We Keep Coding

Saving the IDs for cars with the help of Centroid, The IDs don't remove or update

I am using OpenCv and Trained model and trying assign IDs to the cars with the help of Centroid. There are the following scenarios:
at the beginning all recognized cars get centroid and ID
the cars that leave the frame, their IDs should be removed
new cars that enter into the frame (later) should get new IDs
I have the ID code from a youtube Video , but it dosen't work as it should. the Remove method , removes everything.
If I leave the update method on, the Cars get new IDs every frame. that should not happen.
I am new to the programming and I would appreciate if someone could help me here out.
import cv2
import numpy as np
import pandas as pd
import math
video_name = "videos.mp4"
cap = cv2.VideoCapture(video_name)
net = cv2.dnn.readNetFromONNX("best.onnx")
classes = ['car', 'free_space']
count = 0
center_points_prev_frame = []
tracking_objects = {}
track_id = 0
while True:
ret, img = cap.read()
# ret, frame1 = cap.read()
count += 1
if img is None:
break
img = cv2.resize(img, (1500, 1000))
# frame1 = cv2.resize(frame1, (1500, 1000))
blob = cv2.dnn.blobFromImage(img, scalefactor=1 / 255,
size=(640, 640),
mean=[0, 0, 0, 0],
swapRB=True,
crop=False)
net.setInput(blob)
detections = net.forward()[0]
# print(detections.shape)
# Aufbau: cx, cy, w, h, confidence, class_score
classes_ids = []
confidences = []
boxes = []
rows = detections.shape[0]
img_width, img_height = img.shape[1], img.shape[0]
x_scale = img_width / 640
y_scale = img_height / 640
# apply Non-Maximum Suppression
for i in range(rows):
row = detections[i]
confidence = row[4]
if confidence > 0.3:
classes_score = row[5:]
ind = np.argmax(classes_score)
if classes_score[ind] > 0.3:
classes_ids.append(ind)
confidences.append(confidence)
cx, cy, w, h = row[:4]
x1 = int((cx - w / 2) * x_scale)
y1 = int((cy - h / 2) * y_scale)
# print("X1:",x1 ,"Y1",y1)
width = int(w * x_scale)
height = int(h * y_scale)
box = np.array([x1, y1, width, height])
boxes.append(box)
indices = cv2.dnn.NMSBoxes(boxes, confidences, 0.3, 0.3)
# Point current frame
center_points_cur_frame = []
for i in indices:
x1, y1, w, h = boxes[i]
label = classes[classes_ids[i]]
conf = confidences[i]
text = label + "{:.2f}".format(conf)
if label == 'car':
car_coordinates = [(x1, y1), (x1 + w, y1 + h)]
#cv2.rectangle(img, (x1, y1), (x1 + w, y1 + h), (51, 51, 255), 2)
# center points
cx = int((x1 + x1 + w) / 2)
cy = int((y1 + y1 + h) / 2)
cv2.circle(img, (cx,cy), 3, (255, 0, 255), -1)
cv2.putText(img, str(track_id), (cx,cy), cv2.FONT_HERSHEY_COMPLEX, 0.3, (255, 0, 255), 1)
center_points_cur_frame.append((cx, cy))
# Only at the beginning we compare previous and current frame
if count <= 2:
for pt in center_points_cur_frame:
for pt2 in center_points_prev_frame:
distance = math.hypot(pt2[0] - pt[0], pt2[1] - pt[1])
if distance < 20:
tracking_objects[track_id] = pt
track_id += 1
else:
tracking_objects_copy = tracking_objects.copy()
center_points_cur_frame_copy = center_points_cur_frame.copy()
for object_id, pt2 in tracking_objects_copy.items():
object_exists = False
for pt in center_points_cur_frame_copy:
distance = math.hypot(pt2[0] - pt[0], pt2[1] - pt[1])
# Update IDs position
if distance < 20:
tracking_objects[object_id] = pt
object_exists = True
if pt in center_points_cur_frame:
center_points_cur_frame.remove(pt)
continue
############################### Problem ##########################################
# Remove IDs lost
if not object_exists:
tracking_objects.pop(object_id)
# Add new IDs found
for pt in center_points_cur_frame:
tracking_objects[track_id] = pt
track_id += 1
############################### Problem ##########################################
for object_id, pt in tracking_objects.items():
cv2.circle(img, pt, 3, (255, 0, 255), -1)
cv2.putText(img, str(object_id), (pt[0], pt[1] - 2), cv2.FONT_HERSHEY_COMPLEX, 0.3, (255, 0, 255), 1)
print("Tracking objects")
print(tracking_objects)
print("CUR FRAME LEFT PTS")
print(center_points_cur_frame)
# Make a copy of the points
center_points_prev_frame = center_points_cur_frame.copy()
cv2.imshow("Video", img)
cv2.waitKey(1)
# After the loop release the cap object
cap.release()
# Destroy all the windows
cv2.destroyAllWindows()

