On this article, we’re going to learn the way to detect faces in real-time utilizing OpenCV. After detecting the face from the webcam stream, we’re going to save the frames containing the face. Later we’ll go these frames (pictures) to our masks detector classifier to seek out out if the particular person is carrying a masks or not.

We’re additionally going to see the best way to make a customized masks detector utilizing Tensorflow and Keras however you possibly can skip that as I will likely be attaching the educated mannequin file under which you’ll be able to obtain and use. Right here is the checklist of subtopics we’re going to cowl:

1. What’s Face Detection?
2. Face Detection Strategies
3. Face detection algorithm
4. Face recognition
5. Face Detection utilizing Python
6. Face Detection utilizing OpenCV
7. Create a mannequin to recognise faces carrying a masks (Non-obligatory)
8. How you can do Actual-time Masks detection 

What is Face Detection?

The aim of face detection is to find out if there are any faces within the picture or video. If a number of faces are current, every face is enclosed by a bounding field and thus we all know the placement of the faces

The first goal of face detection algorithms is to precisely and effectively decide the presence and place of faces in a picture or video. The algorithms analyze the visible content material of the information, looking for patterns and options that correspond to facial traits. By using numerous methods, resembling machine studying, picture processing, and sample recognition, face detection algorithms intention to tell apart faces from different objects or background components throughout the visible information.

Human faces are troublesome to mannequin as there are a lot of variables that may change for instance facial features, orientation, lighting situations, and partial occlusions resembling sun shades, scarfs, masks, and so on. The results of the detection provides the face location parameters and it may very well be required in numerous varieties, for example, a rectangle masking the central a part of the face, eye facilities or landmarks together with eyes, nostril and mouth corners, eyebrows, nostrils, and so on.

Face Detection Strategies

There are two fundamental approaches for Face Detection:

1. Function Base Strategy
2. Picture Base Strategy

Function Base Strategy

Objects are normally acknowledged by their distinctive options. There are lots of options in a human face, which might be acknowledged between a face and lots of different objects. It locates faces by extracting structural options like eyes, nostril, mouth and so on. after which makes use of them to detect a face. Sometimes, some kind of statistical classifier certified then useful to separate between facial and non-facial areas. As well as, human faces have specific textures which can be utilized to distinguish between a face and different objects. Furthermore, the sting of options may help to detect the objects from the face. Within the coming part, we’ll implement a feature-based method by utilizing the OpenCV tutorial.

Picture Base Strategy

Basically, Picture-based strategies depend on methods from statistical evaluation and machine studying to seek out the related traits of face and non-face pictures. The realized traits are within the type of distribution fashions or discriminant capabilities that’s consequently used for face detection. On this methodology, we use completely different algorithms resembling Neural-networks, HMM, SVM, AdaBoost studying. Within the coming part, we’ll see how we are able to detect faces with MTCNN or Multi-Job Cascaded Convolutional Neural Community, which is an Picture-based method of face detection

Face detection algorithm

One of many widespread algorithms that use a feature-based method is the Viola-Jones algorithm and right here I’m briefly going to debate it. If you wish to find out about it intimately, I’d recommend going via this text, Face Detection utilizing Viola Jones Algorithm.

Viola-Jones algorithm is called after two laptop imaginative and prescient researchers who proposed the tactic in 2001, Paul Viola and Michael Jones of their paper, “Speedy Object Detection utilizing a Boosted Cascade of Easy Options”. Regardless of being an outdated framework, Viola-Jones is sort of highly effective, and its utility has confirmed to be exceptionally notable in real-time face detection. This algorithm is painfully gradual to coach however can detect faces in real-time with spectacular pace.

Given a picture(this algorithm works on grayscale pictures), the algorithm seems to be at many smaller subregions and tries to discover a face by searching for particular options in every subregion. It must test many various positions and scales as a result of a picture can include many faces of assorted sizes. Viola and Jones used Haar-like options to detect faces on this algorithm.

Face Recognition

Face detection and Face Recognition are sometimes used interchangeably however these are fairly completely different. The truth is, Face detection is simply a part of Face Recognition.

