Commit 64e99f69 authored by Sparkf's avatar Sparkf 🏙️
Browse files

optimize module

parent 3165d0e6

train1/ld_module_binary.py

+1 −1
Original line number Diff line number Diff line 
import numpy as np

import cv2

import ld_module_transform



from numba import njit, prange



def get_bin_img(img, kernel_size=3, sobel_dirn='X', sobel_thresh=(0, 255), r_thresh=(0, 255),

                s_thresh=(0, 255), b_thresh=(0, 255), g_thresh=(0, 255)):

train1/ld_module_detection.py

+18 −16
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ import os 
import json

from skimage.filters import threshold_otsu

import time



from numba import njit, prange



def intensity_map(input_array, distance):

    histogram = np.sum(input_array[input_array.shape[0] // 2:, :], axis=0)
@@ -39,12 +39,14 @@ def find_point(input_img, start_W): 
def find_hist_iteration(input_img, baseline=500, start_W=0):

    input_img_hist_iter = input_img[baseline:baseline + 149, start_W:start_W + 200]

    find_hist_iteration_iter = np.sum(input_img_hist_iter[input_img_hist_iter.shape[0] // 2:, :], axis=0)

    peak_hist = find_peaks(find_hist_iteration_iter, distance=250)[0] or [0]

    if (find_hist_iteration_iter[peak_hist[0]] < 20) or peak_hist.size == 0:

        find_hist_iteration(baseline - 50, start_W)

    peak_hist = np.argmax(find_hist_iteration_iter)

    if (find_hist_iteration_iter[peak_hist] < 20):

        find_hist_iteration(input_img,baseline - 50, start_W)

    else:

        pass

    return (peak_hist[0] + start_W), baseline + 50

    return (peak_hist + start_W), baseline + 50









def gen_windows(input_img, bottom_H, midpoint_W, H, W):
@@ -54,36 +56,36 @@ def gen_windows(input_img, bottom_H, midpoint_W, H, W): 
    W = 100

    # window_arr = input_img[]

    histogram_window = np.sum(window[window.shape[0] // 2:, :], axis=0)

    window_peak = find_peaks(histogram_window, distance=100)[0]



    # window_peak = find_peaks(histogram_window, distance=100)[0]

    window_peak = np.argmax(histogram_window)

    return_mid = 0



    if window_peak.size > 0:



    if histogram_window[window_peak] > 5 and np.abs(window_peak - (W / 2)) < 40:

        return_mid = midpoint_W - (W / 2) + window_peak

    else:

        return_mid = midpoint_W

    else:

        return_mid = midpoint_W



        find_indicator = 0

    # plt.plot(histogram_window)

    # plt.show()

    return bottom_H - H / 2, return_mid, find_indicator





def fit_lane(input_img,midpoint):

    midpoint_arr = np.zeros((0, 2)).astype(int)

    xcl = 0

    ycl = 0

    rcl = 0



    # midpoint_arr = find_point(input_img, midpoint - 100)

    # divisionzero error !

    # ycl, xcl, rcl, _ = circle_fit.hyper_fit(midpoint_arr)



    try:

        midpoint_arr = find_point(input_img,midpoint - 100)

        # plt.scatter(x=midpoint_arr.T[0], y=midpoint_arr.T[1], s=8)

        ycl, xcl, rcl, _ = circle_fit.hyper_fit(midpoint_arr)

        # print(rcl)

        # if (rcl > 1000):

        #     plt.gca().add_artist(plt.Circle((ycl, xcl), rcl, color='r', fill=False))

        print(rcl)

    except Exception:

        pass

    return midpoint_arr, ycl, xcl, rcl
 
 No newline at end of file

train1/ld_module_transform.py

+1 −1
Original line number Diff line number Diff line
@@ -9,7 +9,7 @@ import json 
from skimage.filters import threshold_otsu

import time

import ld_module_binary



from numba import njit, prange





def transform_to(input_img):

train1/main.py

+63 −58
Original line number Diff line number Diff line
@@ -17,44 +17,7 @@ rootdir = 'D:/train_set/clips/examine/' 
foldername = "null"







for subdir, dirs, files in os.walk(rootdir):

    for d in dirs:

