys.stdout.write(',%s' % lp_str)
cv2.imwrite('%s/%s_output.png' % (output_dir, bname), I,
[int(cv2.IMWRITE_PNG_COMPRESSION), 9])
def detect_vehicle(img_path, output_dir, loaded_models, bname):
vehicle_net, vehicle_meta, vehicle_threshold = loaded_models[0]
R, _ = detect(vehicle_net,
vehicle_meta,
img_path.encode('utf-8'),
thresh=vehicle_threshold)
R = [r for r in R if r[0].decode(encoding='utf-8') in ['car']]
print('%d cars found' % len(R))
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate((WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
cv2.imwrite('%s/%s_%dcar.png' % (output_dir, bname, i), Icar)
lwrite('%s/%s_cars.txt' % (output_dir, bname), Lcars)
def augment_sample(I,pts, dim_w, dim_h, cls):
maxsum,maxangle = 50,np.array([20.,20.,25.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
I = im2single(I)
iwh = getWH(I.shape)
# codigo original
# whratio = random.uniform(2., 4.)
# wsiz = random.uniform(dim * .2, dim * 1.)
# carro
if cls=='0':
whratio = random.uniform(2.75, 3.25)
wsiz = random.uniform(dim_w * .2, dim_w * 0.7)
else:
whratio = random.uniform(0.7, 1.2)
wsiz = random.uniform(dim_w * .2, dim_w * 0.7)
# whratio = 1.
# wsiz = random.uniform(dim_w*.2, dim_w*1.)
# moto
# whratio = random.uniform(0.7, 1.2)
# wsiz = random.uniform(dim_w * .3, dim_w * 0.7)
hsiz = wsiz/whratio
dx = random.uniform(0.,dim_w - wsiz)
dy = random.uniform(0.,dim_h - hsiz)
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
pts = pts*iwh.reshape((2,1))
T = find_T_matrix(pts2ptsh(pts),pph)
H = perspective_transform((dim_w,dim_h),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim_w, dim_h)
# hsv_mod = np.random.rand(3).astype('float32')
# hsv_mod = (hsv_mod - .5)*.3
# hsv_mod[0] *= 360
# Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
# if random.random() > .5:
# Iroi,pts = flip_image_and_pts(Iroi,pts)
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def __init__(self, highscore_handler):
self.items = {}
self.items["button"] = {}
self.items["days"] = {}
self.items["times"] = {}
self.items["points"] = {}
scores = highscore_handler.get_top_scores()
self.items["days"]["1st"] = Label(scores[0]["day"], 24, 210, 205)
self.items["times"]["1st"] = Label(scores[0]["time"], 24, 210, 237)
self.items["points"]["1st"] = Label(scores[0]["points"], 38, 426, 214)
self.items["days"]["2nd"] = Label(scores[1]["day"], 24, 210, 285)
self.items["times"]["2nd"] = Label(scores[1]["time"], 24, 210, 317)
self.items["points"]["2nd"] = Label(scores[1]["points"], 38, 426, 294)
self.items["days"]["3rd"] = Label(scores[2]["day"], 24, 210, 365)
self.items["times"]["3rd"] = Label(scores[2]["time"], 24, 210, 397)
self.items["points"]["3rd"] = Label(scores[2]["points"], 38, 426, 374)
self.items["button"]["return"] = TextButton("Return", 212, 466)
def draw_without_car(self, img, Llp_shapes, Llp_str, wh, tl):
for i in range(len(Llp_shapes)):
if Llp_shapes[i] is not None:
pts = Llp_shapes[i].pts * wh.reshape(2, 1) + tl.reshape(2, 1)
ptspx = pts * np.array(img.shape[1::-1], dtype=float).reshape(
2, 1)
draw_losangle(img, ptspx, RED, 3)
if Llp_str[i] is not None:
llp = Label(0, tl=pts.min(1), br=pts.max(1))
write2img(img, llp, Llp_str[i])
return img
def on_any_event(event):
if event.is_directory:
return None
elif event.event_type == 'created':