Face recognition is a technique of figuring out or verifying the id of a person utilizing their face. There are numerous algorithms that may do face recognition however their accuracy may differ. Right here I’m going to explain how we do face recognition utilizing deep studying.

The truth is right here is an article, Face Recognition Python which exhibits the best way to implement Face Recognition.

Face Detection utilizing Python

As talked about earlier than, right here we’re going to see how we are able to detect faces by utilizing an Picture-based method. MTCNN or Multi-Job Cascaded Convolutional Neural Community is certainly some of the widespread and most correct face detection instruments that work this precept. As such, it’s primarily based on a deep studying structure, it particularly consists of three neural networks (P-Web, R-Web, and O-Web) linked in a cascade.

So, let’s see how we are able to use this algorithm in Python to detect faces in real-time. First, it’s essential to set up MTCNN library which accommodates a educated mannequin that may detect faces.

pip set up mtcnn

Now allow us to see the best way to use MTCNN:

from mtcnn import MTCNN
import cv2
detector = MTCNN()
#Load a videopip TensorFlow
video_capture = cv2.VideoCapture(0)

whereas (True):
    ret, body = video_capture.learn()
    body = cv2.resize(body, (600, 400))
    bins = detector.detect_faces(body)
    if bins:

        field = bins[0]['box']
        conf = bins[0]['confidence']
        x, y, w, h = field[0], field[1], field[2], field[3]

        if conf > 0.5:
            cv2.rectangle(body, (x, y), (x + w, y + h), (255, 255, 255), 1)

    cv2.imshow("Body", body)
    if cv2.waitKey(25) & 0xFF == ord('q'):
        break

video_capture.launch()
cv2.destroyAllWindows()

Face Detection utilizing OpenCV

On this part, we’re going to carry out real-time face detection utilizing OpenCV from a stay stream by way of our webcam.

As you recognize movies are mainly made up of frames, that are nonetheless pictures. We carry out face detection for every body in a video. So with regards to detecting a face in a nonetheless picture and detecting a face in a real-time video stream, there’s not a lot distinction between them.

We will likely be utilizing Haar Cascade algorithm, also referred to as Voila-Jones algorithm to detect faces. It’s mainly a machine studying object detection algorithm that’s used to determine objects in a picture or video. In OpenCV, now we have a number of educated  Haar Cascade fashions that are saved as XML recordsdata. As a substitute of making and coaching the mannequin from scratch, we use this file. We’re going to use “haarcascade_frontalface_alt2.xml” file on this mission. Now allow us to begin coding this up

Step one is to seek out the trail to the “haarcascade_frontalface_alt2.xml” file. We do that by utilizing the os module of Python language.

import os
cascPath = os.path.dirname(
    cv2.__file__) + "/information/haarcascade_frontalface_alt2.xml"

The subsequent step is to load our classifier. The trail to the above XML file goes as an argument to CascadeClassifier() methodology of OpenCV.

faceCascade = cv2.CascadeClassifier(cascPath)

After loading the classifier, allow us to open the webcam utilizing this straightforward OpenCV one-liner code

video_capture = cv2.VideoCapture(0)

Subsequent, we have to get the frames from the webcam stream, we do that utilizing the learn() perform. We use it in infinite loop to get all of the frames till the time we wish to shut the stream.

whereas True:
    # Seize frame-by-frame
    ret, body = video_capture.learn()

The learn() perform returns:

1. The precise video body learn (one body on every loop)
2. A return code

The return code tells us if now we have run out of frames, which can occur if we’re studying from a file. This doesn’t matter when studying from the webcam since we are able to report perpetually, so we’ll ignore it.

