func.py

import argparse
import numpy as np
import copy
import itertools
import os
import cv2 as cv
import time
import csv
import math
import pyautogui



def get_args():
    parser = argparse.ArgumentParser()

    parser.add_argument("--device", type=int, default=0)
    parser.add_argument("--width", help='cap width', type=int, default=640)
    parser.add_argument("--height", help='cap height', type=int, default=480)

    parser.add_argument('--use_static_image_mode', action='store_true')
    parser.add_argument("--min_detection_confidence",
                        help='min_detection_confidence',
                        type=float,
                        default=0.7)
    parser.add_argument("--min_tracking_confidence",
                        help='min_tracking_confidence',
                        type=int,
                        default=0.5)

    args = parser.parse_args()

    return args


def select_mode(key, mode):
    number = -1
    if 48 <= key <= 57:  # 0 ~ 9
        number = key - 48
    if key == 110:  # n
        mode = 0
    if key == 107:  # k
        mode = 1
    if key == 104:  # h
        mode = 2
    return number, mode


def calc_bounding_rect(image, landmarks):
    image_width, image_height = image.shape[1], image.shape[0]

    landmark_array = np.empty((0, 2), int)

    for _, landmark in enumerate(landmarks.landmark):
        landmark_x = min(int(landmark.x * image_width), image_width - 1)
        landmark_y = min(int(landmark.y * image_height), image_height - 1)

        landmark_point = [np.array((landmark_x, landmark_y))]

        landmark_array = np.append(landmark_array, landmark_point, axis=0)

    x, y, w, h = cv.boundingRect(landmark_array)

    return [x, y, x + w, y + h]


def calc_landmark_list(image, landmarks):
    image_width, image_height = image.shape[1], image.shape[0]

    landmark_point = []

    # Keypoint
    for _, landmark in enumerate(landmarks.landmark):
        landmark_x = min(int(landmark.x * image_width), image_width - 1)
        landmark_y = min(int(landmark.y * image_height), image_height - 1)
        # landmark_z = landmark.z

        landmark_point.append([landmark_x, landmark_y])

    return landmark_point


def pre_process_landmark(landmark_list):
    temp_landmark_list = copy.deepcopy(landmark_list)

    # Convert to relative coordinates
    base_x, base_y = 0, 0
    for index, landmark_point in enumerate(temp_landmark_list):
        if index == 0:
            base_x, base_y = landmark_point[0], landmark_point[1]

        temp_landmark_list[index][0] = temp_landmark_list[index][0] - base_x
        temp_landmark_list[index][1] = temp_landmark_list[index][1] - base_y

    # Convert to a one-dimensional list
    temp_landmark_list = list(
        itertools.chain.from_iterable(temp_landmark_list))

    # Normalization
    max_value = max(list(map(abs, temp_landmark_list)))

    def normalize_(n):
        return n / max_value

    temp_landmark_list = list(map(normalize_, temp_landmark_list))

    return temp_landmark_list


def pre_process_point_history(image, point_history):
    image_width, image_height = image.shape[1], image.shape[0]

    temp_point_history = copy.deepcopy(point_history)

    # Convert to relative coordinates
    base_x, base_y = 0, 0
    for index, point in enumerate(temp_point_history):
        if index == 0:
            base_x, base_y = point[0], point[1]

        temp_point_history[index][0] = (temp_point_history[index][0] - base_x) / image_width
        temp_point_history[index][1] = (temp_point_history[index][1] - base_y) / image_height