        # for file in files:

        #     impath = os.path.join(subdir, file)

        # read into seq

        # buffer first three image



        # img_buffer_array = np.zeros([4, 720, 1280, 3]).astype('uint8')

        # for k1 in range(1, 4):

        #     print(subdir + d + "/" + str(k1) + ".jpg")

        #     input_img = cv2.imread(subdir + d + "/" + str(k1) + ".jpg")

        #     input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)

        #     img_buffer_array[k1 - 1] = input_img

        #     print(k1)

        # rotate_num = 3



        for k2 in range(1, 21):

            input_img = cv2.imread(subdir + d + "/" + str(k2) + ".jpg")

            input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)



            # yellow filter

            input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)

            original_img = input_img

            # img_buffer_array[rotate_num] = input_img

            # input_img = (img_buffer_array[(rotate_num) % 4] * 0.25 + img_buffer_array[(rotate_num - 1) % 4] * 0.25 +

            #              img_buffer_array[

            #                  (rotate_num - 2) % 4] * 0.25 + img_buffer_array[(rotate_num - 3) % 4] * 0.25).astype(

            #     'uint8')

            # input_img = np.maximum.reduce([img_buffer_array[(rotate_num) % 4], img_buffer_array[(rotate_num - 1) % 4],

            #                                img_buffer_array[(rotate_num - 2) % 4],

            #                                img_buffer_array[(rotate_num - 3) % 4]]).astype('uint8')

            # input_img = input_img[:,:,0]

            # foldername = subdir[-19:]

            foldername = d

            filename = str(k2)

            i = 0



def lane_detection(input_img, original_img, i):

    # 1 perspective transformation

    transformed_img = ld_module_transform.transform_to(input_img)
@@ -93,9 +56,11 @@ for subdir, dirs, files in os.walk(rootdir): 


        if 100 < midpoint < 500:

            point_array, ycl, xcl, rcl = ld_module_detection.fit_lane(input_img, midpoint)

            # print(point_array)



            # 3.1.3.1 draw line over the original image

                    if point_array.size > 0 and rcl > 800 and rcl < 2147483647:

            if point_array.size > 0:

                # and rcl > 800 and rcl < 2147483647

                for point in point_array:

                    cv2.circle(mark_layer, tuple(point), 10, (0, 0, 255), thickness=-1)

                    cv2.circle(mark_layer, tuple([int(ycl), int(xcl)]), int(rcl), (0, 255, 0), thickness=10)
@@ -111,7 +76,47 @@ for subdir, dirs, files in os.walk(rootdir): 
        original_img = original_img * mark_layer_mask + mark_layer_trans



        # 4 save image

        # simulate not save image

        cv2.imwrite("op_module/" + foldername + "_" + filename + ".png", original_img)





for subdir, dirs, files in os.walk(rootdir):

    for d in dirs:

        # for file in files:

        #     impath = os.path.join(subdir, file)

        # read into seq

        # buffer first three image



        # img_buffer_array = np.zeros([4, 720, 1280, 3]).astype('uint8')

        # for k1 in range(1, 4):

        #     print(subdir + d + "/" + str(k1) + ".jpg")

        #     input_img = cv2.imread(subdir + d + "/" + str(k1) + ".jpg")

        #     input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)

        #     img_buffer_array[k1 - 1] = input_img

        #     print(k1)

        # rotate_num = 3



        for k2 in range(1, 21):

            input_img = cv2.imread(subdir + d + "/" + str(k2) + ".jpg")

            input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)



            # yellow filter

            input_img = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)

            original_img = input_img

            # img_buffer_array[rotate_num] = input_img

            # input_img = (img_buffer_array[(rotate_num) % 4] * 0.25 + img_buffer_array[(rotate_num - 1) % 4] * 0.25 +

            #              img_buffer_array[

            #                  (rotate_num - 2) % 4] * 0.25 + img_buffer_array[(rotate_num - 3) % 4] * 0.25).astype(

            #     'uint8')

            # input_img = np.maximum.reduce([img_buffer_array[(rotate_num) % 4], img_buffer_array[(rotate_num - 1) % 4],

            #                                img_buffer_array[(rotate_num - 2) % 4],

            #                                img_buffer_array[(rotate_num - 3) % 4]]).astype('uint8')

            # input_img = input_img[:,:,0]

            # foldername = subdir[-19:]

            foldername = d

            filename = str(k2)

            i = 0



            lane_detection(input_img, original_img, i)



print("--- %s seconds ---" % (time.time() - start_time))

CRA Git | Maintained and supported by SUSTech CRA and CCSE