We Keep Coding

frame.shape NameError: name 'frame' is not defined

I don't know anything about Python, but I have a job that requires processing, so I need to implement some functions.
Below is my code.
When I ran Python,
Traceback (most recent call last): File "C:\Users\user\Desktop\bodypix\bodypix.py", line 80, in
frame.shape
NameError: name 'frame' is not defined
This error is checked.
Why does this error appear?
If you know how to solve this problem, I would really appreciate your help.
import tensorflow as tf
from tf_bodypix.api import download_model, load_model, BodyPixModelPaths
import cv2
from matplotlib import pyplot as plt
import numpy as np
# # 2. Detections
# In[2]:
load_model(download_model(BodyPixModelPaths.MOBILENET_FLOAT_50_STRIDE_16))
# In[3]:
bodypix_model = load_model(download_model(BodyPixModelPaths.MOBILENET_FLOAT_50_STRIDE_16))
# In[27]:
# get vid cap device
cap = cv2.VideoCapture(0)
# loop through frame
while cap.isOpened():
ret, frame = cap.read()
# BodyPix Detections
result = bodypix_model.predict_single(frame)
mask = result.get_mask(threshold=0.5).numpy().astype(np.uint8)
masked_image = cv2.bitwise_and(frame, frame, mask=mask)
# Show result to user on desktop
cv2.imshow('BodyPix', masked_image)
# Break loop outcome
if cv2.waitKey(10) & 0xFF == ord('q'):
break
cap.release() # Releases webcam or capture device
cv2.destroyAllWindows() # Closes imshow frames
# # 3. Add Virtual Background
# In[12]:
img = cv2.imread('beach.jpg')
img = img[:480, :640, :]
# In[13]:
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
# In[14]:
img.shape
# In[15]:
frame.shape
# In[24]:
plt.imshow(mask)
# In[23]:
plt.imshow(np.where(np.add(mask, -1) == -1, 1, np.add(mask, -1)))
# In[ ]:
# get vid cap device
cap = cv2.VideoCapture(0)
# loop through frame
while cap.isOpened():
ret, frame = cap.read()
# BodyPix Detections
result = bodypix_model.predict_single(frame)
mask = result.get_mask(threshold=0.5).numpy().astype(np.uint8)
masked_image = cv2.bitwise_and(frame, frame, mask=mask)
# Apply virtual background
neg = np.add(mask, -1)
inverse = np.where(neg==-1, 1, neg).astype(np.uint8)
masked_background = cv2.bitwise_and(img, img, mask=inverse)
final = cv2.add(masked_image, masked_background)
# Show result to user on desktop
cv2.imshow('BodyPix', final)
# Break loop outcome
if cv2.waitKey(10) & 0xFF == ord('q'):
break
cap.release() # Releases webcam or capture device
cv2.destroyAllWindows() # Closes imshow frames

You're referencing frame.shape prior to frame being assigned. Notice how img.shape is allowed since before this there is an assignment: img = cv2.imread('beach.jpg').
Read the documentation to see what "frame" should be assigned to.

Mediapipe process() first 'self' argument

I am trying to use mediapipe to track hands. I am using Python 3.7.9 on Windows 10, my code is below:
import cv2
import mediapipe as mp
mp_drawing = mp.solutions.drawing_utils
mp_hands = mp.solutions.hands
cap = cv2.VideoCapture(0)
while (True):
success, img = cap.read()
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
results = mp_hands.Hands.process(imgRGB)
print(result)
if cv2.waitKey(10) & 0xFF == ord('q'):
break
I'm getting this error:
Traceback (most recent call last):
File "C:/Users/Tomáš/PycharmProjects/pythonProject/hand_detect.py", line 11, in <module>
results = mp_hands.Hands.process(imgRGB)
TypeError: process() missing 1 required positional argument: 'image'
[ WARN:1] global D:\a\opencv-python\opencv-python\opencv\modules\videoio\src\cap_msmf.cpp (438) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback
Error says that I need to pass one more argument 'self' before I pass argument 'image'. I've been browsing a lot and every related code doesnt use first argument in the process() function. Could anyone help me solve this error?

