第一次写博客求助
#AI项目名称
实时口罩识别
#主要应用领域(主要介绍该领域存在的问题以及你对这些问题的思考、想去解决这些问题的思路等。)
领域 :领域主要在一些人群密集的场所
问题:人群密集场所人口流动十分的大,所以需要进出时佩戴口罩,就目前学校的检测都是通过人力检测这样耗费了人力。
思路:可不可以通过在深度学习后实现自动检测呢?
解决办法:通过改进学习过的口罩佩戴识别实验达到目标
#项目开发语言、工具与平台
Python
Sublime
win10的操作系统
附上代码请大佬观摩
部分程序代码
# -*- coding:utf-8 -*-
import cv2
import time
import argparse
import numpy as np
from PIL import Image
from keras.models import model_from_json
from utils.anchor_generator import generate_anchors
from utils.anchor_decode import decode_bbox
from utils.nms import single_class_non_max_suppression
from load_model.tensorflow_loader import load_tf_model, tf_inference
'''yangsongling 改写部分'''
# 获取视频流
cap = cv2.VideoCapture(0)
# 指定编码格式
fourcc = cv2.VideoWriter_fourcc(*'MJPG')
# cv2.VideoWriter的参数分别为:保存路径,编码格式,帧率,帧大小
out = cv2.VideoWriter("avis/001.avi", fourcc, 20.0, (640,480))
#保存avi后不必删除下次打开会自动覆盖
while(cap.isOpened()):
ret, frame = cap.read()
if ret==True:
# 如果帧的大小与上述的(640, 480)不一致,需要resize
out.write(frame)
cv2.imshow('frame',frame)
#按q关闭窗口
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
#导入口罩智能识别模型
sess, graph = load_tf_model('models\face_mask_detection.pb')
# anchor configuration锚点设置
feature_map_sizes = [[33, 33], [17, 17], [9, 9], [5, 5], [3, 3]]
anchor_sizes = [[0.04, 0.056], [0.08, 0.11], [0.16, 0.22], [0.32, 0.45], [0.64, 0.72]]
anchor_ratios = [[1, 0.62, 0.42]] * 5
# generate anchors生成锚点
anchors = generate_anchors(feature_map_sizes, anchor_sizes, anchor_ratios)
#以下用于推断(inference),批大小为1,模型输出形状为[1,N,4],因此将锚点的dim扩展为[1,anchor_num,4]
anchors_exp = np.expand_dims(anchors, axis=0)
#将推断结果分为两类,一类Mask,表示佩戴了口罩,另外一类是NoMask,表示没有佩戴口罩
id2class = {0: 'mask', 1: 'NoMask'}
def inference(image, conf_thresh=0.5, iou_thresh=0.4, target_shape=(160, 160), draw_result=True, show_result=True):
''' 检测推理的主要功能
# :param image:3D numpy图片数组
# :param conf_thresh:分类概率的最小阈值。
# :param iou_thresh:网管的IOU门限
# :param target_shape:模型输入大小。
# :param draw_result:是否将边框拖入图像。
# :param show_result:是否显示图像。
'''
# image = np.copy(image)
output_info = []
height, width, _ = image.shape
image_resized = cv2.resize(image, target_shape)
image_np = image_resized / 255.0 # 归一化到0~1
image_exp = np.expand_dims(image_np, axis=0)
y_bboxes_output, y_cls_output = tf_inference(sess, graph, image_exp)
# remove the batch dimension, for batch is always 1 for inference.
y_bboxes = decode_bbox(anchors_exp, y_bboxes_output)[0]
y_cls = y_cls_output[0]
# 为了加快速度,请执行单类NMS,而不是多类NMS。
bbox_max_scores = np.max(y_cls, axis=1)
bbox_max_score_classes = np.argmax(y_cls, axis=1)
# keep_idx是nms之后的活动边界框。
keep_idxs = single_class_non_max_suppression(y_bboxes, bbox_max_scores, conf_thresh=conf_thresh,iou_thresh=iou_thresh)
for idx in keep_idxs:
conf = float(bbox_max_scores[idx])
class_id = bbox_max_score_classes[idx]
bbox = y_bboxes[idx]
# 裁剪坐标,避免该值超出图像边界。
xmin = max(0, int(bbox[0] * width))
ymin = max(0, int(bbox[1] * height))
xmax = min(int(bbox[2] * width), width)
ymax = min(int(bbox[3] * height), height)
if draw_result:
if class_id == 0:
color = (0, 255, 0)
else:
color = (255, 0, 0)
cv2.rectangle(image, (xmin, ymin), (xmax, ymax), color, 2)
cv2.putText(image, "%s: %.2f" % (id2class[class_id], conf), (xmin + 2, ymin - 2),
cv2.FONT_HERSHEY_SIMPLEX, 1, color)
output_info.append([class_id, conf, xmin, ymin, xmax, ymax])
if show_result:
Image.fromarray(image).show()
return output_info
def run_on_video(video_path, output_video_name, conf_thresh):
cap = cv2.VideoCapture(video_path)
height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT)
width = cap.get(cv2.CAP_PROP_FRAME_WIDTH)
fps = cap.get(cv2.CAP_PROP_FPS)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
#writer = cv2.VideoWriter(output_video_name, fourcc, int(fps), (int(width), int(height)))
total_frames = cap.get(cv2.CAP_PROP_FRAME_COUNT)
if not cap.isOpened():
raise ValueError("Video open failed.")
return
status = True
idx = 0
while status:
start_stamp = time.time()
status, img_raw = cap.read()
img_raw = cv2.cvtColor(img_raw, cv2.COLOR_BGR2RGB)
read_frame_stamp = time.time()
if (status):
inference(img_raw,
conf_thresh,
iou_thresh=0.5,
target_shape=(260, 260),
draw_result=True,
show_result=False)
cv2.imshow('image', img_raw[:, :, ::-1])
cv2.waitKey(1)
inference_stamp = time.time()
# writer.write(img_raw)
write_frame_stamp = time.time()
idx += 1
print("%d of %d" % (idx, total_frames))
print("read_frame:%f, infer time:%f, write time:%f" % (read_frame_stamp - start_stamp, inference_stamp - read_frame_stamp, write_frame_stamp - inference_stamp))
run_on_video("avis/001.avi", '', conf_thresh=0.5)
我把需要的文件也上传到百度云了
https://pan.baidu.com/s/1xZNUrz8TV-QFdfLfulOZFw
提取码 s8nj
写完之后
问题
然后有没有大佬教教我怎么搞?
注:本人是一名大一学生还在学习中,过程中可能用到过前辈的东西没注明来处
看到可找我我撤销文章,毕竟第一次写这个.