    # Convert to a one-dimensional list
    temp_point_history = list(
        itertools.chain.from_iterable(temp_point_history))

    return temp_point_history


def logging_csv(number, mode, landmark_list, point_history_list):
    if mode == 0:
        pass
    if mode == 1 and (0 <= number <= 9):
        csv_path = 'model/keypoint_classifier/keypoint.csv'
        with open(csv_path, 'a', newline="") as f:
            writer = csv.writer(f)
            writer.writerow([number, *landmark_list])
    if mode == 2 and (0 <= number <= 9):
        csv_path = 'model/point_history_classifier/point_history.csv'
        with open(csv_path, 'a', newline="") as f:
            writer = csv.writer(f)
            writer.writerow([number, *point_history_list])
    return


def draw_landmarks(image, landmark_point):
    # 接続線
    if len(landmark_point) > 0:
        # 親指
        cv.line(image, tuple(landmark_point[2]), tuple(landmark_point[3]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[2]), tuple(landmark_point[3]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[3]), tuple(landmark_point[4]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[3]), tuple(landmark_point[4]), (255, 255, 255), 2)

        # 人差指
        cv.line(image, tuple(landmark_point[5]), tuple(landmark_point[6]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[5]), tuple(landmark_point[6]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[6]), tuple(landmark_point[7]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[6]), tuple(landmark_point[7]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[7]), tuple(landmark_point[8]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[7]), tuple(landmark_point[8]), (255, 255, 255), 2)

        # 中指
        cv.line(image, tuple(landmark_point[9]), tuple(landmark_point[10]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[9]), tuple(landmark_point[10]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[10]), tuple(landmark_point[11]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[10]), tuple(landmark_point[11]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[11]), tuple(landmark_point[12]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[11]), tuple(landmark_point[12]), (255, 255, 255), 2)

        # 薬指
        cv.line(image, tuple(landmark_point[13]), tuple(landmark_point[14]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[13]), tuple(landmark_point[14]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[14]), tuple(landmark_point[15]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[14]), tuple(landmark_point[15]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[15]), tuple(landmark_point[16]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[15]), tuple(landmark_point[16]), (255, 255, 255), 2)

        # 小指
        cv.line(image, tuple(landmark_point[17]), tuple(landmark_point[18]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[17]), tuple(landmark_point[18]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[18]), tuple(landmark_point[19]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[18]), tuple(landmark_point[19]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[19]), tuple(landmark_point[20]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[19]), tuple(landmark_point[20]), (255, 255, 255), 2)

        # 手の平
        cv.line(image, tuple(landmark_point[0]), tuple(landmark_point[1]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[0]), tuple(landmark_point[1]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[1]), tuple(landmark_point[2]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[1]), tuple(landmark_point[2]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[2]), tuple(landmark_point[5]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[2]), tuple(landmark_point[5]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[5]), tuple(landmark_point[9]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[5]), tuple(landmark_point[9]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[9]), tuple(landmark_point[13]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[9]), tuple(landmark_point[13]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[13]), tuple(landmark_point[17]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[13]), tuple(landmark_point[17]), (255, 255, 255), 2)
        cv.line(image, tuple(landmark_point[17]), tuple(landmark_point[0]), (0, 0, 0), 6)
        cv.line(image, tuple(landmark_point[17]), tuple(landmark_point[0]), (255, 255, 255), 2)

    # キーポイント
    for index, landmark in enumerate(landmark_point):
        if index == 0:  # 手首1
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 1:  # 手首2
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 2:  # 親指：付け根
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 3:  # 親指：第1関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 4:  # 親指：指先
            cv.circle(image, (landmark[0], landmark[1]), 8, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 8, (0, 0, 0), 1)
        if index == 5:  # 人差指：付け根
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 6:  # 人差指：第2関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 7:  # 人差指：第1関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 8:  # 人差指：指先
            cv.circle(image, (landmark[0], landmark[1]), 8, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 8, (0, 0, 0), 1)
        if index == 9:  # 中指：付け根
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 10:  # 中指：第2関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 11:  # 中指：第1関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 12:  # 中指：指先
            cv.circle(image, (landmark[0], landmark[1]), 8, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 8, (0, 0, 0), 1)
        if index == 13:  # 薬指：付け根
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 14:  # 薬指：第2関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 15:  # 薬指：第1関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 16:  # 薬指：指先
            cv.circle(image, (landmark[0], landmark[1]), 8, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 8, (0, 0, 0), 1)
        if index == 17:  # 小指：付け根
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 18:  # 小指：第2関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 19:  # 小指：第1関節
            cv.circle(image, (landmark[0], landmark[1]), 5, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 5, (0, 0, 0), 1)
        if index == 20:  # 小指：指先
            cv.circle(image, (landmark[0], landmark[1]), 8, (255, 255, 255), -1)
            cv.circle(image, (landmark[0], landmark[1]), 8, (0, 0, 0), 1)