i = i[0] leads to IndexError: invalid index to scalar variable [duplicate]

This question already has answers here:
How to fix IndexError: invalid index to scalar variable
(6 answers)
Closed 2 months ago.
Im getting an error every time i run this script in my environment
Traceback (most recent call last):
File "FaceMark.py", line 55, in <module>
i = i[0]
IndexError: invalid index to scalar variable.
The camera does turns on but as soon it detects my hand or face the camera windows shuts down and it throws me the error posted above.
here's the entire script:
import cv2
import mediapipe as mp
import time
import numpy as np
thres = 0.45 # Threshold to detect object
nms_threshold = 0.2`your text`
cap = cv2.VideoCapture()
cap.set(3, 1280)
cap.set(4, 720)
cap.set(10, 150)
classNames = []
classFile = 'coco.names'
with open(classFile, 'rt') as f:
classNames = f.read().rstrip('\n').split('\n')
configPath = 'ssd_mobilenet_v3_large_coco_2020_01_14.pbtxt'
weightsPath = 'frozen_inference_graph.pb'
net = cv2.dnn_DetectionModel(weightsPath, configPath)
net.setInputSize(320, 320)
net.setInputScale(1.0 / 127.5)
net.setInputMean((127.5, 127.5, 127.5))
net.setInputSwapRB(True)
cap = cv2.VideoCapture(0)
pTime = 0
cTime = 0
mpDraw = mp.solutions.drawing_utils
mpFaceMesh = mp.solutions.face_mesh
faceMesh = mpFaceMesh.FaceMesh(max_num_faces=2)
drawSpec = mpDraw.DrawingSpec(thickness=1, circle_radius=2)
mpHands = mp.solutions.hands
hands = mpHands.Hands()
mpDrawHand = mp.solutions.drawing_utils
while True:
success, img = cap.read()
imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
classIds, confs, bbox = net.detect(img, confThreshold=thres)
bbox = list(bbox)
confs = list(np.array(confs).reshape(1, -1)[0])
confs = list(map(float, confs))
indices = cv2.dnn.NMSBoxes(bbox, confs, thres, nms_threshold)
results = faceMesh.process(imgRGB)
resultsHand = hands.process(imgRGB)
for i in indices:
i = i[0]
box = bbox[i]
# colors = np.random.uniform(0, 255, size=(len(box), 3))
x, y, w, h = box[0], box[1], box[2], box[3]
cv2.rectangle(img, (x, y), (x + w, h + y), color=(0, 255, 0), thickness=2)
cv2.putText(img, classNames[classIds[i][0] - 1].upper(), (box[0] + 10, box[1] + 30),
cv2.FONT_HERSHEY_PLAIN, 1, (0, 255, 0), 2)
print("Objects Ids: ", classIds)
if resultsHand.multi_hand_landmarks:
for handLms in resultsHand.multi_hand_landmarks:
for id, lm in enumerate(handLms.landmark):
print(id, lm)
h, w, c = img.shape
cx, cy = int(lm.x * w), int(lm.y * h)
cv2.circle(img, (cx, cy), 5, (255, 0, 255), cv2.FILLED)
mpDrawHand.draw_landmarks(img, handLms, mpHands.HAND_CONNECTIONS)
if results.multi_face_landmarks:
for faceLms in results.multi_face_landmarks:
mpDraw.draw_landmarks(img, faceLms, mpFaceMesh.FACE_CONNECTIONS,
drawSpec, drawSpec)
for id, lm in enumerate(faceLms.landmark):`
# print(lm)
ih, iw, ic = img.shape
x, y = int(lm.x * iw), int(lm.y * ih)
print("Face id: ", id, x, y)
cTime = time.time()
fps = 1 / (cTime - pTime)
pTime = cTime
cv2.putText(img, f'FPS: {int(fps)}', (20, 70), cv2.FONT_HERSHEY_PLAIN,
3, (255, 0, 0), 3)
cv2.imshow('image', img)
key = cv2.waitKey(1)
if key == 27:
break
cap.release()
cv2.destroyAllWindows()
how can i solve the problem around the indexes loop? i have tried other solutions here in similar questions, but i havent had any luck.

