82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
|
import argparse
|
||
|
|
import os
|
||
|
|
import platform
|
||
|
|
import sys
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
import cv2
|
||
|
|
import torch
|
||
|
|
import torch.backends.cudnn as cudnn
|
||
|
|
|
||
|
|
from read_data import LoadImages, LoadStreams
|
||
|
|
|
||
|
|
class TrafficDetection():
|
||
|
|
def __init__(self, video_path=None, model=None):
|
||
|
|
self.model = model
|
||
|
|
self.classes = self.model.names
|
||
|
|
self.imgsz = 640
|
||
|
|
|
||
|
|
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.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||
|
|
self.dataset = LoadImages(self.video_name, img_size=self.imgsz)
|
||
|
|
self.flag = 0
|
||
|
|
|
||
|
|
def use_webcam(self, source):
|
||
|
|
# self.dataset.release() # Release any existing video capture
|
||
|
|
# self.cap = cv2.VideoCapture(0) # Open default webcam
|
||
|
|
# print('use_webcam')
|
||
|
|
self.source = source
|
||
|
|
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()
|
||
|
|
|
||
|
|
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
|
||
|
|
results = self.model(img, size=640)
|
||
|
|
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
|
||
|
|
|
||
|
|
# Loop through each detected object and count the people
|
||
|
|
accuracy = 0
|
||
|
|
num_people = 0
|
||
|
|
|
||
|
|
color = (255, 200, 90)
|
||
|
|
|
||
|
|
for obj in results.xyxy[0]:
|
||
|
|
# xmin, ymin, xmax, ymax = map(int, obj[:4])
|
||
|
|
# accuracy = obj[4]
|
||
|
|
# if (accuracy > 0.5):
|
||
|
|
|
||
|
|
# cv2.rectangle(img, (xmin, ymin), (xmax, ymax), (0, 0, 255), 2)
|
||
|
|
# cv2.putText(img, f" {round(float(accuracy), 2), self.classes[obj[-1].item()]}", (xmin, ymin),
|
||
|
|
# cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
|
||
|
|
xmin, ymin, xmax, ymax = map(int, obj[:4])
|
||
|
|
|
||
|
|
accuracy = obj[4]
|
||
|
|
|
||
|
|
c = int(obj[-1])
|
||
|
|
|
||
|
|
cv2.rectangle(img, (xmin, ymin), (xmax, ymax), color, 2)
|
||
|
|
cv2.putText(img, f"{self.classes[c]}, {round(float(accuracy), 2)}", (xmin, ymin),
|
||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 0, 255), 2)
|
||
|
|
|
||
|
|
# Draw the number of people on the frame and display it
|
||
|
|
ret, jpeg = cv2.imencode(".jpg", img)
|
||
|
|
# print(num_people)
|
||
|
|
return jpeg.tobytes(), num_people\
|