    return image


def draw_bounding_rect(use_brect, image, brect):
    if use_brect:
        # Outer rectangle
        cv.rectangle(image, (brect[0], brect[1]), (brect[2], brect[3]),
                     (0, 0, 0), 1)

    return image


def draw_info_text(image, brect, handedness, hand_sign_text,
                   finger_gesture_text):
    cv.rectangle(image, (brect[0], brect[1]), (brect[2], brect[1] - 22),
                 (0, 0, 0), -1)

    info_text = handedness.classification[0].label[0:]
    if hand_sign_text != "":
        info_text = info_text + ':' + hand_sign_text
    cv.putText(image, info_text, (brect[0] + 5, brect[1] - 4),
               cv.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 1, cv.LINE_AA)

    if finger_gesture_text != "":
        cv.putText(image, "Finger Gesture:" + finger_gesture_text, (10, 60),
                   cv.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 4, cv.LINE_AA)
        cv.putText(image, "Finger Gesture:" + finger_gesture_text, (10, 60),
                   cv.FONT_HERSHEY_SIMPLEX, 1.0, (255, 255, 255), 2,
                   cv.LINE_AA)

    return image


def draw_point_history(image, point_history):
    for index, point in enumerate(point_history):
        if point[0] != 0 and point[1] != 0:
            cv.circle(image, (point[0], point[1]), 1 + int(index / 2),
                      (152, 251, 152), 2)

    return image


def draw_info(image, fps, mode, number):
    cv.putText(image, "FPS:" + str(fps), (10, 30), cv.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 0), 4, cv.LINE_AA)
    cv.putText(image, "FPS:" + str(fps), (10, 30), cv.FONT_HERSHEY_SIMPLEX, 1.0, (255, 255, 255), 2, cv.LINE_AA)

    mode_string = ['Logging Key Point', 'Logging Point History']
    if 1 <= mode <= 2:
        cv.putText(image, "MODE:" + mode_string[mode - 1], (10, 90),
                   cv.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 1,
                   cv.LINE_AA)
        if 0 <= number <= 9:
            cv.putText(image, "NUM:" + str(number), (10, 110),
                       cv.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 1,
                       cv.LINE_AA)
    return image


def control_keyboard(most_common_keypoint_id, select_right_id, command, keyboard_TF=True, print_TF=True, speed_up=False):
    if speed_up == False:
        if most_common_keypoint_id[0][0] == select_right_id and most_common_keypoint_id[0][1] == 5:
            if keyboard_TF:
                pyautogui.press(command)
            if print_TF:
                print(command)
    # if speed_up == True:
    #     if most_common_keypoint_id[0][0] == 0 and most_common_keypoint_id[0][1] == 5:
    #         print(i, time.time() - presstime_4)
    #         if i == 3 and time.time() - presstime_4 > 0.3:
    #             pyautogui.press('right')
    #             i = 0
    #             presstime_4 = time.time()
    #         elif i == 3 and time.time() - presstime_4 > 0.25:
    #             pyautogui.press('right')
    #             presstime_4 = time.time()
    #         elif time.time() - presstime_4 > 1:
    #             pyautogui.press('right')
    #             i += 1
    #             presstime_4 = time.time()
        # if speed_up == True:
        #     i += 1
        #     if i > 3:
        #         pyautogui.press(command)
        #         pyautogui.press(command)
        #         pyautogui.press(command)





