# USAGE
# python detect_mask_video.py
# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import argparse
import imutils
import time
import cv2
import os
def detect_and_predict_mask(frame, faceNet, maskNet):
# grab the dimensions of the frame and then construct a blob
# from it
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300),
(104.0, 177.0, 123.0))
# pass the blob through the network and obtain the face detections
faceNet.setInput(blob)
detections = faceNet.forward()
# initialize our list of faces, their corresponding locations,
# and the list of predictions from our face mask network
faces = []
locs = []
preds = []
# loop over the detections
for i in range(0, detections.shape[2]):
# extract the confidence (i.e., probability) associated with
# the detection
confidence = detections[0, 0, i, 2]
# filter out weak detections by ensuring the confidence is
# greater than the minimum confidence
if confidence > args["confidence"]:
# compute the (x, y)-coordinates of the bounding box for
# the object
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
# ensure the bounding boxes fall within the dimensions of
# the frame
(startX, startY) = (max(0, startX), max(0, startY))
(endX, endY) = (min(w - 1, endX), min(h - 1, endY))
# extract the face ROI, convert it from BGR to RGB channel
# ordering, resize it to 224x224, and preprocess it
face = frame[startY:endY, startX:endX]
face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
face = cv2.resize(face, (224, 224))
face = img_to_array(face)
face = preprocess_input(face)
# add the face and bounding boxes to their respective
# lists
faces.append(face)
locs.append((startX, startY, endX, endY))
# only make a predictions if at least one face was detected
if len(faces) > 0:
# for faster inference we'll make batch predictions on *all*
# faces at the same time rather than one-by-one predictions
# in the above `for` loop
faces = np.array(faces, dtype="float32")
preds = maskNet.predict(faces, batch_size=32)
# return a 2-tuple of the face locations and their corresponding
# locations
return (locs, preds)
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-f", "--face", type=str,
default="face_detector",
help="path to face detector model directory")
ap.add_argument("-m", "--model", type=str,
default="mask_detector.model",
help="path to trained face mask detector model")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())
# load our serialized face detector model from disk
print("[INFO] loading face detector model...")
prototxtPath = os.path.sep.join([args["face"], "deploy.prototxt"])
weightsPath = os.path.sep.join([args["face"],
"res10_300x300_ssd_iter_140000.caffemodel"])
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)
# load the face mask detector model from disk
print("[INFO] loading face mask detector model...")
maskNet = load_model(args["model"])
# initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
time.sleep(2.0)
# loop over the frames from the video stream
while True:
# grab the frame from the threaded video stream and resize it
# to have a maximum width of 400 pixels
frame = vs.read()
frame = imutils.resize(frame, width=400)
# detect faces in the frame and determine if they are wearing a
# face mask or not
(locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)
# loop over the detected face locations and their corresponding
# locations
for (box, pred) in zip(locs, preds):
# unpack the bounding box and predictions
(startX, startY, endX, endY) = box
(mask, withoutMask) = pred
# determine the class label and color we'll use to draw
# the bounding box and text
label = "Mask" if mask > withoutMask else "No Mask"
color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
# include the probability in the label
label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)
# display the label and bounding box rectangle on the output
# frame
cv2.putText(frame, label, (startX, startY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)
# show the output frame
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()
没有合适的资源?快使用搜索试试~ 我知道了~
基于PyTorch的口罩检测与分类mask_detection代码详解.zip
共24个文件
jpg:18个
png:2个
py:2个
1星 需积分: 40 62 下载量 61 浏览量
2020-10-25
17:13:07
上传
评论 7
收藏 4.96MB ZIP 举报
温馨提示
针对口罩检测,进行调研,包括了分类器的设计,人脸检测的设计。 其中主要分为两阶段,先是人脸检测,然后将检测到的人脸,进行二分类,标签为戴口罩,不戴口罩。包括了pytorch的代码,ppt的讲解,技术文档。 人脸识别是MTCNN,然后分类可以自己训练,我采用的是ResNet-18.
资源推荐
资源详情
资源评论
收起资源包目录
基于PyTorch的口罩检测与分类mask_detection代码详解.zip (24个子文件)
mask_detection.pptx 1.81MB
0_0_benxi_0187.jpg 6KB
0_0_0 copy 84.jpg 20KB
0_0_aidai_0014.jpg 6KB
1603594935(1).jpg 814KB
0_0_0 copy 10.jpg 4KB
1603597166(1).jpg 121KB
pic2.jpg 54KB
0_0_1 copy 13.jpg 17KB
0_0_0 copy 82.jpg 7KB
1603598728(1).jpg 422KB
0_0_caiguoqing_0007.jpg 7KB
0_0_baobeier_0064.jpg 5KB
1603597057(1).jpg 121KB
mask__detection_video.py 5KB
图片1.png 619KB
out.jpg 37KB
pic1.jpeg 77KB
20200217180115673.png 798KB
0_0_liuqianhan_0150.jpg 6KB
1603596793(1).jpg 73KB
1603596849(1).jpg 39KB
0.jpg 21KB
mask_detection_image.py 4KB
共 24 条
- 1
资源评论
- fwherr2021-08-15资源不对他所讲文字描述说明,坑人文档
是否龙磊磊真的一无所有
- 粉丝: 422
- 资源: 32
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功