python类DIST_L2的实例源码

def update(self,frame,events):
        falloff = self.falloff

        img = frame.img
        pts = [denormalize(pt['norm_pos'],frame.img.shape[:-1][::-1],flip_y=True) for pt in events.get('gaze_positions',[]) if pt['confidence']>=self.g_pool.min_data_confidence]

        overlay = np.ones(img.shape[:-1],dtype=img.dtype)

        # draw recent gaze postions as black dots on an overlay image.
        for gaze_point in pts:
            try:
                overlay[int(gaze_point[1]),int(gaze_point[0])] = 0
            except:
                pass

        out = cv2.distanceTransform(overlay,cv2.DIST_L2, 5)

        # fix for opencv binding inconsitency
        if type(out)==tuple:
            out = out[0]

        overlay =  1/(out/falloff+1)

        img[:] = np.multiply(img, cv2.cvtColor(overlay,cv2.COLOR_GRAY2RGB), casting="unsafe")

def __init__(self, blob_labels, blob_list):
    binary = (blob_labels >= 255).astype(np.uint8)
    dist, labels = cv2.distanceTransformWithLabels(binary, cv2.DIST_L2, 3)
    newlabels = 255*np.ones(blob_labels.shape, np.uint8)
#    plt.imshow(dist)
#    plt.show()
#    plt.imshow(labels)
#    plt.show()
    used_labels = set()
    for i, pk in enumerate(blob_list):
        label = labels[int(pk.x), int(pk.y)]
        #assert(label not in used_labels)
        if label in used_labels:
          raise RuntimeError("Adjacent blobs connected by diagonal. Cannot handle it!")
        used_labels.add(label)
        mask = (labels == label)
        newlabels[mask] = i
    self.labels = newlabels

def __call__(self, roi_slice, num):
    blob_labels = self.blob_labels[roi_slice]
    # everthing not pertaining to blobs becomes 1
    binary = (blob_labels >= 255).astype(np.uint8)
    blob_mask = (blob_labels == num)
    dist, voronoilabels = cv2.distanceTransformWithLabels(binary, cv2.DIST_L2, 3)
    vl = set(voronoilabels[blob_mask])
    if len(vl) != 1:
      print 'WARNING: In MaskVoronoiLocal, more than one label pertains to the area of the blob.'
      return np.ones(blob_labels.shape, np.bool)
    vl = vl.pop()
#    plt.imshow(binary)
#    plt.colorbar()
#    plt.show()
#    plt.imshow(voronoilabels)
#    plt.colorbar()
#    plt.show()
    return voronoilabels == vl

def dist_mask(mask, max_dist=10):
    mask = mask.astype(np.uint8)

    def get_dist(m):
        d = cv2.distanceTransform(m, cv2.DIST_L2, maskSize=3)
        d[d > max_dist] = max_dist
        return d / max_dist

    dist = get_dist(mask) - get_dist(1 - mask)
    # TODO - check in the notebook
    # TODO - what is the proper power?
   #pow = 0.5
   #dist[dist > 0] = dist[dist > 0] ** pow
   #dist[dist < 0] = -((-dist[dist < 0]) ** pow)
    return (1 + dist) / 2  # from 0 to 1