Segmentation of color image using depth information

I have an already acquired database of color and depth images. My goal is to use the depth image to segment the color image using the information from the nearest object. The problem I have is that the 2 images have different resolutions (depth -> 240*320, color ->480*640) so I found a problem during segmentation. To remedy this problem I looked everywhere to find a solution and what I found is as follows :

1) the use of registration based on calibration information

2) mapping always using calibration information

My problem is that I haven't found the right approach that I can follow and that is very clear.

Note that the calibration information I have is :

fx, fy ,cx ,cy ,k1 ,k2 ,k3 ,p1 ,p2, for the color image and the depth image.

I will be grateful if someone can help me and any information can be useful.

This is the depth and the color image i want to segment the hand in the color image using the depth image

Answer 1

[Image Analyst]

Assuming they both cover the very same field of view, I'd simply resize them to the same size with imresize(). Can you do that?

[jenny jenny]

Thank you very much, sir, for your answer, I tried to apply this function but when I apply it it doesn't work since the object in the color image is larger than the depth image, it may be due to the fact that the amount of information in the color image is greater than the depth image. I found that I have to map the color image to the space of the depth image if you have an idea I will be grateful

[Image Analyst]

An idea based on what? Based on what you shared, that's my only idea. Usually people attach images when asking for image processing advice. Try reading this link

[jenny jenny]

Thank you sir for your idea and for your comment i will try to modify the question by adding descriptive images

[jenny jenny]

for clarity this is a link to the same problem https://stackoverflow.com/questions/44863359/how-can-i-convert-color-stream-1920x1080-into-depth-stream512x424-in-kinect

[jenny jenny]

Hello Sir, I added the color and depth images