-
Notifications
You must be signed in to change notification settings - Fork 0
/
YOLOv5Hash.py
267 lines (216 loc) · 11.9 KB
/
YOLOv5Hash.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
import argparse
import time
from pathlib import Path
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, load_classifier, time_synchronized
import numpy as np
from matplotlib import pyplot as plt
from sklearn.cluster import KMeans
from gtts import gTTS
import playsound
import os
# TTS
def speak(text):
tts = gTTS(text=text, lang='ko')
# 파일 이름 설정
filename = 'mmyeong.mp3'
tts.save(filename)
playsound.playsound(filename)
os.remove(filename) # 한 객체당 mp3파일을 계속 만들어서 한객체 생성후 삭제 -> 객체 생성 삭제 반복
def image_min_max(image, k=3): # k-means 최대 최소 값 구하는 함수
image = image.reshape((image.shape[0] * image.shape[1], 3)) # height, width 통합
clt = KMeans(n_clusters=k) # k개의 데이터 평균을 만들어 데이터를 clustering하는 알고리즘
clt.fit(image) # 컬러값
n1 = clt.cluster_centers_ # 컬러값 numpy 배열
min_BGR = np.apply_along_axis(lambda a: np.min(a), 0, n1) # 최소값
max_BGR = np.apply_along_axis(lambda a: np.max(a), 0, n1) # 최대값
# print("\nmin", min_BGR) #클러스터 최대최소값 확인
# print("max", max_BGR)
return min_BGR, max_BGR
def image_Binarization(image, min, max): # 원본 이미지에 적용하는 함수
dst = cv2.inRange(image, min, max) # 추출된 RGB값 최소 최대 범위 지정
kernel = np.ones((33, 33), np.uint8)
# 모폴로지 노이즈 제거
closed = cv2.morphologyEx(dst, cv2.MORPH_CLOSE, kernel)
opened = cv2.morphologyEx(closed, cv2.MORPH_OPEN, kernel)
avg = dst.mean()
gray = cv2.resize(opened, (5, 5)) # 5x5 크기로 축소
hash = 1 * (gray > avg) # True False 를 0과 1로 변환
sum_width = []
sum_length = []
for a in hash[3, :]:
sum_width.append(a) # 3행 추출
for a in hash[:, 3]:
sum_length.append(a) # 3열 추출
if sum(sum_width) + sum(sum_length) == 10: # 3행 3열 합이 10이면 사거리
print("전방에 사거리블록이 있습니다.")
# speak("전방에 사거리블록이 있습니다.")
elif sum(sum_width) + sum(sum_length) == 8: # 3행 3열 합이 8이면 삼거리
print("전방에 사거리블록이 있습니다.")
# speak("전방에 삼거리블록이 있습니다.")
plt.imshow(opened, cmap='gray')
plt.savefig('result.jpg') # 이미지 파일 저장
def detect(save_img=False):
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
save_img = not opt.nosave and not source.endswith('.txt') # save inference images
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://'))
# Directories
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Initialize
set_logging()
device = select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check img_size
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
for path, img, im0s, vid_cap in dataset:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized()
pred = model(img, augment=opt.augment)[0]
# Apply NMS
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t2 = time_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
else:
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or view_img: # Add bbox to image
label = f'{names[int(cls)]} {conf:.2f}'
plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
x = int(xyxy[0]) # x좌표
y = int(xyxy[1]) # y좌표
w = int(xyxy[2]) # 넓이
h = int(xyxy[3]) # 높이
middle_x = int((x + w) / 2) # x좌표 시작점
middle_y = int((y + h) / 2) # y좌표 시작점
if names[int(cls)] == "ThreeWayBlock" or names[int(cls)] == "IntersectionBlock" and conf >= 0.6:
a = 10
region = im0[int(middle_y) - a:int(middle_y) + a, int(middle_x) - a:int(middle_x) + a]
min, max = image_min_max(region)
img_b_box = im0[y:h, x:w] # 바운딩 박스 좌표
image_Binarization(img_b_box, min, max) # 바운딩 박스만 이진화 진행
elif names[int(cls)] == "GoStraight": # 직진
print('직진 블록이 있습니다.')
# speak('직진 블록이 있습니다.')
elif names[int(cls)] == "Stop": # 정지
print('정지 블록이 있습니다.')
# speak('정지 블록이 있습니다.')
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path += '.mp4'
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer.write(im0)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
print(f"Results saved to {save_dir}{s}")
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='weights/last.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='0', help='source') # file/folder, 0 for webcam
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
# defalut 값 설정으로 boundingbox 출력 범위 제한
parser.add_argument('--conf-thres', type=float, default=0.6, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='display results')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--update', action='store_true', help='update all models')
parser.add_argument('--project', default='runs/detect', help='save results to project/name')
parser.add_argument('--name', default='exp', help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
opt = parser.parse_args()
print(opt)
check_requirements(exclude=('pycocotools', 'thop'))
with torch.no_grad():
if opt.update: # update all models (to fix SourceChangeWarning)
for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
detect()
strip_optimizer(opt.weights)
else:
detect()