The variable i returns an integer value. This is not a list or tuple. If you change the for loop as follows, it will likely work.
for i in indices:
box = bbox[i]
# colors = np.random.uniform(0, 255, size=(len(box), 3))
x, y, w, h = box[0], box[1], box[2], box[3]
cv2.rectangle(img, (x, y), (x + w, h + y), color=(0, 255, 0), thickness=2)
cv2.putText(img, classNames[classIds[i] - 1].upper(), (box[0] + 10, box[1] + 30),
cv2.FONT_HERSHEY_PLAIN, 1, (0, 255, 0), 2)
print("Objects Ids: ", classIds)

urllib.error.HTTPError: HTTP Error 404: Not Found in python using esp32

I'm working on face detection attendance project using esp32 cam on python which detect the student face and then add it to excel file, I already did the arduino side using camera web server example, it gives me an error in python code related to url it can not read it, and here is my code:
import pandas as pd
import cv2
import urllib.request
import numpy as np
import os
from datetime import datetime
import face_recognition
path = r'C:\Users\96655\Downloads\ATTENDANCE\image_folder'
url = 'http://192.168.8.135/cam-hi.jpg'
##'''cam.bmp / cam-lo.jpg /cam-hi.jpg / cam.mjpeg '''
if 'Attendance.csv' in os.listdir(os.path.join(os.getcwd(), 'ATTENDANCE')):
print("there iss..")
os.remove("Attendance.csv")
else:
df = pd.DataFrame(list())
df.to_csv("Attendance.csv")
images = []
classNames = []
myList = os.listdir(path)
print(myList)
for cl in myList:
curImg = cv2.imread(f'{path}/{cl}')
images.append(curImg)
classNames.append(os.path.splitext(cl)[0])
print(classNames)
def findEncodings(images):
encodeList = []
for img in images:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
encode = face_recognition.face_encodings(img)[0]
encodeList.append(encode)
return encodeList
def markAttendance(name):
with open("Attendance.csv", 'r+') as f:
myDataList = f.readlines()
nameList = []
for line in myDataList:
entry = line.split(',')
nameList.append(entry[0])
if name not in nameList:
now = datetime.now()
dtString = now.strftime('%H:%M:%S')
f.writelines(f'\n{name},{dtString}')
encodeListKnown = findEncodings(images)
print('Encoding Complete')
#cap = cv2.VideoCapture(0)
while True:
#success, img = cap.read()
img_resp = urllib.request.urlopen(url)
imgnp = np.array(bytearray(img_resp.read()), dtype=np.uint8)
img = cv2.imdecode(imgnp, -1)
# img = captureScreen()
imgS = cv2.resize(img, (0, 0), None, 0.25, 0.25)
imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)
facesCurFrame = face_recognition.face_locations(imgS)
encodesCurFrame = face_recognition.face_encodings(imgS, facesCurFrame)
for encodeFace, faceLoc in zip(encodesCurFrame, facesCurFrame):
matches = face_recognition.compare_faces(encodeListKnown, encodeFace)
faceDis = face_recognition.face_distance(encodeListKnown, encodeFace)
# print(faceDis)
matchIndex = np.argmin(faceDis)
if matches[matchIndex]:
name = classNames[matchIndex].upper()
# print(name)
y1, x2, y2, x1 = faceLoc
y1, x2, y2, x1 = y1 * 4, x2 * 4, y2 * 4, x1 * 4
cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), 2)
cv2.rectangle(img, (x1, y2 - 35), (x2, y2),
(0, 255, 0), cv2.FILLED)
cv2.putText(img, name, (x1 + 6, y2 - 6),
cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 255), 2)
markAttendance(name)
cv2.imshow('Webcam', img)
key = cv2.waitKey(5)
if key == ord('q'):
break
cv2.destroyAllWindows()
cv2.imread
and this is the error it gives me :
urllib.error.HTTPError: HTTP Error 404: Not Found

