update
This commit is contained in:
4
.gitignore
vendored
4
.gitignore
vendored
@ -136,3 +136,7 @@ dmypy.json
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
*.jpg
|
||||
*.png
|
||||
*.pth
|
||||
|
||||
63
checkobject.py
Normal file
63
checkobject.py
Normal file
@ -0,0 +1,63 @@
|
||||
import cv2 as cv
|
||||
#from segmentation import get_object_mask
|
||||
import os, time
|
||||
|
||||
def get_object_location(pfile, mask_path = 'lianhua_1.jpg'):
|
||||
kernel = cv.getStructuringElement(cv.MORPH_ELLIPSE, (3, 3)) # 定义结构元素
|
||||
fgbg = cv.createBackgroundSubtractorMOG2(detectShadows=False)
|
||||
nu, nn = 0, 1
|
||||
flag = False
|
||||
T1 = time.time()
|
||||
# 设置文件
|
||||
cap = cv.VideoCapture(pfile)
|
||||
while True:
|
||||
# 读取一帧
|
||||
ret, frame = cap.read()
|
||||
nn += 1
|
||||
if (not ret):
|
||||
break
|
||||
if flag:
|
||||
flag = False
|
||||
print('flag change>>{}>>{}'.format(pfile, nn))
|
||||
return '1'
|
||||
|
||||
frame = cv.resize(frame, (512, 640), interpolation=cv.INTER_CUBIC)
|
||||
frame = cv.medianBlur(frame, ksize=3)
|
||||
frame_motion = frame.copy()
|
||||
|
||||
# 计算前景掩码
|
||||
fgmask = fgbg.apply(frame_motion)
|
||||
draw1 = cv.threshold(fgmask, 25, 255, cv.THRESH_BINARY)[1] # 二值化
|
||||
draw1 = cv.dilate(draw1, kernel, iterations=1)
|
||||
if nn<10: #判断10帧内有入侵动作
|
||||
flag = check_tings(mask_path, draw1)
|
||||
T2 = time.time()
|
||||
print('single video >>> {}-->{}-->{}'.format(pfile, nn, (T2 - T1)))
|
||||
return '0'
|
||||
|
||||
def check_tings(mask_path, img):
|
||||
dics = {}
|
||||
mask_img = cv.imread(mask_path)
|
||||
img = cv.bitwise_and(mask_img[:,:,0], img)
|
||||
contours_m, hierarchy_m = cv.findContours(img.copy(), cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
|
||||
for contour in contours_m:
|
||||
# print('contour', hierarchy_m)
|
||||
dics[len(contour)] = contour
|
||||
if len(dics.keys()) > 0:
|
||||
cc = sorted(dics.keys())
|
||||
iouArea = cv.contourArea(dics[cc[-1]])
|
||||
# if iouArea>10000 and iouArea<40000:
|
||||
if iouArea>10000 and iouArea<40000:
|
||||
return '1'
|
||||
else:
|
||||
return '0'
|
||||
else:
|
||||
return '0'
|
||||
|
||||
if __name__ == '__main__':
|
||||
pfile = "videos/20230130-100958_e5910f7d-90dd-4f6b-9468-689ba45fe656.mp4"
|
||||
mask_path = 'models/lianhua_1.jpg'
|
||||
#frame_path = 'frame'
|
||||
#result_path = 'result'
|
||||
get_object_location(pfile, mask_path)
|
||||
|
||||
23
ieemoo-ai-filtervideo.py
Normal file
23
ieemoo-ai-filtervideo.py
Normal file
@ -0,0 +1,23 @@
|
||||
from flask import request,Flask, jsonify
|
||||
from checkobject import get_object_location
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
app = Flask(__name__)
|
||||
@app.route('/filtervideo', methods=['POST'])
|
||||
def filtervideo():
|
||||
videourls = request.form.get('videoUrls')
|
||||
videoid = request.form.get('id')
|
||||
videopath = os.sep.join(['data', videoid+'.mp4'])
|
||||
barcode = request.form.get('barcode')
|
||||
videourls = videourls.split(',')
|
||||
results = []
|
||||
for name in videourls:
|
||||
videos = requests.get(url)
|
||||
videos.save(videopath)
|
||||
flag = get_object_location(videopath)
|
||||
results.append({'id':videoids, 'result':flags})
|
||||
return result
|
||||
|
||||
if __name__ == '__main__':
|
||||
app.run()
|
||||
180
segpredict.py
Normal file
180
segpredict.py
Normal file
@ -0,0 +1,180 @@
|
||||
import os
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||||
|
||||
import numpy as np
|
||||
import cv2
|
||||
import matplotlib.pyplot as plt
|
||||
import albumentations as albu
|
||||
import torch
|
||||
import segmentation_models_pytorch as smp
|
||||
from torch.utils.data import Dataset as BaseDataset
|
||||
import imageio
|
||||
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
### Dataloader
|
||||
|
||||
class Dataset(BaseDataset):
|
||||
"""CamVid数据集。进行图像读取，图像增强增强和图像预处理.