The problem is that you do not create an object of mp_hands.Hands before you want to process it. The following code solves it and prints some results. By the way, this was well documentated in the documentation link i commented before.. :
import cv2
import mediapipe as mp
mp_drawing = mp.solutions.drawing_utils
mp_hands = mp.solutions.hands
cap = cv2.VideoCapture(0, cv2.CAP_DSHOW) # i had problems before reading webcam feeds, so i added cv2.CAP_DSHOW here
while True:
success, img = cap.read()
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# you have to create an object of mp_hands.Hands to get results
# alternatively you could do: results = mp_hands.Hands().process(imgRGB)
with mp_hands.Hands() as hands:
results = hands.process(imgRGB)
# continue loop if no results were found
if not results.multi_hand_landmarks:
continue
# print some results
for hand_landmarks in results.multi_hand_landmarks:
print(
f'Index finger tip coordinates: (',
f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].x}, '
f'{hand_landmarks.landmark[mp_hands.HandLandmark.INDEX_FINGER_TIP].y})'
)
if cv2.waitKey(10) & 0xFF == ord('q'):
break
Edit:
This is more or less the same code from here:
import cv2
import mediapipe as mp
mp_drawing = mp.solutions.drawing_utils
mp_drawing_styles = mp.solutions.drawing_styles
mp_hands = mp.solutions.hands
# initialize webcam
cap = cv2.VideoCapture(0, cv2.CAP_DSHOW)
with mp_hands.Hands(model_complexity=0,
min_detection_confidence=0.5,
min_tracking_confidence=0.5) as hands:
while cap.isOpened():
success, image = cap.read()
if not success:
print("Ignoring empty camera frame.")
# If loading a video, use 'break' instead of 'continue'.
continue
# To improve performance, optionally mark the image as not writeable to
# pass by reference.
image.flags.writeable = False
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
results = hands.process(image)
# Draw the hand annotations on the image.
image.flags.writeable = True
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
if results.multi_hand_landmarks:
for hand_landmarks in results.multi_hand_landmarks:
mp_drawing.draw_landmarks(
image,
hand_landmarks,
mp_hands.HAND_CONNECTIONS,
mp_drawing_styles.get_default_hand_landmarks_style(),
mp_drawing_styles.get_default_hand_connections_style())
# Flip the image horizontally for a selfie-view display.
cv2.imshow('MediaPipe Hands', cv2.flip(image, 1))
if cv2.waitKey(5) & 0xFF == 27:
break
cap.release()

How to capture video by video from one rtsp Url using Opencv?

The server is sending video by video using the same RTSP URL(rtsp://192.168.0.2:8554/)
I can capture and display video using opencv.
import numpy as np
import cv2 as cv
os.environ["OPENCV_FFMPEG_CAPTURE_OPTIONS"] = "rtsp_transport;udp"
cap = cv.VideoCapture('rtsp://192.168.0.2:8554/')
while cap.isOpened():
ret, frame = cap.read()
# if frame is read correctly ret is True
if not ret:
print("Can't receive frame (stream end?). Exiting ...")
break
cv.imshow('frame', frame)
if cv.waitKey(1) == ord('q'):
break
cap.release()
cv.destroyAllWindows()
This program returns error when going on to the next video.
I tried this, but this didn't work.
import cv2 as cv
import os
import time
os.environ["OPENCV_FFMPEG_CAPTURE_OPTIONS"] = "rtsp_transport;udp"
cap = cv.VideoCapture('rtsp://192.168.0.26:8554/')
if not cap.isOpened():
print("Cannot open camera")
exit()
while True:
try:
time.sleep(2)
# Capture frame-by-frame
ret, frame = cap.read()
# if frame is read correctly ret is True
# Our operations on the frame come here
# Display the resulting frame
cv.imshow('frame',frame)
if cv.waitKey(1) == ord('q'):
break
except:
print("Exception!!")
# When everything done, release the capture
cap.release()
cv.destroyAllWindows()
Can I get some help?
Thanks in advance!

