We Keep Coding

How do i make detection only on spesific area

I'm working on a project trying to do object detection and text detection using both yolo and easyocr. Since I'm a beginner and really new to computer vision, I would be glad if someone can help me.
Here's the code:
import cv2
import numpy as np
import easyocr
# Load Yolo
net = cv2.dnn.readNet('yolov4-tiny-custom_3000.weights', 'yolov4-tiny-custom.cfg')
classes = []
with open("obj.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
cap = cv2.VideoCapture('car1.mp4')
# Declare Ocr
cascade_src = 'haarcascade_russian_plate_number.xml'
cascade = cv2.CascadeClassifier(cascade_src)
reader = easyocr.Reader(['en'], gpu = False)
# Declare Ocr
while True:
_, frame = cap.read()
height, width, channels = frame.shape
#frame = cv2.resize(frame, (800, 600))
# Yolo Detection
# Detecting objects
blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
# Showing informations on the screen
class_ids = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
color = colors[class_ids[i]]
cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
cv2.putText(frame, label, (x, y + 30), cv2.FONT_HERSHEY_PLAIN, 3, color, 3)
print("Jenis Mobil: " +label)
# Text Reader Using Ocr
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
plate = cascade.detectMultiScale(gray, 1.1, 5)
for x,y,w,h in plate:
wT,hT,cT = frame.shape
a,b = (int(0.02*wT),int(0.02*hT))
plate2 = frame[y+a:y+h-a,x+b:x+w-b,:]
cv2.rectangle(frame,(x,y),(x+w,y+h),(60,60,255),2)
cv2.rectangle(frame,(x-1,y-40),(x+w+1,y),(60,60,255),-1)
result = reader.readtext(plate2)
for detek in result:
top_left = (int(detek[0][0][0]), int(detek[0][0][1]))
bottom_right = (int(detek[0][2][0]), int(detek[0][2][1]))
text = detek[1]
cv2.putText(frame,text,(x,y-10),cv2.FONT_HERSHEY_SIMPLEX,0.9,(255,255,255),2)
print("Nomor Kendaran: " + text)
# Text Reader Using Ocr
cv2.imshow("Detection", frame)
key = cv2.waitKey(1)
if key == 27:
break
cap.release()
cv2.destroyAllWindows()
I am trying to use ROI to detect the object but I am not able to do it.
Any advice please?

Crop the image before it is fed to the model
while True:
_, frame = cap.read()
im_crop = im[y1:y2, x1:x2] # set x1,x2,y1,y2 based on your ROI
blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
this will speed up the inference time as well as there is less data to process by the model

How to convert cv2 pictures into a video frame

I have the following code which i am trying to use to detect objects. I have made some changes and now i am trying to make it work so that it will use a camera to detect objects. What it does now is takes a picture in a loop and doesnt use a video.
Here is my code.
import numpy as np
import cv2
net = cv2.dnn.readNet("yolov3.weights", "yolov3.cfg")
classes = []
with open("coco.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layers_names = net.getLayerNames()
outputlayers = [layers_names[i - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
class_ids = []
confidences = []
boxes = []
cap = cv2.VideoCapture(0)
while True:
_, image = cap.read()
height, width, channels = image.shape
blob = cv2.dnn.blobFromImage(image, 0.00392, (416, 416), (0, 0, 0), True,
crop=False)
net.setInput(blob)
outs = net.forward(outputlayers)
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence >= 0.5:
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[3] * width)
h = int(detection[3] * height)
x = int(center_x - width / 2)
y = int(center_y - height / 2)
boxes.append([x, y, width, height])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
objects_detecetd = len(boxes)
font = cv2.FONT_HERSHEY_PLAIN
for i in range(len(boxes)):
if i in indexes:
x, y, width, height = boxes[i]
label = str(classes[class_ids[i]])
color = colors[i]
print(label)
cv2.rectangle(image, (x, y), (x + width, y + height), color, 2)
cv2.putText(image, label, (x, y + 30), font, 4, color, 3)
cv2.imshow("Image", image)
cv2.waitKey(5)
cv2.destroyAllWindows()
cv2.destroyAllWindows()
cap.release