|
||||
|
||||
Args:
|
||||
images_dir (str): 图像文件夹所在路径
|
||||
masks_dir (str): 图像分割的标签图像所在路径
|
||||
class_values (list): 用于图像分割的所有类别数
|
||||
augmentation (albumentations.Compose): 数据传输管道
|
||||
preprocessing (albumentations.Compose): 数据预处理
|
||||
"""
|
||||
# CamVid数据集中用于图像分割的所有标签类别
|
||||
#CLASSES = ['sky', 'building', 'pole', 'road', 'pavement',
|
||||
# 'tree', 'signsymbol', 'fence', 'car',
|
||||
# 'pedestrian', 'bicyclist', 'unlabelled']
|
||||
CLASSES = ['front']
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
images_dir,
|
||||
# masks_dir,
|
||||
classes=None,
|
||||
augmentation=None,
|
||||
preprocessing=None,
|
||||
):
|
||||
self.ids = os.listdir(images_dir)
|
||||
self.images_fps = [os.path.join(images_dir, image_id) for image_id in self.ids]
|
||||
|
||||
# convert str names to class values on masks
|
||||
self.class_values = [self.CLASSES.index(cls.lower()) for cls in classes]
|
||||
|
||||
self.augmentation = augmentation
|
||||
self.preprocessing = preprocessing
|
||||
|
||||
def __getitem__(self, i):
|
||||
|
||||
# read data
|
||||
image = cv2.imread(self.images_fps[i])
|
||||
image = cv2.resize(image, (512, 512)) # 改变图片分辨率
|
||||
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
|
||||
# 图像增强应用
|
||||
if self.augmentation:
|
||||
sample = self.augmentation(image=image)
|
||||
image = sample['image']
|
||||
|
||||
# 图像预处理应用
|
||||
if self.preprocessing:
|
||||
sample = self.preprocessing(image=image)
|
||||
image = sample['image']
|
||||
|
||||
return image
|
||||
|
||||
def __len__(self):
|
||||
return len(self.ids)
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
|
||||
def get_validation_augmentation():
|
||||
"""调整图像使得图片的分辨率长宽能被32整除"""
|
||||
test_transform = [
|
||||
albu.PadIfNeeded(384, 480)
|
||||
]
|
||||
return albu.Compose(test_transform)
|
||||
|
||||
|
||||
def to_tensor(x, **kwargs):
|
||||
return x.transpose(2, 0, 1).astype('float32')
|
||||
|
||||
|
||||
def get_preprocessing(preprocessing_fn):
|
||||
"""进行图像预处理操作
|
||||
|
||||
Args:
|
||||
preprocessing_fn (callbale): 数据规范化的函数
|
||||
(针对每种预训练的神经网络)
|
||||
Return:
|
||||
transform: albumentations.Compose
|
||||
"""
|
||||
|
||||
_transform = [
|
||||
albu.Lambda(image=preprocessing_fn),
|
||||
albu.Lambda(image=to_tensor),
|
||||
]
|
||||
return albu.Compose(_transform)
|
||||
|
||||
|
||||
# 图像分割结果的可视化展示
|
||||
def visualize(**images):
|
||||
"""PLot images in one row."""
