Hello i'm using python to track objects in a video and i want to show an image on top of the object instead of a text.
The current line that im using to show text on top of the target box :
cv2.putText(img_current_frame ,"object name",(int(bbox[0]), int(bbox[1]-45)),0, 0.75, (0,0,0),2)
There's already an answer for this: overlay a smaller image on a larger image python OpenCv
In your case, you could wrap this functionality with the following:
def overlay_image(im1, im2, x_offset, y_offset):
'''Mutates im1, placing im2 over it at a given offset.'''
im1[y_offset:y_offset+im2.shape[0], x_offset:x_offset+im2.shape[1]] = im2
then call it:
im_over = cv2.imread("my_overlay_image.png")
overlay_image(img_current_frame, im_over, 10, 10)
(as per the referenced solution)
You might prefer to composite text with the PIL .text() method:
from PIL import Image, ImageDraw
img = Image.open("blank.png").convert("RGBA")
d = ImageDraw.Draw(img)
d.text((10, 10), "Hello world!")
img.show()
Or if you have pixels, then use alpha_composite().
If you stick with cv2, then addWeighted() will help you blend in a logo image with alpha set to taste. Or you can just use the matrix addition operator:
output = img_current_frame + logo
