-
Notifications
You must be signed in to change notification settings - Fork 1
/
demo_with_hough.py
186 lines (148 loc) · 7.86 KB
/
demo_with_hough.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
# This demo_from_yolopv2.py is copied from YOLOPv2 github.
import argparse
import time
from pathlib import Path
import cv2
import torch
import numpy as np
# Conclude setting / general reprocessing / plots / metrices / datasets
from utils.utils_pv2 import \
time_synchronized,select_device, increment_path,\
scale_coords,xyxy2xywh,non_max_suppression,split_for_trace_model,\
driving_area_mask,lane_line_mask,plot_one_box,show_seg_result,\
AverageMeter,\
LoadImages
def make_parser():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='data/weights/yolopv2.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/example.jpg', help='source') # file/folder, 0 for webcam
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.3, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='0', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
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('--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')
return parser
def detect_hough_lines(image, min_line_length, max_line_gap, threshold=50):
# Convert the image to grayscale if it's not
if len(image.shape) == 3:
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
else:
gray = (image * 255).astype(np.uint8) # Convert binary mask to grayscale
# Detect lines using Hough Transform
lines = cv2.HoughLinesP(gray, 1, np.pi / 180, threshold, minLineLength=min_line_length, maxLineGap=max_line_gap)
if lines is not None:
for line in lines:
x1, y1, x2, y2 = line[0]
cv2.line(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
return image
def detect():
# setting and directories
source, weights, save_txt, imgsz = opt.source, opt.weights, opt.save_txt, opt.img_size
save_img = not opt.nosave and not source.endswith('.txt') # save inference images
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
inf_time = AverageMeter()
waste_time = AverageMeter()
nms_time = AverageMeter()
# Load model
stride =32
model = torch.jit.load(weights)
device = select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
model = model.to(device)
if half:
model.half() # to FP16
model.eval()
# Set Dataloader
vid_path, vid_writer = None, None
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# 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,anchor_grid],seg,ll= model(img)
t2 = time_synchronized()
tw1 = time_synchronized()
pred = split_for_trace_model(pred,anchor_grid)
tw2 = time_synchronized()
# Apply NMS
t3 = time_synchronized()
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t4 = time_synchronized()
da_seg_mask = driving_area_mask(seg)
ll_seg_mask = lane_line_mask(ll)
hough_img = detect_hough_lines(ll_seg_mask, min_line_length=300, max_line_gap=20)
show_seg_result(im0s, (da_seg_mask, hough_img), is_demo=True)
# Process detections
for i, det in enumerate(pred): # detections per image
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
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0s.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 : # Add bbox to image
plot_one_box(xyxy, im0, line_thickness=3)
# Print time (inference)
print(f'{s}Done. ({t2 - t1:.3f}s)')
show_seg_result(im0, (da_seg_mask,ll_seg_mask), is_demo=True)
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
print(f" The image with the result is saved in: {save_path}")
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))
w,h = im0.shape[1], im0.shape[0]
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)
inf_time.update(t2-t1,img.size(0))
nms_time.update(t4-t3,img.size(0))
waste_time.update(tw2-tw1,img.size(0))
print('inf : (%.4fs/frame) nms : (%.4fs/frame)' % (inf_time.avg,nms_time.avg))
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
opt = make_parser().parse_args()
print(opt)
with torch.no_grad():
detect()