|
||||
n = len(images)
|
||||
plt.figure(figsize=(16, 5))
|
||||
for i, (name, image) in enumerate(images.items()):
|
||||
plt.subplot(1, n, i + 1)
|
||||
plt.xticks([])
|
||||
plt.yticks([])
|
||||
plt.title(' '.join(name.split('_')).title())
|
||||
plt.imshow(image)
|
||||
plt.show()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
if __name__ == '__main__':
|
||||
|
||||
DATA_DIR = './data/CamVid/'
|
||||
|
||||
x_test_dir = os.path.join(DATA_DIR, 'abc')
|
||||
|
||||
img_test = cv2.imread('data/CamVid/abc/pic_unscan_front.jpg')
|
||||
height = img_test.shape[0]
|
||||
weight = img_test.shape[1]
|
||||
print(type(img_test))
|
||||
print('>>>>>>shape {}'.format(img_test.shape))
|
||||
|
||||
#ENCODER = 'resnet18'
|
||||
ENCODER = 'mobilenet_v2'
|
||||
ENCODER_WEIGHTS = 'imagenet'
|
||||
CLASSES = ['front']
|
||||
ACTIVATION = 'sigmoid' # could be None for logits or 'softmax2d' for multiclass segmentation
|
||||
DEVICE = 'cuda'
|
||||
|
||||
# 按照权重预训练的相同方法准备数据
|
||||
preprocessing_fn = smp.encoders.get_preprocessing_fn(ENCODER, ENCODER_WEIGHTS)
|
||||
|
||||
# 加载最佳模型
|
||||
best_model = torch.load('./best_model.pth')
|
||||
|
||||
# 创建检测数据集
|
||||
predict_dataset = Dataset(
|
||||
x_test_dir,
|
||||
augmentation=get_validation_augmentation(),
|
||||
preprocessing=get_preprocessing(preprocessing_fn),
|
||||
classes=CLASSES,
|
||||
)
|
||||
|
||||
# 对检测图像进行图像分割并进行图像可视化展示
|
||||
predict_dataset_vis = Dataset(
|
||||
x_test_dir,
|
||||
classes=CLASSES,
|
||||
)
|
||||
|
||||
for i in range(len(predict_dataset)):
|
||||
# 原始图像image_vis
|
||||
image_vis = predict_dataset_vis[i].astype('uint8')
|
||||
image = predict_dataset[i]
|
||||
|
||||
# 通过图像分割得到的0-1图像pr_mask
|
||||
x_tensor = torch.from_numpy(image).to(DEVICE).unsqueeze(0)
|
||||
pr_mask = best_model.predict(x_tensor)
|
||||
pr_mask = (pr_mask.squeeze().cpu().numpy().round())
|
||||
print('>>>>>>> pr_mask{}'.format(pr_mask.shape))
|
||||
print('>>>>>>{} {}'.format(height, weight))
|
||||
|
||||
# 恢复图片原来的分辨率
|
||||
#image_vis = cv2.resize(image_vis, (weight, height))
|
||||
#pr_mask = cv2.resize(pr_mask, (weight, height))
|
||||
pr_mask = cv2.resize(pr_mask[0,:,:], (weight, height))
|
||||
# 保存图像分割后的黑白结果图像
|
||||
imageio.imwrite('f_test_out.png', pr_mask)
|
||||
# 原始图像和图像分割结果的可视化展示
|
||||
# visualize(
|
||||
# image=image_vis,
|
||||
# predicted_mask=pr_mask
|
||||
# )
|
||||
|
||||
222
segtrain.py
Normal file
222
segtrain.py
Normal file
@ -0,0 +1,222 @@
|
||||
import os
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||||
|
||||
import numpy as np
|
||||
import cv2
|
||||
import matplotlib.pyplot as plt
|
||||
import albumentations as albu
|
||||
import torch
|
||||
import segmentation_models_pytorch as smp
|
||||
from torch.utils.data import DataLoader
|
||||
from torch.utils.data import Dataset as BaseDataset
|
||||
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
|
||||
class Dataset(BaseDataset):
|
||||
#CLASSES = ['sky', 'building', 'pole', 'road', 'pavement',
|
||||
# 'tree', 'signsymbol', 'fence', 'car',
|
||||
# 'pedestrian', 'bicyclist', 'unlabelled']
|
||||
|
||||
CLASSES = ['front', 'background']
|
||||