For this particular classifier to work, we have to convert the body into greyscale.

grey = cv2.cvtColor(body, cv2.COLOR_BGR2GRAY)

The faceCascade object has a way detectMultiScale(), which receives a body(picture) as an argument and runs the classifier cascade over the picture. The time period MultiScale signifies that the algorithm seems to be at subregions of the picture in a number of scales, to detect faces of various sizes.

  faces = faceCascade.detectMultiScale(grey,
                                         scaleFactor=1.1,
                                         minNeighbors=5,
                                         minSize=(60, 60),
                                         flags=cv2.CASCADE_SCALE_IMAGE)

Allow us to undergo these arguments of this perform:

• scaleFactor – Parameter specifying how a lot the picture dimension is diminished at every picture scale. By rescaling the enter picture, you possibly can resize a bigger face to a smaller one, making it detectable by the algorithm. 1.05 is an effective potential worth for this, which suggests you utilize a small step for resizing, i.e. cut back the scale by 5%, you enhance the prospect of an identical dimension with the mannequin for detection is discovered.
• minNeighbors – Parameter specifying what number of neighbors every candidate rectangle ought to need to retain it. This parameter will have an effect on the standard of the detected faces. Larger worth ends in fewer detections however with greater high quality. 3~6 is an effective worth for it.
• flags –Mode of operation
• minSize – Minimal potential object dimension. Objects smaller than which might be ignored.

The variable faces now include all of the detections for the goal picture. Detections are saved as pixel coordinates. Every detection is outlined by its top-left nook coordinates and the width and peak of the rectangle that encompasses the detected face.

To point out the detected face, we’ll draw a rectangle over it.OpenCV’s rectangle() attracts rectangles over pictures, and it must know the pixel coordinates of the top-left and bottom-right corners. The coordinates point out the row and column of pixels within the picture. We will simply get these coordinates from the variable face.

for (x,y,w,h) in faces:
        cv2.rectangle(body, (x, y), (x + w, y + h),(0,255,0), 2)

rectangle() accepts the next arguments:

• The unique picture
• The coordinates of the top-left level of the detection
• The coordinates of the bottom-right level of the detection
• The color of the rectangle (a tuple that defines the quantity of purple, inexperienced, and blue (0-255)).In our case, we set as inexperienced simply maintaining the inexperienced part as 255 and relaxation as zero.
• The thickness of the rectangle strains

Subsequent, we simply show the ensuing body and likewise set a strategy to exit this infinite loop and shut the video feed. By urgent the ‘q’ key, we are able to exit the script right here

 cv2.imshow('Video', body)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

The subsequent two strains are simply to scrub up and launch the image.

video_capture.launch()
cv2.destroyAllWindows()

Listed below are the complete code and output.

import cv2
import os
cascPath = os.path.dirname(
    cv2.__file__) + "/information/haarcascade_frontalface_alt2.xml"
faceCascade = cv2.CascadeClassifier(cascPath)
video_capture = cv2.VideoCapture(0)
whereas True:
    # Seize frame-by-frame
    ret, body = video_capture.learn()
    grey = cv2.cvtColor(body, cv2.COLOR_BGR2GRAY)
    faces = faceCascade.detectMultiScale(grey,
                                         scaleFactor=1.1,
                                         minNeighbors=5,
                                         minSize=(60, 60),
                                         flags=cv2.CASCADE_SCALE_IMAGE)
    for (x,y,w,h) in faces:
        cv2.rectangle(body, (x, y), (x + w, y + h),(0,255,0), 2)
        # Show the ensuing body
    cv2.imshow('Video', body)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
video_capture.launch()
cv2.destroyAllWindows()

Output:

Create a mannequin to acknowledge faces carrying a masks

On this part, we’re going to make a classifier that may differentiate between faces with masks and with out masks. In case you wish to skip this half, here’s a hyperlink to obtain the pre-trained mannequin. Put it aside and transfer on to the subsequent part to know the best way to use it to detect masks utilizing OpenCV. Try our assortment of OpenCV programs that will help you develop your expertise and perceive higher.

So for creating this classifier, we want information within the type of Photographs. Fortunately now we have a dataset containing pictures faces with masks and and not using a masks. Since these pictures are very much less in quantity, we can’t practice a neural community from scratch. As a substitute, we finetune a pre-trained community known as MobileNetV2 which is educated on the Imagenet dataset.