    # print(most_common_keypoint_id)
    # elif select_left_id == -1:
    #     if right_id == -1 and left_id == select_right_id:
    #         if keyboard_TF:
    #             pyautogui.press(command)
    #         if print_TF:
    #             print(command)
    # elif select_right_id == -1:
    #     if left_id == -1 and right_id == select_left_id:
    #         if keyboard_TF:
    #             pyautogui.press(command)
    #         if print_TF:
    #             print(command)


def pick_gesture_command():
    left_number = input('left gesture number :')
    right_number = input('right gesture number :')
    command = input('what command :')
    return int(left_number), int(right_number), command


def pick_number(inputstring):
    keepask = True
    while keepask:
        try:
            number = input(f'{inputstring} :')
            number = int(number)
            if number < -1 or number > 3 or number == 0:
                raise Exception('number is not in range')
        except:
            print('choose again')

        else:
            keepask = False
            # print('choosing nicely')
    return number


def pick_command(inputstring='what command'):
    keepask = True
    while keepask:
        try:
            com = input(f'{inputstring} :')
            com_list = ['\t', '\n', '\r', ' ', '!', '"', '#', '$', '%', '&', "'", '(',
                        ')', '*', '+', ',', '-', '.', '/', '0', '1', '2', '3', '4', '5', '6', '7',
                        '8', '9', ':', ';', '<', '=', '>', '?', '@', '[', '\\', ']', '^', '_', '`',
                        'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',
                        'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '{', '|', '}', '~',
                        'accept', 'add', 'alt', 'altleft', 'altright', 'apps', 'backspace',
                        'browserback', 'browserfavorites', 'browserforward', 'browserhome',
                        'browserrefresh', 'browsersearch', 'browserstop', 'capslock', 'clear',
                        'convert', 'ctrl', 'ctrlleft', 'ctrlright', 'decimal', 'del', 'delete',
                        'divide', 'down', 'end', 'enter', 'esc', 'escape', 'execute', 'f1', 'f10',
                        'f11', 'f12', 'f13', 'f14', 'f15', 'f16', 'f17', 'f18', 'f19', 'f2', 'f20',
                        'f21', 'f22', 'f23', 'f24', 'f3', 'f4', 'f5', 'f6', 'f7', 'f8', 'f9',
                        'final', 'fn', 'hanguel', 'hangul', 'hanja', 'help', 'home', 'insert', 'junja',
                        'kana', 'kanji', 'launchapp1', 'launchapp2', 'launchmail',
                        'launchmediaselect', 'left', 'modechange', 'multiply', 'nexttrack',
                        'nonconvert', 'num0', 'num1', 'num2', 'num3', 'num4', 'num5', 'num6',
                        'num7', 'num8', 'num9', 'numlock', 'pagedown', 'pageup', 'pause', 'pgdn',
                        'pgup', 'playpause', 'prevtrack', 'print', 'printscreen', 'prntscrn',
                        'prtsc', 'prtscr', 'return', 'right', 'scrolllock', 'select', 'separator',
                        'shift', 'shiftleft', 'shiftright', 'sleep', 'space', 'stop', 'subtract', 'tab',
                        'up', 'volumedown', 'volumemute', 'volumeup', 'win', 'winleft', 'winright', 'yen',
                        'command', 'option', 'optionleft', 'optionright']
            if com not in com_list:
                raise Exception('number is not in range')
        except:
            print('choose again')

        else:
            keepask = False
            print('choosing nicely')
    return com


def findDistance(p1, p2, img, draw=True, r=15, t=3):
    x1, y1 = p1
    x2, y2 = p2
    cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

    if draw:
        cv.line(img, (x1, y1), (x2, y2), (255, 0, 255), t)
        cv.circle(img, (x1, y1), r, (255, 0, 255), cv.FILLED)
        cv.circle(img, (x2, y2), r, (255, 0, 255), cv.FILLED)
        cv.circle(img, (cx, cy), r, (0, 0, 255), cv.FILLED)
        length = math.hypot(x2 - x1, y2 - y1)

    return length, img, [x1, y1, x2, y2, cx, cy]