I solved this by using multi-threaded program.
Main file
from datasets import LoadStreams
import threading
import os
import logging
import cv2
import torch
import time
logger = logging.getLogger(__name__)
def select_device(device='', batch_size=None):
# device = 'cpu' or '0' or '0,1,2,3'
cpu_request = device.lower() == 'cpu'
if device and not cpu_request: # if device requested other than 'cpu'
os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availablity
cuda = False if cpu_request else torch.cuda.is_available()
if cuda:
c = 1024 ** 2 # bytes to MB
ng = torch.cuda.device_count()
if ng > 1 and batch_size: # check that batch_size is compatible with device_count
assert batch_size % ng == 0, f'batch-size {batch_size} not multiple of GPU count {ng}'
x = [torch.cuda.get_device_properties(i) for i in range(ng)]
s = f'Using torch {torch.__version__} '
for i, d in enumerate((device or '0').split(',')):
if i == 1:
s = ' ' * len(s)
logger.info(f"{s}CUDA:{d} ({x[i].name}, {x[i].total_memory / c}MB)")
else:
logger.info(f'Using torch {torch.__version__} CPU')
logger.info('') # skip a line
return torch.device('cuda:0' if cuda else 'cpu')
def detect(rtsp_url):
dataset = LoadStreams(rtsp_url)
device = select_device('')
count = 0
view_img = True
# img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
try:
for frame_idx, (path, img, im0s, vid_cap) in enumerate(dataset): # for every frame
count += 1
im0 = im0s[0].copy()
if view_img:
cv2.imshow(str(path), im0)
# if cv2.waitKey(1) == ord('q'): # q to quit
# raise StopIteration
except:
print("finish execption")
dataset.stop()
return "good"
if __name__ == '__main__':
rtsp_url = "rtsp://192.168.0.26:8554/"
while True:
for thread in threading.enumerate():
print(thread.name)
print(detect(rtsp_url))
dataset class file
import glob
import logging
import math
import os
import random
import shutil
import time
import re
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from threading import Thread
import cv2
import numpy as np
import torch
class LoadStreams: # multiple IP or RTSP cameras
def __init__(self, sources='streams.txt', img_size=640):
self.mode = 'stream'
self.img_size = img_size
self.capture = None
self.my_thread = None
self.stopFlag = False
if os.path.isfile(sources):
with open(sources, 'r') as f:
sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
else:
sources = [sources]
n = len(sources)
self.imgs = [None] * n
self.sources = [clean_str(x) for x in sources] # clean source names for later
s = sources[0]
# for i, s in enumerate(sources):
# Start the thread to read frames from the video stream
# print('%g/%g: %s... ' % (i + 1, n, s), end='')
cap = cv2.VideoCapture(eval(s) if s.isnumeric() else s)
assert cap.isOpened(), 'Failed to open %s' % s
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS) % 100
self.ret, self.imgs[0] = cap.read() # guarantee first frame
thread = Thread(target=self.update, args=([0, cap]), daemon=True)
print(' success (%gx%g at %.2f FPS).' % (w, h, fps))
thread.start()
self.capture = cap
self.my_thread = thread
print('') # newline
# check for common shapes
s = np.stack([letterbox(x, new_shape=self.img_size)[0].shape for x in self.imgs], 0) # inference shapes
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
def update(self, index, cap):
# Read next stream frame in a daemon thread
n = 0
while cap.isOpened() and not self.stopFlag:
n += 1
# _, self.imgs[index] = cap.read()
cap.grab()
if n == 4: # read every 4th frame
_, self.imgs[index] = cap.retrieve()
n = 0
time.sleep(0.01) # wait time
def stop(self):
self.stopFlag = True
try:
# self.capture.release()
# self.my_thrsead.join()
print("stop thread!!")
except:
print("ERROR stopping thread!!")
def __iter__(self):
self.count = -1
return self
def __next__(self):
self.count += 1
img0 = self.imgs.copy()
if cv2.waitKey(1) == ord('q'): # q to quit
cv2.destroyAllWindows()
raise StopIteration
if not self.ret:
print("error!!!")
self.stop()
# Letterbox
img = [letterbox(x, new_shape=self.img_size, auto=self.rect)[0] for x in img0]
# Stack
img = np.stack(img, 0)
# Convert
img = img[:, :, :, ::-1].transpose(0, 3, 1, 2) # BGR to RGB, to bsx3x416x416
img = np.ascontiguousarray(img)
return self.sources, img, img0, None
def __len__(self):
return 0 # 1E12 frames = 32 streams at 30 FPS for 30 years
# def stop(self):
def clean_str(s):
# Cleans a string by replacing special characters with underscore _
return re.sub(pattern="[|##!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
# Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
shape = img.shape[:2] # current shape [height, width]
if isinstance(new_shape, int):
new_shape = (new_shape, new_shape)
# Scale ratio (new / old)
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
if not scaleup: # only scale down, do not scale up (for better test mAP)
r = min(r, 1.0)
# Compute padding
ratio = r, r # width, height ratios
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
if auto: # minimum rectangle
dw, dh = np.mod(dw, 32), np.mod(dh, 32) # wh padding
elif scaleFill: # stretch
dw, dh = 0.0, 0.0
new_unpad = (new_shape[1], new_shape[0])
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
dw /= 2 # divide padding into 2 sides
dh /= 2
if shape[::-1] != new_unpad: # resize
img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
return img, ratio, (dw, dh)
while cap.isOpened() and not self.stopFlag:
this line is especially important because
without this line the threads will be stacked and will have memory error
as the stack stacks up.

