Calculating distance from Intel Realsense R200 Depth Camera

Question

I have been trying to calculate the distances of objects with values of R200 camera. I installed PyRealsense and librealsense(legacy). And examples of PyRealsense are working without any problem.

I have created a code for this purpose:

import pyrealsense as pyrs
from pyrealsense.constants import rs_option
depth_stream = pyrs.stream.DepthStream()
infrared_stream = pyrs.stream.InfraredStream()

with pyrs.Service() as serv:
    with serv.Device(streams=(depth_stream, infrared_stream, )) as dev:
        #dev.apply_ivcam_preset(0)
        while True:
            dev.wait_for_frames()

            print(dev.infrared) 

It returns a matrix that values changing with depending on the position of the object:

 [37 37 39 ... 20 20 21]
 [35 35 38 ... 17 18 19]
 [34 33 37 ... 19 20 20]]
[[40 36 30 ... 16 15 17]
 [40 37 28 ... 14 14 19]
 [42 39 28 ... 14 16 20]

Which column of this matrix is represent distance value or what should I do to calculate the distance.

Brooklime

Instead of editing your question and adding [SOLVED] to the title you must create an answer and mark it as correct, that is the correct way to indicate that a problem was solved in SO – Jurisprudent

Answer 1

While searching on Google, I have found an example for calculatin distance with RealSense camera:

https://github.com/intel/intel-iot-refkit/blob/master/meta-refkit-extra/doc/computervision.rst

I had to edit it to make it work with PyRealSense 2.0:

#!/usr/bin/python3

import sys

import numpy as np
import cv2
import pyrealsense as pyrs

with pyrs.Service() as serv:
    serv.start()
    with serv.Device() as cam:
        cat_cascade = cv2.CascadeClassifier("/usr/share/opencv/haarcascades/haarcascade_frontalcatface.xml")

        for x in range(30):
            # stabilize exposure
            cam.wait_for_frames()

        while True:
        # get image from web cam
            cam.wait_for_frames()
            img = cam.color

            cats = cat_cascade.detectMultiScale(img)
            for (x,y,w,h) in cats:
                # find center
                cx = int(round(x+(w/2)))
                cy = int(round(y+(h/2)))

                depth = cam.depth[cy][cx]

                print("Cat found, distance " + str(depth/10.0) + " cm")

It calculates distance when it shows a cat face. I have started to learn Tensorflow and my knowledge about OpenCV is poor. Can you explain me, what is the easiest way to port this code to TensorFlow or CAFFE.

Brooklime