def __init__(
|
||||
self,
|
||||
images_dir,
|
||||
masks_dir,
|
||||
classes=None,
|
||||
augmentation=None,
|
||||
preprocessing=None,
|
||||
):
|
||||
self.ids = os.listdir(images_dir)
|
||||
self.images_fps = [os.path.join(images_dir, image_id) for image_id in self.ids]
|
||||
self.masks_fps = [os.path.join(masks_dir, image_id) for image_id in self.ids]
|
||||
|
||||
# convert str names to class values on masks
|
||||
self.class_values = [self.CLASSES.index(cls.lower()) for cls in classes]
|
||||
|
||||
self.augmentation = augmentation
|
||||
self.preprocessing = preprocessing
|
||||
|
||||
def __getitem__(self, i):
|
||||
|
||||
# read data
|
||||
image = cv2.imread(self.images_fps[i])
|
||||
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||||
mask = cv2.imread(self.masks_fps[i], 0)
|
||||
|
||||
masks = [(mask == v) for v in self.class_values]
|
||||
mask = np.stack(masks, axis=-1).astype('float')
|
||||
|
||||
if self.augmentation:
|
||||
#print('>>>>>>>{}'.format(image.shape[:2]))
|
||||
sample = self.augmentation(image=image, mask=mask)
|
||||
image, mask = sample['image'], sample['mask']
|
||||
|
||||
if self.preprocessing:
|
||||
sample = self.preprocessing(image=image, mask=mask)
|
||||
image, mask = sample['image'], sample['mask']
|
||||
|
||||
return image, mask
|
||||
|
||||
def __len__(self):
|
||||
return len(self.ids)
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
|
||||
def get_training_augmentation():
|
||||
train_transform = [
|
||||
|
||||
albu.HorizontalFlip(p=0.5),
|
||||
|
||||
albu.ShiftScaleRotate(scale_limit=0.5, rotate_limit=0, shift_limit=0.1, p=1, border_mode=0),
|
||||
|
||||
albu.PadIfNeeded(min_height=320, min_width=320, always_apply=True, border_mode=0),
|
||||
albu.RandomCrop(height=320, width=320, always_apply=True),
|
||||
|
||||
albu.IAAAdditiveGaussianNoise(p=0.2),
|
||||
albu.IAAPerspective(p=0.5),
|
||||
|
||||
albu.OneOf(
|
||||
[
|
||||
albu.CLAHE(p=1),
|
||||
albu.RandomBrightness(p=1),
|
||||
albu.RandomGamma(p=1),
|
||||
],
|
||||
p=0.9,
|
||||
),
|
||||
|
||||
albu.OneOf(
|
||||
[
|
||||
albu.IAASharpen(p=1),
|
||||
albu.Blur(blur_limit=3, p=1),
|
||||
albu.MotionBlur(blur_limit=3, p=1),
|
||||
],
|
||||
p=0.9,
|
||||
),
|
||||
|
||||
albu.OneOf(
|
||||
[
|
||||
albu.RandomContrast(p=1),
|
||||
albu.HueSaturationValue(p=1),
|
||||
],
|
||||
p=0.9,
|
||||
),
|
||||
]
|
||||
return albu.Compose(train_transform)
|
||||
|
||||
|
||||
def get_validation_augmentation():
|
||||
test_transform = [
|
||||
albu.PadIfNeeded(384, 480)
|
||||
]
|
||||
return albu.Compose(test_transform)
|
||||
|
||||
|
||||
def to_tensor(x, **kwargs):
|
||||
return x.transpose(2, 0, 1).astype('float32')
|
||||
|
||||
|
||||
def get_preprocessing(preprocessing_fn):
|
||||
|
||||
_transform = [
|
||||
albu.Lambda(image=preprocessing_fn),
|
||||
albu.Lambda(image=to_tensor, mask=to_tensor),
|
||||
]
|
||||
return albu.Compose(_transform)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------
|
||||
if __name__ == '__main__':
|
||||
|
||||
DATA_DIR = './data/CamVid/'
|
||||
|
||||
if not os.path.exists(DATA_DIR):
|
||||
print('Loading data...')