OpenCV video not getting saved

I am trying to save a video in OpenCV but i keep getting the error "could not demultiplex stream". I then checked size and found out that it was in kB. I primarily want to save grayscale videos how do i make it possible?
Is there any specific codec i need to use?
mplayer gives the following output
MPlayer 1.1-4.8 (C) 2000-2012 MPlayer Team
mplayer: could not connect to socket
mplayer: No such file or directory
Failed to open LIRC support. You will not be able to use your remote control.
Playing output.avi.
libavformat version 54.20.4 (external)
Mismatching header version 54.20.3
AVI file format detected.
[aviheader] Video stream found, -vid 0
AVI: Missing video stream!? Contact the author, it may be a bug :(
libavformat file format detected.
[lavf] stream 0: video (mpeg4), -vid 0
VIDEO: [MP4V] 1280x720 24bpp -nan fps 0.0 kbps ( 0.0 kbyte/s)
Clip info:
encoder: Lavf54.20.4
Load subtitles in ./
Failed to open VDPAU backend libvdpau_nouveau.so: cannot open shared object file: No such file or directory
[vdpau] Error when calling vdp_device_create_x11: 1
==========================================================================
Opening video decoder: [ffmpeg] FFmpeg's libavcodec codec family
libavcodec version 54.35.1 (external)
Mismatching header version 54.35.0
Unsupported AVPixelFormat 53
Selected video codec: [ffodivx] vfm: ffmpeg (FFmpeg MPEG-4)
==========================================================================
Audio: no sound
Starting playback...
V: 0.0 0/ 0 ??% ??% ??,?% 0 0
Exiting... (End of file)
Right now i tried with multiple codec formats
import imutils
import cv2
import numpy as np
interval = 30
outfilename = 'output.avi'
threshold=100.
fps = 10
cap = cv2.VideoCapture("video.mp4")
ret, frame = cap.read()
height, width, nchannels = frame.shape
fourcc = cv2.cv.CV_FOURCC(*'DIVX')
out = cv2.VideoWriter( outfilename,fourcc, fps, (width,height))
ret, frame = cap.read()
frame = imutils.resize(frame, width=500)
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
while(True):
frame0 = frame
ret, frame = cap.read()
frame = imutils.resize(frame, width=500)
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
if not ret:
deletedcount +=1
break
if np.sum( np.absolute(frame-frame0) )/np.size(frame) > threshold:
out.write(frame)
else:
print "Deleted"
cv2.imshow('Feed - Press "q" to exit',frame)
key = cv2.waitKey(interval) & 0xFF
if key == ord('q'):
print('received key q' )
break
cap.release()
out.release()
print('Successfully completed')

