Augmented Reality using OpenCV Python | Homograph p.2

In the previous part, we created our detector and found the matches. In this video, we will take it a step further to find the homography to detect the bounding box and prepare the image for augmentation.

🚀🚀 My Urdu/Hindi AI YouTube Channel 🚀🚀

Code and Files:

Premium Courses:
✔️ Computer Vision Game Development Course:
✔️ Computer Vision with Arduino Course:
✔️ Advanced Drone Programming Course:
✔️ Learn to Build Computer Vision Mobile Apps:
✔️ Jetson Nano Premium Course:

⚙️⚙️⚙️—-My Gear — ⚙️⚙️⚙️

Follow Me:

#ComputerVision
#OpenCV
#CVZone

[grisheldaathallah]

Thank you! you really helped me learn python, the way you explain makes things easier to understand for a beginner like me.

[whiteboardsessions]

VIDEO IS VERY HELPFUL THIS CHANNEL IS BSET OF ALL CHANNEL

[Vbarnaaa]

Thanks for the great tutorial!! I would be interested, how to remove the flickering of the boundingbox/ videolayer position! Is there any way to smoothen it out?

[qzorn]

this is a sweet ai video, things are starting to develop, no opencv puns please. thanks :)

[mohamedihmeida]

Thank you for the video. Could you explain how can we count the outlier matching points after applying RANSAC?

[abeyantony]

i am not able to get a proper bounding box please help

[kowkinsap]

How to increase amount of features if I have simple shape (peace sign) on white background?

[skripsisitorus]

Sir, I tried your coding but I was wrong here. cv2.imshow('img2', img2)
NameError: name 'img2' is not defined
And it's the same code as yours.
pts = np.float32([[0, 0], [0, hT], [wT, hT], [wT, 0]]).reshape(-1, 1, 2)
dst = cv2.perspectiveTransform(pts, matrix)
img2 = cv2.polylines(imgWebcam, [np.int32(dst)], True, (255, 0, 255), 3)
Can you tell me how to fix it sir?

[CrazyMindTheKing]

one thing of the video are disabled on openCV

[NilayPaul-eckk]

Getting triangular bounding box . Please help

[dipanjalrakshit]

im getting this error img2 and imgWrap that names not defined
the code is same as yours
cv2.imshow('img2', img2)
NameError: name 'img2' is not defined
And it's the same code as yours.
pts = np.float32([[0, 0], [0, hT], [wT, hT], [wT, 0]]).reshape(-1, 1, 2)
dst = cv2.perspectiveTransform(pts, matrix)
img2 = cv2.polylines(imgWebcam, [np.int32(dst)], True, (255, 0, 255), 3)
Can you tell me how to fix it sir?

[mertolojis]

my box is bigger than the img why how can ı fix this sir?