img_show.py

import matplotlib.pyplot as plt
import numpy as np
import numpy as np
import matplotlib.colors as cl
from PIL import Image

UNKNOWN_FLOW_THRESH = 1e7
SMALLFLOW = 0.0
LARGEFLOW = 1e8

def make_color_wheel():
    """
    Generate color wheel according Middlebury color code
    :return: Color wheel
    """
    RY = 15
    YG = 6
    GC = 4
    CB = 11
    BM = 13
    MR = 6

    ncols = RY + YG + GC + CB + BM + MR

    colorwheel = np.zeros([ncols, 3])

    col = 0

    # RY
    colorwheel[0:RY, 0] = 255
    colorwheel[0:RY, 1] = np.transpose(np.floor(255*np.arange(0, RY) / RY))
    col += RY

    # YG
    colorwheel[col:col+YG, 0] = 255 - np.transpose(np.floor(255*np.arange(0, YG) / YG))
    colorwheel[col:col+YG, 1] = 255
    col += YG

    # GC
    colorwheel[col:col+GC, 1] = 255
    colorwheel[col:col+GC, 2] = np.transpose(np.floor(255*np.arange(0, GC) / GC))
    col += GC

    # CB
    colorwheel[col:col+CB, 1] = 255 - np.transpose(np.floor(255*np.arange(0, CB) / CB))
    colorwheel[col:col+CB, 2] = 255
    col += CB

    # BM
    colorwheel[col:col+BM, 2] = 255
    colorwheel[col:col+BM, 0] = np.transpose(np.floor(255*np.arange(0, BM) / BM))
    col += + BM

    # MR
    colorwheel[col:col+MR, 2] = 255 - np.transpose(np.floor(255 * np.arange(0, MR) / MR))
    colorwheel[col:col+MR, 0] = 255

    return colorwheel

def compute_color(u, v):
    """
    compute optical flow color map
    :param u: optical flow horizontal map
    :param v: optical flow vertical map
    :return: optical flow in color code
    """
    [h, w] = u.shape
    img = np.zeros([h, w, 3])
    nanIdx = np.isnan(u) | np.isnan(v)
    u[nanIdx] = 0
    v[nanIdx] = 0

    colorwheel = make_color_wheel()
    ncols = np.size(colorwheel, 0)

    rad = np.sqrt(u**2+v**2)

    a = np.arctan2(-v, -u) / np.pi

    fk = (a+1) / 2 * (ncols - 1) + 1

    k0 = np.floor(fk).astype(int)

    k1 = k0 + 1
    k1[k1 == ncols+1] = 1
    f = fk - k0

    for i in range(0, np.size(colorwheel,1)):
        tmp = colorwheel[:, i]
        col0 = tmp[k0-1] / 255
        col1 = tmp[k1-1] / 255
        col = (1-f) * col0 + f * col1

        idx = rad <= 1
        col[idx] = 1-rad[idx]*(1-col[idx])
        notidx = np.logical_not(idx)

        col[notidx] *= 0.75
        img[:, :, i] = np.uint8(np.floor(255 * col*(1-nanIdx)))

    return img

def flow_to_image(flow, display=False):
    """
    Convert flow into middlebury color code image
    :param flow: optical flow map
    :return: optical flow image in middlebury color
    """
    u = flow[:, :, 0]
    v = flow[:, :, 1]

    maxu = -999.
    maxv = -999.
    minu = 999.
    minv = 999.

    idxUnknow = (abs(u) > UNKNOWN_FLOW_THRESH) | (abs(v) > UNKNOWN_FLOW_THRESH)
    u[idxUnknow] = 0
    v[idxUnknow] = 0

    maxu = max(maxu, np.max(u))
    minu = min(minu, np.min(u))

    maxv = max(maxv, np.max(v))
    minv = min(minv, np.min(v))

    rad = np.sqrt(u ** 2 + v ** 2)
    maxrad = max(-1, np.max(rad))

    if display:
        print("max flow: %.4f\nflow range:\nu = %.3f .. %.3f\nv = %.3f .. %.3f" % (maxrad, minu,maxu, minv, maxv))

    u = u/(maxrad + np.finfo(float).eps)
    v = v/(maxrad + np.finfo(float).eps)

    img = compute_color(u, v)

    idx = np.repeat(idxUnknow[:, :, np.newaxis], 3, axis=2)
    img[idx] = 0

    return np.uint8(img)

def tensor2array_flow(flow):
    flow = flow.detach().cpu().numpy().transpose(1,2,0)
    img = flow_to_image(flow)
    array = img.transpose(2,0,1)
    return array

def show_flow(flow):
    """
    visualize optical flow map using matplotlib
    :param filename: optical flow file
    :return: None
    """
    flow = flow.detach().cpu().numpy().transpose(1,2,0)
    img = flow_to_image(flow)
    plt.figure()
    plt.imshow(img)
    #plt.show()


def visualize_flow(flow, mode='Y'):
    """
    this function visualize the input flow
    :param flow: input flow in array
    :param mode: choose which color mode to visualize the flow (Y: Ccbcr, RGB: RGB color)
    :return: None
    """
    if mode == 'Y':
        # Ccbcr color wheel
        img = flow_to_image(flow)
        plt.imshow(img)
        plt.show()
    elif mode == 'RGB':
        (h, w) = flow.shape[0:2]
        du = flow[:, :, 0]
        dv = flow[:, :, 1]
        valid = flow[:, :, 2]
        max_flow = max(np.max(du), np.max(dv))
        img = np.zeros((h, w, 3), dtype=np.float64)
        # angle layer
        img[:, :, 0] = np.arctan2(dv, du) / (2 * np.pi)
        # magnitude layer, normalized to 1
        img[:, :, 1] = np.sqrt(du * du + dv * dv) * 8 / max_flow
        # phase layer
        img[:, :, 2] = 8 - img[:, :, 1]
        # clip to [0,1]
        small_idx = img[:, :, 0:3] < 0
        large_idx = img[:, :, 0:3] > 1
        img[small_idx] = 0
        img[large_idx] = 1
        # convert to rgb
        img = cl.hsv_to_rgb(img)
        # remove invalid point
        img[:, :, 0] = img[:, :, 0] * valid
        img[:, :, 1] = img[:, :, 1] * valid
        img[:, :, 2] = img[:, :, 2] * valid
        # show
        plt.imshow(img)
        plt.show()

    return None

def img_show_singleimage(image):
    image=image.detach().cpu()
    plt.figure()
    img = image.numpy().transpose(1,2,0)
    #print(img.shape)
    if img.shape[2] == 1:
        plt.imshow(img, cmap='gray')
    elif img.shape[2] == 3:
        plt.imshow(img)
    #plt.show()

def img_show_singleimage_numpy(image):
    plt.figure()
    img = image
    if img.shape[2] == 1:
        plt.imshow(img)
    elif img.shape[2] == 3:
        plt.imshow(img)
    #plt.show()