Allow us to first import all the mandatory libraries we’re going to want.

from tensorflow.keras.preprocessing.picture import ImageDataGenerator
from tensorflow.keras.functions import MobileNetV2
from tensorflow.keras.layers import AveragePooling2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Enter
from tensorflow.keras.fashions import Mannequin
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.functions.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.picture import img_to_array
from tensorflow.keras.preprocessing.picture import load_img
from tensorflow.keras.utils import to_categorical
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import os

The subsequent step is to learn all the photographs and assign them to some checklist. Right here we get all of the paths related to these pictures after which label them accordingly. Keep in mind our dataset is contained in two folders viz- with_masks and without_masks. So we are able to simply get the labels by extracting the folder identify from the trail. Additionally, we preprocess the picture and resize it to 224x 224 dimensions.

imagePaths = checklist(paths.list_images('/content material/drive/My Drive/dataset'))
information = []
labels = []
# loop over the picture paths
for imagePath in imagePaths:
	# extract the category label from the filename
	label = imagePath.cut up(os.path.sep)[-2]
	# load the enter picture (224x224) and preprocess it
	picture = load_img(imagePath, target_size=(224, 224))
	picture = img_to_array(picture)
	picture = preprocess_input(picture)
	# replace the information and labels lists, respectively
	information.append(picture)
	labels.append(label)
# convert the information and labels to NumPy arrays
information = np.array(information, dtype="float32")
labels = np.array(labels)

The subsequent step is to load the pre-trained mannequin and customise it in response to our drawback. So we simply take away the highest layers of this pre-trained mannequin and add few layers of our personal. As you possibly can see the final layer has two nodes as now we have solely two outputs. That is known as switch studying.

baseModel = MobileNetV2(weights="imagenet", include_top=False,
	input_shape=(224, 224, 3))
# assemble the top of the mannequin that will likely be positioned on high of the
# the bottom mannequin
headModel = baseModel.output
headModel = AveragePooling2D(pool_size=(7, 7))(headModel)
headModel = Flatten(identify="flatten")(headModel)
headModel = Dense(128, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(2, activation="softmax")(headModel)

# place the top FC mannequin on high of the bottom mannequin (this may change into
# the precise mannequin we'll practice)
mannequin = Mannequin(inputs=baseModel.enter, outputs=headModel)
# loop over all layers within the base mannequin and freeze them so they'll
# *not* be up to date throughout the first coaching course of
for layer in baseModel.layers:
	layer.trainable = False

Now we have to convert the labels into one-hot encoding. After that, we cut up the information into coaching and testing units to judge them. Additionally, the subsequent step is information augmentation which considerably will increase the range of knowledge obtainable for coaching fashions, with out really accumulating new information. Knowledge augmentation methods resembling cropping, rotation, shearing and horizontal flipping are generally used to coach massive neural networks.

lb = LabelBinarizer()
labels = lb.fit_transform(labels)
labels = to_categorical(labels)
# partition the information into coaching and testing splits utilizing 80% of
# the information for coaching and the remaining 20% for testing
(trainX, testX, trainY, testY) = train_test_split(information, labels,
	test_size=0.20, stratify=labels, random_state=42)
# assemble the coaching picture generator for information augmentation
aug = ImageDataGenerator(
	rotation_range=20,
	zoom_range=0.15,
	width_shift_range=0.2,
	height_shift_range=0.2,
	shear_range=0.15,
	horizontal_flip=True,
	fill_mode="nearest")

The subsequent step is to compile the mannequin and practice it on the augmented information.

INIT_LR = 1e-4
EPOCHS = 20
BS = 32
print("[INFO] compiling mannequin...")
choose = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
mannequin.compile(loss="binary_crossentropy", optimizer=choose,
	metrics=["accuracy"])
# practice the top of the community
print("[INFO] coaching head...")
H = mannequin.match(
	aug.movement(trainX, trainY, batch_size=BS),
	steps_per_epoch=len(trainX) // BS,
	validation_data=(testX, testY),
	validation_steps=len(testX) // BS,
	epochs=EPOCHS)

Now that our mannequin is educated, allow us to plot a graph to see its studying curve. Additionally, we save the mannequin for later use. Here’s a hyperlink to this educated mannequin.

