-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathmain.py
132 lines (109 loc) · 5.23 KB
/
main.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
# initializing the settings of YOLOv3
from absl import flags
import sys
import time # to calculate frames per second
import numpy as np
import cv2
import matplotlib.pyplot as plt # just for color map
import os
import tensorflow as tf
from yolov3_tf2.models import YoloV3
from yolov3_tf2.dataset import transform_images # used for resizing our image for the yolo format
from yolov3_tf2.utils import convert_boxes
from deep_sort import preprocessing
from deep_sort import nn_matching
from deep_sort.detection import Detection
from deep_sort.tracker import Tracker
from tools import generate_detections as gdet
os.environ["CUDA_VISIBLE_DEVICES"]="-1" #to make it run on the cpu only
FLAGS = flags.FLAGS
FLAGS(sys.argv)
class_names = [c.strip() for c in open('./data/labels/coco.names').readlines()]
yolo = YoloV3(classes=len(class_names))
yolo.load_weights('./weights/yolov3.tf')
max_cosine_distance = 0.5
nn_budget = None
nms_max_overlap = 0.8
model_filename = 'model_data/mars-small128.pb'
encoder = gdet.create_box_encoder(model_filename, batch_size=1)
metric = nn_matching.NearestNeighborDistanceMetric('cosine', max_cosine_distance, nn_budget)
tracker = Tracker(metric)
vid = cv2.VideoCapture('D:\learning\Projects\Car detection and tracking using YOLOv3\data\pideo\est.mp4')
codec = cv2.VideoWriter_fourcc(*'DIVX')
vid_fps = int(vid.get(cv2.CAP_PROP_FPS))
vidwidth, vid_height = int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)), int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT))
out = cv2.VideoWriter('./data/video/resultsf.avi', codec, vid_fps, (vidwidth, vid_height))
from _collections import deque
pts = [deque(maxlen=30) for _ in range(1000)]
counter = []
while True:
_, img = vid.read()
if img is None:
print('Completed')
break
img_in = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img_in = tf.expand_dims(img_in, 0)
img_in = transform_images(img_in, 416)
t1 = time.time()
boxes, scores, classes, nums = yolo.predict(img_in)
classes = classes[0]
names = []
for i in range(len(classes)):
names.append(class_names[int(classes[i])])
names = np.array(names)
converted_boxes = convert_boxes(img, boxes[0])
features = encoder(img, converted_boxes)
detections = [Detection(bbox, score, class_name, feature) for bbox, score, class_name, feature in
zip(converted_boxes, scores[0], names, features)]
boxs = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
classes = np.array([d.class_name for d in detections])
indices = preprocessing.non_max_suppression(boxs, classes, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
tracker.predict()
tracker.update(detections)
cmap = plt.get_cmap('tab20b')
colors = [cmap(i)[:3] for i in np.linspace(0, 1, 20)]
current_count = int(0)
for track in tracker.tracks:
if not track.is_confirmed() or track.time_since_update > 1:
continue
bbox = track.to_tlbr()
class_name = track.get_class()
color = colors[int(track.track_id) % len(colors)]
color = [i * 255 for i in color]
if(class_name=="person"):
img = cv2.rectangle(img, (int(bbox[0]), int(bbox[1])), (int(bbox[2]), int(bbox[3])), color, 2) # top left, botom right
img = cv2.rectangle(img, (int(bbox[0]), int(bbox[1] - 30)), (int(bbox[0]) + (len(class_name) + len(str(track.track_id))) * 17, int(bbox[1])), color, 2)
cv2.putText(img, class_name + "-" + str(track.track_id), (int(bbox[0]), int(bbox[1] - 10)), 0, 0.75, (255, 255, 255), 2)
center = (int(((bbox[0]) + (bbox[2])) / 2), int(((bbox[1]) + (bbox[3])) / 2))
pts[track.track_id].append(center)
for j in range(1, len(pts[track.track_id])):
if pts[track.track_id][j - 1] is None or pts[track.track_id][j] is None:
continue
thickness = int(np.sqrt(64 / float(j + 1)) * 2)
cv2.line(img, (pts[track.track_id][j - 1]), (pts[track.track_id][j]), color, thickness)
height, width, _ = img.shape
cv2.line(img, (0, int(3 * height / 6 + height / 20)), (width, int(3 * height / 6 + height / 20)), (0, 255, 0),
thickness=2)
cv2.line(img, (0, int(3 * height / 6 - height / 20)), (width, int(3 * height / 6 - height / 20)), (0, 255, 0),
thickness=2)
center_y = int(((bbox[1]) + (bbox[3])) / 2)
if center_y <= int(3 * height / 6 + height / 20) and center_y >= int(3 * height / 6 - height / 20):
if class_name == 'truck' or class_name == 'car':
counter.append(int(track.track_id))
current_count += 1
total_count = len(set(counter))
cv2.putText(img, "Current Vehicle Count: " + str(current_count), (0, 80), 0, 1, (0, 0, 255), 2)
cv2.putText(img, "Total Vehicle Count: " + str(total_count), (0, 130), 0, 1, (0, 0, 255), 2)
fps = 1. / (time.time() - t1)
cv2.putText(img, "FPS: {:.2f}".format(fps), (0, 30), 0, 1, (0, 0, 255), 2)
cv2.namedWindow('output', 0)
cv2.resizeWindow('output', 1024, 768)
cv2.imshow('output', img)
out.write(img)
if cv2.waitKey(1) == ord('q'):
break
vid.release()
out.release()
cv2.destroyAllWindows()