Error while loading Yolov5 custom model using OpenCV Python

I was trying to predict defects on a metal plate using yolov5 pre-trained weights.it was throwing this error:
**
File "C:\Users\acer.spyder-py3\metallic surface defect detection\untitled3.py", line 59, in post_process
if confidence >= CONFIDENCE_THRESHOLD:
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
**
import cv2
import numpy as np
# Constants.
INPUT_WIDTH = 640
INPUT_HEIGHT = 640
SCORE_THRESHOLD = 0.5
NMS_THRESHOLD = 0.45
CONFIDENCE_THRESHOLD = 0.45
# Text parameters.
FONT_FACE = cv2.FONT_HERSHEY_SIMPLEX
FONT_SCALE = 0.7
THICKNESS = 1
# Colors.
BLACK = (0,0,0)
BLUE = (255,178,50)
YELLOW = (0,255,255)
def draw_label(im, label, x, y):
"""Draw text onto image at location."""
# Get text size.
text_size = cv2.getTextSize(label, FONT_FACE, FONT_SCALE, THICKNESS)
dim, baseline = text_size[0], text_size[1]
# Use text size to create a BLACK rectangle.
cv2.rectangle(im, (x,y), (x + dim[0], y + dim[1] + baseline), (0,0,0), cv2.FILLED);
# Display text inside the rectangle.
cv2.putText(im, label, (x, y + dim[1]), FONT_FACE, FONT_SCALE, YELLOW, THICKNESS, cv2.LINE_AA)
def pre_process(input_image, net):
# Create a 4D blob from a frame.
blob = cv2.dnn.blobFromImage(input_image, 1/255, (INPUT_WIDTH, INPUT_HEIGHT), [0,0,0], 1, crop=False)
# Sets the input to the network.
net.setInput(blob)
# Run the forward pass to get output of the output layers.
outputs = net.forward(net.getUnconnectedOutLayersNames())
return outputs
def post_process(input_image, outputs):
# Lists to hold respective values while unwrapping.
class_ids = []
confidences = []
boxes = []
# Rows.
rows = outputs[0].shape[1]
image_height, image_width = input_image.shape[:2]
# Resizing factor.
x_factor = image_width / INPUT_WIDTH
y_factor = image_height / INPUT_HEIGHT
# Iterate through detections.
for r in range(rows):
row = outputs[0][0][r]
confidence = row[4]
# Discard bad detections and continue.
if confidence >= CONFIDENCE_THRESHOLD:
classes_scores = row[5:]
# Get the index of max class score.
class_id = np.argmax(classes_scores)
# Continue if the class score is above threshold.
if (classes_scores[class_id] > SCORE_THRESHOLD):
confidences.append(confidence)
class_ids.append(class_id)
cx, cy, w, h = row[0], row[1], row[2], row[3]
left = int((cx - w/2) * x_factor)
top = int((cy - h/2) * y_factor)
width = int(w * x_factor)
height = int(h * y_factor)
box = np.array([left, top, width, height])
boxes.append(box)
# Perform non maximum suppression to eliminate redundant, overlapping boxes with lower confidences.
indices = cv2.dnn.NMSBoxes(boxes, confidences, CONFIDENCE_THRESHOLD, NMS_THRESHOLD)
for i in indices:
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
# Draw bounding box.
cv2.rectangle(input_image, (left, top), (left + width, top + height), BLUE, 3*THICKNESS)
# Class label.
label = "{}:{:.2f}".format(classes[class_ids[i]], confidences[i])
# Draw label.
draw_label(input_image, label, left, top)
return input_image
if __name__ == '__main__':
# Load class names.
classesFile = "defects.names"
classes = None
with open(classesFile, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
# Load image.
frame = cv2.imread('img_02_3436787300_00007_jpg.rf.e9923d3a70d1aeb92e45896b9c12cfa3.jpg')
# Give the weight files to the model and load the network using them.
modelWeights = "models_train/best.onnx"
net = cv2.dnn.readNet(modelWeights)
# Process image.
detections = pre_process(frame, net)
img = post_process(frame.copy(), detections)
"""
Put efficiency information. The function getPerfProfile returns the overall time for inference(t)
and the timings for each of the layers(in layersTimes).
"""
t, _ = net.getPerfProfile()
label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
print(label)
cv2.putText(img, label, (20, 40), FONT_FACE, FONT_SCALE, (0, 0, 255), THICKNESS, cv2.LINE_AA)
cv2.imshow('Output', img)
cv2.waitKey(0)
I have little bit idea of deploying models into commercial use. If you find any other errors also please inform me . thanks in advance