N = EPOCHS
plt.model.use("ggplot")
plt.determine()
plt.plot(np.arange(0, N), H.historical past["loss"], label="train_loss")
plt.plot(np.arange(0, N), H.historical past["val_loss"], label="val_loss")
plt.plot(np.arange(0, N), H.historical past["accuracy"], label="train_acc")
plt.plot(np.arange(0, N), H.historical past["val_accuracy"], label="val_acc")
plt.title("Coaching Loss and Accuracy")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="decrease left")

Output:

#To save lots of the educated mannequin
mannequin.save('mask_recog_ver2.h5')

How you can do Actual-time Masks detection 

Earlier than transferring to the subsequent half, ensure to obtain the above mannequin from this hyperlink and place it in the identical folder because the python script you’re going to write the under code in.

Now that our mannequin is educated, we are able to modify the code within the first part in order that it could possibly detect faces and likewise inform us if the particular person is carrying a masks or not.

To ensure that our masks detector mannequin to work, it wants pictures of faces. For this, we’ll detect the frames with faces utilizing the strategies as proven within the first part after which go them to our mannequin after preprocessing them. So allow us to first import all of the libraries we want.

import cv2
import os
from tensorflow.keras.preprocessing.picture import img_to_array
from tensorflow.keras.fashions import load_model
from tensorflow.keras.functions.mobilenet_v2 import preprocess_input
import numpy as np

The primary few strains are precisely the identical as the primary part. The one factor that’s completely different is that now we have assigned our pre-trained masks detector mannequin to the variable mannequin.

ascPath = os.path.dirname(
    cv2.__file__) + "/information/haarcascade_frontalface_alt2.xml"
faceCascade = cv2.CascadeClassifier(cascPath)
mannequin = load_model("mask_recog1.h5")

video_capture = cv2.VideoCapture(0)
whereas True:
    # Seize frame-by-frame
    ret, body = video_capture.learn()
    grey = cv2.cvtColor(body, cv2.COLOR_BGR2GRAY)
    faces = faceCascade.detectMultiScale(grey,
                                         scaleFactor=1.1,
                                         minNeighbors=5,
                                         minSize=(60, 60),
                                         flags=cv2.CASCADE_SCALE_IMAGE)

Subsequent, we outline some lists. The faces_list accommodates all of the faces which might be detected by the faceCascade mannequin and the preds checklist is used to retailer the predictions made by the masks detector mannequin.

faces_list=[]
preds=[]

Additionally because the faces variable accommodates the top-left nook coordinates, peak and width of the rectangle encompassing the faces, we are able to use that to get a body of the face after which preprocess that body in order that it may be fed into the mannequin for prediction. The preprocessing steps are identical which might be adopted when coaching the mannequin within the second part. For instance, the mannequin is educated on RGB pictures so we convert the picture into RGB right here

    for (x, y, w, h) in faces:
        face_frame = body[y:y+h,x:x+w]
        face_frame = cv2.cvtColor(face_frame, cv2.COLOR_BGR2RGB)
        face_frame = cv2.resize(face_frame, (224, 224))
        face_frame = img_to_array(face_frame)
        face_frame = np.expand_dims(face_frame, axis=0)
        face_frame =  preprocess_input(face_frame)
        faces_list.append(face_frame)
        if len(faces_list)>0:
            preds = mannequin.predict(faces_list)
        for pred in preds:
        #masks include probabily of carrying a masks and vice versa
            (masks, withoutMask) = pred 

After getting the predictions, we draw a rectangle over the face and put a label in response to the predictions.

label = "Masks" if masks > withoutMask else "No Masks"
        shade = (0, 255, 0) if label == "Masks" else (0, 0, 255)
        label = "{}: {:.2f}%".format(label, max(masks, withoutMask) * 100)
        cv2.putText(body, label, (x, y- 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.45, shade, 2)

        cv2.rectangle(body, (x, y), (x + w, y + h),shade, 2)

The remainder of the steps are the identical as the primary part.

cv2.imshow('Video', body)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
video_capture.launch()
cv2.destroyAllWindows()