# Take any action here when a file is first created.
print("Received created event - %s." % event.src_path)
try:
print('\tScanning %s' % event.src_path)
try:
img_path = event.src_path
print('\tScanning %s' % img_path)
bname = basename(splitext(img_path)[0])
R, _ = detect(vehicle_net,
vehicle_meta,
img_path.encode('utf-8'),
thresh=vehicle_threshold)
R = [r for r in R if r[0] in ['car', 'bus']]
print('\t\t%d cars found' % len(R))
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
cv2.imwrite(
'%s/%s_%dcar.png' % (output_dir, bname, i),
Icar)
except:
traceback.print_exc()
sys.exit(1)
except:
traceback.print_exc()
sys.exit(1)
def vehicle_detection(img_path, output_dir):
try:
if not isdir(output_dir):
makedirs(output_dir)
bname = basename(splitext(img_path)[0])
plates = []
# Vehicle detection
R, _ = detect(vehicle_net,
vehicle_meta,
img_path,
thresh=vehicle_threshold)
R = [r for r in R if r[0] in ['car', 'bus', 'motorbike']]
# print '\t\t%d cars found' % len(R)
if not len(R):
return ("", plates)
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate((WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
carImagePath = '%s/%s_%dcar.png' % (output_dir, bname, i)
cv2.imwrite(carImagePath, Icar)
#print("CarImagePath: ", carImagePath)
# LP detection
LPImagePath = LPDection(carImagePath)
if LPImagePath:
lp_str = OCRDection(LPImagePath)
if lp_str:
plates.append(lp_str)
lwrite('%s/%s_cars.txt' % (output_dir, bname), Lcars)
# draw yellow box around the cars and red box around license plates
genOutput(img_path, output_dir, bname)
return ('%s/%s_output.png' % (output_dir, bname), plates)
except:
traceback.print_exc()
return ("", plates)
class TestLabel:
def setup(self):
self.labeler = Label()
def teardown(self):
pass
def test_label_benign_domain(self):
actual = self.labeler.label("google.com")
assert actual == 0
def test_check_for_benign_domain(self):
actual = self.labeler.check_for_benign_domain("google.com")
assert actual == True
def test_label_malicious_domain(self):
actual = self.labeler.label("creativebookmark.com")
assert actual == 1
def test_check_for_malicious_domain(self):
actual = self.labeler.check_for_malicious_domain("creativebookmark.com")
assert actual == True
def test_case_insensitivity(self):
actual = self.labeler.label("crEATivebookmark.com")
assert actual == 1
def test_get_domain_variations(self):
actual = self.labeler.get_domain_variations("google.com")
assert "https://www.google.com" in actual
assert "http://www.google.com" in actual
assert "www.google.com" in actual
def test_list_lower(self):
actual = self.labeler.list_lower(["ABC", "abc", "CDE", "FGE"])
assert actual == ["abc", "abc", "cde", "fge"]
def test_get_domain_labels(self):
actual = self.labeler.get_domain_labels({"google.com": 0, "creativebookmark.com": 1, "crEATivebookmark.com": 2,"test.com": 3})
assert actual[0,0] == 0
assert actual[0,1] == 1
assert actual[1,0] == 1
assert actual[1,1] == 0
assert actual[2,0] == 1
assert actual[2,1] == 0
assert actual[3,0] == 0
assert actual[3,1] == 1
def gen_output(output_dir):
YELLOW = (0, 255, 255)
RED = (0, 0, 255)
bname = splitext(basename(img_path))[0]
I = cv2.imread(img_path)
detected_cars_labels = '%s/%s_cars.txt' % (output_dir, bname)
Lcar = lread(detected_cars_labels)
if Lcar:
for i, lcar in enumerate(Lcar):
draw_label(I, lcar, color=YELLOW, thickness=3)
