nfsrules

def pre_process(img):
    """ Prepare image to be feed to a Keras convolutive model.
    
    img: 3-channel Numpy array image of size.
    Returns a resized and smoothed 250x70 RGB image. 
    """
    # Crop relevant area from input image
    img = crop(img,600,1080,0,1800)
    # Resize to model's input size (250,70)
    img = cv2.resize(img,(250,70), interpolation = cv2.INTER_LANCZOS4)#INTER_CUBIC)

nfsrules

# Get numpy array from matplotlib figure
target_map = get_figure(target_map, cmap='inferno').astype('uint8')

# Crop unnecessary regions from canvas
target_map = crop(target_map,9,63,33,232)

# Resize to original image size
target_map = cv2.resize(target_map,(1800,480), interpolation = cv2.INTER_CUBIC)

# Create a binary mask. You may want to change the binary threshold

nfsrules

# Create video writer
writer = cv2.VideoWriter("sample_output.avi", 
                         cv2.VideoWriter_fourcc(*"MJPG"), 
                         30,(1800,480))

for frame in tqdm(merged_maps):
    writer.write(frame.astype('uint8'))
    
writer.release()

nfsrules

# Convert RGB to BGR. (optional)
dst_map = cv2.cvtColor(dst_map, cv2.COLOR_RGB2BGR)

# Add feature map and original image
merged_img = cv2.add(dst_map, cropped_img)

nfsrules

# Default Python's libraries
import os


import numpy as np
import pandas as pd
from tqdm import tqdm
import keras.backend as K

# Graphic libraries