A simple search led me to this SO post, highlighting a common issue recently.
Following this blog got me close but I faced the issue above.
net.getUnconnectedOutLayers() returns an array of index values. The output layers are obtained from net.getLayerNames() based on these index values.
In the following case net.getUnconnectedOutLayers() returns:
array([200, 227, 254])
We get the output layers from output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers() which returns:
['yolo_82', 'yolo_94', 'yolo_106']
Code:
The following is the complete working code for OpenCV version 4.5.5 (CPU):
image = cv2.imread(os.path.join(path, 'horse.jpg'))
Width = image.shape[1]
Height = image.shape[0]
scale = 0.00392
classes = None
with open(os.path.join(path, 'coco.names'), 'r') as f:
classes = [line.strip() for line in f.readlines()]
COLORS = np.random.uniform(0, 255, size=(len(classes), 3))
net = cv2.dnn.readNet(os.path.join(path, 'yolov3.weights'), os.path.join(path, 'yolov3.cfg'))
blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True, crop=False)
net.setInput(blob)
def get_output_layers(net):
layer_names = net.getLayerNames()
output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers()]
return output_layers
def draw_bounding_box(img, class_id, confidence, x, y, x_plus_w, y_plus_h):
label = str(classes[class_id])
color = COLORS[class_id]
img = cv2.rectangle(img, (x,y), (x_plus_w,y_plus_h), color, 2)
img = cv2.putText(img, label, (x-10,y-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
# run inference through the network
# and gather predictions from output layers
outs = net.forward(get_output_layers(net))
# initialization
class_ids = []
confidences = []
boxes = []
conf_threshold = 0.5
nms_threshold = 0.4
image2 = image.copy()
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
center_x = int(detection[0] * Width)
center_y = int(detection[1] * Height)
w = int(detection[2] * Width)
h = int(detection[3] * Height)
x = center_x - w / 2
y = center_y - h / 2
class_ids.append(class_id)
confidences.append(float(confidence))
boxes.append([x, y, w, h])
# apply non-max suppression
indices = cv2.dnn.NMSBoxes(boxes, confidences, conf_threshold, nms_threshold)
for i in indices:
i = i # i[0]
box = boxes[i]
x = box[0]
y = box[1]
w = box[2]
h = box[3]
draw_bounding_box(image2, class_ids[i], confidences[i], round(x), round(y), round(x+w), round(y+h))
Result:
Sample output:

The problem may be related to incompatible version of your installed modules.
Download .pt model.
wget https://github.com/ultralytics/YOLOv5/releases/download/v6.1/YOLOv5s.pt
And export to ONNX using your machine:
git clone https://github.com/ultralytics/YOLOv5
cd YOLOv5
pip install -r requirements.txt
pip install onnx
python3 export.py --weights models/YOLOv5s.pt --include onnx
Use the new converted .onnx file can solve the problem.

'NoneType' object has no attribute 'shape' in OpenCV recursion [duplicate]