lp_label = '%s/%s_%dcar_lp.txt' % (output_dir, bname, i)
lp_label_str = '%s/%s_%dcar_lp_str.txt' % (output_dir, bname, i)
C = cv2.imread('%s/%s_%dcar.png' % (output_dir, bname, i))
if isfile(lp_label):
Llp = lread(lp_label)
for j, llp in enumerate(Llp):
draw_label(I,
llp,
color=RED,
thickness=3,
lp=True,
lcar=lcar,
C=C)
if isfile(lp_label_str):
with open(lp_label_str, 'r') as f:
lp_str = f.read().strip()
cwh = np.array(C.shape[1::-1]).astype(float)
iwh = np.array(I.shape[1::-1]).astype(float)
tl = tuple(
np.add((llp.tl() * cwh).tolist(),
(lcar.tl() * iwh).tolist()) / iwh)
br = tuple(
np.add((llp.br() * cwh).tolist(),
(lcar.tl() * iwh).tolist()) / iwh)
temp_label = Label(0, tl=tl, br=br)
write2img(I, temp_label, lp_str)
return I
def sample_validate(image_abs_path, gt_file):
L = readShapes(gt_file)[0]
pts_transformed = L.pts
model_stride = 16.0
image_ndarray = cv2.imread(image_abs_path)
tl, br = pts_transformed.min(1), pts_transformed.max(1)
llp = Label(0, tl, br)
YY, is_there_plate = labels2output_map(llp, pts_transformed, 304, 304,
model_stride, L.cls, image_abs_path)
print('There is place: %s | Class %s ' % (str(is_there_plate), L.cls))
print('Car ')
print(np.matrix(YY[..., 0]))
print('Non-object')
print(np.matrix(YY[..., 10]))
print('Moto')
print(np.matrix(YY[..., 9]))
def augment_sample(I,pts,dim):
maxsum,maxangle = 120,np.array([80.,80.,45.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
I = im2single(I) # /255.0 归一化
iwh = getWH(I.shape) #得到宽高
whratio = random.uniform(2.,4.) # 随即取一个2-4的值作为宽高比
wsiz = random.uniform(dim*.2,dim*1.) # 宽取0.2*208 到 208之间
hsiz = wsiz/whratio
dx = random.uniform(0.,dim - wsiz)
dy = random.uniform(0.,dim - hsiz)
#下面涉及到整个变换
# In the first 3 lines, the original corner points are transformed into a rectangular bounding box with aspect ratio
# varying between 2:1 and 4:1. In other words, T matrix rectifies the LP with a random aspect ratio. Then,
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
pts = pts*iwh.reshape((2,1)) #将点恢复到真实坐标值
T = find_T_matrix(pts2ptsh(pts),pph)
#in the next two lines, a perspective transformation with random rotation (H) is combined with T to
#generate the final transformation.
H = perspective_transform((dim,dim),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim)
hsv_mod = np.random.rand(3).astype('float32')
hsv_mod = (hsv_mod - .5)*.3
hsv_mod[0] *= 360
Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
if random.random() > .5:
Iroi,pts = flip_image_and_pts(Iroi,pts)
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def augment_sample(I,pts,dim):
maxsum,maxangle = 120,np.array([80.,80.,45.])
angles = np.random.rand(3)*maxangle
if angles.sum() > maxsum:
angles = (angles/angles.sum())*(maxangle/maxangle.sum())
# chuyển qua ma trận float32, chia cho 255
I = im2single(I)
# Lấy w, h dạng ma trận
iwh = getWH(I.shape)
whratio = random.uniform(2.,4.)
wsiz = random.uniform(dim*.2,dim*1.)
hsiz = wsiz/whratio
dx = random.uniform(0.,dim - wsiz)
dy = random.uniform(0.,dim - hsiz)
pph = getRectPts(dx,dy,dx+wsiz,dy+hsiz)
# Lấy tọa độ thật
pts = pts*iwh.reshape((2,1))
T = find_T_matrix(pts2ptsh(pts),pph)
H = perspective_transform((dim,dim),angles=angles)
H = np.matmul(H,T)
Iroi,pts = project(I,H,pts,dim)
hsv_mod = np.random.rand(3).astype('float32')
hsv_mod = (hsv_mod - .5)*.3
hsv_mod[0] *= 360
Iroi = hsv_transform(Iroi,hsv_mod)
Iroi = np.clip(Iroi,0.,1.)
