aravindpai

bbox=outputs['instances'].pred_boxes.tensor.cpu().numpy()
print(bbox)

aravindpai

classes=outputs['instances'].pred_classes.cpu().numpy()
print(classes)

aravindpai

#frame rate of a video
FPS=cap.get(cv2.CAP_PROP_FPS)
print(FPS)

aravindpai

#read an image
img = cv2.imread("frames/30.png")

#pass to the model
outputs = predictor(img)

aravindpai

%%time
frames = os.listdir('frames/')
frames.sort(key=lambda f: int(re.sub('\D', '', f)))

frame_array=[]

for i in range(len(frames)):
    
    #reading each files
    img = cv2.imread('frames/'+frames[i])

aravindpai

from tqdm import tqdm
thresh=100
_ = [find_closest_people(names[i],thresh) for i in tqdm(range(len(names))) ]

aravindpai

def find_closest_people(name,thresh):

  img = cv2.imread('frames/'+name)
  outputs = predictor(img)
  classes=outputs['instances'].pred_classes.cpu().numpy()
  bbox=outputs['instances'].pred_boxes.tensor.cpu().numpy()
  ind = np.where(classes==0)[0]
  person=bbox[ind]
  midpoints = [mid_point(img,person,i) for i in range(len(person))]
  num = len(midpoints)

aravindpai

import os
import re

names=os.listdir('frames/')
names.sort(key=lambda f: int(re.sub('\D', '', f)))

aravindpai

img = change_2_red(img,person,p1,p2)

plt.figure(figsize=(20,10))
plt.imshow(img)

aravindpai

def change_2_red(img,person,p1,p2):
  risky = np.unique(p1+p2)
  for i in risky:
    x1,y1,x2,y2 = person[i]
    _ = cv2.rectangle(img, (x1, y1), (x2, y2), (255,0,0), 2)  
  return img