Can I take a live stream URL and incorporate it into my code?

I'm trying to copy the URL of my phone that is live streaming, and import it into my code so that it opens a new window with the live stream visible.
The URL I'm trying to import is https://192.168.1.69:8080
Here's my code:
import cv2
import numpy as np
def make_coordinates(image, line_parameters):
try:
slope, intercept = line_parameters
except TypeError:
slope, intercept = 1,1
y1 = image.shape[0]
y2 = int(y1*(3/4)) #Line length
x1 = int((y1 - intercept)/slope)
x2 = int((y2 - intercept)/slope)
return np.array([x1, y1, x2, y2])
def averaged_slope_intercept(image, lines):
left_fit = []
right_fit = []
for line in lines:
x1, y1, x2, y2 = line.reshape(4)
parameters = np.polyfit((x1, x2), (y1, y2), 1)
print(parameters)
slope = parameters[0]
intercept = parameters[1]
if slope < 0:
left_fit.append((slope, intercept))
else:
right_fit.append((slope, intercept))
left_fit_average = np.average(left_fit, axis=0)
right_fit_average = np.average(right_fit, axis=0)
left_line = make_coordinates(image, left_fit_average)
right_line = make_coordinates(image, right_fit_average)
return np.array([left_line, right_line])
def canny(image):
gray = cv2.cvtColor(frame, cv2.COLOR_RGB2GRAY)
blur = cv2.GaussianBlur(gray, (5, 5), 0)
canny = cv2.Canny(blur, 50, 150)
return canny
def display_lines(image, lines):
line_image = np.zeros_like(image)
if lines is not None:
for x1, y1, x2, y2 in lines:
cv2.line(line_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
return line_image
def region_of_interest(image):
height = image.shape[0]
polygons = np.array([
[(300, height), (1300, height), (500, 400)] #Dimensions of Polygon
])
mask = np.zeros_like(image)
cv2.fillPoly(mask, polygons, 255)
masked_image = cv2.bitwise_and(image, mask)
return masked_image
# image = cv2.imread('test_image.jpg')
# lane_image = np.copy(image)
# canny_image = canny(lane_image)
# cropped_image = region_of_interest(canny_image)
# lines = cv2.HoughLinesP(cropped_image, 2, np.pi/180, 100, np.array([]), minLineLength=40, maxLineGap=5)
# averaged_lines = averaged_slope_intercept(lane_image, lines)
# line_image = display_lines(lane_image, averaged_lines)
# combo_image = cv2.addWeighted(lane_image, 0.8, line_image, 1, 1)
# cv2.imshow("result", combo_image)
# cv2.waitKey(0)
cap = cv2.VideoCapture("coast.mp4")
while(cap.isOpened()):
_, frame = cap.read()
canny_image = canny(frame)
cropped_image = region_of_interest(canny_image)
lines = cv2.HoughLinesP(cropped_image, 2, np.pi/180, 250, np.array([]), minLineLength=40, maxLineGap=5) #Number of minimum line votes
averaged_lines = averaged_slope_intercept(frame, lines)
line_image = display_lines(frame, averaged_lines)
combo_image = cv2.addWeighted(frame, 0.8, line_image, 1, 1)
cv2.imshow("Lane-Detection", combo_image)
if cv2.waitKey(1) == ord('w'):
break
cap.release()
cv2.destroyAllWindows()
I'm trying to place it where the "coast.mp4" is.
The code is for detecting lanes lines when driving, and I'm able to run the code with videos that are already downloaded on my computer (e.g. a video called "coast.mp4"), but I thought it would be interesting to see if I could implement a live stream so that the computer can detect lines in real-time. Is this possible?