Right here is the entire code and output:

import cv2
import os
from tensorflow.keras.preprocessing.picture import img_to_array
from tensorflow.keras.fashions import load_model
from tensorflow.keras.functions.mobilenet_v2 import preprocess_input
import numpy as np

cascPath = os.path.dirname(
    cv2.__file__) + "/information/haarcascade_frontalface_alt2.xml"
faceCascade = cv2.CascadeClassifier(cascPath)
mannequin = load_model("mask_recog1.h5")

video_capture = cv2.VideoCapture(0)
whereas True:
    # Seize frame-by-frame
    ret, body = video_capture.learn()
    grey = cv2.cvtColor(body, cv2.COLOR_BGR2GRAY)
    faces = faceCascade.detectMultiScale(grey,
                                         scaleFactor=1.1,
                                         minNeighbors=5,
                                         minSize=(60, 60),
                                         flags=cv2.CASCADE_SCALE_IMAGE)
    faces_list=[]
    preds=[]
    for (x, y, w, h) in faces:
        face_frame = body[y:y+h,x:x+w]
        face_frame = cv2.cvtColor(face_frame, cv2.COLOR_BGR2RGB)
        face_frame = cv2.resize(face_frame, (224, 224))
        face_frame = img_to_array(face_frame)
        face_frame = np.expand_dims(face_frame, axis=0)
        face_frame =  preprocess_input(face_frame)
        faces_list.append(face_frame)
        if len(faces_list)>0:
            preds = mannequin.predict(faces_list)
        for pred in preds:
            (masks, withoutMask) = pred
        label = "Masks" if masks > withoutMask else "No Masks"
        shade = (0, 255, 0) if label == "Masks" else (0, 0, 255)
        label = "{}: {:.2f}%".format(label, max(masks, withoutMask) * 100)
        cv2.putText(body, label, (x, y- 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.45, shade, 2)

        cv2.rectangle(body, (x, y), (x + w, y + h),shade, 2)
        # Show the ensuing body
    cv2.imshow('Video', body)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break
video_capture.launch()
cv2.destroyAllWindows()

Output:

This brings us to the tip of this text the place we realized the best way to detect faces in real-time and likewise designed a mannequin that may detect faces with masks. Utilizing this mannequin we have been in a position to modify the face detector to masks detector.

Replace: I educated one other mannequin which may classify pictures into carrying a masks, not carrying a masks and never correctly carrying a masks. Here’s a hyperlink of the Kaggle pocket book of this mannequin. You may modify it and likewise obtain the mannequin from there and use it in as a substitute of the mannequin we educated on this article. Though this mannequin is just not as environment friendly because the mannequin we educated right here, it has an additional function of detecting not correctly worn masks.

If you’re utilizing this mannequin it’s essential to make some minor modifications to the code. Exchange the earlier strains with these strains.

#Listed below are some minor modifications in opencv code
for (field, pred) in zip(locs, preds):
        # unpack the bounding field and predictions
        (startX, startY, endX, endY) = field
        (masks, withoutMask,notproper) = pred

        # decide the category label and shade we'll use to attract
        # the bounding field and textual content
        if (masks > withoutMask and masks>notproper):
            label = "With out Masks"
        elif ( withoutMask > notproper and withoutMask > masks):
            label = "Masks"
        else:
            label = "Put on Masks Correctly"

        if label == "Masks":
            shade = (0, 255, 0)
        elif label=="With out Masks":
            shade = (0, 0, 255)
        else:
            shade = (255, 140, 0)

        # embody the likelihood within the label
        label = "{}: {:.2f}%".format(label,
                                     max(masks, withoutMask, notproper) * 100)

        # show the label and bounding field rectangle on the output
        # body
        cv2.putText(body, label, (startX, startY - 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.45, shade, 2)
        cv2.rectangle(body, (startX, startY), (endX, endY), shade, 2)

It’s also possible to upskill with Nice Studying’s PGP Synthetic Intelligence and Machine Studying Course. The course gives mentorship from {industry} leaders, and additionally, you will have the chance to work on real-time industry-relevant initiatives.

Additional Studying

1. Actual-Time Object Detection Utilizing TensorFlow
2. YOLO object detection utilizing OpenCV
3. Object Detection in Pytorch | What’s Object Detection?