yolov5识别屏幕指定区域
yolov5
yolov5 - Ultralytics YOLOv8的前身,是一个用于目标检测、图像分割和图像分类任务的先进模型。
项目地址:https://gitcode.com/gh_mirrors/yo/yolov5
免费下载资源
·
import cv2
import numpy as np
from numpy import random
from PIL import ImageGrab
import cv2 as CV2
import time
import win32api
import torch
from yolov5_camera_detect.models.experimental import attempt_load
from yolov5_camera_detect.utils.general import (check_img_size, non_max_suppression, scale_coords, plot_one_box)
from yolov5_camera_detect.utils.torch_utils import select_device
print('Setup complete. Using torch %s %s' % (
torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))
# Initialize
device = select_device()
frame_h = 480
frame_w = 800
obj_count = 0 # 警戒区目标
obj_count_old = 0 # 警戒区旧目标
take_photo_num = 0; # 拍照次数
# 每个监测不一定都检测得到,所以做个缓冲区用于取平均值,因为要避免某帧的目标丢失,会造成目标数量的跳变,引发拍照记录
obj_count_buf = np.array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0]) # 10个值
# Load model
model = attempt_load('weights/yolov5s.pt', map_location=device) # load FP32 model cuda
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))] #people框的颜色
# imgsz = check_img_size(486, s=model.stride.max()) # check img_size
frame_mask = np.zeros((frame_h, frame_w, 3), dtype=np.uint8) # 做一个相同尺寸格式的图片mask frame_mask隐藏的那个
postion = [(200, 100), (275, 391), (632, 381), (600, 70)] # 警戒区位置点,逆时针从左上角开始 # 识别区坐标
CV2.fillPoly(frame_mask, [np.array(postion)], (0, 0, 255)) # 警戒区内数字填充255,0,0成为mask 在frame_mask上绘制多边形并对其填充,位置、颜色
def process_img(original_image): # 原图处理函数
processed_img = CV2.cvtColor(original_image, CV2.COLOR_BGR2RGB) # BGR格式转换RGB
processed_img = CV2.resize(processed_img, (frame_w, frame_h)) # 改变输入尺寸
return processed_img
def MouseEvent(a, b, c, d, e): # 鼠标处理事件响应函数
if (a == 1): # 获取左键点击坐标点
print(b, c)
CV2.namedWindow('frame')
CV2.setMouseCallback('frame', MouseEvent) # 窗口与回调函数绑定 # 点击窗口(图片执行mouseevent函数)
while (1):
# get a frame
# frame = cv2.imread('4.jpg')
# frame = process_img(frame)
# cv2.imshow('nihao',frame)
# frame = np.array(cv2.VideoCapture(0))
# print(frame)
frame = np.array(ImageGrab.grab(bbox=(0, 100, 800, 600))) # frame为一个数组 ,np.array,将抓的图转换为数组,frame是数组
# bbox:(x_左,y_上,x_右,y_下),数字是线的坐标
if np.shape(frame): # frame有数据才能往下执行
# processing
frame = process_img(frame) # BGR格式转换RGB
img = frame.copy() # img为gpu格式,常规方法不能读取,im0为img的copy版可直接读取
# print("img:",np.shape(img)) #img: (480, 800, 3),480个[],每个800个数据,3维(高度、宽度、通道数)
# print(img),数组
img = np.transpose(img, (2, 0, 1)) # torch.Size([480, 800, 3])转torch.Size([3, 480, 800])
# print("img:",np.shape(img))
img = torch.from_numpy(img).to(device)
img = img.float() # uint8 to fp32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
# print(np.shape(img))#>>>torch.Size([3, 416, 352])
if img.ndimension() == 3:
img = img.unsqueeze(0) # 这个函数主要是对数据维度进行扩充,在0的位置加了一维
# print(np.shape(img))#>>>torch.Size([1, 3, 416, 352])
pred = model(img)[0]
# Apply NMS 非极大值抑制
pred = non_max_suppression(pred, 0.5, 0.5) # 大于0.4阈值的输出,只显示classes:>= 1,不能显示0?
# # 绘图 包含区域红色,标记的两种圆圈
if pred != [None]:
for i, det in enumerate(pred):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], frame.shape).round()
# Write results
for *xyxy, conf, cls in reversed(det):
if cls == 0: # 只显示0(person)的标签,因为non_max_suppression(只显示classes:>= 1)的标签
label = '%s %.2f' % (names[int(cls)], conf)
plot_one_box(xyxy, frame, label=label, color=colors[int(cls)],
line_thickness=1) # utils.general专用画框标注函数
xy = torch.tensor(xyxy).tolist() # 张量转换成列表形式
x, y, x1, y1 = int(xy[0]), int(xy[1]), int(xy[2]), int(xy[3]) # 获取左顶右底坐标
center_xy = (int(np.average([x, x1])), int(np.average([y, y1]))) # 计算中心点
if (frame_mask[(center_xy[1], center_xy[0])] == [0, 0, 255]).all(): # 中心点在警戒区
obj_color = (0, 0, 0) # 改变中心点颜色,警戒区域外颜色
obj_count += 1
else:
obj_color = (0, 0, 255) # 改变中心点颜色 警戒区域内颜色
CV2.circle(frame, center_xy, 10, obj_color, 4) # 开始画点,画圆圈
obj_count_buf = np.append(obj_count_buf[1:], obj_count) # 保持更新10个缓冲区
cbr = int(np.around(np.average(obj_count_buf)))#cbr是当前区域内人数
CV2.putText(frame, 'obj_count :%s obj take_photo: %s' % (cbr, take_photo_num), (100, 20),
CV2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255), 2) # 文字信息显示
frame = CV2.addWeighted(frame, 1.0, frame_mask, 0.1, 0.0) # 叠加掩码图片进实时图,将frame_mask叠加到frame中
if (obj_count_old != cbr):#警戒区人数有变化
take_photo_num += 1
CV2.imwrite("./photo/%s.jpg" % take_photo_num, frame, [int(CV2.IMWRITE_JPEG_QUALITY), 50]) # 保存图片
print('take photo number :%s' % take_photo_num) # 显示记录的照片张数
CV2.putText(frame, 'take photo', (100, 300), CV2.FONT_HERSHEY_SIMPLEX, 3, (0, 0, 255), 3) # 文字信息显示
obj_count_old = cbr # 保存上个数据
obj_count = 0 # 目标显示清零,等待下次探测
# show a frame
# CV2.imshow("capture", frame[:,:,::-1])
CV2.imshow("frame", frame)
CV2.imshow("frame_mask", frame_mask[:,:,::-1])
if CV2.waitKey(1) & 0xFF == ord('q'):
break
CV2.destroyAllWindows()
GitHub 加速计划 / yo / yolov5
49.35 K
16.03 K
下载
yolov5 - Ultralytics YOLOv8的前身,是一个用于目标检测、图像分割和图像分类任务的先进模型。
最近提交(Master分支:2 个月前 )
79b7336f
* Update Integrations table
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Update README.md
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Update README.zh-CN.md
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
---------
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> 4 天前
94a62456
* fix: quad training
* fix: quad training in segmentation 6 天前
更多推荐
已为社区贡献3条内容
所有评论(0)