CODEWITHSUNDEEP
pythonscikit-image
Jason French
Jason French

Reputation: 404

Compute area of rooftops in map images

I'm an R user having trouble with image analysis in Python. What's an efficient way to compute the area of a building at the center in the image? The goal is to apply an edge algorithm to a Google Maps static image and compute the surface area of the rooftop of an address.

from pygeocoder import Geocoder
import urllib
import numpy as np
from scipy import ndimage
from skimage import filter, io, measure
import matplotlib.pyplot as plt

def getMap(address):
    """Geocode address and retreive image centered
    around lat/long"""

    results = Geocoder.geocode(address)
    lat, lng = results[0].coordinates
    zip_code = results[0].postal_code

    map_url = 'https://maps.googleapis.com/maps/api/staticmap?center={0},{1}&size=640x640&zoom=19&sensor=false&maptype=roadmap&&style=visibility:simplified|gamma:0.1'
    request_url = map_url.format(lat, lng)
    req = urllib.urlopen(request_url)
    return(req)

def mapEdge(req):
    """Convert img to bytearray and do edge detection
    on centered building"""

    img = io.imread(req.geturl(),flatten=True)
    labels, numobjects = ndimage.label(img)
    edges = filter.canny(img, sigma=3)
    plt.imshow(edges, cmap=plt.cm.gray)
    plt.show()

map_tmp = getMap('1403 Elmwood Ave., Evanston, IL')
mapEdge(map_tmp)

Upvotes: 0

Views: 1909

Answers (2)

milind_mayank
milind_mayank

Reputation: 81

One way to proceed would be to use contour finding technique available in opencv and then detect the center of the contour. The code is in c++ but can be very easily be converted into python

    findContours( dst4, contours2, hierarchy2, CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE);
    vector<vector<Point> > contours_poly2( contours2.size() );
    vector<Rect> boundRect2( contours2.size() );
    cout << contours2.size()<<endl;
    Mat drawing1=Mat::zeros(dst4.rows,dst4.cols,dst4.depth());
    for( int i = 0; i < contours2.size(); i++ ){
        approxPolyDP( Mat(contours2[i]), contours_poly2[i], 3, true );
        boundRect2[i] = boundingRect( Mat(contours_poly2[i]) );
    }

Now that you have a vector of bounding rectangle and thus if the center of the bounding rectangle is very close to the center of your image then its a positive match.

Here is a tutorial for contour finding using python http://opencvpython.blogspot.in/2012/06/hi-this-article-is-tutorial-which-try.html

Hope this helps

Upvotes: 1

Fuxi
Fuxi

Reputation: 5508

I would look at one of those libraries:

Upvotes: 0

Related Questions