In ORB-SLAM, finding Translation vector that is coming out a random value

Question

I am trying to find out the translation vector (basically pose estimation) between two consecutive images. Here is what I did in OpenCV (.js):

1. Take input from the webcam
2. Get the consecutive images
3. Find feature in both the image using ORB
4. Applied BFMatcher to get the matching
5. Applied ratio test for the good matches
6. Now with the help of keypoint of both the images I found out the Essential matrix using cv.findEssentialMat(pt1,pt2...)
7. Since I have Essential matrix I can find out the Rotational matrix and translational vector b/w the consecutive two images

But this way I am getting a random value of translation vector, I am working on visual-inertial SLAM for that I need to find acceleration from the visual (and that can be found out If I have the correct translation b/w images).

I doubt if the matching is giving me the good result. Can someone please help me with this issue?

EDIT: I am adding the result what I am able to achieve so far: Matching and other result