If this is a streaming URL, you can simply do it like this
cv2.VideoCapture("https://192.168.1.69:8080/video")

i just get a big X on my image not on the road marking

before it would show me the lines but when I tried to make the lines blue and add them to the image I just get a massive blue X on my image?
I've rewritten the code again and even found a tutorial but still no luck, still get the same issue
import cv2
import numpy as np
def make_coordinates (image, line_parameters):
slope, incercept = line_parameters
y1 = image.shape[0]
y2 = int(y1*(3/5))
x1 = int((y1 - incercept)/slope)
x2 = int((y2 - incercept)/slope)
return np.array([x1, y1, x2, y2])
def average_slope_intercept(image, lines):
left_fit = []
right_fit = []
for line in lines:
x1, y1, x2, y2 = line.reshape(4)
parameters = np.polyfit((x1, x2), (y1, y2), 1)
slope = parameters[0]
intercept = parameters[1]
if slope < 0:
left_fit.append((slope, intercept))
else:
right_fit.append((slope, intercept))
left_fit_average = np.average(left_fit, axis = 0)
right_fit_average = np.average(right_fit, axis = 0)
left_line = make_coordinates(image, left_fit_average)
right_line = make_coordinates(image, right_fit_average)
return np.array([left_line, right_line])
def canny(image):
gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
blur = cv2.GaussianBlur(gray, (5, 5),0)
canny = cv2.Canny(blur, 50, 150)
return canny
def display_lines(image, lines):
line_image = np.zeros_like(image)
if lines is not None:
for line in lines:
x1, y1, x2, y2 = line.reshape(4)
cv2.line(line_image, (x1, y1), (x2, y2), (255, 0, 0), 10)
return line_image
def region_of_interest(image):
height = image.shape[0]
polygons = np.array([
[(200, height), (1100, height), (550, 250)]
])
mask = np.zeros_like(image)
cv2.fillPoly(mask, polygons, 255)
masked_images = cv2.bitwise_and(image, mask)
return masked_images
image = cv2.imread('test_image.jpg')
lane_image = np.copy(image)
canny_image = canny(lane_image)
cropped_image = region_of_interest(canny_image)
lines = cv2.HoughLinesP(cropped_image, 2, np.pi/180, 100, np.array([]), minLineLength=40, maxLineGap=5)
averaged_lines = average_slope_intercept(lane_image, lines)
line_image = display_lines(lane_image, averaged_lines)
combo_image = cv2.addWeighted(lane_image, 0.8, line_image, 1, 1)
cv2.imshow("results", line_image)
cv2.waitKey(0)
i don't​ get any errors on my terminal window

its suppose to draw lines half way up the picture not like the picture below.
This is what i get when im trying to add lines to the road