|
||||
os.system('git clone https://github.com/alexgkendall/SegNet-Tutorial ./data')
|
||||
print('Done!')
|
||||
|
||||
x_train_dir = os.path.join(DATA_DIR, 'train')
|
||||
y_train_dir = os.path.join(DATA_DIR, 'trainannot')
|
||||
|
||||
x_valid_dir = os.path.join(DATA_DIR, 'val')
|
||||
y_valid_dir = os.path.join(DATA_DIR, 'valannot')
|
||||
|
||||
#ENCODER = 'se_resnext50_32x4d'
|
||||
#ENCODER = 'resnet18'
|
||||
ENCODER = 'mobilenet_v2'
|
||||
ENCODER_WEIGHTS = 'imagenet'
|
||||
CLASSES = ['front', 'background']
|
||||
ACTIVATION = 'sigmoid' # could be None for logits or 'softmax2d' for multiclass segmentation
|
||||
DEVICE = 'cuda'
|
||||
|
||||
#model = smp.UnetPlusPlus(
|
||||
model = smp.Unet(
|
||||
encoder_name=ENCODER,
|
||||
encoder_weights=ENCODER_WEIGHTS,
|
||||
classes=len(CLASSES),
|
||||
activation=ACTIVATION,
|
||||
)
|
||||
|
||||
preprocessing_fn = smp.encoders.get_preprocessing_fn(ENCODER, ENCODER_WEIGHTS)
|
||||
|
||||
train_dataset = Dataset(
|
||||
x_train_dir,
|
||||
y_train_dir,
|
||||
augmentation=get_training_augmentation(),
|
||||
preprocessing=get_preprocessing(preprocessing_fn),
|
||||
classes=CLASSES,
|
||||
)
|
||||
|
||||
valid_dataset = Dataset(
|
||||
x_valid_dir,
|
||||
y_valid_dir,
|
||||
augmentation=get_validation_augmentation(),
|
||||
preprocessing=get_preprocessing(preprocessing_fn),
|
||||
classes=CLASSES,
|
||||
)
|
||||
|
||||
train_loader = DataLoader(train_dataset, batch_size=16, shuffle=True, num_workers=0)
|
||||
valid_loader = DataLoader(valid_dataset, batch_size=1, shuffle=False, num_workers=0)
|
||||
|
||||
loss = smp.utils.losses.DiceLoss()
|
||||
metrics = [
|
||||
smp.utils.metrics.IoU(threshold=0.5),
|
||||
]
|
||||
|
||||
optimizer = torch.optim.Adam([
|
||||
dict(params=model.parameters(), lr=0.0001),
|
||||
])
|
||||
|
||||
train_epoch = smp.utils.train.TrainEpoch(
|
||||
model,
|
||||
loss=loss,
|
||||
metrics=metrics,
|
||||
optimizer=optimizer,
|
||||
device=DEVICE,
|
||||
verbose=True,
|
||||
)
|
||||
|
||||
valid_epoch = smp.utils.train.ValidEpoch(
|
||||
model,
|
||||
loss=loss,
|
||||
metrics=metrics,
|
||||
device=DEVICE,
|
||||
verbose=True,
|
||||
)
|
||||
|
||||
max_score = 0
|
||||
|
||||
for i in range(0, 100):
|
||||
|
||||
print('\nEpoch: {}'.format(i))
|
||||
train_logs = train_epoch.run(train_loader)
|
||||
valid_logs = valid_epoch.run(valid_loader)
|
||||
|
||||
if max_score < valid_logs['iou_score']:
|
||||
max_score = valid_logs['iou_score']
|
||||
torch.save(model, './best_model.pth')
|
||||
print('Model saved!')
|
||||
|
||||
if i == 25:
|
||||
optimizer.param_groups[0]['lr'] = 1e-5
|
||||
print('Decrease decoder learning rate to 1e-5!')
|
||||
Reference in New Issue
Block a user