This question already has answers here:
Why do I get AttributeError: 'NoneType' object has no attribute 'something'?
(11 answers)
Closed 1 year ago.
I came across a problem: the code works so that when a car passes the camera, a video of its passage is saved, then the function starts again through recursion, but exactly at 4th cycle the code gives an error
(H, W) = image.shape[:2]
AttributeError: 'NoneType' object has no attribute 'shape'
Here is the code itself:
import cv2 as cv
import numpy as np
import uuid
import os.path
import os
def camera():
print("new cycle")
confThreshold = 0.6
nmsThreshold = 0.1
inpWidth = 416
inpHeight = 416
classesFile = "car.names"
classes = None
with open(classesFile, 'rt') as f:
classes = f.read().rstrip('\n').split('\n')
modelConf = "car.cfg"
modelWeights = "cars_last.weights"
cap = cv.VideoCapture("rtsp://.../user=admin_password=tlJwpbo6_channel=1_stream=0.sdp?real_stream:")
ret, image = cap.read()
(H, W) = image.shape[:2]
global empty
global newname
newname = str(uuid.uuid4())
global output
output = cv.VideoWriter(newname+'.avi', cv.VideoWriter_fourcc('M','J','P','G'), 10,
(W, H))
print(newname)
empty = []
def postprocess(frame, outs):
frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
classIDs = []
confidences = []
boxes = []
boxes1=[]
cv.cvtColor(frame, cv.COLOR_RGB2BGR)
for out in outs:
for detection in out:
scores = detection[5:]
classID = np.argmax(scores)
confidence = scores[classID]
if confidence > confThreshold:
centerX = int(detection[0] * frameWidth)
centerY = int(detection[1] * frameHeight)
width = int(detection[2] * frameWidth)
height = int(detection[3] * frameHeight)
left = int(centerX - width / 2)
top = int(centerY - height / 2)
x = int(centerX - (width / 2))
y = int(centerY - (height / 2))
boxes1.append([x, y, int(width), int(height)])
classIDs.append(classID)
confidences.append(float(confidence))
boxes.append([left, top, width, height])
idxs = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
if len(idxs) > 0:
empty.clear()
empty.append(0)
else:
empty.append(1)
if len(empty)>100:
empty.clear()
if (os.path.isfile(newname+".avi"))==True and os.path.getsize(newname+".avi")!=0:
camera()
indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
i = i[0]
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
drawPred(classIDs[i], confidences[i], left, top, left + width, top + height)
output.write(frame)
def drawPred(classId, conf, left, top, right, bottom):
# Draw a bounding box.
cv.rectangle(frame, (left, top), (right, bottom), (255, 178, 50), 3)
label = '%.2f' % conf
# Get the label for the class name and its confidence
if classes:
assert (classId < len(classes))
label = '%s:%s' % (classes[classId], label)
labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
top = max(top, labelSize[1])
cv.rectangle(frame, (left, top - round(1.5 * labelSize[1])), (left + round(1.5 * labelSize[0]), top + baseLine),
(255, 255, 255), cv.FILLED)
cv.rectangle(frame, (left,top),(right,bottom), (255,255,255), 1 )
cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 0), 1)
def getOutputsNames(net):
layersNames = net.getLayerNames()
return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]
net = cv.dnn.readNetFromDarknet(modelConf, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
winName = 'DL OD with OpenCV'
cv.namedWindow(winName, cv.WINDOW_NORMAL)
while cv.waitKey(1) < 0:
hasFrame, frame = cap.read()
blob = cv.dnn.blobFromImage(frame, 1 / 255, (inpWidth, inpHeight), [0, 0, 0], 1, crop=False)
net.setInput(blob)
outs = net.forward(getOutputsNames(net))
postprocess(frame, outs)
cv.imshow(winName, frame)
cap.release()
output.release()
camera()

As spotted in the doc about the read function :
Parameters
[out]
image
the video frame is returned here. If no frames has been grabbed the image will be empty.
You should check the return status to know if you have image data.
Returns
false if no frames has been grabbed

all i had to do is to put camera connection out of recursion, I have put it outside the camera func thx all for help)
cap = cv.VideoCapture("rtsp:///user=admin_password=tlJwpbo6_channel=1_stream=0.sdp?real_stream:")
ret, image = cap.read()

Python, pillow grab not load the images frames correctly

I'm trying to use pillow.grab to get frames of my screen. For later detect objects for every frame.
import numpy as np
import cv2
from PIL import ImageGrab as ig
import time
# Load Yolo
net = cv2.dnn.readNet("yolov3_training_last.weights", "yolov3_testing.cfg")
# Name custom object
classes = ["amongus"]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
last_time = time.time()
while(True):
img_ = ig.grab(bbox=None)
open_cv_image = np.array(img_)
open_cv_image = open_cv_image[:, :, ::-1].copy()
img = cv2.resize(open_cv_image, None, fx=0.4, fy=0.4)
height, width, channels = img.shape
# Detecting objects
blob = cv2.dnn.blobFromImage(img, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
# Showing informations on the screen
class_ids = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.3:
# Object detected
print(class_id)
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
print(indexes)
font = cv2.FONT_HERSHEY_PLAIN
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
color = colors[class_ids[i]]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
#cv2.putText(img, label, (x, y + 30), font, 3, color, 2)
cv2.imshow("Image", np.array(img_))
#key = cv2.waitKey(0)
cv2.destroyAllWindows()
If I uncomment the #key = cv2.waitKey(0) works because I'm taking just one frame for every time I press a key, but once I comment that part, I got this screen.
I'm assuming (not sure at all if it's because of that) that this is happening because a lot of frames are coming, but if I sleep(n) the while fps will be so low. (I guess?)
What's happening / how to fix it?