pts = np.array(pts)
if random.random() > .5:
Iroi,pts = flip_image_and_pts(Iroi,pts)
# lấy giá trị tọa độ top-left, bot-right
tl,br = pts.min(1),pts.max(1)
llp = Label(0,tl,br)
return Iroi,llp,pts
def draw(self, img, Lcars, Llp_shapes, Llp_str):
for i, lcar in enumerate(Lcars):
draw_label(img, lcar, color=YELLOW, thickness=3)
if Llp_shapes[i] is not None:
# print("Llp.shapes[i].pts: ", Llp_shapes[i].pts)
pts = Llp_shapes[i].pts * lcar.wh().reshape(
2, 1) + lcar.tl().reshape(2, 1)
# print("pts: ", pts)
ptspx = pts * np.array(img.shape[1::-1], dtype=float).reshape(
2, 1)
# print("ptspx: ", ptspx)
draw_losangle(img, ptspx, RED, 3)
if Llp_str[i] is not None:
llp = Label(0, tl=pts.min(1), br=pts.max(1))
write2img(img, llp, Llp_str[i])
return img
def predict(self, img, bname):
# bname = basename(splitext(img_path)[0])
# img = cv2.imread(img_path)
# img = img_path.encode('utf-8')
# print(img)
output_dir = "output/tmp"
R, _ = detect_image(self.vehicle_net,
self.vehicle_meta,
img,
thresh=self.vehicle_threshold)
# print(detect(vehicle_net, vehicle_meta, img ,thresh=vehicle_threshold))
# print("R :", [r for r in R if not math.isnan(r[2][0])])
# print("R: ", R[0][2][0])
R = [r for r in R if r[0].decode('utf-8') in ['car', 'bus']]
print('\t\t{} cars found'.format(len(R)))
cars_img = []
Lcars = []
if len(R):
# Iorig = cv2.imread(img_path)
Iorig = img
WH = np.array(Iorig.shape[1::-1], dtype=float)
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
# cv2.imwrite('{}/{}_{}car.png'.format(output_dir, bname, i), Icar)
cars_img.append(Icar)
# lwrite('{}/{}_cars.txt'.format(output_dir, bname), Lcars)
return cars_img, Lcars
def detect_vehicle(self, img, filename):
data = []
copy = img
R, boxes, confidences, class_ids = self.vehicle.detect_objects(copy, str(filename).split('.')[0] + '.txt')
if len(R):
WH = np.array(copy.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(boxes[i])/np.concatenate((WH, WH))).tolist()
tl = np.array([cx - w/2., cy - h/2.])
br = np.array([cx + w/2., cy + h/2.])
label = Label(0, tl, br)
Lcars.append(label)
data.append((cx, cy, w, h))
cv2.imwrite('%s/%s-car.png' % (self.output_dir, filename), copy)
lwrite('%s/%s-car.txt' % (self.output_dir, filename), Lcars)
return data
def generate_outputs(input_dir, output_dir):
img_files = image_files_from_folder(input_dir)
for img_file in img_files:
bname = splitext(basename(img_file))[0]
I = cv2.imread(img_file)
detected_cars_labels = '%s/%s_cars.txt' % (output_dir, bname)
Lcar = lread(detected_cars_labels)
sys.stdout.write('%s' % bname)
if Lcar:
for i, lcar in enumerate(Lcar):
draw_label(I, lcar, color=YELLOW, thickness=3)
lp_label = '%s/%s_%dcar_lp.txt' % (output_dir, bname, i)
lp_label_str = '%s/%s_%dcar_lp_str.txt' % (output_dir, bname, i)
if isfile(lp_label):
Llp_shapes = readShapes(lp_label)
pts = Llp_shapes[0].pts * lcar.wh().reshape(2, 1) + lcar.tl().reshape(2, 1)
ptspx = pts * np.array(I.shape[1::-1], dtype=float).reshape(2, 1)
draw_losangle(I, ptspx, RED, 3)
if isfile(lp_label_str):
with open(lp_label_str, 'r') as f:
lp_str = f.read().strip()
llp = Label(0, tl=pts.min(1), br=pts.max(1))
write2img(I, llp, lp_str)
sys.stdout.write(',%s' % lp_str)
cv2.imwrite('%s/%s_output.png' % (output_dir, bname), I)
def car_detect(Iorig):
Lcars=[]
R = []
vehicle_threshold = .5
R = detect(vehicle_net, vehicle_meta, Iorig,thresh=vehicle_threshold)
R = [r for r in R if r[0] in [b'car','bus']]
#print('\t\t%d cars found' % len(R))
if len(R):
WH = np.array(Iorig.shape[1::-1],dtype=float)
Lcars = []
for i,r in enumerate(R):
cx,cy,w,h = (old_div(np.array(r[2]),np.concatenate( (WH,WH) ))).tolist()
tl = np.array([cx - w/2., cy - h/2.])
br = np.array([cx + w/2., cy + h/2.])
label = Label(0,tl,br)
Icar = crop_region(Iorig,label)
cv2.imwrite("crop1.png",Icar)
Icar1 = cv2.imread("crop1.png")
Lcars.append(label)
return Lcars
def draw_car(img, Lcars, Tcars, Ccars, IDcars, Llps, lp_strs):
print ('Performing outputting car ...')
