99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
|
import datetime
|
||
|
|
import os
|
||
|
|
import time
|
||
|
|
import ffmpeg
|
||
|
|
import torch
|
||
|
|
import cv2
|
||
|
|
import numpy as np
|
||
|
|
from multiprocessing import Process, Manager
|
||
|
|
from threading import Thread
|
||
|
|
from read_data import LoadImages, LoadStreams
|
||
|
|
import torch.backends.cudnn as cudnn
|
||
|
|
|
||
|
|
class FaceDetection():
|
||
|
|
time_reference = datetime.datetime.now()
|
||
|
|
counter_frame = 0
|
||
|
|
processed_fps = 0
|
||
|
|
global num_people
|
||
|
|
num_people = 100
|
||
|
|
global accuracy
|
||
|
|
accuracy = 1
|
||
|
|
|
||
|
|
def __init__(self,video_path=None, model=None):
|
||
|
|
|
||
|
|
self.model = model
|
||
|
|
self.classes = self.model.names
|
||
|
|
|
||
|
|
self.frame = [None]
|
||
|
|
|
||
|
|
if video_path is not None:
|
||
|
|
self.video_name = video_path
|
||
|
|
else:
|
||
|
|
self.video_name = 'vid2.mp4' # A default video file
|
||
|
|
|
||
|
|
|
||
|
|
self.dataset = LoadImages(self.video_name)
|
||
|
|
|
||
|
|
def use_webcam(self, source):
|
||
|
|
# self.dataset.release() # Release any existing video capture
|
||
|
|
# self.cap = cv2.VideoCapture(0) # Open default webcam
|
||
|
|
# print('use_webcam')
|
||
|
|
source = source
|
||
|
|
self.imgsz = 640
|
||
|
|
cudnn.benchmark = True
|
||
|
|
self.dataset = LoadStreams(source, img_size=self.imgsz)
|
||
|
|
|
||
|
|
def class_to_label(self, x):
|
||
|
|
return self.classes[int(x)]
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
def get_frame(self):
|
||
|
|
|
||
|
|
for im0s in self.dataset:
|
||
|
|
# print(self.dataset.mode)
|
||
|
|
# print(self.dataset)
|
||
|
|
if self.dataset.mode == 'stream':
|
||
|
|
img = im0s[0].copy()
|
||
|
|
else:
|
||
|
|
img = im0s.copy()
|
||
|
|
|
||
|
|
results = self.model(img, size=640)
|
||
|
|
|
||
|
|
num_people = 0
|
||
|
|
bgr = (0, 255, 0)
|
||
|
|
|
||
|
|
for obj in results.xyxy[0]:
|
||
|
|
|
||
|
|
|
||
|
|
if obj[-1] == 0: # 0 is the class ID for 'person'
|
||
|
|
|
||
|
|
# Draw bounding boxes around people
|
||
|
|
xmin, ymin, xmax, ymax = map(int, obj[:4])
|
||
|
|
global accuracy
|
||
|
|
accuracy = obj[4]
|
||
|
|
if (accuracy > 0.5):
|
||
|
|
num_people += 1
|
||
|
|
cv2.rectangle(img, (xmin, ymin), (xmax, ymax), (0, 0, 255), 2)
|
||
|
|
cv2.putText(img, f" {round(float(accuracy), 2)}", (xmin, ymin),
|
||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
|
||
|
|
|
||
|
|
#cv2.putText(img, f'FPS: {int(self.cap.get(cv2.CAP_PROP_FPS))}', (10, 50), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
|
||
|
|
# cv2.putText(img, f'People: {num_people}', (10, 80), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
|
||
|
|
# cv2.putText(img, f'Processed FPS: {VideoPeopleDetection.processed_fps}', (10, 110), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
|
||
|
|
|
||
|
|
|
||
|
|
# Draw the number of people on the frame and display it
|
||
|
|
|
||
|
|
|
||
|
|
ret, jpeg = cv2.imencode(".jpg", img)
|
||
|
|
# print(jpeg.shape)
|
||
|
|
|
||
|
|
|
||
|
|
return jpeg.tobytes()
|
||
|
|
|
||
|
|
def time_synchronized():
|
||
|
|
# pytorch-accurate time
|
||
|
|
if torch.cuda.is_available():
|
||
|
|
torch.cuda.synchronize()
|
||
|
|
return time.time()
|