import numpy as np
import cv2
cap = cv2.VideoCapture(0)
out = cv2.VideoWriter('output.avi',-1, 20.0, (640,480))
while(cap.isOpened()):
ret, frame = cap.read()
if ret:
gray = cv2.cvtColor(src=frame, code=cv2.COLOR_BGR2GRAY)
out.write(gray)
cv2.imshow('frame', gray)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
else:
break
cap.release()
out.release()
cv2.destroyAllWindows()
Try this one
Select Intel iyuv codec.
The out.avi is non working file.
The output.avi is new working file.

If video is not getting saved, possibly the reason may be its capture size which is hardcoded as (640,480).
You can try the below code:
cap = cv2.VideoCapture(0)
fourcc_codec = cv2.VideoWriter_fourcc(*'XVID')
fps = 20.0
capture_size = (int(cap.get(3)), int(cap.get(4)))
out = cv2.VideoWriter("output.avi", fourcc_codec, fps, capture_size)

You can also check if you are passing the correct shape, do it like this:
h, w, _ = frame.shape
size = (w, h)
out = cv2.VideoWriter('video.avi', cv2.VideoWriter_fourcc(*'XVID'), 30, size)

Opencv python background substraction and motion tracking

I read about opencv on google and found the following sample code online to play with:
import cv2
def diffImg(t0, t1, t2):
d1 = cv2.absdiff(t2, t1)
d2 = cv2.absdiff(t1, t0)
return cv2.bitwise_and(d1, d2)
cam = cv2.VideoCapture('vid1.mp4')
winName = "Movement Indicator"
cv2.namedWindow(winName, cv2.CV_WINDOW_AUTOSIZE)
# Read three images first:
t_minus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
t = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
t_plus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
while True:
cv2.imshow( winName, diffImg(t_minus, t, t_plus) )
# Read next image
t_minus = t
t = t_plus
t_plus = cv2.cvtColor(cam.read()[1], cv2.COLOR_RGB2GRAY)
key = cv2.waitKey(10)
if key == 27:
cv2.destroyWindow(winName)
break
print "Goodbye"
It produces the following kind of output for a sample video that I give to it:
So I am getting such results with this script. Now what I am trying to figure out is -
1) Get the bounding rect for the moving object in the video file
2) copy the contents of that bounding rect from original video frame to another and write the finished video to a file
Also, the screenshots on trying Kanishak Katahra's solution below I am getting the following output in the result window in the right side in the screenshot below -

Make the point of interest in the output you are getting as 1s. Make the rest as 0.
Convert it to 3D array of size same as original image.
Multiply original image with the output you are getting.
import cv2
import numpy as np
from numpy import newaxis
import time
def diffimg (a,b,c):
t0 = cv2.absdiff(a,b)
t1 = cv2.absdiff(b,c)
t3 = cv2.bitwise_and(t0,t1)
return t3
cap = cv2.VideoCapture(0)
t = cap.read() [1]
tp = cap.read() [1]
tpp = cap.read() [1]
t = cv2.cvtColor(t,cv2.COLOR_BGR2GRAY)
tp = cv2.cvtColor(tp,cv2.COLOR_BGR2GRAY)
tpp = cv2.cvtColor(tpp,cv2.COLOR_BGR2GRAY)
while True:
img = diffimg(t,tp,tpp)
cv2.imshow("motion detct",img)
key = cv2.waitKey(10)
res,img2 = cap.read()
#print img2.shape
t = tp
tp = tpp
tpp = cv2.cvtColor(img2,cv2.COLOR_BGR2GRAY)
cv2.imshow('image',img)
print img
img[img <= 10] = 0 #Try adjusting this value for better results.
img[img != 0] = 1
img = np.repeat(img[:, :, np.newaxis], 3, axis=2)
img3 = np.multiply( img,img2)
cv2.imshow('result',img3)
if key == 27:
cv2.destroyAllWindows()
break;
print "Goodbye User"