YELLOW = ( 0,255,255)
RED = ( 0, 0,255)
WHITE = (255,255,255)
I = img
if Lcars:
for i,(lcar, tcar, ccar, idcar) in enumerate(zip(Lcars, Tcars, Ccars, IDcars)):
draw_label(I,lcar,color=YELLOW,thickness=3)
if (ccar is not np.nan):
car_cat = str(tcar.decode("utf-8")) + " " + ccar + " " + str(idcar)
else:
car_cat = str(tcar.decode("utf-8")) + " " + str(idcar)
draw_text(I,lcar,car_cat,color=YELLOW,thickness=1)
lp_label = Llps[i]
lp_label_str = lp_strs[i]
if (lp_label is not np.nan):
pts = lp_label.pts*lcar.wh().reshape(2,1) + lcar.tl().reshape(2,1)
ptspx = pts*np.array(I.shape[1::-1],dtype=float).reshape(2,1)
draw_losangle(I,ptspx,RED,3)
if (lp_label_str is not np.nan):
lp_str = lp_label_str.strip()
llp = Label(0,tl=pts.min(1),br=pts.max(1))
write2img(I,llp,lp_str)
sys.stdout.write('%s\n' % lp_str)
else:
if (lp_label_str is not np.nan):
lp_str = lp_label_str.strip()
draw_text2(I,lcar,lp_str,color=WHITE,thickness=3)
sys.stdout.write('%s\n' % lp_str)
return I
print('\t\t%d cars found' % len(R))
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br)
Icar = crop_region(Iorig, label)
Lcars.append(label)
cv2.imwrite('%s/%s_%dcar.png' % (output_dir, bname, i),
Icar)
lwrite('%s/%s_cars.txt' % (output_dir, bname), Lcars)
except:
traceback.print_exc()
sys.exit(1)
sys.exit(0)
def getSquare(self):
tl, br = self.pts.min(1), self.pts.max(1)
return Label(-1, tl, br)
def __init__(self, cl, pts, prob):
self.pts = pts
tl = np.amin(pts, 1)
br = np.amax(pts, 1)
Label.__init__(self, cl, tl, br, prob)
sys.stdout.write('%s' % bname)
if Lcar:
for i, lcar in enumerate(Lcar):
draw_label(I, lcar, color=YELLOW, thickness=3)
lp_label = '%s/%s_%dcar_lp.txt' % (output_dir, bname, i)
lp_label_str = '%s/%s_%dcar_lp_str.txt' % (output_dir, bname, i)
if isfile(lp_label):
Llp_shapes = readShapes(lp_label)
pts = Llp_shapes[0].pts * lcar.wh().reshape(
2, 1) + lcar.tl().reshape(2, 1)
ptspx = pts * np.array(I.shape[1::-1], dtype=float).reshape(
2, 1)
draw_losangle(I, ptspx, RED, 3)
if isfile(lp_label_str):
with open(lp_label_str, 'r', encoding='utf-8') as f:
lp_str = f.read().strip()
llp = Label(0, tl=pts.min(1), br=pts.max(1))
I = write2img(I, llp, lp_str)
sys.stdout.write(',%s' % lp_str)
cv2.imwrite('%s/%s_output.png' % (output_dir, bname), I)
sys.stdout.write('\n')
from src.display import Display
from src.label import Label
from src.save import Save
from src.transform import Transform
from sys import argv
if len(argv) < 2:
print('You must specify a name argument.')
else:
config = Config().get()
capture = Capture(config)
trans = Transform(config)
display = Display()
detect = Detect()
label = Label()
with capture, display:
key = ''
while key != 'q':
success = False
image = capture.frame()
disk = trans.image_copy(image)
disk = trans.image_color_flip(disk)
small = trans.scale_image(image)
locs = detect.locations(small)
if len(locs) == 1:
success = True
loc = trans.scale_location(locs[0])
label.set_image(image).set_location(loc)
image = label.outline().header(argv[1]).get_image()
print('\t\t%d vehicles found' % len(R))
if len(R):
Iorig = cv2.imread(img_path)
WH = np.array(Iorig.shape[1::-1], dtype=float)
Lcars = []
for i, r in enumerate(R):
cx, cy, w, h = (np.array(r[2]) / np.concatenate(
(WH, WH))).tolist()
tl = np.array([cx - w / 2., cy - h / 2.])
br = np.array([cx + w / 2., cy + h / 2.])
label = Label(0, tl, br, category=r[0].decode("utf-8"))
Icar = crop_region(Iorig, label)
Lcars.append(label)
cv2.imwrite(
# '%s/%s_%dcar.png' % (output_dir, bname, i), Icar)
'%s/%s_car_%d.png' % (output_dir, bname, i),
Icar)
lwrite('%s/%s_cars.txt' % (output_dir, bname),
Lcars,
write_category_names=True)
except:
traceback.print_exc()