Homograph Matrix Off in Image Stitching

asked 2016-01-16 18:33:01 -0500

procoding gravatar image

I am trying to do an image stitching project where I use point pairs calculated by tracking points between frames of a video using the Lucas Kanade algorithm to find homography matrices. After writing the program and it came time for stitching together the frames of a video, I decided to run a test where I simply display the perspective warped versions of each image onto a black canvas to see how the Homography matrix had warped them. When I did this, instead of moving over bit by bit between frames, frames were translated further and further distances, way off from a slight nudge between frames

[----------------------------------------------------------------------------Empty Space---------------------------------------]

[Frame0---------------------------------------------------------------------------------------------------------------------------]

[------------Frame1-------------------------------------------------------------------------------------------------------------- ]

[-------------------------------------------Frame 2-------------------------------------------------------------------------------]

[---------------------------------------------------------------------------------------------------------------Frame 3-----------]

Subsequent frames would be out of visual range. I am not quiet sure why this is happening. I implemented a back-projection error check to make sure only points with accurate optical flow calculations were passed on. I also set the back-projection threshold for findHomography to be 10, 1, and then 0.5, all to no avail. I am stitching multiple images, so I am multiplying my homography matrices between frames. This seems to be compounding the error. Why is this happening and how can I fix my homography matrices? Here is my code (ignore commented out tests. Also, some of the indentation formatting might have been messed with while copying over to the forum):

import numpy as np
import sys
import cv2
import math

lastFeatures = None
currentFeatures = None
opticFlow = None
panRow = None
Rows = None
finalPanorama = None

def loadRow(dirPath, fType, numImages,  column):
    imageRow = []
    for i in range(0, numImages):
            imageRow.append(cv2.imread("%s/%i_%i.%s" % (dirPath, column, i, fType), cv2.IMREAD_COLOR))
    return imageRow

def findNthFeatures(prevImg, prevPnts, nxtImg):

    back_threshold = 0.5

    nxtDescriptors = []
    prevGrey = None
    nxtGrey = None
    nxtPnts = prevPnts[:]

    prevGrey = cv2.cvtColor(prevImg, cv2.COLOR_BGR2GRAY)
    nxtGrey = cv2.cvtColor(nxtImg, cv2.COLOR_BGR2GRAY)

    lucasKanadeParams = dict(winSize = (19,19), maxLevel = 100, criteria = (cv2.TERM_CRITERIA_EPS |     cv2.TERM_CRITERIA_COUNT, 10, 0.03))

    nxtPnts, status, err = cv2.calcOpticalFlowPyrLK(prevGrey, nxtGrey, prevPnts, None, **lucasKanadeParams)
    backProjections, status, err = cv2.calcOpticalFlowPyrLK(nxtGrey, prevGrey, nxtPnts, None, **lucasKanadeParams)
    d = abs(prevPnts - backProjections).reshape(-1, 2).max(-1)
    status = d < back_threshold
    goodNew = nxtPnts[status].copy()
    goodLast = prevPnts[status].copy()

    return goodLast, goodNew

def getHomographies(videoName):
    color = np.random.randint(0,255,(100,3))    
    lastFrame = None
    currentFrame = None
    lastKeypoints = None
    currentKeypoints = None
    firstImage = True
    featureRefreshRate = 5

    feature_params = dict( maxCorners = 100,
                        qualityLevel = 0.1,
                        minDistance = 8,
                        blockSize = 15)

    frameCount = 0

    Homographies = []

    cv2.namedWindow('display', cv2.WINDOW_NORMAL) 
    cap = cv2.VideoCapture(videoName)
    flags, frame = cap.read()

    while flags:
    if firstImage:                                                
        firstImage = False
            lastFrame = frame[:,:].copy()
            lastGray = cv2.cvtColor(lastFrame, cv2.COLOR_BGR2GRAY)
        lastKeypoints = cv2.goodFeaturesToTrack(lastGray, mask = None, **feature_params)
            flags, frame = cap.read()
            frameCount += 1
        else:
            mask = np.zeros_like(lastFrame)           
            currentFrame = frame[:,:].copy()
            frameCount += 1

        lastKeypoints, currentKeypoints = findNthFeatures(lastFrame, lastKeypoints, currentFrame)
  #         for i,(new,old) in enumerate(zip(currentKeypoints, lastKeypoints)):
  #             a, b = new.ravel()
  #             c, d = old.ravel()
   #             mask = cv2.line(mask, (a,b), (c,d), color[i].tolist(), 2)
   #             frame = cv2.circle(frame, (a,b), 5, color[i].tolist(), -1)
   #         img = cv2 ...
(more)
edit retag flag offensive close merge delete